2019-05-27 06:55:06 +00:00
|
|
|
/* SPDX-License-Identifier: GPL-2.0-or-later */
|
2008-02-07 08:13:50 +00:00
|
|
|
/* memcontrol.h - Memory Controller
|
|
|
|
*
|
|
|
|
* Copyright IBM Corporation, 2007
|
|
|
|
* Author Balbir Singh <balbir@linux.vnet.ibm.com>
|
|
|
|
*
|
2008-02-07 08:13:51 +00:00
|
|
|
* Copyright 2007 OpenVZ SWsoft Inc
|
|
|
|
* Author: Pavel Emelianov <xemul@openvz.org>
|
2008-02-07 08:13:50 +00:00
|
|
|
*/
|
|
|
|
|
|
|
|
#ifndef _LINUX_MEMCONTROL_H
|
|
|
|
#define _LINUX_MEMCONTROL_H
|
2009-01-08 02:08:02 +00:00
|
|
|
#include <linux/cgroup.h>
|
2011-05-26 23:25:38 +00:00
|
|
|
#include <linux/vm_event_item.h>
|
2012-12-18 22:21:56 +00:00
|
|
|
#include <linux/hardirq.h>
|
2012-12-18 22:22:09 +00:00
|
|
|
#include <linux/jump_label.h>
|
2015-09-08 22:01:02 +00:00
|
|
|
#include <linux/page_counter.h>
|
|
|
|
#include <linux/vmpressure.h>
|
|
|
|
#include <linux/eventfd.h>
|
2017-07-06 22:40:52 +00:00
|
|
|
#include <linux/mm.h>
|
|
|
|
#include <linux/vmstat.h>
|
2015-09-08 22:01:02 +00:00
|
|
|
#include <linux/writeback.h>
|
2016-03-15 21:57:25 +00:00
|
|
|
#include <linux/page-flags.h>
|
2011-05-26 23:25:38 +00:00
|
|
|
|
2008-02-07 08:13:51 +00:00
|
|
|
struct mem_cgroup;
|
2020-08-07 06:20:49 +00:00
|
|
|
struct obj_cgroup;
|
2008-02-07 08:13:59 +00:00
|
|
|
struct page;
|
|
|
|
struct mm_struct;
|
2012-12-18 22:22:34 +00:00
|
|
|
struct kmem_cache;
|
2008-02-07 08:13:51 +00:00
|
|
|
|
2017-05-03 21:55:13 +00:00
|
|
|
/* Cgroup-specific page state, on top of universal node page state */
|
|
|
|
enum memcg_stat_item {
|
2020-06-03 23:02:01 +00:00
|
|
|
MEMCG_SWAP = NR_VM_NODE_STAT_ITEMS,
|
2017-05-03 21:55:13 +00:00
|
|
|
MEMCG_SOCK,
|
2020-08-12 01:30:21 +00:00
|
|
|
MEMCG_PERCPU_B,
|
2016-01-20 23:03:22 +00:00
|
|
|
MEMCG_NR_STAT,
|
2011-01-13 23:47:37 +00:00
|
|
|
};
|
|
|
|
|
2018-04-10 23:29:45 +00:00
|
|
|
enum memcg_memory_event {
|
|
|
|
MEMCG_LOW,
|
2017-05-03 21:55:13 +00:00
|
|
|
MEMCG_HIGH,
|
|
|
|
MEMCG_MAX,
|
|
|
|
MEMCG_OOM,
|
2018-06-14 22:28:05 +00:00
|
|
|
MEMCG_OOM_KILL,
|
2020-06-02 04:49:52 +00:00
|
|
|
MEMCG_SWAP_HIGH,
|
2018-06-08 00:05:35 +00:00
|
|
|
MEMCG_SWAP_MAX,
|
|
|
|
MEMCG_SWAP_FAIL,
|
2018-04-10 23:29:45 +00:00
|
|
|
MEMCG_NR_MEMORY_EVENTS,
|
2017-05-03 21:55:13 +00:00
|
|
|
};
|
|
|
|
|
2012-01-13 01:17:59 +00:00
|
|
|
struct mem_cgroup_reclaim_cookie {
|
2016-07-28 22:46:05 +00:00
|
|
|
pg_data_t *pgdat;
|
2012-01-13 01:17:59 +00:00
|
|
|
unsigned int generation;
|
|
|
|
};
|
|
|
|
|
2017-05-03 21:55:13 +00:00
|
|
|
#ifdef CONFIG_MEMCG
|
|
|
|
|
|
|
|
#define MEM_CGROUP_ID_SHIFT 16
|
|
|
|
#define MEM_CGROUP_ID_MAX USHRT_MAX
|
|
|
|
|
|
|
|
struct mem_cgroup_id {
|
|
|
|
int id;
|
2018-10-26 22:09:28 +00:00
|
|
|
refcount_t ref;
|
2017-05-03 21:55:13 +00:00
|
|
|
};
|
|
|
|
|
2015-09-08 22:01:02 +00:00
|
|
|
/*
|
|
|
|
* Per memcg event counter is incremented at every pagein/pageout. With THP,
|
2020-08-12 01:32:40 +00:00
|
|
|
* it will be incremented by the number of pages. This counter is used
|
|
|
|
* to trigger some periodic events. This is straightforward and better
|
2015-09-08 22:01:02 +00:00
|
|
|
* than using jiffies etc. to handle periodic memcg event.
|
|
|
|
*/
|
|
|
|
enum mem_cgroup_events_target {
|
|
|
|
MEM_CGROUP_TARGET_THRESH,
|
|
|
|
MEM_CGROUP_TARGET_SOFTLIMIT,
|
|
|
|
MEM_CGROUP_NTARGETS,
|
|
|
|
};
|
|
|
|
|
2019-05-14 22:46:57 +00:00
|
|
|
struct memcg_vmstats_percpu {
|
|
|
|
long stat[MEMCG_NR_STAT];
|
2018-04-10 23:29:45 +00:00
|
|
|
unsigned long events[NR_VM_EVENT_ITEMS];
|
2015-09-08 22:01:02 +00:00
|
|
|
unsigned long nr_page_events;
|
|
|
|
unsigned long targets[MEM_CGROUP_NTARGETS];
|
|
|
|
};
|
|
|
|
|
|
|
|
struct mem_cgroup_reclaim_iter {
|
|
|
|
struct mem_cgroup *position;
|
|
|
|
/* scan generation, increased every round-trip */
|
|
|
|
unsigned int generation;
|
|
|
|
};
|
|
|
|
|
2017-07-06 22:40:52 +00:00
|
|
|
struct lruvec_stat {
|
|
|
|
long count[NR_VM_NODE_STAT_ITEMS];
|
|
|
|
};
|
|
|
|
|
2021-02-24 20:03:15 +00:00
|
|
|
struct batched_lruvec_stat {
|
|
|
|
s32 count[NR_VM_NODE_STAT_ITEMS];
|
|
|
|
};
|
|
|
|
|
mm, memcg: assign memcg-aware shrinkers bitmap to memcg
Imagine a big node with many cpus, memory cgroups and containers. Let
we have 200 containers, every container has 10 mounts, and 10 cgroups.
All container tasks don't touch foreign containers mounts. If there is
intensive pages write, and global reclaim happens, a writing task has to
iterate over all memcgs to shrink slab, before it's able to go to
shrink_page_list().
Iteration over all the memcg slabs is very expensive: the task has to
visit 200 * 10 = 2000 shrinkers for every memcg, and since there are
2000 memcgs, the total calls are 2000 * 2000 = 4000000.
So, the shrinker makes 4 million do_shrink_slab() calls just to try to
isolate SWAP_CLUSTER_MAX pages in one of the actively writing memcg via
shrink_page_list(). I've observed a node spending almost 100% in
kernel, making useless iteration over already shrinked slab.
This patch adds bitmap of memcg-aware shrinkers to memcg. The size of
the bitmap depends on bitmap_nr_ids, and during memcg life it's
maintained to be enough to fit bitmap_nr_ids shrinkers. Every bit in
the map is related to corresponding shrinker id.
Next patches will maintain set bit only for really charged memcg. This
will allow shrink_slab() to increase its performance in significant way.
See the last patch for the numbers.
[ktkhai@virtuozzo.com: v9]
Link: http://lkml.kernel.org/r/153112549031.4097.3576147070498769979.stgit@localhost.localdomain
[ktkhai@virtuozzo.com: add comment to mem_cgroup_css_online()]
Link: http://lkml.kernel.org/r/521f9e5f-c436-b388-fe83-4dc870bfb489@virtuozzo.com
Link: http://lkml.kernel.org/r/153063056619.1818.12550500883688681076.stgit@localhost.localdomain
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Acked-by: Vladimir Davydov <vdavydov.dev@gmail.com>
Tested-by: Shakeel Butt <shakeelb@google.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Guenter Roeck <linux@roeck-us.net>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Josef Bacik <jbacik@fb.com>
Cc: Li RongQing <lirongqing@baidu.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Matthias Kaehlcke <mka@chromium.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Philippe Ombredanne <pombredanne@nexb.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Sahitya Tummala <stummala@codeaurora.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Waiman Long <longman@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-17 22:47:37 +00:00
|
|
|
/*
|
|
|
|
* Bitmap of shrinker::id corresponding to memcg-aware shrinkers,
|
|
|
|
* which have elements charged to this memcg.
|
|
|
|
*/
|
|
|
|
struct memcg_shrinker_map {
|
|
|
|
struct rcu_head rcu;
|
2020-03-23 23:36:10 +00:00
|
|
|
unsigned long map[];
|
mm, memcg: assign memcg-aware shrinkers bitmap to memcg
Imagine a big node with many cpus, memory cgroups and containers. Let
we have 200 containers, every container has 10 mounts, and 10 cgroups.
All container tasks don't touch foreign containers mounts. If there is
intensive pages write, and global reclaim happens, a writing task has to
iterate over all memcgs to shrink slab, before it's able to go to
shrink_page_list().
Iteration over all the memcg slabs is very expensive: the task has to
visit 200 * 10 = 2000 shrinkers for every memcg, and since there are
2000 memcgs, the total calls are 2000 * 2000 = 4000000.
So, the shrinker makes 4 million do_shrink_slab() calls just to try to
isolate SWAP_CLUSTER_MAX pages in one of the actively writing memcg via
shrink_page_list(). I've observed a node spending almost 100% in
kernel, making useless iteration over already shrinked slab.
This patch adds bitmap of memcg-aware shrinkers to memcg. The size of
the bitmap depends on bitmap_nr_ids, and during memcg life it's
maintained to be enough to fit bitmap_nr_ids shrinkers. Every bit in
the map is related to corresponding shrinker id.
Next patches will maintain set bit only for really charged memcg. This
will allow shrink_slab() to increase its performance in significant way.
See the last patch for the numbers.
[ktkhai@virtuozzo.com: v9]
Link: http://lkml.kernel.org/r/153112549031.4097.3576147070498769979.stgit@localhost.localdomain
[ktkhai@virtuozzo.com: add comment to mem_cgroup_css_online()]
Link: http://lkml.kernel.org/r/521f9e5f-c436-b388-fe83-4dc870bfb489@virtuozzo.com
Link: http://lkml.kernel.org/r/153063056619.1818.12550500883688681076.stgit@localhost.localdomain
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Acked-by: Vladimir Davydov <vdavydov.dev@gmail.com>
Tested-by: Shakeel Butt <shakeelb@google.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Guenter Roeck <linux@roeck-us.net>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Josef Bacik <jbacik@fb.com>
Cc: Li RongQing <lirongqing@baidu.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Matthias Kaehlcke <mka@chromium.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Philippe Ombredanne <pombredanne@nexb.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Sahitya Tummala <stummala@codeaurora.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Waiman Long <longman@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-17 22:47:37 +00:00
|
|
|
};
|
|
|
|
|
2015-09-08 22:01:02 +00:00
|
|
|
/*
|
2019-12-01 01:50:12 +00:00
|
|
|
* per-node information in memory controller.
|
2015-09-08 22:01:02 +00:00
|
|
|
*/
|
2016-07-28 22:46:05 +00:00
|
|
|
struct mem_cgroup_per_node {
|
2015-09-08 22:01:02 +00:00
|
|
|
struct lruvec lruvec;
|
2018-02-01 00:16:45 +00:00
|
|
|
|
2021-02-24 20:03:15 +00:00
|
|
|
/*
|
|
|
|
* Legacy local VM stats. This should be struct lruvec_stat and
|
|
|
|
* cannot be optimized to struct batched_lruvec_stat. Because
|
|
|
|
* the threshold of the lruvec_stat_cpu can be as big as
|
|
|
|
* MEMCG_CHARGE_BATCH * PAGE_SIZE. It can fit into s32. But this
|
|
|
|
* filed has no upper limit.
|
|
|
|
*/
|
mm: memcontrol: don't batch updates of local VM stats and events
The kernel test robot noticed a 26% will-it-scale pagefault regression
from commit 42a300353577 ("mm: memcontrol: fix recursive statistics
correctness & scalabilty"). This appears to be caused by bouncing the
additional cachelines from the new hierarchical statistics counters.
We can fix this by getting rid of the batched local counters instead.
Originally, there were *only* group-local counters, and they were fully
maintained per cpu. A reader of a stats file high up in the cgroup tree
would have to walk the entire subtree and collect each level's per-cpu
counters to get the recursive view. This was prohibitively expensive,
and so we switched to per-cpu batched updates of the local counters
during a983b5ebee57 ("mm: memcontrol: fix excessive complexity in
memory.stat reporting"), reducing the complexity from nr_subgroups *
nr_cpus to nr_subgroups.
With growing machines and cgroup trees, the tree walk itself became too
expensive for monitoring top-level groups, and this is when the culprit
patch added hierarchy counters on each cgroup level. When the per-cpu
batch size would be reached, both the local and the hierarchy counters
would get batch-updated from the per-cpu delta simultaneously.
This makes local and hierarchical counter reads blazingly fast, but it
unfortunately makes the write-side too cache line intense.
Since local counter reads were never a problem - we only centralized
them to accelerate the hierarchy walk - and use of the local counters
are becoming rarer due to replacement with hierarchical views (ongoing
rework in the page reclaim and workingset code), we can make those local
counters unbatched per-cpu counters again.
The scheme will then be as such:
when a memcg statistic changes, the writer will:
- update the local counter (per-cpu)
- update the batch counter (per-cpu). If the batch is full:
- spill the batch into the group's atomic_t
- spill the batch into all ancestors' atomic_ts
- empty out the batch counter (per-cpu)
when a local memcg counter is read, the reader will:
- collect the local counter from all cpus
when a hiearchy memcg counter is read, the reader will:
- read the atomic_t
We might be able to simplify this further and make the recursive
counters unbatched per-cpu counters as well (batch upward propagation,
but leave per-cpu collection to the readers), but that will require a
more in-depth analysis and testing of all the callsites. Deal with the
immediate regression for now.
Link: http://lkml.kernel.org/r/20190521151647.GB2870@cmpxchg.org
Fixes: 42a300353577 ("mm: memcontrol: fix recursive statistics correctness & scalabilty")
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: kernel test robot <rong.a.chen@intel.com>
Tested-by: kernel test robot <rong.a.chen@intel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-06-13 22:55:46 +00:00
|
|
|
struct lruvec_stat __percpu *lruvec_stat_local;
|
|
|
|
|
|
|
|
/* Subtree VM stats (batched updates) */
|
2021-02-24 20:03:15 +00:00
|
|
|
struct batched_lruvec_stat __percpu *lruvec_stat_cpu;
|
2018-02-01 00:16:45 +00:00
|
|
|
atomic_long_t lruvec_stat[NR_VM_NODE_STAT_ITEMS];
|
|
|
|
|
2017-01-11 00:58:04 +00:00
|
|
|
unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
|
2015-09-08 22:01:02 +00:00
|
|
|
|
2019-12-01 01:50:03 +00:00
|
|
|
struct mem_cgroup_reclaim_iter iter;
|
2015-09-08 22:01:02 +00:00
|
|
|
|
mm, memcg: assign memcg-aware shrinkers bitmap to memcg
Imagine a big node with many cpus, memory cgroups and containers. Let
we have 200 containers, every container has 10 mounts, and 10 cgroups.
All container tasks don't touch foreign containers mounts. If there is
intensive pages write, and global reclaim happens, a writing task has to
iterate over all memcgs to shrink slab, before it's able to go to
shrink_page_list().
Iteration over all the memcg slabs is very expensive: the task has to
visit 200 * 10 = 2000 shrinkers for every memcg, and since there are
2000 memcgs, the total calls are 2000 * 2000 = 4000000.
So, the shrinker makes 4 million do_shrink_slab() calls just to try to
isolate SWAP_CLUSTER_MAX pages in one of the actively writing memcg via
shrink_page_list(). I've observed a node spending almost 100% in
kernel, making useless iteration over already shrinked slab.
This patch adds bitmap of memcg-aware shrinkers to memcg. The size of
the bitmap depends on bitmap_nr_ids, and during memcg life it's
maintained to be enough to fit bitmap_nr_ids shrinkers. Every bit in
the map is related to corresponding shrinker id.
Next patches will maintain set bit only for really charged memcg. This
will allow shrink_slab() to increase its performance in significant way.
See the last patch for the numbers.
[ktkhai@virtuozzo.com: v9]
Link: http://lkml.kernel.org/r/153112549031.4097.3576147070498769979.stgit@localhost.localdomain
[ktkhai@virtuozzo.com: add comment to mem_cgroup_css_online()]
Link: http://lkml.kernel.org/r/521f9e5f-c436-b388-fe83-4dc870bfb489@virtuozzo.com
Link: http://lkml.kernel.org/r/153063056619.1818.12550500883688681076.stgit@localhost.localdomain
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Acked-by: Vladimir Davydov <vdavydov.dev@gmail.com>
Tested-by: Shakeel Butt <shakeelb@google.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Guenter Roeck <linux@roeck-us.net>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Josef Bacik <jbacik@fb.com>
Cc: Li RongQing <lirongqing@baidu.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Matthias Kaehlcke <mka@chromium.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Philippe Ombredanne <pombredanne@nexb.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Sahitya Tummala <stummala@codeaurora.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Waiman Long <longman@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-17 22:47:37 +00:00
|
|
|
struct memcg_shrinker_map __rcu *shrinker_map;
|
2019-09-23 22:38:12 +00:00
|
|
|
|
2015-09-08 22:01:02 +00:00
|
|
|
struct rb_node tree_node; /* RB tree node */
|
|
|
|
unsigned long usage_in_excess;/* Set to the value by which */
|
|
|
|
/* the soft limit is exceeded*/
|
|
|
|
bool on_tree;
|
|
|
|
struct mem_cgroup *memcg; /* Back pointer, we cannot */
|
|
|
|
/* use container_of */
|
|
|
|
};
|
|
|
|
|
|
|
|
struct mem_cgroup_threshold {
|
|
|
|
struct eventfd_ctx *eventfd;
|
|
|
|
unsigned long threshold;
|
|
|
|
};
|
|
|
|
|
|
|
|
/* For threshold */
|
|
|
|
struct mem_cgroup_threshold_ary {
|
|
|
|
/* An array index points to threshold just below or equal to usage. */
|
|
|
|
int current_threshold;
|
|
|
|
/* Size of entries[] */
|
|
|
|
unsigned int size;
|
|
|
|
/* Array of thresholds */
|
2020-03-23 23:36:10 +00:00
|
|
|
struct mem_cgroup_threshold entries[];
|
2015-09-08 22:01:02 +00:00
|
|
|
};
|
|
|
|
|
|
|
|
struct mem_cgroup_thresholds {
|
|
|
|
/* Primary thresholds array */
|
|
|
|
struct mem_cgroup_threshold_ary *primary;
|
|
|
|
/*
|
|
|
|
* Spare threshold array.
|
|
|
|
* This is needed to make mem_cgroup_unregister_event() "never fail".
|
|
|
|
* It must be able to store at least primary->size - 1 entries.
|
|
|
|
*/
|
|
|
|
struct mem_cgroup_threshold_ary *spare;
|
|
|
|
};
|
|
|
|
|
2016-01-20 23:02:24 +00:00
|
|
|
enum memcg_kmem_state {
|
|
|
|
KMEM_NONE,
|
|
|
|
KMEM_ALLOCATED,
|
|
|
|
KMEM_ONLINE,
|
|
|
|
};
|
|
|
|
|
mem_cgroup: make sure moving_account, move_lock_task and stat_cpu in the same cacheline
The LKP robot found a 27% will-it-scale/page_fault3 performance
regression regarding commit e27be240df53("mm: memcg: make sure
memory.events is uptodate when waking pollers").
What the test does is:
1 mkstemp() a 128M file on a tmpfs;
2 start $nr_cpu processes, each to loop the following:
2.1 mmap() this file in shared write mode;
2.2 write 0 to this file in a PAGE_SIZE step till the end of the file;
2.3 unmap() this file and repeat this process.
3 After 5 minutes, check how many loops they managed to complete, the
higher the better.
The commit itself looks innocent enough as it merely changed some event
counting mechanism and this test didn't trigger those events at all.
Perf shows increased cycles spent on accessing root_mem_cgroup->stat_cpu
in count_memcg_event_mm()(called by handle_mm_fault()) and in
__mod_memcg_state() called by page_add_file_rmap(). So it's likely due
to the changed layout of 'struct mem_cgroup' that either make stat_cpu
falling into a constantly modifying cacheline or some hot fields stop
being in the same cacheline.
I verified this by moving memory_events[] back to where it was:
: --- a/include/linux/memcontrol.h
: +++ b/include/linux/memcontrol.h
: @@ -205,7 +205,6 @@ struct mem_cgroup {
: int oom_kill_disable;
:
: /* memory.events */
: - atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS];
: struct cgroup_file events_file;
:
: /* protect arrays of thresholds */
: @@ -238,6 +237,7 @@ struct mem_cgroup {
: struct mem_cgroup_stat_cpu __percpu *stat_cpu;
: atomic_long_t stat[MEMCG_NR_STAT];
: atomic_long_t events[NR_VM_EVENT_ITEMS];
: + atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS];
:
: unsigned long socket_pressure;
And performance restored.
Later investigation found that as long as the following 3 fields
moving_account, move_lock_task and stat_cpu are in the same cacheline,
performance will be good. To avoid future performance surprise by other
commits changing the layout of 'struct mem_cgroup', this patch makes
sure the 3 fields stay in the same cacheline.
One concern of this approach is, moving_account and move_lock_task could
be modified when a process changes memory cgroup while stat_cpu is a
always read field, it might hurt to place them in the same cacheline. I
assume it is rare for a process to change memory cgroup so this should
be OK.
Link: https://lkml.kernel.org/r/20180528114019.GF9904@yexl-desktop
Link: http://lkml.kernel.org/r/20180601071115.GA27302@intel.com
Signed-off-by: Aaron Lu <aaron.lu@intel.com>
Reported-by: kernel test robot <xiaolong.ye@intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-06-08 00:09:44 +00:00
|
|
|
#if defined(CONFIG_SMP)
|
|
|
|
struct memcg_padding {
|
|
|
|
char x[0];
|
|
|
|
} ____cacheline_internodealigned_in_smp;
|
|
|
|
#define MEMCG_PADDING(name) struct memcg_padding name;
|
|
|
|
#else
|
|
|
|
#define MEMCG_PADDING(name)
|
|
|
|
#endif
|
|
|
|
|
writeback, memcg: Implement foreign dirty flushing
There's an inherent mismatch between memcg and writeback. The former
trackes ownership per-page while the latter per-inode. This was a
deliberate design decision because honoring per-page ownership in the
writeback path is complicated, may lead to higher CPU and IO overheads
and deemed unnecessary given that write-sharing an inode across
different cgroups isn't a common use-case.
Combined with inode majority-writer ownership switching, this works
well enough in most cases but there are some pathological cases. For
example, let's say there are two cgroups A and B which keep writing to
different but confined parts of the same inode. B owns the inode and
A's memory is limited far below B's. A's dirty ratio can rise enough
to trigger balance_dirty_pages() sleeps but B's can be low enough to
avoid triggering background writeback. A will be slowed down without
a way to make writeback of the dirty pages happen.
This patch implements foreign dirty recording and foreign mechanism so
that when a memcg encounters a condition as above it can trigger
flushes on bdi_writebacks which can clean its pages. Please see the
comment on top of mem_cgroup_track_foreign_dirty_slowpath() for
details.
A reproducer follows.
write-range.c::
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <fcntl.h>
#include <sys/types.h>
static const char *usage = "write-range FILE START SIZE\n";
int main(int argc, char **argv)
{
int fd;
unsigned long start, size, end, pos;
char *endp;
char buf[4096];
if (argc < 4) {
fprintf(stderr, usage);
return 1;
}
fd = open(argv[1], O_WRONLY);
if (fd < 0) {
perror("open");
return 1;
}
start = strtoul(argv[2], &endp, 0);
if (*endp != '\0') {
fprintf(stderr, usage);
return 1;
}
size = strtoul(argv[3], &endp, 0);
if (*endp != '\0') {
fprintf(stderr, usage);
return 1;
}
end = start + size;
while (1) {
for (pos = start; pos < end; ) {
long bread, bwritten = 0;
if (lseek(fd, pos, SEEK_SET) < 0) {
perror("lseek");
return 1;
}
bread = read(0, buf, sizeof(buf) < end - pos ?
sizeof(buf) : end - pos);
if (bread < 0) {
perror("read");
return 1;
}
if (bread == 0)
return 0;
while (bwritten < bread) {
long this;
this = write(fd, buf + bwritten,
bread - bwritten);
if (this < 0) {
perror("write");
return 1;
}
bwritten += this;
pos += bwritten;
}
}
}
}
repro.sh::
#!/bin/bash
set -e
set -x
sysctl -w vm.dirty_expire_centisecs=300000
sysctl -w vm.dirty_writeback_centisecs=300000
sysctl -w vm.dirtytime_expire_seconds=300000
echo 3 > /proc/sys/vm/drop_caches
TEST=/sys/fs/cgroup/test
A=$TEST/A
B=$TEST/B
mkdir -p $A $B
echo "+memory +io" > $TEST/cgroup.subtree_control
echo $((1<<30)) > $A/memory.high
echo $((32<<30)) > $B/memory.high
rm -f testfile
touch testfile
fallocate -l 4G testfile
echo "Starting B"
(echo $BASHPID > $B/cgroup.procs
pv -q --rate-limit 70M < /dev/urandom | ./write-range testfile $((2<<30)) $((2<<30))) &
echo "Waiting 10s to ensure B claims the testfile inode"
sleep 5
sync
sleep 5
sync
echo "Starting A"
(echo $BASHPID > $A/cgroup.procs
pv < /dev/urandom | ./write-range testfile 0 $((2<<30)))
v2: Added comments explaining why the specific intervals are being used.
v3: Use 0 @nr when calling cgroup_writeback_by_id() to use best-effort
flushing while avoding possible livelocks.
v4: Use get_jiffies_64() and time_before/after64() instead of raw
jiffies_64 and arthimetic comparisons as suggested by Jan.
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-08-26 16:06:56 +00:00
|
|
|
/*
|
|
|
|
* Remember four most recent foreign writebacks with dirty pages in this
|
|
|
|
* cgroup. Inode sharing is expected to be uncommon and, even if we miss
|
|
|
|
* one in a given round, we're likely to catch it later if it keeps
|
|
|
|
* foreign-dirtying, so a fairly low count should be enough.
|
|
|
|
*
|
|
|
|
* See mem_cgroup_track_foreign_dirty_slowpath() for details.
|
|
|
|
*/
|
|
|
|
#define MEMCG_CGWB_FRN_CNT 4
|
|
|
|
|
|
|
|
struct memcg_cgwb_frn {
|
|
|
|
u64 bdi_id; /* bdi->id of the foreign inode */
|
|
|
|
int memcg_id; /* memcg->css.id of foreign inode */
|
|
|
|
u64 at; /* jiffies_64 at the time of dirtying */
|
|
|
|
struct wb_completion done; /* tracks in-flight foreign writebacks */
|
|
|
|
};
|
|
|
|
|
2020-08-07 06:20:49 +00:00
|
|
|
/*
|
|
|
|
* Bucket for arbitrarily byte-sized objects charged to a memory
|
|
|
|
* cgroup. The bucket can be reparented in one piece when the cgroup
|
|
|
|
* is destroyed, without having to round up the individual references
|
|
|
|
* of all live memory objects in the wild.
|
|
|
|
*/
|
|
|
|
struct obj_cgroup {
|
|
|
|
struct percpu_ref refcnt;
|
|
|
|
struct mem_cgroup *memcg;
|
|
|
|
atomic_t nr_charged_bytes;
|
|
|
|
union {
|
|
|
|
struct list_head list;
|
|
|
|
struct rcu_head rcu;
|
|
|
|
};
|
|
|
|
};
|
|
|
|
|
2015-09-08 22:01:02 +00:00
|
|
|
/*
|
|
|
|
* The memory controller data structure. The memory controller controls both
|
|
|
|
* page cache and RSS per cgroup. We would eventually like to provide
|
|
|
|
* statistics based on the statistics developed by Rik Van Riel for clock-pro,
|
|
|
|
* to help the administrator determine what knobs to tune.
|
|
|
|
*/
|
|
|
|
struct mem_cgroup {
|
|
|
|
struct cgroup_subsys_state css;
|
|
|
|
|
2016-07-20 22:44:57 +00:00
|
|
|
/* Private memcg ID. Used to ID objects that outlive the cgroup */
|
|
|
|
struct mem_cgroup_id id;
|
|
|
|
|
2015-09-08 22:01:02 +00:00
|
|
|
/* Accounted resources */
|
2020-10-13 23:52:56 +00:00
|
|
|
struct page_counter memory; /* Both v1 & v2 */
|
|
|
|
|
|
|
|
union {
|
|
|
|
struct page_counter swap; /* v2 only */
|
|
|
|
struct page_counter memsw; /* v1 only */
|
|
|
|
};
|
2016-01-20 23:02:50 +00:00
|
|
|
|
|
|
|
/* Legacy consumer-oriented counters */
|
2020-10-13 23:52:56 +00:00
|
|
|
struct page_counter kmem; /* v1 only */
|
|
|
|
struct page_counter tcpmem; /* v1 only */
|
2015-09-08 22:01:02 +00:00
|
|
|
|
2016-01-14 23:21:29 +00:00
|
|
|
/* Range enforcement for interrupt charges */
|
|
|
|
struct work_struct high_work;
|
|
|
|
|
2015-09-08 22:01:02 +00:00
|
|
|
unsigned long soft_limit;
|
|
|
|
|
|
|
|
/* vmpressure notifications */
|
|
|
|
struct vmpressure vmpressure;
|
|
|
|
|
2018-08-22 04:53:54 +00:00
|
|
|
/*
|
|
|
|
* Should the OOM killer kill all belonging tasks, had it kill one?
|
|
|
|
*/
|
|
|
|
bool oom_group;
|
|
|
|
|
2015-09-08 22:01:02 +00:00
|
|
|
/* protected by memcg_oom_lock */
|
|
|
|
bool oom_lock;
|
|
|
|
int under_oom;
|
|
|
|
|
|
|
|
int swappiness;
|
|
|
|
/* OOM-Killer disable */
|
|
|
|
int oom_kill_disable;
|
|
|
|
|
2019-07-12 03:55:55 +00:00
|
|
|
/* memory.events and memory.events.local */
|
2015-09-18 22:01:59 +00:00
|
|
|
struct cgroup_file events_file;
|
2019-07-12 03:55:55 +00:00
|
|
|
struct cgroup_file events_local_file;
|
2015-09-18 22:01:59 +00:00
|
|
|
|
2018-06-08 00:05:35 +00:00
|
|
|
/* handle for "memory.swap.events" */
|
|
|
|
struct cgroup_file swap_events_file;
|
|
|
|
|
2015-09-08 22:01:02 +00:00
|
|
|
/* protect arrays of thresholds */
|
|
|
|
struct mutex thresholds_lock;
|
|
|
|
|
|
|
|
/* thresholds for memory usage. RCU-protected */
|
|
|
|
struct mem_cgroup_thresholds thresholds;
|
|
|
|
|
|
|
|
/* thresholds for mem+swap usage. RCU-protected */
|
|
|
|
struct mem_cgroup_thresholds memsw_thresholds;
|
|
|
|
|
|
|
|
/* For oom notifier event fd */
|
|
|
|
struct list_head oom_notify;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Should we move charges of a task when a task is moved into this
|
|
|
|
* mem_cgroup ? And what type of charges should we move ?
|
|
|
|
*/
|
|
|
|
unsigned long move_charge_at_immigrate;
|
mem_cgroup: make sure moving_account, move_lock_task and stat_cpu in the same cacheline
The LKP robot found a 27% will-it-scale/page_fault3 performance
regression regarding commit e27be240df53("mm: memcg: make sure
memory.events is uptodate when waking pollers").
What the test does is:
1 mkstemp() a 128M file on a tmpfs;
2 start $nr_cpu processes, each to loop the following:
2.1 mmap() this file in shared write mode;
2.2 write 0 to this file in a PAGE_SIZE step till the end of the file;
2.3 unmap() this file and repeat this process.
3 After 5 minutes, check how many loops they managed to complete, the
higher the better.
The commit itself looks innocent enough as it merely changed some event
counting mechanism and this test didn't trigger those events at all.
Perf shows increased cycles spent on accessing root_mem_cgroup->stat_cpu
in count_memcg_event_mm()(called by handle_mm_fault()) and in
__mod_memcg_state() called by page_add_file_rmap(). So it's likely due
to the changed layout of 'struct mem_cgroup' that either make stat_cpu
falling into a constantly modifying cacheline or some hot fields stop
being in the same cacheline.
I verified this by moving memory_events[] back to where it was:
: --- a/include/linux/memcontrol.h
: +++ b/include/linux/memcontrol.h
: @@ -205,7 +205,6 @@ struct mem_cgroup {
: int oom_kill_disable;
:
: /* memory.events */
: - atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS];
: struct cgroup_file events_file;
:
: /* protect arrays of thresholds */
: @@ -238,6 +237,7 @@ struct mem_cgroup {
: struct mem_cgroup_stat_cpu __percpu *stat_cpu;
: atomic_long_t stat[MEMCG_NR_STAT];
: atomic_long_t events[NR_VM_EVENT_ITEMS];
: + atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS];
:
: unsigned long socket_pressure;
And performance restored.
Later investigation found that as long as the following 3 fields
moving_account, move_lock_task and stat_cpu are in the same cacheline,
performance will be good. To avoid future performance surprise by other
commits changing the layout of 'struct mem_cgroup', this patch makes
sure the 3 fields stay in the same cacheline.
One concern of this approach is, moving_account and move_lock_task could
be modified when a process changes memory cgroup while stat_cpu is a
always read field, it might hurt to place them in the same cacheline. I
assume it is rare for a process to change memory cgroup so this should
be OK.
Link: https://lkml.kernel.org/r/20180528114019.GF9904@yexl-desktop
Link: http://lkml.kernel.org/r/20180601071115.GA27302@intel.com
Signed-off-by: Aaron Lu <aaron.lu@intel.com>
Reported-by: kernel test robot <xiaolong.ye@intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-06-08 00:09:44 +00:00
|
|
|
/* taken only while moving_account > 0 */
|
|
|
|
spinlock_t move_lock;
|
|
|
|
unsigned long move_lock_flags;
|
|
|
|
|
|
|
|
MEMCG_PADDING(_pad1_);
|
|
|
|
|
2019-05-14 22:46:57 +00:00
|
|
|
atomic_long_t vmstats[MEMCG_NR_STAT];
|
|
|
|
atomic_long_t vmevents[NR_VM_EVENT_ITEMS];
|
mm: memcontrol: fix recursive statistics correctness & scalabilty
Right now, when somebody needs to know the recursive memory statistics
and events of a cgroup subtree, they need to walk the entire subtree and
sum up the counters manually.
There are two issues with this:
1. When a cgroup gets deleted, its stats are lost. The state counters
should all be 0 at that point, of course, but the events are not.
When this happens, the event counters, which are supposed to be
monotonic, can go backwards in the parent cgroups.
2. During regular operation, we always have a certain number of lazily
freed cgroups sitting around that have been deleted, have no tasks,
but have a few cache pages remaining. These groups' statistics do not
change until we eventually hit memory pressure, but somebody
watching, say, memory.stat on an ancestor has to iterate those every
time.
This patch addresses both issues by introducing recursive counters at
each level that are propagated from the write side when stats change.
Upward propagation happens when the per-cpu caches spill over into the
local atomic counter. This is the same thing we do during charge and
uncharge, except that the latter uses atomic RMWs, which are more
expensive; stat changes happen at around the same rate. In a sparse
file test (page faults and reclaim at maximum CPU speed) with 5 cgroup
nesting levels, perf shows __mod_memcg_page state at ~1%.
Link: http://lkml.kernel.org/r/20190412151507.2769-4-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Reviewed-by: Roman Gushchin <guro@fb.com>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 22:47:12 +00:00
|
|
|
|
mm: memcontrol: don't batch updates of local VM stats and events
The kernel test robot noticed a 26% will-it-scale pagefault regression
from commit 42a300353577 ("mm: memcontrol: fix recursive statistics
correctness & scalabilty"). This appears to be caused by bouncing the
additional cachelines from the new hierarchical statistics counters.
We can fix this by getting rid of the batched local counters instead.
Originally, there were *only* group-local counters, and they were fully
maintained per cpu. A reader of a stats file high up in the cgroup tree
would have to walk the entire subtree and collect each level's per-cpu
counters to get the recursive view. This was prohibitively expensive,
and so we switched to per-cpu batched updates of the local counters
during a983b5ebee57 ("mm: memcontrol: fix excessive complexity in
memory.stat reporting"), reducing the complexity from nr_subgroups *
nr_cpus to nr_subgroups.
With growing machines and cgroup trees, the tree walk itself became too
expensive for monitoring top-level groups, and this is when the culprit
patch added hierarchy counters on each cgroup level. When the per-cpu
batch size would be reached, both the local and the hierarchy counters
would get batch-updated from the per-cpu delta simultaneously.
This makes local and hierarchical counter reads blazingly fast, but it
unfortunately makes the write-side too cache line intense.
Since local counter reads were never a problem - we only centralized
them to accelerate the hierarchy walk - and use of the local counters
are becoming rarer due to replacement with hierarchical views (ongoing
rework in the page reclaim and workingset code), we can make those local
counters unbatched per-cpu counters again.
The scheme will then be as such:
when a memcg statistic changes, the writer will:
- update the local counter (per-cpu)
- update the batch counter (per-cpu). If the batch is full:
- spill the batch into the group's atomic_t
- spill the batch into all ancestors' atomic_ts
- empty out the batch counter (per-cpu)
when a local memcg counter is read, the reader will:
- collect the local counter from all cpus
when a hiearchy memcg counter is read, the reader will:
- read the atomic_t
We might be able to simplify this further and make the recursive
counters unbatched per-cpu counters as well (batch upward propagation,
but leave per-cpu collection to the readers), but that will require a
more in-depth analysis and testing of all the callsites. Deal with the
immediate regression for now.
Link: http://lkml.kernel.org/r/20190521151647.GB2870@cmpxchg.org
Fixes: 42a300353577 ("mm: memcontrol: fix recursive statistics correctness & scalabilty")
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: kernel test robot <rong.a.chen@intel.com>
Tested-by: kernel test robot <rong.a.chen@intel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-06-13 22:55:46 +00:00
|
|
|
/* memory.events */
|
mm: memcontrol: fix recursive statistics correctness & scalabilty
Right now, when somebody needs to know the recursive memory statistics
and events of a cgroup subtree, they need to walk the entire subtree and
sum up the counters manually.
There are two issues with this:
1. When a cgroup gets deleted, its stats are lost. The state counters
should all be 0 at that point, of course, but the events are not.
When this happens, the event counters, which are supposed to be
monotonic, can go backwards in the parent cgroups.
2. During regular operation, we always have a certain number of lazily
freed cgroups sitting around that have been deleted, have no tasks,
but have a few cache pages remaining. These groups' statistics do not
change until we eventually hit memory pressure, but somebody
watching, say, memory.stat on an ancestor has to iterate those every
time.
This patch addresses both issues by introducing recursive counters at
each level that are propagated from the write side when stats change.
Upward propagation happens when the per-cpu caches spill over into the
local atomic counter. This is the same thing we do during charge and
uncharge, except that the latter uses atomic RMWs, which are more
expensive; stat changes happen at around the same rate. In a sparse
file test (page faults and reclaim at maximum CPU speed) with 5 cgroup
nesting levels, perf shows __mod_memcg_page state at ~1%.
Link: http://lkml.kernel.org/r/20190412151507.2769-4-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Reviewed-by: Roman Gushchin <guro@fb.com>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 22:47:12 +00:00
|
|
|
atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS];
|
2019-07-12 03:55:55 +00:00
|
|
|
atomic_long_t memory_events_local[MEMCG_NR_MEMORY_EVENTS];
|
2015-09-08 22:01:02 +00:00
|
|
|
|
2016-01-20 23:02:47 +00:00
|
|
|
unsigned long socket_pressure;
|
|
|
|
|
|
|
|
/* Legacy tcp memory accounting */
|
2016-01-20 23:02:50 +00:00
|
|
|
bool tcpmem_active;
|
|
|
|
int tcpmem_pressure;
|
2016-01-20 23:02:47 +00:00
|
|
|
|
2018-08-17 22:47:25 +00:00
|
|
|
#ifdef CONFIG_MEMCG_KMEM
|
2015-09-08 22:01:02 +00:00
|
|
|
int kmemcg_id;
|
2016-01-20 23:02:24 +00:00
|
|
|
enum memcg_kmem_state kmem_state;
|
2020-08-07 06:20:49 +00:00
|
|
|
struct obj_cgroup __rcu *objcg;
|
|
|
|
struct list_head objcg_list; /* list of inherited objcgs */
|
2015-09-08 22:01:02 +00:00
|
|
|
#endif
|
|
|
|
|
mm: memcg: relayout structure mem_cgroup to avoid cache interference
0day reported one -22.7% regression for will-it-scale page_fault2
case [1] on a 4 sockets 144 CPU platform, and bisected to it to be
caused by Waiman's optimization (commit bd0b230fe1) of saving one
'struct page_counter' space for 'struct mem_cgroup'.
Initially we thought it was due to the cache alignment change introduced
by the patch, but further debug shows that it is due to some hot data
members ('vmstats_local', 'vmstats_percpu', 'vmstats') sit in 2 adjacent
cacheline (2N and 2N+1 cacheline), and when adjacent cache line prefetch
is enabled, it triggers an "extended level" of cache false sharing for
2 adjacent cache lines.
So exchange the 2 member blocks, while keeping mostly the original
cache alignment, which can restore and even enhance the performance,
and save 64 bytes of space for 'struct mem_cgroup' (from 2880 to 2816,
with 0day's default RHEL-8.3 kernel config)
[1]. https://lore.kernel.org/lkml/20201102091543.GM31092@shao2-debian/
Fixes: bd0b230fe145 ("mm/memcg: unify swap and memsw page counters")
Reported-by: kernel test robot <rong.a.chen@intel.com>
Signed-off-by: Feng Tang <feng.tang@intel.com>
Acked-by: Waiman Long <longman@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-11-25 05:22:21 +00:00
|
|
|
MEMCG_PADDING(_pad2_);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* set > 0 if pages under this cgroup are moving to other cgroup.
|
|
|
|
*/
|
|
|
|
atomic_t moving_account;
|
|
|
|
struct task_struct *move_lock_task;
|
|
|
|
|
|
|
|
/* Legacy local VM stats and events */
|
|
|
|
struct memcg_vmstats_percpu __percpu *vmstats_local;
|
|
|
|
|
|
|
|
/* Subtree VM stats and events (batched updates) */
|
|
|
|
struct memcg_vmstats_percpu __percpu *vmstats_percpu;
|
|
|
|
|
2015-09-08 22:01:02 +00:00
|
|
|
#ifdef CONFIG_CGROUP_WRITEBACK
|
|
|
|
struct list_head cgwb_list;
|
|
|
|
struct wb_domain cgwb_domain;
|
writeback, memcg: Implement foreign dirty flushing
There's an inherent mismatch between memcg and writeback. The former
trackes ownership per-page while the latter per-inode. This was a
deliberate design decision because honoring per-page ownership in the
writeback path is complicated, may lead to higher CPU and IO overheads
and deemed unnecessary given that write-sharing an inode across
different cgroups isn't a common use-case.
Combined with inode majority-writer ownership switching, this works
well enough in most cases but there are some pathological cases. For
example, let's say there are two cgroups A and B which keep writing to
different but confined parts of the same inode. B owns the inode and
A's memory is limited far below B's. A's dirty ratio can rise enough
to trigger balance_dirty_pages() sleeps but B's can be low enough to
avoid triggering background writeback. A will be slowed down without
a way to make writeback of the dirty pages happen.
This patch implements foreign dirty recording and foreign mechanism so
that when a memcg encounters a condition as above it can trigger
flushes on bdi_writebacks which can clean its pages. Please see the
comment on top of mem_cgroup_track_foreign_dirty_slowpath() for
details.
A reproducer follows.
write-range.c::
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <fcntl.h>
#include <sys/types.h>
static const char *usage = "write-range FILE START SIZE\n";
int main(int argc, char **argv)
{
int fd;
unsigned long start, size, end, pos;
char *endp;
char buf[4096];
if (argc < 4) {
fprintf(stderr, usage);
return 1;
}
fd = open(argv[1], O_WRONLY);
if (fd < 0) {
perror("open");
return 1;
}
start = strtoul(argv[2], &endp, 0);
if (*endp != '\0') {
fprintf(stderr, usage);
return 1;
}
size = strtoul(argv[3], &endp, 0);
if (*endp != '\0') {
fprintf(stderr, usage);
return 1;
}
end = start + size;
while (1) {
for (pos = start; pos < end; ) {
long bread, bwritten = 0;
if (lseek(fd, pos, SEEK_SET) < 0) {
perror("lseek");
return 1;
}
bread = read(0, buf, sizeof(buf) < end - pos ?
sizeof(buf) : end - pos);
if (bread < 0) {
perror("read");
return 1;
}
if (bread == 0)
return 0;
while (bwritten < bread) {
long this;
this = write(fd, buf + bwritten,
bread - bwritten);
if (this < 0) {
perror("write");
return 1;
}
bwritten += this;
pos += bwritten;
}
}
}
}
repro.sh::
#!/bin/bash
set -e
set -x
sysctl -w vm.dirty_expire_centisecs=300000
sysctl -w vm.dirty_writeback_centisecs=300000
sysctl -w vm.dirtytime_expire_seconds=300000
echo 3 > /proc/sys/vm/drop_caches
TEST=/sys/fs/cgroup/test
A=$TEST/A
B=$TEST/B
mkdir -p $A $B
echo "+memory +io" > $TEST/cgroup.subtree_control
echo $((1<<30)) > $A/memory.high
echo $((32<<30)) > $B/memory.high
rm -f testfile
touch testfile
fallocate -l 4G testfile
echo "Starting B"
(echo $BASHPID > $B/cgroup.procs
pv -q --rate-limit 70M < /dev/urandom | ./write-range testfile $((2<<30)) $((2<<30))) &
echo "Waiting 10s to ensure B claims the testfile inode"
sleep 5
sync
sleep 5
sync
echo "Starting A"
(echo $BASHPID > $A/cgroup.procs
pv < /dev/urandom | ./write-range testfile 0 $((2<<30)))
v2: Added comments explaining why the specific intervals are being used.
v3: Use 0 @nr when calling cgroup_writeback_by_id() to use best-effort
flushing while avoding possible livelocks.
v4: Use get_jiffies_64() and time_before/after64() instead of raw
jiffies_64 and arthimetic comparisons as suggested by Jan.
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-08-26 16:06:56 +00:00
|
|
|
struct memcg_cgwb_frn cgwb_frn[MEMCG_CGWB_FRN_CNT];
|
2015-09-08 22:01:02 +00:00
|
|
|
#endif
|
|
|
|
|
|
|
|
/* List of events which userspace want to receive */
|
|
|
|
struct list_head event_list;
|
|
|
|
spinlock_t event_list_lock;
|
|
|
|
|
2019-09-23 22:38:15 +00:00
|
|
|
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
|
|
|
|
struct deferred_split deferred_split_queue;
|
|
|
|
#endif
|
|
|
|
|
2015-09-08 22:01:02 +00:00
|
|
|
struct mem_cgroup_per_node *nodeinfo[0];
|
|
|
|
/* WARNING: nodeinfo must be the last member here */
|
|
|
|
};
|
2016-01-14 23:20:56 +00:00
|
|
|
|
2018-02-01 00:16:45 +00:00
|
|
|
/*
|
|
|
|
* size of first charge trial. "32" comes from vmscan.c's magic value.
|
|
|
|
* TODO: maybe necessary to use big numbers in big irons.
|
|
|
|
*/
|
|
|
|
#define MEMCG_CHARGE_BATCH 32U
|
|
|
|
|
2016-01-14 23:20:56 +00:00
|
|
|
extern struct mem_cgroup *root_mem_cgroup;
|
2015-05-22 21:13:20 +00:00
|
|
|
|
2020-12-01 21:58:29 +00:00
|
|
|
enum page_memcg_data_flags {
|
|
|
|
/* page->memcg_data is a pointer to an objcgs vector */
|
|
|
|
MEMCG_DATA_OBJCGS = (1UL << 0),
|
2020-12-01 21:58:30 +00:00
|
|
|
/* page has been accounted as a non-slab kernel page */
|
|
|
|
MEMCG_DATA_KMEM = (1UL << 1),
|
2020-12-01 21:58:29 +00:00
|
|
|
/* the next bit after the last actual flag */
|
2020-12-01 21:58:30 +00:00
|
|
|
__NR_MEMCG_DATA_FLAGS = (1UL << 2),
|
2020-12-01 21:58:29 +00:00
|
|
|
};
|
|
|
|
|
|
|
|
#define MEMCG_DATA_FLAGS_MASK (__NR_MEMCG_DATA_FLAGS - 1)
|
|
|
|
|
mm: memcontrol: Use helpers to read page's memcg data
Patch series "mm: allow mapping accounted kernel pages to userspace", v6.
Currently a non-slab kernel page which has been charged to a memory cgroup
can't be mapped to userspace. The underlying reason is simple: PageKmemcg
flag is defined as a page type (like buddy, offline, etc), so it takes a
bit from a page->mapped counter. Pages with a type set can't be mapped to
userspace.
But in general the kmemcg flag has nothing to do with mapping to
userspace. It only means that the page has been accounted by the page
allocator, so it has to be properly uncharged on release.
Some bpf maps are mapping the vmalloc-based memory to userspace, and their
memory can't be accounted because of this implementation detail.
This patchset removes this limitation by moving the PageKmemcg flag into
one of the free bits of the page->mem_cgroup pointer. Also it formalizes
accesses to the page->mem_cgroup and page->obj_cgroups using new helpers,
adds several checks and removes a couple of obsolete functions. As the
result the code became more robust with fewer open-coded bit tricks.
This patch (of 4):
Currently there are many open-coded reads of the page->mem_cgroup pointer,
as well as a couple of read helpers, which are barely used.
It creates an obstacle on a way to reuse some bits of the pointer for
storing additional bits of information. In fact, we already do this for
slab pages, where the last bit indicates that a pointer has an attached
vector of objcg pointers instead of a regular memcg pointer.
This commits uses 2 existing helpers and introduces a new helper to
converts all read sides to calls of these helpers:
struct mem_cgroup *page_memcg(struct page *page);
struct mem_cgroup *page_memcg_rcu(struct page *page);
struct mem_cgroup *page_memcg_check(struct page *page);
page_memcg_check() is intended to be used in cases when the page can be a
slab page and have a memcg pointer pointing at objcg vector. It does
check the lowest bit, and if set, returns NULL. page_memcg() contains a
VM_BUG_ON_PAGE() check for the page not being a slab page.
To make sure nobody uses a direct access, struct page's
mem_cgroup/obj_cgroups is converted to unsigned long memcg_data.
Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Link: https://lkml.kernel.org/r/20201027001657.3398190-1-guro@fb.com
Link: https://lkml.kernel.org/r/20201027001657.3398190-2-guro@fb.com
Link: https://lore.kernel.org/bpf/20201201215900.3569844-2-guro@fb.com
2020-12-01 21:58:27 +00:00
|
|
|
/*
|
|
|
|
* page_memcg - get the memory cgroup associated with a page
|
|
|
|
* @page: a pointer to the page struct
|
|
|
|
*
|
|
|
|
* Returns a pointer to the memory cgroup associated with the page,
|
|
|
|
* or NULL. This function assumes that the page is known to have a
|
|
|
|
* proper memory cgroup pointer. It's not safe to call this function
|
|
|
|
* against some type of pages, e.g. slab pages or ex-slab pages.
|
|
|
|
*
|
|
|
|
* Any of the following ensures page and memcg binding stability:
|
|
|
|
* - the page lock
|
|
|
|
* - LRU isolation
|
|
|
|
* - lock_page_memcg()
|
|
|
|
* - exclusive reference
|
|
|
|
*/
|
|
|
|
static inline struct mem_cgroup *page_memcg(struct page *page)
|
|
|
|
{
|
2020-12-01 21:58:30 +00:00
|
|
|
unsigned long memcg_data = page->memcg_data;
|
|
|
|
|
mm: memcontrol: Use helpers to read page's memcg data
Patch series "mm: allow mapping accounted kernel pages to userspace", v6.
Currently a non-slab kernel page which has been charged to a memory cgroup
can't be mapped to userspace. The underlying reason is simple: PageKmemcg
flag is defined as a page type (like buddy, offline, etc), so it takes a
bit from a page->mapped counter. Pages with a type set can't be mapped to
userspace.
But in general the kmemcg flag has nothing to do with mapping to
userspace. It only means that the page has been accounted by the page
allocator, so it has to be properly uncharged on release.
Some bpf maps are mapping the vmalloc-based memory to userspace, and their
memory can't be accounted because of this implementation detail.
This patchset removes this limitation by moving the PageKmemcg flag into
one of the free bits of the page->mem_cgroup pointer. Also it formalizes
accesses to the page->mem_cgroup and page->obj_cgroups using new helpers,
adds several checks and removes a couple of obsolete functions. As the
result the code became more robust with fewer open-coded bit tricks.
This patch (of 4):
Currently there are many open-coded reads of the page->mem_cgroup pointer,
as well as a couple of read helpers, which are barely used.
It creates an obstacle on a way to reuse some bits of the pointer for
storing additional bits of information. In fact, we already do this for
slab pages, where the last bit indicates that a pointer has an attached
vector of objcg pointers instead of a regular memcg pointer.
This commits uses 2 existing helpers and introduces a new helper to
converts all read sides to calls of these helpers:
struct mem_cgroup *page_memcg(struct page *page);
struct mem_cgroup *page_memcg_rcu(struct page *page);
struct mem_cgroup *page_memcg_check(struct page *page);
page_memcg_check() is intended to be used in cases when the page can be a
slab page and have a memcg pointer pointing at objcg vector. It does
check the lowest bit, and if set, returns NULL. page_memcg() contains a
VM_BUG_ON_PAGE() check for the page not being a slab page.
To make sure nobody uses a direct access, struct page's
mem_cgroup/obj_cgroups is converted to unsigned long memcg_data.
Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Link: https://lkml.kernel.org/r/20201027001657.3398190-1-guro@fb.com
Link: https://lkml.kernel.org/r/20201027001657.3398190-2-guro@fb.com
Link: https://lore.kernel.org/bpf/20201201215900.3569844-2-guro@fb.com
2020-12-01 21:58:27 +00:00
|
|
|
VM_BUG_ON_PAGE(PageSlab(page), page);
|
2020-12-01 21:58:30 +00:00
|
|
|
VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_OBJCGS, page);
|
|
|
|
|
|
|
|
return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
|
mm: memcontrol: Use helpers to read page's memcg data
Patch series "mm: allow mapping accounted kernel pages to userspace", v6.
Currently a non-slab kernel page which has been charged to a memory cgroup
can't be mapped to userspace. The underlying reason is simple: PageKmemcg
flag is defined as a page type (like buddy, offline, etc), so it takes a
bit from a page->mapped counter. Pages with a type set can't be mapped to
userspace.
But in general the kmemcg flag has nothing to do with mapping to
userspace. It only means that the page has been accounted by the page
allocator, so it has to be properly uncharged on release.
Some bpf maps are mapping the vmalloc-based memory to userspace, and their
memory can't be accounted because of this implementation detail.
This patchset removes this limitation by moving the PageKmemcg flag into
one of the free bits of the page->mem_cgroup pointer. Also it formalizes
accesses to the page->mem_cgroup and page->obj_cgroups using new helpers,
adds several checks and removes a couple of obsolete functions. As the
result the code became more robust with fewer open-coded bit tricks.
This patch (of 4):
Currently there are many open-coded reads of the page->mem_cgroup pointer,
as well as a couple of read helpers, which are barely used.
It creates an obstacle on a way to reuse some bits of the pointer for
storing additional bits of information. In fact, we already do this for
slab pages, where the last bit indicates that a pointer has an attached
vector of objcg pointers instead of a regular memcg pointer.
This commits uses 2 existing helpers and introduces a new helper to
converts all read sides to calls of these helpers:
struct mem_cgroup *page_memcg(struct page *page);
struct mem_cgroup *page_memcg_rcu(struct page *page);
struct mem_cgroup *page_memcg_check(struct page *page);
page_memcg_check() is intended to be used in cases when the page can be a
slab page and have a memcg pointer pointing at objcg vector. It does
check the lowest bit, and if set, returns NULL. page_memcg() contains a
VM_BUG_ON_PAGE() check for the page not being a slab page.
To make sure nobody uses a direct access, struct page's
mem_cgroup/obj_cgroups is converted to unsigned long memcg_data.
Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Link: https://lkml.kernel.org/r/20201027001657.3398190-1-guro@fb.com
Link: https://lkml.kernel.org/r/20201027001657.3398190-2-guro@fb.com
Link: https://lore.kernel.org/bpf/20201201215900.3569844-2-guro@fb.com
2020-12-01 21:58:27 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* page_memcg_rcu - locklessly get the memory cgroup associated with a page
|
|
|
|
* @page: a pointer to the page struct
|
|
|
|
*
|
|
|
|
* Returns a pointer to the memory cgroup associated with the page,
|
|
|
|
* or NULL. This function assumes that the page is known to have a
|
|
|
|
* proper memory cgroup pointer. It's not safe to call this function
|
|
|
|
* against some type of pages, e.g. slab pages or ex-slab pages.
|
|
|
|
*/
|
|
|
|
static inline struct mem_cgroup *page_memcg_rcu(struct page *page)
|
|
|
|
{
|
|
|
|
VM_BUG_ON_PAGE(PageSlab(page), page);
|
|
|
|
WARN_ON_ONCE(!rcu_read_lock_held());
|
|
|
|
|
2020-12-01 21:58:30 +00:00
|
|
|
return (struct mem_cgroup *)(READ_ONCE(page->memcg_data) &
|
|
|
|
~MEMCG_DATA_FLAGS_MASK);
|
mm: memcontrol: Use helpers to read page's memcg data
Patch series "mm: allow mapping accounted kernel pages to userspace", v6.
Currently a non-slab kernel page which has been charged to a memory cgroup
can't be mapped to userspace. The underlying reason is simple: PageKmemcg
flag is defined as a page type (like buddy, offline, etc), so it takes a
bit from a page->mapped counter. Pages with a type set can't be mapped to
userspace.
But in general the kmemcg flag has nothing to do with mapping to
userspace. It only means that the page has been accounted by the page
allocator, so it has to be properly uncharged on release.
Some bpf maps are mapping the vmalloc-based memory to userspace, and their
memory can't be accounted because of this implementation detail.
This patchset removes this limitation by moving the PageKmemcg flag into
one of the free bits of the page->mem_cgroup pointer. Also it formalizes
accesses to the page->mem_cgroup and page->obj_cgroups using new helpers,
adds several checks and removes a couple of obsolete functions. As the
result the code became more robust with fewer open-coded bit tricks.
This patch (of 4):
Currently there are many open-coded reads of the page->mem_cgroup pointer,
as well as a couple of read helpers, which are barely used.
It creates an obstacle on a way to reuse some bits of the pointer for
storing additional bits of information. In fact, we already do this for
slab pages, where the last bit indicates that a pointer has an attached
vector of objcg pointers instead of a regular memcg pointer.
This commits uses 2 existing helpers and introduces a new helper to
converts all read sides to calls of these helpers:
struct mem_cgroup *page_memcg(struct page *page);
struct mem_cgroup *page_memcg_rcu(struct page *page);
struct mem_cgroup *page_memcg_check(struct page *page);
page_memcg_check() is intended to be used in cases when the page can be a
slab page and have a memcg pointer pointing at objcg vector. It does
check the lowest bit, and if set, returns NULL. page_memcg() contains a
VM_BUG_ON_PAGE() check for the page not being a slab page.
To make sure nobody uses a direct access, struct page's
mem_cgroup/obj_cgroups is converted to unsigned long memcg_data.
Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Link: https://lkml.kernel.org/r/20201027001657.3398190-1-guro@fb.com
Link: https://lkml.kernel.org/r/20201027001657.3398190-2-guro@fb.com
Link: https://lore.kernel.org/bpf/20201201215900.3569844-2-guro@fb.com
2020-12-01 21:58:27 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* page_memcg_check - get the memory cgroup associated with a page
|
|
|
|
* @page: a pointer to the page struct
|
|
|
|
*
|
|
|
|
* Returns a pointer to the memory cgroup associated with the page,
|
|
|
|
* or NULL. This function unlike page_memcg() can take any page
|
|
|
|
* as an argument. It has to be used in cases when it's not known if a page
|
|
|
|
* has an associated memory cgroup pointer or an object cgroups vector.
|
|
|
|
*
|
|
|
|
* Any of the following ensures page and memcg binding stability:
|
|
|
|
* - the page lock
|
|
|
|
* - LRU isolation
|
|
|
|
* - lock_page_memcg()
|
|
|
|
* - exclusive reference
|
|
|
|
*/
|
|
|
|
static inline struct mem_cgroup *page_memcg_check(struct page *page)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* Because page->memcg_data might be changed asynchronously
|
|
|
|
* for slab pages, READ_ONCE() should be used here.
|
|
|
|
*/
|
|
|
|
unsigned long memcg_data = READ_ONCE(page->memcg_data);
|
|
|
|
|
2020-12-01 21:58:29 +00:00
|
|
|
if (memcg_data & MEMCG_DATA_OBJCGS)
|
mm: memcontrol: Use helpers to read page's memcg data
Patch series "mm: allow mapping accounted kernel pages to userspace", v6.
Currently a non-slab kernel page which has been charged to a memory cgroup
can't be mapped to userspace. The underlying reason is simple: PageKmemcg
flag is defined as a page type (like buddy, offline, etc), so it takes a
bit from a page->mapped counter. Pages with a type set can't be mapped to
userspace.
But in general the kmemcg flag has nothing to do with mapping to
userspace. It only means that the page has been accounted by the page
allocator, so it has to be properly uncharged on release.
Some bpf maps are mapping the vmalloc-based memory to userspace, and their
memory can't be accounted because of this implementation detail.
This patchset removes this limitation by moving the PageKmemcg flag into
one of the free bits of the page->mem_cgroup pointer. Also it formalizes
accesses to the page->mem_cgroup and page->obj_cgroups using new helpers,
adds several checks and removes a couple of obsolete functions. As the
result the code became more robust with fewer open-coded bit tricks.
This patch (of 4):
Currently there are many open-coded reads of the page->mem_cgroup pointer,
as well as a couple of read helpers, which are barely used.
It creates an obstacle on a way to reuse some bits of the pointer for
storing additional bits of information. In fact, we already do this for
slab pages, where the last bit indicates that a pointer has an attached
vector of objcg pointers instead of a regular memcg pointer.
This commits uses 2 existing helpers and introduces a new helper to
converts all read sides to calls of these helpers:
struct mem_cgroup *page_memcg(struct page *page);
struct mem_cgroup *page_memcg_rcu(struct page *page);
struct mem_cgroup *page_memcg_check(struct page *page);
page_memcg_check() is intended to be used in cases when the page can be a
slab page and have a memcg pointer pointing at objcg vector. It does
check the lowest bit, and if set, returns NULL. page_memcg() contains a
VM_BUG_ON_PAGE() check for the page not being a slab page.
To make sure nobody uses a direct access, struct page's
mem_cgroup/obj_cgroups is converted to unsigned long memcg_data.
Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Link: https://lkml.kernel.org/r/20201027001657.3398190-1-guro@fb.com
Link: https://lkml.kernel.org/r/20201027001657.3398190-2-guro@fb.com
Link: https://lore.kernel.org/bpf/20201201215900.3569844-2-guro@fb.com
2020-12-01 21:58:27 +00:00
|
|
|
return NULL;
|
|
|
|
|
2020-12-01 21:58:30 +00:00
|
|
|
return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* PageMemcgKmem - check if the page has MemcgKmem flag set
|
|
|
|
* @page: a pointer to the page struct
|
|
|
|
*
|
|
|
|
* Checks if the page has MemcgKmem flag set. The caller must ensure that
|
|
|
|
* the page has an associated memory cgroup. It's not safe to call this function
|
|
|
|
* against some types of pages, e.g. slab pages.
|
|
|
|
*/
|
|
|
|
static inline bool PageMemcgKmem(struct page *page)
|
|
|
|
{
|
|
|
|
VM_BUG_ON_PAGE(page->memcg_data & MEMCG_DATA_OBJCGS, page);
|
|
|
|
return page->memcg_data & MEMCG_DATA_KMEM;
|
mm: memcontrol: Use helpers to read page's memcg data
Patch series "mm: allow mapping accounted kernel pages to userspace", v6.
Currently a non-slab kernel page which has been charged to a memory cgroup
can't be mapped to userspace. The underlying reason is simple: PageKmemcg
flag is defined as a page type (like buddy, offline, etc), so it takes a
bit from a page->mapped counter. Pages with a type set can't be mapped to
userspace.
But in general the kmemcg flag has nothing to do with mapping to
userspace. It only means that the page has been accounted by the page
allocator, so it has to be properly uncharged on release.
Some bpf maps are mapping the vmalloc-based memory to userspace, and their
memory can't be accounted because of this implementation detail.
This patchset removes this limitation by moving the PageKmemcg flag into
one of the free bits of the page->mem_cgroup pointer. Also it formalizes
accesses to the page->mem_cgroup and page->obj_cgroups using new helpers,
adds several checks and removes a couple of obsolete functions. As the
result the code became more robust with fewer open-coded bit tricks.
This patch (of 4):
Currently there are many open-coded reads of the page->mem_cgroup pointer,
as well as a couple of read helpers, which are barely used.
It creates an obstacle on a way to reuse some bits of the pointer for
storing additional bits of information. In fact, we already do this for
slab pages, where the last bit indicates that a pointer has an attached
vector of objcg pointers instead of a regular memcg pointer.
This commits uses 2 existing helpers and introduces a new helper to
converts all read sides to calls of these helpers:
struct mem_cgroup *page_memcg(struct page *page);
struct mem_cgroup *page_memcg_rcu(struct page *page);
struct mem_cgroup *page_memcg_check(struct page *page);
page_memcg_check() is intended to be used in cases when the page can be a
slab page and have a memcg pointer pointing at objcg vector. It does
check the lowest bit, and if set, returns NULL. page_memcg() contains a
VM_BUG_ON_PAGE() check for the page not being a slab page.
To make sure nobody uses a direct access, struct page's
mem_cgroup/obj_cgroups is converted to unsigned long memcg_data.
Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Link: https://lkml.kernel.org/r/20201027001657.3398190-1-guro@fb.com
Link: https://lkml.kernel.org/r/20201027001657.3398190-2-guro@fb.com
Link: https://lore.kernel.org/bpf/20201201215900.3569844-2-guro@fb.com
2020-12-01 21:58:27 +00:00
|
|
|
}
|
|
|
|
|
2020-12-01 21:58:28 +00:00
|
|
|
#ifdef CONFIG_MEMCG_KMEM
|
|
|
|
/*
|
|
|
|
* page_objcgs - get the object cgroups vector associated with a page
|
|
|
|
* @page: a pointer to the page struct
|
|
|
|
*
|
|
|
|
* Returns a pointer to the object cgroups vector associated with the page,
|
|
|
|
* or NULL. This function assumes that the page is known to have an
|
|
|
|
* associated object cgroups vector. It's not safe to call this function
|
|
|
|
* against pages, which might have an associated memory cgroup: e.g.
|
|
|
|
* kernel stack pages.
|
|
|
|
*/
|
|
|
|
static inline struct obj_cgroup **page_objcgs(struct page *page)
|
|
|
|
{
|
2020-12-01 21:58:29 +00:00
|
|
|
unsigned long memcg_data = READ_ONCE(page->memcg_data);
|
|
|
|
|
|
|
|
VM_BUG_ON_PAGE(memcg_data && !(memcg_data & MEMCG_DATA_OBJCGS), page);
|
2020-12-01 21:58:30 +00:00
|
|
|
VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, page);
|
2020-12-01 21:58:29 +00:00
|
|
|
|
|
|
|
return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
|
2020-12-01 21:58:28 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* page_objcgs_check - get the object cgroups vector associated with a page
|
|
|
|
* @page: a pointer to the page struct
|
|
|
|
*
|
|
|
|
* Returns a pointer to the object cgroups vector associated with the page,
|
|
|
|
* or NULL. This function is safe to use if the page can be directly associated
|
|
|
|
* with a memory cgroup.
|
|
|
|
*/
|
|
|
|
static inline struct obj_cgroup **page_objcgs_check(struct page *page)
|
|
|
|
{
|
|
|
|
unsigned long memcg_data = READ_ONCE(page->memcg_data);
|
|
|
|
|
2020-12-01 21:58:29 +00:00
|
|
|
if (!memcg_data || !(memcg_data & MEMCG_DATA_OBJCGS))
|
|
|
|
return NULL;
|
2020-12-01 21:58:28 +00:00
|
|
|
|
2020-12-01 21:58:30 +00:00
|
|
|
VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, page);
|
|
|
|
|
2020-12-01 21:58:29 +00:00
|
|
|
return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
|
2020-12-01 21:58:28 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
#else
|
|
|
|
static inline struct obj_cgroup **page_objcgs(struct page *page)
|
|
|
|
{
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline struct obj_cgroup **page_objcgs_check(struct page *page)
|
|
|
|
{
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2020-08-12 01:30:21 +00:00
|
|
|
static __always_inline bool memcg_stat_item_in_bytes(int idx)
|
|
|
|
{
|
|
|
|
if (idx == MEMCG_PERCPU_B)
|
|
|
|
return true;
|
|
|
|
return vmstat_item_in_bytes(idx);
|
|
|
|
}
|
|
|
|
|
2018-08-17 22:48:06 +00:00
|
|
|
static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg)
|
|
|
|
{
|
|
|
|
return (memcg == root_mem_cgroup);
|
|
|
|
}
|
|
|
|
|
2016-03-15 21:57:16 +00:00
|
|
|
static inline bool mem_cgroup_disabled(void)
|
|
|
|
{
|
|
|
|
return !cgroup_subsys_enabled(memory_cgrp_subsys);
|
|
|
|
}
|
|
|
|
|
mm, memcg: avoid stale protection values when cgroup is above protection
Patch series "mm, memcg: memory.{low,min} reclaim fix & cleanup", v4.
This series contains a fix for a edge case in my earlier protection
calculation patches, and a patch to make the area overall a little more
robust to hopefully help avoid this in future.
This patch (of 2):
A cgroup can have both memory protection and a memory limit to isolate it
from its siblings in both directions - for example, to prevent it from
being shrunk below 2G under high pressure from outside, but also from
growing beyond 4G under low pressure.
Commit 9783aa9917f8 ("mm, memcg: proportional memory.{low,min} reclaim")
implemented proportional scan pressure so that multiple siblings in excess
of their protection settings don't get reclaimed equally but instead in
accordance to their unprotected portion.
During limit reclaim, this proportionality shouldn't apply of course:
there is no competition, all pressure is from within the cgroup and should
be applied as such. Reclaim should operate at full efficiency.
However, mem_cgroup_protected() never expected anybody to look at the
effective protection values when it indicated that the cgroup is above its
protection. As a result, a query during limit reclaim may return stale
protection values that were calculated by a previous reclaim cycle in
which the cgroup did have siblings.
When this happens, reclaim is unnecessarily hesitant and potentially slow
to meet the desired limit. In theory this could lead to premature OOM
kills, although it's not obvious this has occurred in practice.
Workaround the problem by special casing reclaim roots in
mem_cgroup_protection. These memcgs are never participating in the
reclaim protection because the reclaim is internal.
We have to ignore effective protection values for reclaim roots because
mem_cgroup_protected might be called from racing reclaim contexts with
different roots. Calculation is relying on root -> leaf tree traversal
therefore top-down reclaim protection invariants should hold. The only
exception is the reclaim root which should have effective protection set
to 0 but that would be problematic for the following setup:
Let's have global and A's reclaim in parallel:
|
A (low=2G, usage = 3G, max = 3G, children_low_usage = 1.5G)
|\
| C (low = 1G, usage = 2.5G)
B (low = 1G, usage = 0.5G)
for A reclaim we have
B.elow = B.low
C.elow = C.low
For the global reclaim
A.elow = A.low
B.elow = min(B.usage, B.low) because children_low_usage <= A.elow
C.elow = min(C.usage, C.low)
With the effective values resetting we have A reclaim
A.elow = 0
B.elow = B.low
C.elow = C.low
and global reclaim could see the above and then
B.elow = C.elow = 0 because children_low_usage > A.elow
Which means that protected memcgs would get reclaimed.
In future we would like to make mem_cgroup_protected more robust against
racing reclaim contexts but that is likely more complex solution than this
simple workaround.
[hannes@cmpxchg.org - large part of the changelog]
[mhocko@suse.com - workaround explanation]
[chris@chrisdown.name - retitle]
Fixes: 9783aa9917f8 ("mm, memcg: proportional memory.{low,min} reclaim")
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Chris Down <chris@chrisdown.name>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Chris Down <chris@chrisdown.name>
Acked-by: Roman Gushchin <guro@fb.com>
Link: http://lkml.kernel.org/r/cover.1594638158.git.chris@chrisdown.name
Link: http://lkml.kernel.org/r/044fb8ecffd001c7905d27c0c2ad998069fdc396.1594638158.git.chris@chrisdown.name
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-07 06:22:01 +00:00
|
|
|
static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root,
|
|
|
|
struct mem_cgroup *memcg,
|
mm, memcg: make scan aggression always exclude protection
This patch is an incremental improvement on the existing
memory.{low,min} relative reclaim work to base its scan pressure
calculations on how much protection is available compared to the current
usage, rather than how much the current usage is over some protection
threshold.
This change doesn't change the experience for the user in the normal
case too much. One benefit is that it replaces the (somewhat arbitrary)
100% cutoff with an indefinite slope, which makes it easier to ballpark
a memory.low value.
As well as this, the old methodology doesn't quite apply generically to
machines with varying amounts of physical memory. Let's say we have a
top level cgroup, workload.slice, and another top level cgroup,
system-management.slice. We want to roughly give 12G to
system-management.slice, so on a 32GB machine we set memory.low to 20GB
in workload.slice, and on a 64GB machine we set memory.low to 52GB.
However, because these are relative amounts to the total machine size,
while the amount of memory we want to generally be willing to yield to
system.slice is absolute (12G), we end up putting more pressure on
system.slice just because we have a larger machine and a larger workload
to fill it, which seems fairly unintuitive. With this new behaviour, we
don't end up with this unintended side effect.
Previously the way that memory.low protection works is that if you are
50% over a certain baseline, you get 50% of your normal scan pressure.
This is certainly better than the previous cliff-edge behaviour, but it
can be improved even further by always considering memory under the
currently enforced protection threshold to be out of bounds. This means
that we can set relatively low memory.low thresholds for variable or
bursty workloads while still getting a reasonable level of protection,
whereas with the previous version we may still trivially hit the 100%
clamp. The previous 100% clamp is also somewhat arbitrary, whereas this
one is more concretely based on the currently enforced protection
threshold, which is likely easier to reason about.
There is also a subtle issue with the way that proportional reclaim
worked previously -- it promotes having no memory.low, since it makes
pressure higher during low reclaim. This happens because we base our
scan pressure modulation on how far memory.current is between memory.min
and memory.low, but if memory.low is unset, we only use the overage
method. In most cromulent configurations, this then means that we end
up with *more* pressure than with no memory.low at all when we're in low
reclaim, which is not really very usable or expected.
With this patch, memory.low and memory.min affect reclaim pressure in a
more understandable and composable way. For example, from a user
standpoint, "protected" memory now remains untouchable from a reclaim
aggression standpoint, and users can also have more confidence that
bursty workloads will still receive some amount of guaranteed
protection.
Link: http://lkml.kernel.org/r/20190322160307.GA3316@chrisdown.name
Signed-off-by: Chris Down <chris@chrisdown.name>
Reviewed-by: Roman Gushchin <guro@fb.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-10-07 00:58:38 +00:00
|
|
|
bool in_low_reclaim)
|
mm, memcg: proportional memory.{low,min} reclaim
cgroup v2 introduces two memory protection thresholds: memory.low
(best-effort) and memory.min (hard protection). While they generally do
what they say on the tin, there is a limitation in their implementation
that makes them difficult to use effectively: that cliff behaviour often
manifests when they become eligible for reclaim. This patch implements
more intuitive and usable behaviour, where we gradually mount more
reclaim pressure as cgroups further and further exceed their protection
thresholds.
This cliff edge behaviour happens because we only choose whether or not
to reclaim based on whether the memcg is within its protection limits
(see the use of mem_cgroup_protected in shrink_node), but we don't vary
our reclaim behaviour based on this information. Imagine the following
timeline, with the numbers the lruvec size in this zone:
1. memory.low=1000000, memory.current=999999. 0 pages may be scanned.
2. memory.low=1000000, memory.current=1000000. 0 pages may be scanned.
3. memory.low=1000000, memory.current=1000001. 1000001* pages may be
scanned. (?!)
* Of course, we won't usually scan all available pages in the zone even
without this patch because of scan control priority, over-reclaim
protection, etc. However, as shown by the tests at the end, these
techniques don't sufficiently throttle such an extreme change in input,
so cliff-like behaviour isn't really averted by their existence alone.
Here's an example of how this plays out in practice. At Facebook, we are
trying to protect various workloads from "system" software, like
configuration management tools, metric collectors, etc (see this[0] case
study). In order to find a suitable memory.low value, we start by
determining the expected memory range within which the workload will be
comfortable operating. This isn't an exact science -- memory usage deemed
"comfortable" will vary over time due to user behaviour, differences in
composition of work, etc, etc. As such we need to ballpark memory.low,
but doing this is currently problematic:
1. If we end up setting it too low for the workload, it won't have
*any* effect (see discussion above). The group will receive the full
weight of reclaim and won't have any priority while competing with the
less important system software, as if we had no memory.low configured
at all.
2. Because of this behaviour, we end up erring on the side of setting
it too high, such that the comfort range is reliably covered. However,
protected memory is completely unavailable to the rest of the system,
so we might cause undue memory and IO pressure there when we *know* we
have some elasticity in the workload.
3. Even if we get the value totally right, smack in the middle of the
comfort zone, we get extreme jumps between no pressure and full
pressure that cause unpredictable pressure spikes in the workload due
to the current binary reclaim behaviour.
With this patch, we can set it to our ballpark estimation without too much
worry. Any undesirable behaviour, such as too much or too little reclaim
pressure on the workload or system will be proportional to how far our
estimation is off. This means we can set memory.low much more
conservatively and thus waste less resources *without* the risk of the
workload falling off a cliff if we overshoot.
As a more abstract technical description, this unintuitive behaviour
results in having to give high-priority workloads a large protection
buffer on top of their expected usage to function reliably, as otherwise
we have abrupt periods of dramatically increased memory pressure which
hamper performance. Having to set these thresholds so high wastes
resources and generally works against the principle of work conservation.
In addition, having proportional memory reclaim behaviour has other
benefits. Most notably, before this patch it's basically mandatory to set
memory.low to a higher than desirable value because otherwise as soon as
you exceed memory.low, all protection is lost, and all pages are eligible
to scan again. By contrast, having a gradual ramp in reclaim pressure
means that you now still get some protection when thresholds are exceeded,
which means that one can now be more comfortable setting memory.low to
lower values without worrying that all protection will be lost. This is
important because workingset size is really hard to know exactly,
especially with variable workloads, so at least getting *some* protection
if your workingset size grows larger than you expect increases user
confidence in setting memory.low without a huge buffer on top being
needed.
Thanks a lot to Johannes Weiner and Tejun Heo for their advice and
assistance in thinking about how to make this work better.
In testing these changes, I intended to verify that:
1. Changes in page scanning become gradual and proportional instead of
binary.
To test this, I experimented stepping further and further down
memory.low protection on a workload that floats around 19G workingset
when under memory.low protection, watching page scan rates for the
workload cgroup:
+------------+-----------------+--------------------+--------------+
| memory.low | test (pgscan/s) | control (pgscan/s) | % of control |
+------------+-----------------+--------------------+--------------+
| 21G | 0 | 0 | N/A |
| 17G | 867 | 3799 | 23% |
| 12G | 1203 | 3543 | 34% |
| 8G | 2534 | 3979 | 64% |
| 4G | 3980 | 4147 | 96% |
| 0 | 3799 | 3980 | 95% |
+------------+-----------------+--------------------+--------------+
As you can see, the test kernel (with a kernel containing this
patch) ramps up page scanning significantly more gradually than the
control kernel (without this patch).
2. More gradual ramp up in reclaim aggression doesn't result in
premature OOMs.
To test this, I wrote a script that slowly increments the number of
pages held by stress(1)'s --vm-keep mode until a production system
entered severe overall memory contention. This script runs in a highly
protected slice taking up the majority of available system memory.
Watching vmstat revealed that page scanning continued essentially
nominally between test and control, without causing forward reclaim
progress to become arrested.
[0]: https://facebookmicrosites.github.io/cgroup2/docs/overview.html#case-study-the-fbtax2-project
[akpm@linux-foundation.org: reflow block comments to fit in 80 cols]
[chris@chrisdown.name: handle cgroup_disable=memory when getting memcg protection]
Link: http://lkml.kernel.org/r/20190201045711.GA18302@chrisdown.name
Link: http://lkml.kernel.org/r/20190124014455.GA6396@chrisdown.name
Signed-off-by: Chris Down <chris@chrisdown.name>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Roman Gushchin <guro@fb.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-10-07 00:58:32 +00:00
|
|
|
{
|
mm, memcg: make scan aggression always exclude protection
This patch is an incremental improvement on the existing
memory.{low,min} relative reclaim work to base its scan pressure
calculations on how much protection is available compared to the current
usage, rather than how much the current usage is over some protection
threshold.
This change doesn't change the experience for the user in the normal
case too much. One benefit is that it replaces the (somewhat arbitrary)
100% cutoff with an indefinite slope, which makes it easier to ballpark
a memory.low value.
As well as this, the old methodology doesn't quite apply generically to
machines with varying amounts of physical memory. Let's say we have a
top level cgroup, workload.slice, and another top level cgroup,
system-management.slice. We want to roughly give 12G to
system-management.slice, so on a 32GB machine we set memory.low to 20GB
in workload.slice, and on a 64GB machine we set memory.low to 52GB.
However, because these are relative amounts to the total machine size,
while the amount of memory we want to generally be willing to yield to
system.slice is absolute (12G), we end up putting more pressure on
system.slice just because we have a larger machine and a larger workload
to fill it, which seems fairly unintuitive. With this new behaviour, we
don't end up with this unintended side effect.
Previously the way that memory.low protection works is that if you are
50% over a certain baseline, you get 50% of your normal scan pressure.
This is certainly better than the previous cliff-edge behaviour, but it
can be improved even further by always considering memory under the
currently enforced protection threshold to be out of bounds. This means
that we can set relatively low memory.low thresholds for variable or
bursty workloads while still getting a reasonable level of protection,
whereas with the previous version we may still trivially hit the 100%
clamp. The previous 100% clamp is also somewhat arbitrary, whereas this
one is more concretely based on the currently enforced protection
threshold, which is likely easier to reason about.
There is also a subtle issue with the way that proportional reclaim
worked previously -- it promotes having no memory.low, since it makes
pressure higher during low reclaim. This happens because we base our
scan pressure modulation on how far memory.current is between memory.min
and memory.low, but if memory.low is unset, we only use the overage
method. In most cromulent configurations, this then means that we end
up with *more* pressure than with no memory.low at all when we're in low
reclaim, which is not really very usable or expected.
With this patch, memory.low and memory.min affect reclaim pressure in a
more understandable and composable way. For example, from a user
standpoint, "protected" memory now remains untouchable from a reclaim
aggression standpoint, and users can also have more confidence that
bursty workloads will still receive some amount of guaranteed
protection.
Link: http://lkml.kernel.org/r/20190322160307.GA3316@chrisdown.name
Signed-off-by: Chris Down <chris@chrisdown.name>
Reviewed-by: Roman Gushchin <guro@fb.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-10-07 00:58:38 +00:00
|
|
|
if (mem_cgroup_disabled())
|
|
|
|
return 0;
|
|
|
|
|
mm, memcg: avoid stale protection values when cgroup is above protection
Patch series "mm, memcg: memory.{low,min} reclaim fix & cleanup", v4.
This series contains a fix for a edge case in my earlier protection
calculation patches, and a patch to make the area overall a little more
robust to hopefully help avoid this in future.
This patch (of 2):
A cgroup can have both memory protection and a memory limit to isolate it
from its siblings in both directions - for example, to prevent it from
being shrunk below 2G under high pressure from outside, but also from
growing beyond 4G under low pressure.
Commit 9783aa9917f8 ("mm, memcg: proportional memory.{low,min} reclaim")
implemented proportional scan pressure so that multiple siblings in excess
of their protection settings don't get reclaimed equally but instead in
accordance to their unprotected portion.
During limit reclaim, this proportionality shouldn't apply of course:
there is no competition, all pressure is from within the cgroup and should
be applied as such. Reclaim should operate at full efficiency.
However, mem_cgroup_protected() never expected anybody to look at the
effective protection values when it indicated that the cgroup is above its
protection. As a result, a query during limit reclaim may return stale
protection values that were calculated by a previous reclaim cycle in
which the cgroup did have siblings.
When this happens, reclaim is unnecessarily hesitant and potentially slow
to meet the desired limit. In theory this could lead to premature OOM
kills, although it's not obvious this has occurred in practice.
Workaround the problem by special casing reclaim roots in
mem_cgroup_protection. These memcgs are never participating in the
reclaim protection because the reclaim is internal.
We have to ignore effective protection values for reclaim roots because
mem_cgroup_protected might be called from racing reclaim contexts with
different roots. Calculation is relying on root -> leaf tree traversal
therefore top-down reclaim protection invariants should hold. The only
exception is the reclaim root which should have effective protection set
to 0 but that would be problematic for the following setup:
Let's have global and A's reclaim in parallel:
|
A (low=2G, usage = 3G, max = 3G, children_low_usage = 1.5G)
|\
| C (low = 1G, usage = 2.5G)
B (low = 1G, usage = 0.5G)
for A reclaim we have
B.elow = B.low
C.elow = C.low
For the global reclaim
A.elow = A.low
B.elow = min(B.usage, B.low) because children_low_usage <= A.elow
C.elow = min(C.usage, C.low)
With the effective values resetting we have A reclaim
A.elow = 0
B.elow = B.low
C.elow = C.low
and global reclaim could see the above and then
B.elow = C.elow = 0 because children_low_usage > A.elow
Which means that protected memcgs would get reclaimed.
In future we would like to make mem_cgroup_protected more robust against
racing reclaim contexts but that is likely more complex solution than this
simple workaround.
[hannes@cmpxchg.org - large part of the changelog]
[mhocko@suse.com - workaround explanation]
[chris@chrisdown.name - retitle]
Fixes: 9783aa9917f8 ("mm, memcg: proportional memory.{low,min} reclaim")
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Chris Down <chris@chrisdown.name>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Chris Down <chris@chrisdown.name>
Acked-by: Roman Gushchin <guro@fb.com>
Link: http://lkml.kernel.org/r/cover.1594638158.git.chris@chrisdown.name
Link: http://lkml.kernel.org/r/044fb8ecffd001c7905d27c0c2ad998069fdc396.1594638158.git.chris@chrisdown.name
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-07 06:22:01 +00:00
|
|
|
/*
|
|
|
|
* There is no reclaim protection applied to a targeted reclaim.
|
|
|
|
* We are special casing this specific case here because
|
|
|
|
* mem_cgroup_protected calculation is not robust enough to keep
|
|
|
|
* the protection invariant for calculated effective values for
|
|
|
|
* parallel reclaimers with different reclaim target. This is
|
|
|
|
* especially a problem for tail memcgs (as they have pages on LRU)
|
|
|
|
* which would want to have effective values 0 for targeted reclaim
|
|
|
|
* but a different value for external reclaim.
|
|
|
|
*
|
|
|
|
* Example
|
|
|
|
* Let's have global and A's reclaim in parallel:
|
|
|
|
* |
|
|
|
|
* A (low=2G, usage = 3G, max = 3G, children_low_usage = 1.5G)
|
|
|
|
* |\
|
|
|
|
* | C (low = 1G, usage = 2.5G)
|
|
|
|
* B (low = 1G, usage = 0.5G)
|
|
|
|
*
|
|
|
|
* For the global reclaim
|
|
|
|
* A.elow = A.low
|
|
|
|
* B.elow = min(B.usage, B.low) because children_low_usage <= A.elow
|
|
|
|
* C.elow = min(C.usage, C.low)
|
|
|
|
*
|
|
|
|
* With the effective values resetting we have A reclaim
|
|
|
|
* A.elow = 0
|
|
|
|
* B.elow = B.low
|
|
|
|
* C.elow = C.low
|
|
|
|
*
|
|
|
|
* If the global reclaim races with A's reclaim then
|
|
|
|
* B.elow = C.elow = 0 because children_low_usage > A.elow)
|
|
|
|
* is possible and reclaiming B would be violating the protection.
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
if (root == memcg)
|
|
|
|
return 0;
|
|
|
|
|
mm, memcg: make scan aggression always exclude protection
This patch is an incremental improvement on the existing
memory.{low,min} relative reclaim work to base its scan pressure
calculations on how much protection is available compared to the current
usage, rather than how much the current usage is over some protection
threshold.
This change doesn't change the experience for the user in the normal
case too much. One benefit is that it replaces the (somewhat arbitrary)
100% cutoff with an indefinite slope, which makes it easier to ballpark
a memory.low value.
As well as this, the old methodology doesn't quite apply generically to
machines with varying amounts of physical memory. Let's say we have a
top level cgroup, workload.slice, and another top level cgroup,
system-management.slice. We want to roughly give 12G to
system-management.slice, so on a 32GB machine we set memory.low to 20GB
in workload.slice, and on a 64GB machine we set memory.low to 52GB.
However, because these are relative amounts to the total machine size,
while the amount of memory we want to generally be willing to yield to
system.slice is absolute (12G), we end up putting more pressure on
system.slice just because we have a larger machine and a larger workload
to fill it, which seems fairly unintuitive. With this new behaviour, we
don't end up with this unintended side effect.
Previously the way that memory.low protection works is that if you are
50% over a certain baseline, you get 50% of your normal scan pressure.
This is certainly better than the previous cliff-edge behaviour, but it
can be improved even further by always considering memory under the
currently enforced protection threshold to be out of bounds. This means
that we can set relatively low memory.low thresholds for variable or
bursty workloads while still getting a reasonable level of protection,
whereas with the previous version we may still trivially hit the 100%
clamp. The previous 100% clamp is also somewhat arbitrary, whereas this
one is more concretely based on the currently enforced protection
threshold, which is likely easier to reason about.
There is also a subtle issue with the way that proportional reclaim
worked previously -- it promotes having no memory.low, since it makes
pressure higher during low reclaim. This happens because we base our
scan pressure modulation on how far memory.current is between memory.min
and memory.low, but if memory.low is unset, we only use the overage
method. In most cromulent configurations, this then means that we end
up with *more* pressure than with no memory.low at all when we're in low
reclaim, which is not really very usable or expected.
With this patch, memory.low and memory.min affect reclaim pressure in a
more understandable and composable way. For example, from a user
standpoint, "protected" memory now remains untouchable from a reclaim
aggression standpoint, and users can also have more confidence that
bursty workloads will still receive some amount of guaranteed
protection.
Link: http://lkml.kernel.org/r/20190322160307.GA3316@chrisdown.name
Signed-off-by: Chris Down <chris@chrisdown.name>
Reviewed-by: Roman Gushchin <guro@fb.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-10-07 00:58:38 +00:00
|
|
|
if (in_low_reclaim)
|
|
|
|
return READ_ONCE(memcg->memory.emin);
|
mm, memcg: proportional memory.{low,min} reclaim
cgroup v2 introduces two memory protection thresholds: memory.low
(best-effort) and memory.min (hard protection). While they generally do
what they say on the tin, there is a limitation in their implementation
that makes them difficult to use effectively: that cliff behaviour often
manifests when they become eligible for reclaim. This patch implements
more intuitive and usable behaviour, where we gradually mount more
reclaim pressure as cgroups further and further exceed their protection
thresholds.
This cliff edge behaviour happens because we only choose whether or not
to reclaim based on whether the memcg is within its protection limits
(see the use of mem_cgroup_protected in shrink_node), but we don't vary
our reclaim behaviour based on this information. Imagine the following
timeline, with the numbers the lruvec size in this zone:
1. memory.low=1000000, memory.current=999999. 0 pages may be scanned.
2. memory.low=1000000, memory.current=1000000. 0 pages may be scanned.
3. memory.low=1000000, memory.current=1000001. 1000001* pages may be
scanned. (?!)
* Of course, we won't usually scan all available pages in the zone even
without this patch because of scan control priority, over-reclaim
protection, etc. However, as shown by the tests at the end, these
techniques don't sufficiently throttle such an extreme change in input,
so cliff-like behaviour isn't really averted by their existence alone.
Here's an example of how this plays out in practice. At Facebook, we are
trying to protect various workloads from "system" software, like
configuration management tools, metric collectors, etc (see this[0] case
study). In order to find a suitable memory.low value, we start by
determining the expected memory range within which the workload will be
comfortable operating. This isn't an exact science -- memory usage deemed
"comfortable" will vary over time due to user behaviour, differences in
composition of work, etc, etc. As such we need to ballpark memory.low,
but doing this is currently problematic:
1. If we end up setting it too low for the workload, it won't have
*any* effect (see discussion above). The group will receive the full
weight of reclaim and won't have any priority while competing with the
less important system software, as if we had no memory.low configured
at all.
2. Because of this behaviour, we end up erring on the side of setting
it too high, such that the comfort range is reliably covered. However,
protected memory is completely unavailable to the rest of the system,
so we might cause undue memory and IO pressure there when we *know* we
have some elasticity in the workload.
3. Even if we get the value totally right, smack in the middle of the
comfort zone, we get extreme jumps between no pressure and full
pressure that cause unpredictable pressure spikes in the workload due
to the current binary reclaim behaviour.
With this patch, we can set it to our ballpark estimation without too much
worry. Any undesirable behaviour, such as too much or too little reclaim
pressure on the workload or system will be proportional to how far our
estimation is off. This means we can set memory.low much more
conservatively and thus waste less resources *without* the risk of the
workload falling off a cliff if we overshoot.
As a more abstract technical description, this unintuitive behaviour
results in having to give high-priority workloads a large protection
buffer on top of their expected usage to function reliably, as otherwise
we have abrupt periods of dramatically increased memory pressure which
hamper performance. Having to set these thresholds so high wastes
resources and generally works against the principle of work conservation.
In addition, having proportional memory reclaim behaviour has other
benefits. Most notably, before this patch it's basically mandatory to set
memory.low to a higher than desirable value because otherwise as soon as
you exceed memory.low, all protection is lost, and all pages are eligible
to scan again. By contrast, having a gradual ramp in reclaim pressure
means that you now still get some protection when thresholds are exceeded,
which means that one can now be more comfortable setting memory.low to
lower values without worrying that all protection will be lost. This is
important because workingset size is really hard to know exactly,
especially with variable workloads, so at least getting *some* protection
if your workingset size grows larger than you expect increases user
confidence in setting memory.low without a huge buffer on top being
needed.
Thanks a lot to Johannes Weiner and Tejun Heo for their advice and
assistance in thinking about how to make this work better.
In testing these changes, I intended to verify that:
1. Changes in page scanning become gradual and proportional instead of
binary.
To test this, I experimented stepping further and further down
memory.low protection on a workload that floats around 19G workingset
when under memory.low protection, watching page scan rates for the
workload cgroup:
+------------+-----------------+--------------------+--------------+
| memory.low | test (pgscan/s) | control (pgscan/s) | % of control |
+------------+-----------------+--------------------+--------------+
| 21G | 0 | 0 | N/A |
| 17G | 867 | 3799 | 23% |
| 12G | 1203 | 3543 | 34% |
| 8G | 2534 | 3979 | 64% |
| 4G | 3980 | 4147 | 96% |
| 0 | 3799 | 3980 | 95% |
+------------+-----------------+--------------------+--------------+
As you can see, the test kernel (with a kernel containing this
patch) ramps up page scanning significantly more gradually than the
control kernel (without this patch).
2. More gradual ramp up in reclaim aggression doesn't result in
premature OOMs.
To test this, I wrote a script that slowly increments the number of
pages held by stress(1)'s --vm-keep mode until a production system
entered severe overall memory contention. This script runs in a highly
protected slice taking up the majority of available system memory.
Watching vmstat revealed that page scanning continued essentially
nominally between test and control, without causing forward reclaim
progress to become arrested.
[0]: https://facebookmicrosites.github.io/cgroup2/docs/overview.html#case-study-the-fbtax2-project
[akpm@linux-foundation.org: reflow block comments to fit in 80 cols]
[chris@chrisdown.name: handle cgroup_disable=memory when getting memcg protection]
Link: http://lkml.kernel.org/r/20190201045711.GA18302@chrisdown.name
Link: http://lkml.kernel.org/r/20190124014455.GA6396@chrisdown.name
Signed-off-by: Chris Down <chris@chrisdown.name>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Roman Gushchin <guro@fb.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-10-07 00:58:32 +00:00
|
|
|
|
mm, memcg: make scan aggression always exclude protection
This patch is an incremental improvement on the existing
memory.{low,min} relative reclaim work to base its scan pressure
calculations on how much protection is available compared to the current
usage, rather than how much the current usage is over some protection
threshold.
This change doesn't change the experience for the user in the normal
case too much. One benefit is that it replaces the (somewhat arbitrary)
100% cutoff with an indefinite slope, which makes it easier to ballpark
a memory.low value.
As well as this, the old methodology doesn't quite apply generically to
machines with varying amounts of physical memory. Let's say we have a
top level cgroup, workload.slice, and another top level cgroup,
system-management.slice. We want to roughly give 12G to
system-management.slice, so on a 32GB machine we set memory.low to 20GB
in workload.slice, and on a 64GB machine we set memory.low to 52GB.
However, because these are relative amounts to the total machine size,
while the amount of memory we want to generally be willing to yield to
system.slice is absolute (12G), we end up putting more pressure on
system.slice just because we have a larger machine and a larger workload
to fill it, which seems fairly unintuitive. With this new behaviour, we
don't end up with this unintended side effect.
Previously the way that memory.low protection works is that if you are
50% over a certain baseline, you get 50% of your normal scan pressure.
This is certainly better than the previous cliff-edge behaviour, but it
can be improved even further by always considering memory under the
currently enforced protection threshold to be out of bounds. This means
that we can set relatively low memory.low thresholds for variable or
bursty workloads while still getting a reasonable level of protection,
whereas with the previous version we may still trivially hit the 100%
clamp. The previous 100% clamp is also somewhat arbitrary, whereas this
one is more concretely based on the currently enforced protection
threshold, which is likely easier to reason about.
There is also a subtle issue with the way that proportional reclaim
worked previously -- it promotes having no memory.low, since it makes
pressure higher during low reclaim. This happens because we base our
scan pressure modulation on how far memory.current is between memory.min
and memory.low, but if memory.low is unset, we only use the overage
method. In most cromulent configurations, this then means that we end
up with *more* pressure than with no memory.low at all when we're in low
reclaim, which is not really very usable or expected.
With this patch, memory.low and memory.min affect reclaim pressure in a
more understandable and composable way. For example, from a user
standpoint, "protected" memory now remains untouchable from a reclaim
aggression standpoint, and users can also have more confidence that
bursty workloads will still receive some amount of guaranteed
protection.
Link: http://lkml.kernel.org/r/20190322160307.GA3316@chrisdown.name
Signed-off-by: Chris Down <chris@chrisdown.name>
Reviewed-by: Roman Gushchin <guro@fb.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-10-07 00:58:38 +00:00
|
|
|
return max(READ_ONCE(memcg->memory.emin),
|
|
|
|
READ_ONCE(memcg->memory.elow));
|
mm, memcg: proportional memory.{low,min} reclaim
cgroup v2 introduces two memory protection thresholds: memory.low
(best-effort) and memory.min (hard protection). While they generally do
what they say on the tin, there is a limitation in their implementation
that makes them difficult to use effectively: that cliff behaviour often
manifests when they become eligible for reclaim. This patch implements
more intuitive and usable behaviour, where we gradually mount more
reclaim pressure as cgroups further and further exceed their protection
thresholds.
This cliff edge behaviour happens because we only choose whether or not
to reclaim based on whether the memcg is within its protection limits
(see the use of mem_cgroup_protected in shrink_node), but we don't vary
our reclaim behaviour based on this information. Imagine the following
timeline, with the numbers the lruvec size in this zone:
1. memory.low=1000000, memory.current=999999. 0 pages may be scanned.
2. memory.low=1000000, memory.current=1000000. 0 pages may be scanned.
3. memory.low=1000000, memory.current=1000001. 1000001* pages may be
scanned. (?!)
* Of course, we won't usually scan all available pages in the zone even
without this patch because of scan control priority, over-reclaim
protection, etc. However, as shown by the tests at the end, these
techniques don't sufficiently throttle such an extreme change in input,
so cliff-like behaviour isn't really averted by their existence alone.
Here's an example of how this plays out in practice. At Facebook, we are
trying to protect various workloads from "system" software, like
configuration management tools, metric collectors, etc (see this[0] case
study). In order to find a suitable memory.low value, we start by
determining the expected memory range within which the workload will be
comfortable operating. This isn't an exact science -- memory usage deemed
"comfortable" will vary over time due to user behaviour, differences in
composition of work, etc, etc. As such we need to ballpark memory.low,
but doing this is currently problematic:
1. If we end up setting it too low for the workload, it won't have
*any* effect (see discussion above). The group will receive the full
weight of reclaim and won't have any priority while competing with the
less important system software, as if we had no memory.low configured
at all.
2. Because of this behaviour, we end up erring on the side of setting
it too high, such that the comfort range is reliably covered. However,
protected memory is completely unavailable to the rest of the system,
so we might cause undue memory and IO pressure there when we *know* we
have some elasticity in the workload.
3. Even if we get the value totally right, smack in the middle of the
comfort zone, we get extreme jumps between no pressure and full
pressure that cause unpredictable pressure spikes in the workload due
to the current binary reclaim behaviour.
With this patch, we can set it to our ballpark estimation without too much
worry. Any undesirable behaviour, such as too much or too little reclaim
pressure on the workload or system will be proportional to how far our
estimation is off. This means we can set memory.low much more
conservatively and thus waste less resources *without* the risk of the
workload falling off a cliff if we overshoot.
As a more abstract technical description, this unintuitive behaviour
results in having to give high-priority workloads a large protection
buffer on top of their expected usage to function reliably, as otherwise
we have abrupt periods of dramatically increased memory pressure which
hamper performance. Having to set these thresholds so high wastes
resources and generally works against the principle of work conservation.
In addition, having proportional memory reclaim behaviour has other
benefits. Most notably, before this patch it's basically mandatory to set
memory.low to a higher than desirable value because otherwise as soon as
you exceed memory.low, all protection is lost, and all pages are eligible
to scan again. By contrast, having a gradual ramp in reclaim pressure
means that you now still get some protection when thresholds are exceeded,
which means that one can now be more comfortable setting memory.low to
lower values without worrying that all protection will be lost. This is
important because workingset size is really hard to know exactly,
especially with variable workloads, so at least getting *some* protection
if your workingset size grows larger than you expect increases user
confidence in setting memory.low without a huge buffer on top being
needed.
Thanks a lot to Johannes Weiner and Tejun Heo for their advice and
assistance in thinking about how to make this work better.
In testing these changes, I intended to verify that:
1. Changes in page scanning become gradual and proportional instead of
binary.
To test this, I experimented stepping further and further down
memory.low protection on a workload that floats around 19G workingset
when under memory.low protection, watching page scan rates for the
workload cgroup:
+------------+-----------------+--------------------+--------------+
| memory.low | test (pgscan/s) | control (pgscan/s) | % of control |
+------------+-----------------+--------------------+--------------+
| 21G | 0 | 0 | N/A |
| 17G | 867 | 3799 | 23% |
| 12G | 1203 | 3543 | 34% |
| 8G | 2534 | 3979 | 64% |
| 4G | 3980 | 4147 | 96% |
| 0 | 3799 | 3980 | 95% |
+------------+-----------------+--------------------+--------------+
As you can see, the test kernel (with a kernel containing this
patch) ramps up page scanning significantly more gradually than the
control kernel (without this patch).
2. More gradual ramp up in reclaim aggression doesn't result in
premature OOMs.
To test this, I wrote a script that slowly increments the number of
pages held by stress(1)'s --vm-keep mode until a production system
entered severe overall memory contention. This script runs in a highly
protected slice taking up the majority of available system memory.
Watching vmstat revealed that page scanning continued essentially
nominally between test and control, without causing forward reclaim
progress to become arrested.
[0]: https://facebookmicrosites.github.io/cgroup2/docs/overview.html#case-study-the-fbtax2-project
[akpm@linux-foundation.org: reflow block comments to fit in 80 cols]
[chris@chrisdown.name: handle cgroup_disable=memory when getting memcg protection]
Link: http://lkml.kernel.org/r/20190201045711.GA18302@chrisdown.name
Link: http://lkml.kernel.org/r/20190124014455.GA6396@chrisdown.name
Signed-off-by: Chris Down <chris@chrisdown.name>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Roman Gushchin <guro@fb.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-10-07 00:58:32 +00:00
|
|
|
}
|
|
|
|
|
2020-08-07 06:22:05 +00:00
|
|
|
void mem_cgroup_calculate_protection(struct mem_cgroup *root,
|
|
|
|
struct mem_cgroup *memcg);
|
|
|
|
|
|
|
|
static inline bool mem_cgroup_supports_protection(struct mem_cgroup *memcg)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* The root memcg doesn't account charges, and doesn't support
|
|
|
|
* protection.
|
|
|
|
*/
|
|
|
|
return !mem_cgroup_disabled() && !mem_cgroup_is_root(memcg);
|
|
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline bool mem_cgroup_below_low(struct mem_cgroup *memcg)
|
|
|
|
{
|
|
|
|
if (!mem_cgroup_supports_protection(memcg))
|
|
|
|
return false;
|
|
|
|
|
|
|
|
return READ_ONCE(memcg->memory.elow) >=
|
|
|
|
page_counter_read(&memcg->memory);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg)
|
|
|
|
{
|
|
|
|
if (!mem_cgroup_supports_protection(memcg))
|
|
|
|
return false;
|
|
|
|
|
|
|
|
return READ_ONCE(memcg->memory.emin) >=
|
|
|
|
page_counter_read(&memcg->memory);
|
|
|
|
}
|
mm: memcontrol: default hierarchy interface for memory
Introduce the basic control files to account, partition, and limit
memory using cgroups in default hierarchy mode.
This interface versioning allows us to address fundamental design
issues in the existing memory cgroup interface, further explained
below. The old interface will be maintained indefinitely, but a
clearer model and improved workload performance should encourage
existing users to switch over to the new one eventually.
The control files are thus:
- memory.current shows the current consumption of the cgroup and its
descendants, in bytes.
- memory.low configures the lower end of the cgroup's expected
memory consumption range. The kernel considers memory below that
boundary to be a reserve - the minimum that the workload needs in
order to make forward progress - and generally avoids reclaiming
it, unless there is an imminent risk of entering an OOM situation.
- memory.high configures the upper end of the cgroup's expected
memory consumption range. A cgroup whose consumption grows beyond
this threshold is forced into direct reclaim, to work off the
excess and to throttle new allocations heavily, but is generally
allowed to continue and the OOM killer is not invoked.
- memory.max configures the hard maximum amount of memory that the
cgroup is allowed to consume before the OOM killer is invoked.
- memory.events shows event counters that indicate how often the
cgroup was reclaimed while below memory.low, how often it was
forced to reclaim excess beyond memory.high, how often it hit
memory.max, and how often it entered OOM due to memory.max. This
allows users to identify configuration problems when observing a
degradation in workload performance. An overcommitted system will
have an increased rate of low boundary breaches, whereas increased
rates of high limit breaches, maximum hits, or even OOM situations
will indicate internally overcommitted cgroups.
For existing users of memory cgroups, the following deviations from
the current interface are worth pointing out and explaining:
- The original lower boundary, the soft limit, is defined as a limit
that is per default unset. As a result, the set of cgroups that
global reclaim prefers is opt-in, rather than opt-out. The costs
for optimizing these mostly negative lookups are so high that the
implementation, despite its enormous size, does not even provide
the basic desirable behavior. First off, the soft limit has no
hierarchical meaning. All configured groups are organized in a
global rbtree and treated like equal peers, regardless where they
are located in the hierarchy. This makes subtree delegation
impossible. Second, the soft limit reclaim pass is so aggressive
that it not just introduces high allocation latencies into the
system, but also impacts system performance due to overreclaim, to
the point where the feature becomes self-defeating.
The memory.low boundary on the other hand is a top-down allocated
reserve. A cgroup enjoys reclaim protection when it and all its
ancestors are below their low boundaries, which makes delegation
of subtrees possible. Secondly, new cgroups have no reserve per
default and in the common case most cgroups are eligible for the
preferred reclaim pass. This allows the new low boundary to be
efficiently implemented with just a minor addition to the generic
reclaim code, without the need for out-of-band data structures and
reclaim passes. Because the generic reclaim code considers all
cgroups except for the ones running low in the preferred first
reclaim pass, overreclaim of individual groups is eliminated as
well, resulting in much better overall workload performance.
- The original high boundary, the hard limit, is defined as a strict
limit that can not budge, even if the OOM killer has to be called.
But this generally goes against the goal of making the most out of
the available memory. The memory consumption of workloads varies
during runtime, and that requires users to overcommit. But doing
that with a strict upper limit requires either a fairly accurate
prediction of the working set size or adding slack to the limit.
Since working set size estimation is hard and error prone, and
getting it wrong results in OOM kills, most users tend to err on
the side of a looser limit and end up wasting precious resources.
The memory.high boundary on the other hand can be set much more
conservatively. When hit, it throttles allocations by forcing
them into direct reclaim to work off the excess, but it never
invokes the OOM killer. As a result, a high boundary that is
chosen too aggressively will not terminate the processes, but
instead it will lead to gradual performance degradation. The user
can monitor this and make corrections until the minimal memory
footprint that still gives acceptable performance is found.
In extreme cases, with many concurrent allocations and a complete
breakdown of reclaim progress within the group, the high boundary
can be exceeded. But even then it's mostly better to satisfy the
allocation from the slack available in other groups or the rest of
the system than killing the group. Otherwise, memory.max is there
to limit this type of spillover and ultimately contain buggy or
even malicious applications.
- The original control file names are unwieldy and inconsistent in
many different ways. For example, the upper boundary hit count is
exported in the memory.failcnt file, but an OOM event count has to
be manually counted by listening to memory.oom_control events, and
lower boundary / soft limit events have to be counted by first
setting a threshold for that value and then counting those events.
Also, usage and limit files encode their units in the filename.
That makes the filenames very long, even though this is not
information that a user needs to be reminded of every time they
type out those names.
To address these naming issues, as well as to signal clearly that
the new interface carries a new configuration model, the naming
conventions in it necessarily differ from the old interface.
- The original limit files indicate the state of an unset limit with
a very high number, and a configured limit can be unset by echoing
-1 into those files. But that very high number is implementation
and architecture dependent and not very descriptive. And while -1
can be understood as an underflow into the highest possible value,
-2 or -10M etc. do not work, so it's not inconsistent.
memory.low, memory.high, and memory.max will use the string
"infinity" to indicate and set the highest possible value.
[akpm@linux-foundation.org: use seq_puts() for basic strings]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Cc: Greg Thelen <gthelen@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-11 23:26:06 +00:00
|
|
|
|
2020-06-03 23:02:24 +00:00
|
|
|
int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask);
|
mm: memcontrol: convert page cache to a new mem_cgroup_charge() API
The try/commit/cancel protocol that memcg uses dates back to when pages
used to be uncharged upon removal from the page cache, and thus couldn't
be committed before the insertion had succeeded. Nowadays, pages are
uncharged when they are physically freed; it doesn't matter whether the
insertion was successful or not. For the page cache, the transaction
dance has become unnecessary.
Introduce a mem_cgroup_charge() function that simply charges a newly
allocated page to a cgroup and sets up page->mem_cgroup in one single
step. If the insertion fails, the caller doesn't have to do anything but
free/put the page.
Then switch the page cache over to this new API.
Subsequent patches will also convert anon pages, but it needs a bit more
prep work. Right now, memcg depends on page->mapping being already set up
at the time of charging, so that it can maintain its own MEMCG_CACHE and
MEMCG_RSS counters. For anon, page->mapping is set under the same pte
lock under which the page is publishd, so a single charge point that can
block doesn't work there just yet.
The following prep patches will replace the private memcg counters with
the generic vmstat counters, thus removing the page->mapping dependency,
then complete the transition to the new single-point charge API and delete
the old transactional scheme.
v2: leave shmem swapcache when charging fails to avoid double IO (Joonsoo)
v3: rebase on preceeding shmem simplification patch
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Alex Shi <alex.shi@linux.alibaba.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Link: http://lkml.kernel.org/r/20200508183105.225460-6-hannes@cmpxchg.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-03 23:01:41 +00:00
|
|
|
|
mm: memcontrol: rewrite uncharge API
The memcg uncharging code that is involved towards the end of a page's
lifetime - truncation, reclaim, swapout, migration - is impressively
complicated and fragile.
Because anonymous and file pages were always charged before they had their
page->mapping established, uncharges had to happen when the page type
could still be known from the context; as in unmap for anonymous, page
cache removal for file and shmem pages, and swap cache truncation for swap
pages. However, these operations happen well before the page is actually
freed, and so a lot of synchronization is necessary:
- Charging, uncharging, page migration, and charge migration all need
to take a per-page bit spinlock as they could race with uncharging.
- Swap cache truncation happens during both swap-in and swap-out, and
possibly repeatedly before the page is actually freed. This means
that the memcg swapout code is called from many contexts that make
no sense and it has to figure out the direction from page state to
make sure memory and memory+swap are always correctly charged.
- On page migration, the old page might be unmapped but then reused,
so memcg code has to prevent untimely uncharging in that case.
Because this code - which should be a simple charge transfer - is so
special-cased, it is not reusable for replace_page_cache().
But now that charged pages always have a page->mapping, introduce
mem_cgroup_uncharge(), which is called after the final put_page(), when we
know for sure that nobody is looking at the page anymore.
For page migration, introduce mem_cgroup_migrate(), which is called after
the migration is successful and the new page is fully rmapped. Because
the old page is no longer uncharged after migration, prevent double
charges by decoupling the page's memcg association (PCG_USED and
pc->mem_cgroup) from the page holding an actual charge. The new bits
PCG_MEM and PCG_MEMSW represent the respective charges and are transferred
to the new page during migration.
mem_cgroup_migrate() is suitable for replace_page_cache() as well,
which gets rid of mem_cgroup_replace_page_cache(). However, care
needs to be taken because both the source and the target page can
already be charged and on the LRU when fuse is splicing: grab the page
lock on the charge moving side to prevent changing pc->mem_cgroup of a
page under migration. Also, the lruvecs of both pages change as we
uncharge the old and charge the new during migration, and putback may
race with us, so grab the lru lock and isolate the pages iff on LRU to
prevent races and ensure the pages are on the right lruvec afterward.
Swap accounting is massively simplified: because the page is no longer
uncharged as early as swap cache deletion, a new mem_cgroup_swapout() can
transfer the page's memory+swap charge (PCG_MEMSW) to the swap entry
before the final put_page() in page reclaim.
Finally, page_cgroup changes are now protected by whatever protection the
page itself offers: anonymous pages are charged under the page table lock,
whereas page cache insertions, swapin, and migration hold the page lock.
Uncharging happens under full exclusion with no outstanding references.
Charging and uncharging also ensure that the page is off-LRU, which
serializes against charge migration. Remove the very costly page_cgroup
lock and set pc->flags non-atomically.
[mhocko@suse.cz: mem_cgroup_charge_statistics needs preempt_disable]
[vdavydov@parallels.com: fix flags definition]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Tested-by: Jet Chen <jet.chen@intel.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Tested-by: Felipe Balbi <balbi@ti.com>
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-08 21:19:22 +00:00
|
|
|
void mem_cgroup_uncharge(struct page *page);
|
2014-08-08 21:19:24 +00:00
|
|
|
void mem_cgroup_uncharge_list(struct list_head *page_list);
|
2009-12-16 00:47:03 +00:00
|
|
|
|
2016-03-15 21:57:19 +00:00
|
|
|
void mem_cgroup_migrate(struct page *oldpage, struct page *newpage);
|
2009-12-16 00:47:03 +00:00
|
|
|
|
2016-07-28 22:46:05 +00:00
|
|
|
static struct mem_cgroup_per_node *
|
|
|
|
mem_cgroup_nodeinfo(struct mem_cgroup *memcg, int nid)
|
2016-07-28 22:45:10 +00:00
|
|
|
{
|
2016-07-28 22:46:05 +00:00
|
|
|
return memcg->nodeinfo[nid];
|
2016-07-28 22:45:10 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
2019-12-01 01:55:34 +00:00
|
|
|
* mem_cgroup_lruvec - get the lru list vector for a memcg & node
|
2016-07-28 22:45:10 +00:00
|
|
|
* @memcg: memcg of the wanted lruvec
|
2020-12-18 22:01:41 +00:00
|
|
|
* @pgdat: pglist_data
|
2016-07-28 22:45:10 +00:00
|
|
|
*
|
2019-12-01 01:55:34 +00:00
|
|
|
* Returns the lru list vector holding pages for a given @memcg &
|
2020-12-18 22:01:41 +00:00
|
|
|
* @pgdat combination. This can be the node lruvec, if the memory
|
2019-12-01 01:55:34 +00:00
|
|
|
* controller is disabled.
|
2016-07-28 22:45:10 +00:00
|
|
|
*/
|
2019-12-01 01:55:34 +00:00
|
|
|
static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg,
|
|
|
|
struct pglist_data *pgdat)
|
2016-07-28 22:45:10 +00:00
|
|
|
{
|
2016-07-28 22:46:05 +00:00
|
|
|
struct mem_cgroup_per_node *mz;
|
2016-07-28 22:45:10 +00:00
|
|
|
struct lruvec *lruvec;
|
|
|
|
|
|
|
|
if (mem_cgroup_disabled()) {
|
2019-12-01 01:55:34 +00:00
|
|
|
lruvec = &pgdat->__lruvec;
|
2016-07-28 22:45:10 +00:00
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
2019-12-01 01:55:52 +00:00
|
|
|
if (!memcg)
|
|
|
|
memcg = root_mem_cgroup;
|
|
|
|
|
2016-07-28 22:46:05 +00:00
|
|
|
mz = mem_cgroup_nodeinfo(memcg, pgdat->node_id);
|
2016-07-28 22:45:10 +00:00
|
|
|
lruvec = &mz->lruvec;
|
|
|
|
out:
|
|
|
|
/*
|
|
|
|
* Since a node can be onlined after the mem_cgroup was created,
|
2016-07-28 22:45:31 +00:00
|
|
|
* we have to be prepared to initialize lruvec->pgdat here;
|
2016-07-28 22:45:10 +00:00
|
|
|
* and if offlined then reonlined, we need to reinitialize it.
|
|
|
|
*/
|
2016-07-28 22:46:05 +00:00
|
|
|
if (unlikely(lruvec->pgdat != pgdat))
|
|
|
|
lruvec->pgdat = pgdat;
|
2016-07-28 22:45:10 +00:00
|
|
|
return lruvec;
|
|
|
|
}
|
|
|
|
|
2020-12-18 22:01:41 +00:00
|
|
|
/**
|
|
|
|
* mem_cgroup_page_lruvec - return lruvec for isolating/putting an LRU page
|
|
|
|
* @page: the page
|
|
|
|
* @pgdat: pgdat of the page
|
|
|
|
*
|
|
|
|
* This function relies on page->mem_cgroup being stable.
|
|
|
|
*/
|
|
|
|
static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page,
|
|
|
|
struct pglist_data *pgdat)
|
|
|
|
{
|
|
|
|
struct mem_cgroup *memcg = page_memcg(page);
|
|
|
|
|
2021-01-12 23:49:11 +00:00
|
|
|
VM_WARN_ON_ONCE_PAGE(!memcg && !mem_cgroup_disabled(), page);
|
2020-12-18 22:01:41 +00:00
|
|
|
return mem_cgroup_lruvec(memcg, pgdat);
|
|
|
|
}
|
2008-07-25 08:47:15 +00:00
|
|
|
|
2020-12-15 20:34:33 +00:00
|
|
|
static inline bool lruvec_holds_page_lru_lock(struct page *page,
|
|
|
|
struct lruvec *lruvec)
|
|
|
|
{
|
|
|
|
pg_data_t *pgdat = page_pgdat(page);
|
|
|
|
const struct mem_cgroup *memcg;
|
|
|
|
struct mem_cgroup_per_node *mz;
|
|
|
|
|
|
|
|
if (mem_cgroup_disabled())
|
|
|
|
return lruvec == &pgdat->__lruvec;
|
|
|
|
|
|
|
|
mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
|
|
|
|
memcg = page_memcg(page) ? : root_mem_cgroup;
|
|
|
|
|
|
|
|
return lruvec->pgdat == pgdat && mz->memcg == memcg;
|
|
|
|
}
|
|
|
|
|
2015-09-08 22:01:07 +00:00
|
|
|
struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
|
2015-09-09 22:35:35 +00:00
|
|
|
|
fs: fsnotify: account fsnotify metadata to kmemcg
Patch series "Directed kmem charging", v8.
The Linux kernel's memory cgroup allows limiting the memory usage of the
jobs running on the system to provide isolation between the jobs. All
the kernel memory allocated in the context of the job and marked with
__GFP_ACCOUNT will also be included in the memory usage and be limited
by the job's limit.
The kernel memory can only be charged to the memcg of the process in
whose context kernel memory was allocated. However there are cases
where the allocated kernel memory should be charged to the memcg
different from the current processes's memcg. This patch series
contains two such concrete use-cases i.e. fsnotify and buffer_head.
The fsnotify event objects can consume a lot of system memory for large
or unlimited queues if there is either no or slow listener. The events
are allocated in the context of the event producer. However they should
be charged to the event consumer. Similarly the buffer_head objects can
be allocated in a memcg different from the memcg of the page for which
buffer_head objects are being allocated.
To solve this issue, this patch series introduces mechanism to charge
kernel memory to a given memcg. In case of fsnotify events, the memcg
of the consumer can be used for charging and for buffer_head, the memcg
of the page can be charged. For directed charging, the caller can use
the scope API memalloc_[un]use_memcg() to specify the memcg to charge
for all the __GFP_ACCOUNT allocations within the scope.
This patch (of 2):
A lot of memory can be consumed by the events generated for the huge or
unlimited queues if there is either no or slow listener. This can cause
system level memory pressure or OOMs. So, it's better to account the
fsnotify kmem caches to the memcg of the listener.
However the listener can be in a different memcg than the memcg of the
producer and these allocations happen in the context of the event
producer. This patch introduces remote memcg charging API which the
producer can use to charge the allocations to the memcg of the listener.
There are seven fsnotify kmem caches and among them allocations from
dnotify_struct_cache, dnotify_mark_cache, fanotify_mark_cache and
inotify_inode_mark_cachep happens in the context of syscall from the
listener. So, SLAB_ACCOUNT is enough for these caches.
The objects from fsnotify_mark_connector_cachep are not accounted as
they are small compared to the notification mark or events and it is
unclear whom to account connector to since it is shared by all events
attached to the inode.
The allocations from the event caches happen in the context of the event
producer. For such caches we will need to remote charge the allocations
to the listener's memcg. Thus we save the memcg reference in the
fsnotify_group structure of the listener.
This patch has also moved the members of fsnotify_group to keep the size
same, at least for 64 bit build, even with additional member by filling
the holes.
[shakeelb@google.com: use GFP_KERNEL_ACCOUNT rather than open-coding it]
Link: http://lkml.kernel.org/r/20180702215439.211597-1-shakeelb@google.com
Link: http://lkml.kernel.org/r/20180627191250.209150-2-shakeelb@google.com
Signed-off-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Amir Goldstein <amir73il@gmail.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-17 22:46:39 +00:00
|
|
|
struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm);
|
|
|
|
|
2020-12-15 20:34:29 +00:00
|
|
|
struct lruvec *lock_page_lruvec(struct page *page);
|
|
|
|
struct lruvec *lock_page_lruvec_irq(struct page *page);
|
|
|
|
struct lruvec *lock_page_lruvec_irqsave(struct page *page,
|
|
|
|
unsigned long *flags);
|
|
|
|
|
|
|
|
#ifdef CONFIG_DEBUG_VM
|
|
|
|
void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page);
|
|
|
|
#else
|
|
|
|
static inline void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2015-09-08 22:01:02 +00:00
|
|
|
static inline
|
|
|
|
struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){
|
|
|
|
return css ? container_of(css, struct mem_cgroup, css) : NULL;
|
|
|
|
}
|
|
|
|
|
2020-08-07 06:20:49 +00:00
|
|
|
static inline bool obj_cgroup_tryget(struct obj_cgroup *objcg)
|
|
|
|
{
|
|
|
|
return percpu_ref_tryget(&objcg->refcnt);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void obj_cgroup_get(struct obj_cgroup *objcg)
|
|
|
|
{
|
|
|
|
percpu_ref_get(&objcg->refcnt);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void obj_cgroup_put(struct obj_cgroup *objcg)
|
|
|
|
{
|
|
|
|
percpu_ref_put(&objcg->refcnt);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* After the initialization objcg->memcg is always pointing at
|
|
|
|
* a valid memcg, but can be atomically swapped to the parent memcg.
|
|
|
|
*
|
|
|
|
* The caller must ensure that the returned memcg won't be released:
|
|
|
|
* e.g. acquire the rcu_read_lock or css_set_lock.
|
|
|
|
*/
|
|
|
|
static inline struct mem_cgroup *obj_cgroup_memcg(struct obj_cgroup *objcg)
|
|
|
|
{
|
|
|
|
return READ_ONCE(objcg->memcg);
|
|
|
|
}
|
|
|
|
|
2018-08-17 22:46:36 +00:00
|
|
|
static inline void mem_cgroup_put(struct mem_cgroup *memcg)
|
|
|
|
{
|
fs: fsnotify: account fsnotify metadata to kmemcg
Patch series "Directed kmem charging", v8.
The Linux kernel's memory cgroup allows limiting the memory usage of the
jobs running on the system to provide isolation between the jobs. All
the kernel memory allocated in the context of the job and marked with
__GFP_ACCOUNT will also be included in the memory usage and be limited
by the job's limit.
The kernel memory can only be charged to the memcg of the process in
whose context kernel memory was allocated. However there are cases
where the allocated kernel memory should be charged to the memcg
different from the current processes's memcg. This patch series
contains two such concrete use-cases i.e. fsnotify and buffer_head.
The fsnotify event objects can consume a lot of system memory for large
or unlimited queues if there is either no or slow listener. The events
are allocated in the context of the event producer. However they should
be charged to the event consumer. Similarly the buffer_head objects can
be allocated in a memcg different from the memcg of the page for which
buffer_head objects are being allocated.
To solve this issue, this patch series introduces mechanism to charge
kernel memory to a given memcg. In case of fsnotify events, the memcg
of the consumer can be used for charging and for buffer_head, the memcg
of the page can be charged. For directed charging, the caller can use
the scope API memalloc_[un]use_memcg() to specify the memcg to charge
for all the __GFP_ACCOUNT allocations within the scope.
This patch (of 2):
A lot of memory can be consumed by the events generated for the huge or
unlimited queues if there is either no or slow listener. This can cause
system level memory pressure or OOMs. So, it's better to account the
fsnotify kmem caches to the memcg of the listener.
However the listener can be in a different memcg than the memcg of the
producer and these allocations happen in the context of the event
producer. This patch introduces remote memcg charging API which the
producer can use to charge the allocations to the memcg of the listener.
There are seven fsnotify kmem caches and among them allocations from
dnotify_struct_cache, dnotify_mark_cache, fanotify_mark_cache and
inotify_inode_mark_cachep happens in the context of syscall from the
listener. So, SLAB_ACCOUNT is enough for these caches.
The objects from fsnotify_mark_connector_cachep are not accounted as
they are small compared to the notification mark or events and it is
unclear whom to account connector to since it is shared by all events
attached to the inode.
The allocations from the event caches happen in the context of the event
producer. For such caches we will need to remote charge the allocations
to the listener's memcg. Thus we save the memcg reference in the
fsnotify_group structure of the listener.
This patch has also moved the members of fsnotify_group to keep the size
same, at least for 64 bit build, even with additional member by filling
the holes.
[shakeelb@google.com: use GFP_KERNEL_ACCOUNT rather than open-coding it]
Link: http://lkml.kernel.org/r/20180702215439.211597-1-shakeelb@google.com
Link: http://lkml.kernel.org/r/20180627191250.209150-2-shakeelb@google.com
Signed-off-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Amir Goldstein <amir73il@gmail.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-17 22:46:39 +00:00
|
|
|
if (memcg)
|
|
|
|
css_put(&memcg->css);
|
2018-08-17 22:46:36 +00:00
|
|
|
}
|
|
|
|
|
2016-01-14 23:21:32 +00:00
|
|
|
#define mem_cgroup_from_counter(counter, member) \
|
|
|
|
container_of(counter, struct mem_cgroup, member)
|
|
|
|
|
2015-09-08 22:01:02 +00:00
|
|
|
struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *,
|
|
|
|
struct mem_cgroup *,
|
|
|
|
struct mem_cgroup_reclaim_cookie *);
|
|
|
|
void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *);
|
2016-10-07 23:57:23 +00:00
|
|
|
int mem_cgroup_scan_tasks(struct mem_cgroup *,
|
|
|
|
int (*)(struct task_struct *, void *), void *);
|
2015-09-08 22:01:02 +00:00
|
|
|
|
2016-03-15 21:57:16 +00:00
|
|
|
static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg)
|
|
|
|
{
|
|
|
|
if (mem_cgroup_disabled())
|
|
|
|
return 0;
|
|
|
|
|
2016-07-20 22:44:57 +00:00
|
|
|
return memcg->id.id;
|
2016-03-15 21:57:16 +00:00
|
|
|
}
|
2016-07-20 22:44:57 +00:00
|
|
|
struct mem_cgroup *mem_cgroup_from_id(unsigned short id);
|
2016-03-15 21:57:16 +00:00
|
|
|
|
2019-03-05 23:45:52 +00:00
|
|
|
static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m)
|
|
|
|
{
|
|
|
|
return mem_cgroup_from_css(seq_css(m));
|
|
|
|
}
|
|
|
|
|
2017-07-06 22:40:25 +00:00
|
|
|
static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec)
|
|
|
|
{
|
|
|
|
struct mem_cgroup_per_node *mz;
|
|
|
|
|
|
|
|
if (mem_cgroup_disabled())
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
|
|
|
|
return mz->memcg;
|
|
|
|
}
|
|
|
|
|
2016-01-14 23:21:32 +00:00
|
|
|
/**
|
|
|
|
* parent_mem_cgroup - find the accounting parent of a memcg
|
|
|
|
* @memcg: memcg whose parent to find
|
|
|
|
*
|
|
|
|
* Returns the parent memcg, or NULL if this is the root or the memory
|
|
|
|
* controller is in legacy no-hierarchy mode.
|
|
|
|
*/
|
|
|
|
static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
|
|
|
|
{
|
|
|
|
if (!memcg->memory.parent)
|
|
|
|
return NULL;
|
|
|
|
return mem_cgroup_from_counter(memcg->memory.parent, memory);
|
|
|
|
}
|
|
|
|
|
2015-09-08 22:01:02 +00:00
|
|
|
static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg,
|
|
|
|
struct mem_cgroup *root)
|
|
|
|
{
|
|
|
|
if (root == memcg)
|
|
|
|
return true;
|
|
|
|
return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup);
|
|
|
|
}
|
2011-12-11 21:47:03 +00:00
|
|
|
|
2014-12-10 23:44:33 +00:00
|
|
|
static inline bool mm_match_cgroup(struct mm_struct *mm,
|
|
|
|
struct mem_cgroup *memcg)
|
2009-01-08 02:08:07 +00:00
|
|
|
{
|
2012-10-08 23:34:12 +00:00
|
|
|
struct mem_cgroup *task_memcg;
|
2014-12-10 23:44:30 +00:00
|
|
|
bool match = false;
|
2012-05-29 22:06:25 +00:00
|
|
|
|
2009-01-08 02:08:07 +00:00
|
|
|
rcu_read_lock();
|
2012-10-08 23:34:12 +00:00
|
|
|
task_memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
|
2014-12-10 23:44:30 +00:00
|
|
|
if (task_memcg)
|
2014-12-10 23:44:33 +00:00
|
|
|
match = mem_cgroup_is_descendant(task_memcg, memcg);
|
2009-01-08 02:08:07 +00:00
|
|
|
rcu_read_unlock();
|
2012-05-29 22:06:25 +00:00
|
|
|
return match;
|
2009-01-08 02:08:07 +00:00
|
|
|
}
|
2008-02-07 08:13:53 +00:00
|
|
|
|
2015-09-08 22:01:07 +00:00
|
|
|
struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page);
|
memcg: add page_cgroup_ino helper
This patchset introduces a new user API for tracking user memory pages
that have not been used for a given period of time. The purpose of this
is to provide the userspace with the means of tracking a workload's
working set, i.e. the set of pages that are actively used by the
workload. Knowing the working set size can be useful for partitioning the
system more efficiently, e.g. by tuning memory cgroup limits
appropriately, or for job placement within a compute cluster.
==== USE CASES ====
The unified cgroup hierarchy has memory.low and memory.high knobs, which
are defined as the low and high boundaries for the workload working set
size. However, the working set size of a workload may be unknown or
change in time. With this patch set, one can periodically estimate the
amount of memory unused by each cgroup and tune their memory.low and
memory.high parameters accordingly, therefore optimizing the overall
memory utilization.
Another use case is balancing workloads within a compute cluster. Knowing
how much memory is not really used by a workload unit may help take a more
optimal decision when considering migrating the unit to another node
within the cluster.
Also, as noted by Minchan, this would be useful for per-process reclaim
(https://lwn.net/Articles/545668/). With idle tracking, we could reclaim idle
pages only by smart user memory manager.
==== USER API ====
The user API consists of two new files:
* /sys/kernel/mm/page_idle/bitmap. This file implements a bitmap where each
bit corresponds to a page, indexed by PFN. When the bit is set, the
corresponding page is idle. A page is considered idle if it has not been
accessed since it was marked idle. To mark a page idle one should set the
bit corresponding to the page by writing to the file. A value written to the
file is OR-ed with the current bitmap value. Only user memory pages can be
marked idle, for other page types input is silently ignored. Writing to this
file beyond max PFN results in the ENXIO error. Only available when
CONFIG_IDLE_PAGE_TRACKING is set.
This file can be used to estimate the amount of pages that are not
used by a particular workload as follows:
1. mark all pages of interest idle by setting corresponding bits in the
/sys/kernel/mm/page_idle/bitmap
2. wait until the workload accesses its working set
3. read /sys/kernel/mm/page_idle/bitmap and count the number of bits set
* /proc/kpagecgroup. This file contains a 64-bit inode number of the
memory cgroup each page is charged to, indexed by PFN. Only available when
CONFIG_MEMCG is set.
This file can be used to find all pages (including unmapped file pages)
accounted to a particular cgroup. Using /sys/kernel/mm/page_idle/bitmap, one
can then estimate the cgroup working set size.
For an example of using these files for estimating the amount of unused
memory pages per each memory cgroup, please see the script attached
below.
==== REASONING ====
The reason to introduce the new user API instead of using
/proc/PID/{clear_refs,smaps} is that the latter has two serious
drawbacks:
- it does not count unmapped file pages
- it affects the reclaimer logic
The new API attempts to overcome them both. For more details on how it
is achieved, please see the comment to patch 6.
==== PATCHSET STRUCTURE ====
The patch set is organized as follows:
- patch 1 adds page_cgroup_ino() helper for the sake of
/proc/kpagecgroup and patches 2-3 do related cleanup
- patch 4 adds /proc/kpagecgroup, which reports cgroup ino each page is
charged to
- patch 5 introduces a new mmu notifier callback, clear_young, which is
a lightweight version of clear_flush_young; it is used in patch 6
- patch 6 implements the idle page tracking feature, including the
userspace API, /sys/kernel/mm/page_idle/bitmap
- patch 7 exports idle flag via /proc/kpageflags
==== SIMILAR WORKS ====
Originally, the patch for tracking idle memory was proposed back in 2011
by Michel Lespinasse (see http://lwn.net/Articles/459269/). The main
difference between Michel's patch and this one is that Michel implemented
a kernel space daemon for estimating idle memory size per cgroup while
this patch only provides the userspace with the minimal API for doing the
job, leaving the rest up to the userspace. However, they both share the
same idea of Idle/Young page flags to avoid affecting the reclaimer logic.
==== PERFORMANCE EVALUATION ====
SPECjvm2008 (https://www.spec.org/jvm2008/) was used to evaluate the
performance impact introduced by this patch set. Three runs were carried
out:
- base: kernel without the patch
- patched: patched kernel, the feature is not used
- patched-active: patched kernel, 1 minute-period daemon is used for
tracking idle memory
For tracking idle memory, idlememstat utility was used:
https://github.com/locker/idlememstat
testcase base patched patched-active
compiler 537.40 ( 0.00)% 532.26 (-0.96)% 538.31 ( 0.17)%
compress 305.47 ( 0.00)% 301.08 (-1.44)% 300.71 (-1.56)%
crypto 284.32 ( 0.00)% 282.21 (-0.74)% 284.87 ( 0.19)%
derby 411.05 ( 0.00)% 413.44 ( 0.58)% 412.07 ( 0.25)%
mpegaudio 189.96 ( 0.00)% 190.87 ( 0.48)% 189.42 (-0.28)%
scimark.large 46.85 ( 0.00)% 46.41 (-0.94)% 47.83 ( 2.09)%
scimark.small 412.91 ( 0.00)% 415.41 ( 0.61)% 421.17 ( 2.00)%
serial 204.23 ( 0.00)% 213.46 ( 4.52)% 203.17 (-0.52)%
startup 36.76 ( 0.00)% 35.49 (-3.45)% 35.64 (-3.05)%
sunflow 115.34 ( 0.00)% 115.08 (-0.23)% 117.37 ( 1.76)%
xml 620.55 ( 0.00)% 619.95 (-0.10)% 620.39 (-0.03)%
composite 211.50 ( 0.00)% 211.15 (-0.17)% 211.67 ( 0.08)%
time idlememstat:
17.20user 65.16system 2:15:23elapsed 1%CPU (0avgtext+0avgdata 8476maxresident)k
448inputs+40outputs (1major+36052minor)pagefaults 0swaps
==== SCRIPT FOR COUNTING IDLE PAGES PER CGROUP ====
#! /usr/bin/python
#
import os
import stat
import errno
import struct
CGROUP_MOUNT = "/sys/fs/cgroup/memory"
BUFSIZE = 8 * 1024 # must be multiple of 8
def get_hugepage_size():
with open("/proc/meminfo", "r") as f:
for s in f:
k, v = s.split(":")
if k == "Hugepagesize":
return int(v.split()[0]) * 1024
PAGE_SIZE = os.sysconf("SC_PAGE_SIZE")
HUGEPAGE_SIZE = get_hugepage_size()
def set_idle():
f = open("/sys/kernel/mm/page_idle/bitmap", "wb", BUFSIZE)
while True:
try:
f.write(struct.pack("Q", pow(2, 64) - 1))
except IOError as err:
if err.errno == errno.ENXIO:
break
raise
f.close()
def count_idle():
f_flags = open("/proc/kpageflags", "rb", BUFSIZE)
f_cgroup = open("/proc/kpagecgroup", "rb", BUFSIZE)
with open("/sys/kernel/mm/page_idle/bitmap", "rb", BUFSIZE) as f:
while f.read(BUFSIZE): pass # update idle flag
idlememsz = {}
while True:
s1, s2 = f_flags.read(8), f_cgroup.read(8)
if not s1 or not s2:
break
flags, = struct.unpack('Q', s1)
cgino, = struct.unpack('Q', s2)
unevictable = (flags >> 18) & 1
huge = (flags >> 22) & 1
idle = (flags >> 25) & 1
if idle and not unevictable:
idlememsz[cgino] = idlememsz.get(cgino, 0) + \
(HUGEPAGE_SIZE if huge else PAGE_SIZE)
f_flags.close()
f_cgroup.close()
return idlememsz
if __name__ == "__main__":
print "Setting the idle flag for each page..."
set_idle()
raw_input("Wait until the workload accesses its working set, "
"then press Enter")
print "Counting idle pages..."
idlememsz = count_idle()
for dir, subdirs, files in os.walk(CGROUP_MOUNT):
ino = os.stat(dir)[stat.ST_INO]
print dir + ": " + str(idlememsz.get(ino, 0) / 1024) + " kB"
==== END SCRIPT ====
This patch (of 8):
Add page_cgroup_ino() helper to memcg.
This function returns the inode number of the closest online ancestor of
the memory cgroup a page is charged to. It is required for exporting
information about which page is charged to which cgroup to userspace,
which will be introduced by a following patch.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Reviewed-by: Andres Lagar-Cavilla <andreslc@google.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Greg Thelen <gthelen@google.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-09 22:35:28 +00:00
|
|
|
ino_t page_cgroup_ino(struct page *page);
|
2009-12-16 11:19:59 +00:00
|
|
|
|
2016-01-20 23:03:02 +00:00
|
|
|
static inline bool mem_cgroup_online(struct mem_cgroup *memcg)
|
|
|
|
{
|
|
|
|
if (mem_cgroup_disabled())
|
|
|
|
return true;
|
|
|
|
return !!(memcg->css.flags & CSS_ONLINE);
|
|
|
|
}
|
|
|
|
|
2008-02-07 08:14:32 +00:00
|
|
|
/*
|
|
|
|
* For memory reclaim.
|
|
|
|
*/
|
2011-05-26 23:25:33 +00:00
|
|
|
int mem_cgroup_select_victim_node(struct mem_cgroup *memcg);
|
2015-09-08 22:01:02 +00:00
|
|
|
|
|
|
|
void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
|
2017-01-11 00:58:04 +00:00
|
|
|
int zid, int nr_pages);
|
2015-09-08 22:01:02 +00:00
|
|
|
|
2017-01-11 00:58:04 +00:00
|
|
|
static inline
|
|
|
|
unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec,
|
|
|
|
enum lru_list lru, int zone_idx)
|
|
|
|
{
|
|
|
|
struct mem_cgroup_per_node *mz;
|
|
|
|
|
|
|
|
mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
|
2020-08-15 00:31:37 +00:00
|
|
|
return READ_ONCE(mz->lru_zone_size[zone_idx][lru]);
|
2015-09-08 22:01:02 +00:00
|
|
|
}
|
|
|
|
|
memcg: punt high overage reclaim to return-to-userland path
Currently, try_charge() tries to reclaim memory synchronously when the
high limit is breached; however, if the allocation doesn't have
__GFP_WAIT, synchronous reclaim is skipped. If a process performs only
speculative allocations, it can blow way past the high limit. This is
actually easily reproducible by simply doing "find /". slab/slub
allocator tries speculative allocations first, so as long as there's
memory which can be consumed without blocking, it can keep allocating
memory regardless of the high limit.
This patch makes try_charge() always punt the over-high reclaim to the
return-to-userland path. If try_charge() detects that high limit is
breached, it adds the overage to current->memcg_nr_pages_over_high and
schedules execution of mem_cgroup_handle_over_high() which performs
synchronous reclaim from the return-to-userland path.
As long as kernel doesn't have a run-away allocation spree, this should
provide enough protection while making kmemcg behave more consistently.
It also has the following benefits.
- All over-high reclaims can use GFP_KERNEL regardless of the specific
gfp mask in use, e.g. GFP_NOFS, when the limit was breached.
- It copes with prio inversion. Previously, a low-prio task with
small memory.high might perform over-high reclaim with a bunch of
locks held. If a higher prio task needed any of these locks, it
would have to wait until the low prio task finished reclaim and
released the locks. By handing over-high reclaim to the task exit
path this issue can be avoided.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Michal Hocko <mhocko@kernel.org>
Reviewed-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-06 02:46:11 +00:00
|
|
|
void mem_cgroup_handle_over_high(void);
|
|
|
|
|
2018-06-08 00:06:18 +00:00
|
|
|
unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg);
|
2016-10-07 23:57:23 +00:00
|
|
|
|
mm, memcg: proportional memory.{low,min} reclaim
cgroup v2 introduces two memory protection thresholds: memory.low
(best-effort) and memory.min (hard protection). While they generally do
what they say on the tin, there is a limitation in their implementation
that makes them difficult to use effectively: that cliff behaviour often
manifests when they become eligible for reclaim. This patch implements
more intuitive and usable behaviour, where we gradually mount more
reclaim pressure as cgroups further and further exceed their protection
thresholds.
This cliff edge behaviour happens because we only choose whether or not
to reclaim based on whether the memcg is within its protection limits
(see the use of mem_cgroup_protected in shrink_node), but we don't vary
our reclaim behaviour based on this information. Imagine the following
timeline, with the numbers the lruvec size in this zone:
1. memory.low=1000000, memory.current=999999. 0 pages may be scanned.
2. memory.low=1000000, memory.current=1000000. 0 pages may be scanned.
3. memory.low=1000000, memory.current=1000001. 1000001* pages may be
scanned. (?!)
* Of course, we won't usually scan all available pages in the zone even
without this patch because of scan control priority, over-reclaim
protection, etc. However, as shown by the tests at the end, these
techniques don't sufficiently throttle such an extreme change in input,
so cliff-like behaviour isn't really averted by their existence alone.
Here's an example of how this plays out in practice. At Facebook, we are
trying to protect various workloads from "system" software, like
configuration management tools, metric collectors, etc (see this[0] case
study). In order to find a suitable memory.low value, we start by
determining the expected memory range within which the workload will be
comfortable operating. This isn't an exact science -- memory usage deemed
"comfortable" will vary over time due to user behaviour, differences in
composition of work, etc, etc. As such we need to ballpark memory.low,
but doing this is currently problematic:
1. If we end up setting it too low for the workload, it won't have
*any* effect (see discussion above). The group will receive the full
weight of reclaim and won't have any priority while competing with the
less important system software, as if we had no memory.low configured
at all.
2. Because of this behaviour, we end up erring on the side of setting
it too high, such that the comfort range is reliably covered. However,
protected memory is completely unavailable to the rest of the system,
so we might cause undue memory and IO pressure there when we *know* we
have some elasticity in the workload.
3. Even if we get the value totally right, smack in the middle of the
comfort zone, we get extreme jumps between no pressure and full
pressure that cause unpredictable pressure spikes in the workload due
to the current binary reclaim behaviour.
With this patch, we can set it to our ballpark estimation without too much
worry. Any undesirable behaviour, such as too much or too little reclaim
pressure on the workload or system will be proportional to how far our
estimation is off. This means we can set memory.low much more
conservatively and thus waste less resources *without* the risk of the
workload falling off a cliff if we overshoot.
As a more abstract technical description, this unintuitive behaviour
results in having to give high-priority workloads a large protection
buffer on top of their expected usage to function reliably, as otherwise
we have abrupt periods of dramatically increased memory pressure which
hamper performance. Having to set these thresholds so high wastes
resources and generally works against the principle of work conservation.
In addition, having proportional memory reclaim behaviour has other
benefits. Most notably, before this patch it's basically mandatory to set
memory.low to a higher than desirable value because otherwise as soon as
you exceed memory.low, all protection is lost, and all pages are eligible
to scan again. By contrast, having a gradual ramp in reclaim pressure
means that you now still get some protection when thresholds are exceeded,
which means that one can now be more comfortable setting memory.low to
lower values without worrying that all protection will be lost. This is
important because workingset size is really hard to know exactly,
especially with variable workloads, so at least getting *some* protection
if your workingset size grows larger than you expect increases user
confidence in setting memory.low without a huge buffer on top being
needed.
Thanks a lot to Johannes Weiner and Tejun Heo for their advice and
assistance in thinking about how to make this work better.
In testing these changes, I intended to verify that:
1. Changes in page scanning become gradual and proportional instead of
binary.
To test this, I experimented stepping further and further down
memory.low protection on a workload that floats around 19G workingset
when under memory.low protection, watching page scan rates for the
workload cgroup:
+------------+-----------------+--------------------+--------------+
| memory.low | test (pgscan/s) | control (pgscan/s) | % of control |
+------------+-----------------+--------------------+--------------+
| 21G | 0 | 0 | N/A |
| 17G | 867 | 3799 | 23% |
| 12G | 1203 | 3543 | 34% |
| 8G | 2534 | 3979 | 64% |
| 4G | 3980 | 4147 | 96% |
| 0 | 3799 | 3980 | 95% |
+------------+-----------------+--------------------+--------------+
As you can see, the test kernel (with a kernel containing this
patch) ramps up page scanning significantly more gradually than the
control kernel (without this patch).
2. More gradual ramp up in reclaim aggression doesn't result in
premature OOMs.
To test this, I wrote a script that slowly increments the number of
pages held by stress(1)'s --vm-keep mode until a production system
entered severe overall memory contention. This script runs in a highly
protected slice taking up the majority of available system memory.
Watching vmstat revealed that page scanning continued essentially
nominally between test and control, without causing forward reclaim
progress to become arrested.
[0]: https://facebookmicrosites.github.io/cgroup2/docs/overview.html#case-study-the-fbtax2-project
[akpm@linux-foundation.org: reflow block comments to fit in 80 cols]
[chris@chrisdown.name: handle cgroup_disable=memory when getting memcg protection]
Link: http://lkml.kernel.org/r/20190201045711.GA18302@chrisdown.name
Link: http://lkml.kernel.org/r/20190124014455.GA6396@chrisdown.name
Signed-off-by: Chris Down <chris@chrisdown.name>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Roman Gushchin <guro@fb.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-10-07 00:58:32 +00:00
|
|
|
unsigned long mem_cgroup_size(struct mem_cgroup *memcg);
|
|
|
|
|
mm, oom: add oom victim's memcg to the oom context information
The current oom report doesn't display victim's memcg context during the
global OOM situation. While this information is not strictly needed, it
can be really helpful for containerized environments to locate which
container has lost a process. Now that we have a single line for the oom
context, we can trivially add both the oom memcg (this can be either
global_oom or a specific memcg which hits its hard limits) and task_memcg
which is the victim's memcg.
Below is the single line output in the oom report after this patch.
- global oom context information:
oom-kill:constraint=<constraint>,nodemask=<nodemask>,cpuset=<cpuset>,mems_allowed=<mems_allowed>,global_oom,task_memcg=<memcg>,task=<comm>,pid=<pid>,uid=<uid>
- memcg oom context information:
oom-kill:constraint=<constraint>,nodemask=<nodemask>,cpuset=<cpuset>,mems_allowed=<mems_allowed>,oom_memcg=<memcg>,task_memcg=<memcg>,task=<comm>,pid=<pid>,uid=<uid>
[penguin-kernel@I-love.SAKURA.ne.jp: use pr_cont() in mem_cgroup_print_oom_context()]
Link: http://lkml.kernel.org/r/201812190723.wBJ7NdkN032628@www262.sakura.ne.jp
Link: http://lkml.kernel.org/r/1542799799-36184-2-git-send-email-ufo19890607@gmail.com
Signed-off-by: yuzhoujian <yuzhoujian@didichuxing.com>
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Cc: Roman Gushchin <guro@fb.com>
Cc: Yang Shi <yang.s@alibaba-inc.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 08:36:10 +00:00
|
|
|
void mem_cgroup_print_oom_context(struct mem_cgroup *memcg,
|
2015-09-08 22:01:07 +00:00
|
|
|
struct task_struct *p);
|
2008-02-07 08:14:32 +00:00
|
|
|
|
mm, oom: add oom victim's memcg to the oom context information
The current oom report doesn't display victim's memcg context during the
global OOM situation. While this information is not strictly needed, it
can be really helpful for containerized environments to locate which
container has lost a process. Now that we have a single line for the oom
context, we can trivially add both the oom memcg (this can be either
global_oom or a specific memcg which hits its hard limits) and task_memcg
which is the victim's memcg.
Below is the single line output in the oom report after this patch.
- global oom context information:
oom-kill:constraint=<constraint>,nodemask=<nodemask>,cpuset=<cpuset>,mems_allowed=<mems_allowed>,global_oom,task_memcg=<memcg>,task=<comm>,pid=<pid>,uid=<uid>
- memcg oom context information:
oom-kill:constraint=<constraint>,nodemask=<nodemask>,cpuset=<cpuset>,mems_allowed=<mems_allowed>,oom_memcg=<memcg>,task_memcg=<memcg>,task=<comm>,pid=<pid>,uid=<uid>
[penguin-kernel@I-love.SAKURA.ne.jp: use pr_cont() in mem_cgroup_print_oom_context()]
Link: http://lkml.kernel.org/r/201812190723.wBJ7NdkN032628@www262.sakura.ne.jp
Link: http://lkml.kernel.org/r/1542799799-36184-2-git-send-email-ufo19890607@gmail.com
Signed-off-by: yuzhoujian <yuzhoujian@didichuxing.com>
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Cc: Roman Gushchin <guro@fb.com>
Cc: Yang Shi <yang.s@alibaba-inc.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 08:36:10 +00:00
|
|
|
void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg);
|
|
|
|
|
2018-08-17 22:47:11 +00:00
|
|
|
static inline void mem_cgroup_enter_user_fault(void)
|
2013-09-12 22:13:42 +00:00
|
|
|
{
|
2018-08-17 22:47:11 +00:00
|
|
|
WARN_ON(current->in_user_fault);
|
|
|
|
current->in_user_fault = 1;
|
2013-09-12 22:13:42 +00:00
|
|
|
}
|
|
|
|
|
2018-08-17 22:47:11 +00:00
|
|
|
static inline void mem_cgroup_exit_user_fault(void)
|
2013-09-12 22:13:42 +00:00
|
|
|
{
|
2018-08-17 22:47:11 +00:00
|
|
|
WARN_ON(!current->in_user_fault);
|
|
|
|
current->in_user_fault = 0;
|
2013-09-12 22:13:42 +00:00
|
|
|
}
|
|
|
|
|
mm: memcg: do not trap chargers with full callstack on OOM
The memcg OOM handling is incredibly fragile and can deadlock. When a
task fails to charge memory, it invokes the OOM killer and loops right
there in the charge code until it succeeds. Comparably, any other task
that enters the charge path at this point will go to a waitqueue right
then and there and sleep until the OOM situation is resolved. The problem
is that these tasks may hold filesystem locks and the mmap_sem; locks that
the selected OOM victim may need to exit.
For example, in one reported case, the task invoking the OOM killer was
about to charge a page cache page during a write(), which holds the
i_mutex. The OOM killer selected a task that was just entering truncate()
and trying to acquire the i_mutex:
OOM invoking task:
mem_cgroup_handle_oom+0x241/0x3b0
mem_cgroup_cache_charge+0xbe/0xe0
add_to_page_cache_locked+0x4c/0x140
add_to_page_cache_lru+0x22/0x50
grab_cache_page_write_begin+0x8b/0xe0
ext3_write_begin+0x88/0x270
generic_file_buffered_write+0x116/0x290
__generic_file_aio_write+0x27c/0x480
generic_file_aio_write+0x76/0xf0 # takes ->i_mutex
do_sync_write+0xea/0x130
vfs_write+0xf3/0x1f0
sys_write+0x51/0x90
system_call_fastpath+0x18/0x1d
OOM kill victim:
do_truncate+0x58/0xa0 # takes i_mutex
do_last+0x250/0xa30
path_openat+0xd7/0x440
do_filp_open+0x49/0xa0
do_sys_open+0x106/0x240
sys_open+0x20/0x30
system_call_fastpath+0x18/0x1d
The OOM handling task will retry the charge indefinitely while the OOM
killed task is not releasing any resources.
A similar scenario can happen when the kernel OOM killer for a memcg is
disabled and a userspace task is in charge of resolving OOM situations.
In this case, ALL tasks that enter the OOM path will be made to sleep on
the OOM waitqueue and wait for userspace to free resources or increase
the group's limit. But a userspace OOM handler is prone to deadlock
itself on the locks held by the waiting tasks. For example one of the
sleeping tasks may be stuck in a brk() call with the mmap_sem held for
writing but the userspace handler, in order to pick an optimal victim,
may need to read files from /proc/<pid>, which tries to acquire the same
mmap_sem for reading and deadlocks.
This patch changes the way tasks behave after detecting a memcg OOM and
makes sure nobody loops or sleeps with locks held:
1. When OOMing in a user fault, invoke the OOM killer and restart the
fault instead of looping on the charge attempt. This way, the OOM
victim can not get stuck on locks the looping task may hold.
2. When OOMing in a user fault but somebody else is handling it
(either the kernel OOM killer or a userspace handler), don't go to
sleep in the charge context. Instead, remember the OOMing memcg in
the task struct and then fully unwind the page fault stack with
-ENOMEM. pagefault_out_of_memory() will then call back into the
memcg code to check if the -ENOMEM came from the memcg, and then
either put the task to sleep on the memcg's OOM waitqueue or just
restart the fault. The OOM victim can no longer get stuck on any
lock a sleeping task may hold.
Debugged by Michal Hocko.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: azurIt <azurit@pobox.sk>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: David Rientjes <rientjes@google.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-12 22:13:44 +00:00
|
|
|
static inline bool task_in_memcg_oom(struct task_struct *p)
|
|
|
|
{
|
2015-11-06 02:46:09 +00:00
|
|
|
return p->memcg_in_oom;
|
mm: memcg: do not trap chargers with full callstack on OOM
The memcg OOM handling is incredibly fragile and can deadlock. When a
task fails to charge memory, it invokes the OOM killer and loops right
there in the charge code until it succeeds. Comparably, any other task
that enters the charge path at this point will go to a waitqueue right
then and there and sleep until the OOM situation is resolved. The problem
is that these tasks may hold filesystem locks and the mmap_sem; locks that
the selected OOM victim may need to exit.
For example, in one reported case, the task invoking the OOM killer was
about to charge a page cache page during a write(), which holds the
i_mutex. The OOM killer selected a task that was just entering truncate()
and trying to acquire the i_mutex:
OOM invoking task:
mem_cgroup_handle_oom+0x241/0x3b0
mem_cgroup_cache_charge+0xbe/0xe0
add_to_page_cache_locked+0x4c/0x140
add_to_page_cache_lru+0x22/0x50
grab_cache_page_write_begin+0x8b/0xe0
ext3_write_begin+0x88/0x270
generic_file_buffered_write+0x116/0x290
__generic_file_aio_write+0x27c/0x480
generic_file_aio_write+0x76/0xf0 # takes ->i_mutex
do_sync_write+0xea/0x130
vfs_write+0xf3/0x1f0
sys_write+0x51/0x90
system_call_fastpath+0x18/0x1d
OOM kill victim:
do_truncate+0x58/0xa0 # takes i_mutex
do_last+0x250/0xa30
path_openat+0xd7/0x440
do_filp_open+0x49/0xa0
do_sys_open+0x106/0x240
sys_open+0x20/0x30
system_call_fastpath+0x18/0x1d
The OOM handling task will retry the charge indefinitely while the OOM
killed task is not releasing any resources.
A similar scenario can happen when the kernel OOM killer for a memcg is
disabled and a userspace task is in charge of resolving OOM situations.
In this case, ALL tasks that enter the OOM path will be made to sleep on
the OOM waitqueue and wait for userspace to free resources or increase
the group's limit. But a userspace OOM handler is prone to deadlock
itself on the locks held by the waiting tasks. For example one of the
sleeping tasks may be stuck in a brk() call with the mmap_sem held for
writing but the userspace handler, in order to pick an optimal victim,
may need to read files from /proc/<pid>, which tries to acquire the same
mmap_sem for reading and deadlocks.
This patch changes the way tasks behave after detecting a memcg OOM and
makes sure nobody loops or sleeps with locks held:
1. When OOMing in a user fault, invoke the OOM killer and restart the
fault instead of looping on the charge attempt. This way, the OOM
victim can not get stuck on locks the looping task may hold.
2. When OOMing in a user fault but somebody else is handling it
(either the kernel OOM killer or a userspace handler), don't go to
sleep in the charge context. Instead, remember the OOMing memcg in
the task struct and then fully unwind the page fault stack with
-ENOMEM. pagefault_out_of_memory() will then call back into the
memcg code to check if the -ENOMEM came from the memcg, and then
either put the task to sleep on the memcg's OOM waitqueue or just
restart the fault. The OOM victim can no longer get stuck on any
lock a sleeping task may hold.
Debugged by Michal Hocko.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: azurIt <azurit@pobox.sk>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: David Rientjes <rientjes@google.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-12 22:13:44 +00:00
|
|
|
}
|
|
|
|
|
2013-10-16 20:46:59 +00:00
|
|
|
bool mem_cgroup_oom_synchronize(bool wait);
|
2018-08-22 04:53:54 +00:00
|
|
|
struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim,
|
|
|
|
struct mem_cgroup *oom_domain);
|
|
|
|
void mem_cgroup_print_oom_group(struct mem_cgroup *memcg);
|
mm: memcg: do not trap chargers with full callstack on OOM
The memcg OOM handling is incredibly fragile and can deadlock. When a
task fails to charge memory, it invokes the OOM killer and loops right
there in the charge code until it succeeds. Comparably, any other task
that enters the charge path at this point will go to a waitqueue right
then and there and sleep until the OOM situation is resolved. The problem
is that these tasks may hold filesystem locks and the mmap_sem; locks that
the selected OOM victim may need to exit.
For example, in one reported case, the task invoking the OOM killer was
about to charge a page cache page during a write(), which holds the
i_mutex. The OOM killer selected a task that was just entering truncate()
and trying to acquire the i_mutex:
OOM invoking task:
mem_cgroup_handle_oom+0x241/0x3b0
mem_cgroup_cache_charge+0xbe/0xe0
add_to_page_cache_locked+0x4c/0x140
add_to_page_cache_lru+0x22/0x50
grab_cache_page_write_begin+0x8b/0xe0
ext3_write_begin+0x88/0x270
generic_file_buffered_write+0x116/0x290
__generic_file_aio_write+0x27c/0x480
generic_file_aio_write+0x76/0xf0 # takes ->i_mutex
do_sync_write+0xea/0x130
vfs_write+0xf3/0x1f0
sys_write+0x51/0x90
system_call_fastpath+0x18/0x1d
OOM kill victim:
do_truncate+0x58/0xa0 # takes i_mutex
do_last+0x250/0xa30
path_openat+0xd7/0x440
do_filp_open+0x49/0xa0
do_sys_open+0x106/0x240
sys_open+0x20/0x30
system_call_fastpath+0x18/0x1d
The OOM handling task will retry the charge indefinitely while the OOM
killed task is not releasing any resources.
A similar scenario can happen when the kernel OOM killer for a memcg is
disabled and a userspace task is in charge of resolving OOM situations.
In this case, ALL tasks that enter the OOM path will be made to sleep on
the OOM waitqueue and wait for userspace to free resources or increase
the group's limit. But a userspace OOM handler is prone to deadlock
itself on the locks held by the waiting tasks. For example one of the
sleeping tasks may be stuck in a brk() call with the mmap_sem held for
writing but the userspace handler, in order to pick an optimal victim,
may need to read files from /proc/<pid>, which tries to acquire the same
mmap_sem for reading and deadlocks.
This patch changes the way tasks behave after detecting a memcg OOM and
makes sure nobody loops or sleeps with locks held:
1. When OOMing in a user fault, invoke the OOM killer and restart the
fault instead of looping on the charge attempt. This way, the OOM
victim can not get stuck on locks the looping task may hold.
2. When OOMing in a user fault but somebody else is handling it
(either the kernel OOM killer or a userspace handler), don't go to
sleep in the charge context. Instead, remember the OOMing memcg in
the task struct and then fully unwind the page fault stack with
-ENOMEM. pagefault_out_of_memory() will then call back into the
memcg code to check if the -ENOMEM came from the memcg, and then
either put the task to sleep on the memcg's OOM waitqueue or just
restart the fault. The OOM victim can no longer get stuck on any
lock a sleeping task may hold.
Debugged by Michal Hocko.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: azurIt <azurit@pobox.sk>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: David Rientjes <rientjes@google.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-12 22:13:44 +00:00
|
|
|
|
2012-07-31 23:43:02 +00:00
|
|
|
#ifdef CONFIG_MEMCG_SWAP
|
2020-06-03 23:02:11 +00:00
|
|
|
extern bool cgroup_memory_noswap;
|
2009-01-08 02:07:57 +00:00
|
|
|
#endif
|
2009-01-08 02:08:02 +00:00
|
|
|
|
mm: memcontrol: fix NULL pointer crash in test_clear_page_writeback()
Jaegeuk and Brad report a NULL pointer crash when writeback ending tries
to update the memcg stats:
BUG: unable to handle kernel NULL pointer dereference at 00000000000003b0
IP: test_clear_page_writeback+0x12e/0x2c0
[...]
RIP: 0010:test_clear_page_writeback+0x12e/0x2c0
Call Trace:
<IRQ>
end_page_writeback+0x47/0x70
f2fs_write_end_io+0x76/0x180 [f2fs]
bio_endio+0x9f/0x120
blk_update_request+0xa8/0x2f0
scsi_end_request+0x39/0x1d0
scsi_io_completion+0x211/0x690
scsi_finish_command+0xd9/0x120
scsi_softirq_done+0x127/0x150
__blk_mq_complete_request_remote+0x13/0x20
flush_smp_call_function_queue+0x56/0x110
generic_smp_call_function_single_interrupt+0x13/0x30
smp_call_function_single_interrupt+0x27/0x40
call_function_single_interrupt+0x89/0x90
RIP: 0010:native_safe_halt+0x6/0x10
(gdb) l *(test_clear_page_writeback+0x12e)
0xffffffff811bae3e is in test_clear_page_writeback (./include/linux/memcontrol.h:619).
614 mod_node_page_state(page_pgdat(page), idx, val);
615 if (mem_cgroup_disabled() || !page->mem_cgroup)
616 return;
617 mod_memcg_state(page->mem_cgroup, idx, val);
618 pn = page->mem_cgroup->nodeinfo[page_to_nid(page)];
619 this_cpu_add(pn->lruvec_stat->count[idx], val);
620 }
621
622 unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
623 gfp_t gfp_mask,
The issue is that writeback doesn't hold a page reference and the page
might get freed after PG_writeback is cleared (and the mapping is
unlocked) in test_clear_page_writeback(). The stat functions looking up
the page's node or zone are safe, as those attributes are static across
allocation and free cycles. But page->mem_cgroup is not, and it will
get cleared if we race with truncation or migration.
It appears this race window has been around for a while, but less likely
to trigger when the memcg stats were updated first thing after
PG_writeback is cleared. Recent changes reshuffled this code to update
the global node stats before the memcg ones, though, stretching the race
window out to an extent where people can reproduce the problem.
Update test_clear_page_writeback() to look up and pin page->mem_cgroup
before clearing PG_writeback, then not use that pointer afterward. It
is a partial revert of 62cccb8c8e7a ("mm: simplify lock_page_memcg()")
but leaves the pageref-holding callsites that aren't affected alone.
Link: http://lkml.kernel.org/r/20170809183825.GA26387@cmpxchg.org
Fixes: 62cccb8c8e7a ("mm: simplify lock_page_memcg()")
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: Jaegeuk Kim <jaegeuk@kernel.org>
Tested-by: Jaegeuk Kim <jaegeuk@kernel.org>
Reported-by: Bradley Bolen <bradleybolen@gmail.com>
Tested-by: Brad Bolen <bradleybolen@gmail.com>
Cc: Vladimir Davydov <vdavydov@virtuozzo.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: <stable@vger.kernel.org> [4.6+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-08-18 22:15:48 +00:00
|
|
|
struct mem_cgroup *lock_page_memcg(struct page *page);
|
|
|
|
void __unlock_page_memcg(struct mem_cgroup *memcg);
|
2016-03-15 21:57:22 +00:00
|
|
|
void unlock_page_memcg(struct page *page);
|
mm: memcontrol: fix missed end-writeback page accounting
Commit 0a31bc97c80c ("mm: memcontrol: rewrite uncharge API") changed
page migration to uncharge the old page right away. The page is locked,
unmapped, truncated, and off the LRU, but it could race with writeback
ending, which then doesn't unaccount the page properly:
test_clear_page_writeback() migration
wait_on_page_writeback()
TestClearPageWriteback()
mem_cgroup_migrate()
clear PCG_USED
mem_cgroup_update_page_stat()
if (PageCgroupUsed(pc))
decrease memcg pages under writeback
release pc->mem_cgroup->move_lock
The per-page statistics interface is heavily optimized to avoid a
function call and a lookup_page_cgroup() in the file unmap fast path,
which means it doesn't verify whether a page is still charged before
clearing PageWriteback() and it has to do it in the stat update later.
Rework it so that it looks up the page's memcg once at the beginning of
the transaction and then uses it throughout. The charge will be
verified before clearing PageWriteback() and migration can't uncharge
the page as long as that is still set. The RCU lock will protect the
memcg past uncharge.
As far as losing the optimization goes, the following test results are
from a microbenchmark that maps, faults, and unmaps a 4GB sparse file
three times in a nested fashion, so that there are two negative passes
that don't account but still go through the new transaction overhead.
There is no actual difference:
old: 33.195102545 seconds time elapsed ( +- 0.01% )
new: 33.199231369 seconds time elapsed ( +- 0.03% )
The time spent in page_remove_rmap()'s callees still adds up to the
same, but the time spent in the function itself seems reduced:
# Children Self Command Shared Object Symbol
old: 0.12% 0.11% filemapstress [kernel.kallsyms] [k] page_remove_rmap
new: 0.12% 0.08% filemapstress [kernel.kallsyms] [k] page_remove_rmap
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Cc: <stable@vger.kernel.org> [3.17.x]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-10-29 21:50:48 +00:00
|
|
|
|
mm: memcontrol: fix recursive statistics correctness & scalabilty
Right now, when somebody needs to know the recursive memory statistics
and events of a cgroup subtree, they need to walk the entire subtree and
sum up the counters manually.
There are two issues with this:
1. When a cgroup gets deleted, its stats are lost. The state counters
should all be 0 at that point, of course, but the events are not.
When this happens, the event counters, which are supposed to be
monotonic, can go backwards in the parent cgroups.
2. During regular operation, we always have a certain number of lazily
freed cgroups sitting around that have been deleted, have no tasks,
but have a few cache pages remaining. These groups' statistics do not
change until we eventually hit memory pressure, but somebody
watching, say, memory.stat on an ancestor has to iterate those every
time.
This patch addresses both issues by introducing recursive counters at
each level that are propagated from the write side when stats change.
Upward propagation happens when the per-cpu caches spill over into the
local atomic counter. This is the same thing we do during charge and
uncharge, except that the latter uses atomic RMWs, which are more
expensive; stat changes happen at around the same rate. In a sparse
file test (page faults and reclaim at maximum CPU speed) with 5 cgroup
nesting levels, perf shows __mod_memcg_page state at ~1%.
Link: http://lkml.kernel.org/r/20190412151507.2769-4-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Reviewed-by: Roman Gushchin <guro@fb.com>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 22:47:12 +00:00
|
|
|
/*
|
|
|
|
* idx can be of type enum memcg_stat_item or node_stat_item.
|
|
|
|
* Keep in sync with memcg_exact_page_state().
|
|
|
|
*/
|
|
|
|
static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
|
|
|
|
{
|
|
|
|
long x = atomic_long_read(&memcg->vmstats[idx]);
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
if (x < 0)
|
|
|
|
x = 0;
|
|
|
|
#endif
|
|
|
|
return x;
|
|
|
|
}
|
|
|
|
|
mm: writeback: use exact memcg dirty counts
Since commit a983b5ebee57 ("mm: memcontrol: fix excessive complexity in
memory.stat reporting") memcg dirty and writeback counters are managed
as:
1) per-memcg per-cpu values in range of [-32..32]
2) per-memcg atomic counter
When a per-cpu counter cannot fit in [-32..32] it's flushed to the
atomic. Stat readers only check the atomic. Thus readers such as
balance_dirty_pages() may see a nontrivial error margin: 32 pages per
cpu.
Assuming 100 cpus:
4k x86 page_size: 13 MiB error per memcg
64k ppc page_size: 200 MiB error per memcg
Considering that dirty+writeback are used together for some decisions the
errors double.
This inaccuracy can lead to undeserved oom kills. One nasty case is
when all per-cpu counters hold positive values offsetting an atomic
negative value (i.e. per_cpu[*]=32, atomic=n_cpu*-32).
balance_dirty_pages() only consults the atomic and does not consider
throttling the next n_cpu*32 dirty pages. If the file_lru is in the
13..200 MiB range then there's absolutely no dirty throttling, which
burdens vmscan with only dirty+writeback pages thus resorting to oom
kill.
It could be argued that tiny containers are not supported, but it's more
subtle. It's the amount the space available for file lru that matters.
If a container has memory.max-200MiB of non reclaimable memory, then it
will also suffer such oom kills on a 100 cpu machine.
The following test reliably ooms without this patch. This patch avoids
oom kills.
$ cat test
mount -t cgroup2 none /dev/cgroup
cd /dev/cgroup
echo +io +memory > cgroup.subtree_control
mkdir test
cd test
echo 10M > memory.max
(echo $BASHPID > cgroup.procs && exec /memcg-writeback-stress /foo)
(echo $BASHPID > cgroup.procs && exec dd if=/dev/zero of=/foo bs=2M count=100)
$ cat memcg-writeback-stress.c
/*
* Dirty pages from all but one cpu.
* Clean pages from the non dirtying cpu.
* This is to stress per cpu counter imbalance.
* On a 100 cpu machine:
* - per memcg per cpu dirty count is 32 pages for each of 99 cpus
* - per memcg atomic is -99*32 pages
* - thus the complete dirty limit: sum of all counters 0
* - balance_dirty_pages() only sees atomic count -99*32 pages, which
* it max()s to 0.
* - So a workload can dirty -99*32 pages before balance_dirty_pages()
* cares.
*/
#define _GNU_SOURCE
#include <err.h>
#include <fcntl.h>
#include <sched.h>
#include <stdlib.h>
#include <stdio.h>
#include <sys/stat.h>
#include <sys/sysinfo.h>
#include <sys/types.h>
#include <unistd.h>
static char *buf;
static int bufSize;
static void set_affinity(int cpu)
{
cpu_set_t affinity;
CPU_ZERO(&affinity);
CPU_SET(cpu, &affinity);
if (sched_setaffinity(0, sizeof(affinity), &affinity))
err(1, "sched_setaffinity");
}
static void dirty_on(int output_fd, int cpu)
{
int i, wrote;
set_affinity(cpu);
for (i = 0; i < 32; i++) {
for (wrote = 0; wrote < bufSize; ) {
int ret = write(output_fd, buf+wrote, bufSize-wrote);
if (ret == -1)
err(1, "write");
wrote += ret;
}
}
}
int main(int argc, char **argv)
{
int cpu, flush_cpu = 1, output_fd;
const char *output;
if (argc != 2)
errx(1, "usage: output_file");
output = argv[1];
bufSize = getpagesize();
buf = malloc(getpagesize());
if (buf == NULL)
errx(1, "malloc failed");
output_fd = open(output, O_CREAT|O_RDWR);
if (output_fd == -1)
err(1, "open(%s)", output);
for (cpu = 0; cpu < get_nprocs(); cpu++) {
if (cpu != flush_cpu)
dirty_on(output_fd, cpu);
}
set_affinity(flush_cpu);
if (fsync(output_fd))
err(1, "fsync(%s)", output);
if (close(output_fd))
err(1, "close(%s)", output);
free(buf);
}
Make balance_dirty_pages() and wb_over_bg_thresh() work harder to
collect exact per memcg counters. This avoids the aforementioned oom
kills.
This does not affect the overhead of memory.stat, which still reads the
single atomic counter.
Why not use percpu_counter? memcg already handles cpus going offline, so
no need for that overhead from percpu_counter. And the percpu_counter
spinlocks are more heavyweight than is required.
It probably also makes sense to use exact dirty and writeback counters
in memcg oom reports. But that is saved for later.
Link: http://lkml.kernel.org/r/20190329174609.164344-1-gthelen@google.com
Signed-off-by: Greg Thelen <gthelen@google.com>
Reviewed-by: Roman Gushchin <guro@fb.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: <stable@vger.kernel.org> [4.16+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-04-06 01:39:18 +00:00
|
|
|
/*
|
|
|
|
* idx can be of type enum memcg_stat_item or node_stat_item.
|
|
|
|
* Keep in sync with memcg_exact_page_state().
|
|
|
|
*/
|
mm: memcontrol: make cgroup stats and events query API explicitly local
Patch series "mm: memcontrol: memory.stat cost & correctness".
The cgroup memory.stat file holds recursive statistics for the entire
subtree. The current implementation does this tree walk on-demand
whenever the file is read. This is giving us problems in production.
1. The cost of aggregating the statistics on-demand is high. A lot of
system service cgroups are mostly idle and their stats don't change
between reads, yet we always have to check them. There are also always
some lazily-dying cgroups sitting around that are pinned by a handful
of remaining page cache; the same applies to them.
In an application that periodically monitors memory.stat in our
fleet, we have seen the aggregation consume up to 5% CPU time.
2. When cgroups die and disappear from the cgroup tree, so do their
accumulated vm events. The result is that the event counters at
higher-level cgroups can go backwards and confuse some of our
automation, let alone people looking at the graphs over time.
To address both issues, this patch series changes the stat
implementation to spill counts upwards when the counters change.
The upward spilling is batched using the existing per-cpu cache. In a
sparse file stress test with 5 level cgroup nesting, the additional cost
of the flushing was negligible (a little under 1% of CPU at 100% CPU
utilization, compared to the 5% of reading memory.stat during regular
operation).
This patch (of 4):
memcg_page_state(), lruvec_page_state(), memcg_sum_events() are
currently returning the state of the local memcg or lruvec, not the
recursive state.
In practice there is a demand for both versions, although the callers
that want the recursive counts currently sum them up by hand.
Per default, cgroups are considered recursive entities and generally we
expect more users of the recursive counters, with the local counts being
special cases. To reflect that in the name, add a _local suffix to the
current implementations.
The following patch will re-incarnate these functions with recursive
semantics, but with an O(1) implementation.
[hannes@cmpxchg.org: fix bisection hole]
Link: http://lkml.kernel.org/r/20190417160347.GC23013@cmpxchg.org
Link: http://lkml.kernel.org/r/20190412151507.2769-2-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Reviewed-by: Roman Gushchin <guro@fb.com>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 22:47:06 +00:00
|
|
|
static inline unsigned long memcg_page_state_local(struct mem_cgroup *memcg,
|
|
|
|
int idx)
|
2017-05-03 21:55:03 +00:00
|
|
|
{
|
mm: memcontrol: don't batch updates of local VM stats and events
The kernel test robot noticed a 26% will-it-scale pagefault regression
from commit 42a300353577 ("mm: memcontrol: fix recursive statistics
correctness & scalabilty"). This appears to be caused by bouncing the
additional cachelines from the new hierarchical statistics counters.
We can fix this by getting rid of the batched local counters instead.
Originally, there were *only* group-local counters, and they were fully
maintained per cpu. A reader of a stats file high up in the cgroup tree
would have to walk the entire subtree and collect each level's per-cpu
counters to get the recursive view. This was prohibitively expensive,
and so we switched to per-cpu batched updates of the local counters
during a983b5ebee57 ("mm: memcontrol: fix excessive complexity in
memory.stat reporting"), reducing the complexity from nr_subgroups *
nr_cpus to nr_subgroups.
With growing machines and cgroup trees, the tree walk itself became too
expensive for monitoring top-level groups, and this is when the culprit
patch added hierarchy counters on each cgroup level. When the per-cpu
batch size would be reached, both the local and the hierarchy counters
would get batch-updated from the per-cpu delta simultaneously.
This makes local and hierarchical counter reads blazingly fast, but it
unfortunately makes the write-side too cache line intense.
Since local counter reads were never a problem - we only centralized
them to accelerate the hierarchy walk - and use of the local counters
are becoming rarer due to replacement with hierarchical views (ongoing
rework in the page reclaim and workingset code), we can make those local
counters unbatched per-cpu counters again.
The scheme will then be as such:
when a memcg statistic changes, the writer will:
- update the local counter (per-cpu)
- update the batch counter (per-cpu). If the batch is full:
- spill the batch into the group's atomic_t
- spill the batch into all ancestors' atomic_ts
- empty out the batch counter (per-cpu)
when a local memcg counter is read, the reader will:
- collect the local counter from all cpus
when a hiearchy memcg counter is read, the reader will:
- read the atomic_t
We might be able to simplify this further and make the recursive
counters unbatched per-cpu counters as well (batch upward propagation,
but leave per-cpu collection to the readers), but that will require a
more in-depth analysis and testing of all the callsites. Deal with the
immediate regression for now.
Link: http://lkml.kernel.org/r/20190521151647.GB2870@cmpxchg.org
Fixes: 42a300353577 ("mm: memcontrol: fix recursive statistics correctness & scalabilty")
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: kernel test robot <rong.a.chen@intel.com>
Tested-by: kernel test robot <rong.a.chen@intel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-06-13 22:55:46 +00:00
|
|
|
long x = 0;
|
|
|
|
int cpu;
|
|
|
|
|
|
|
|
for_each_possible_cpu(cpu)
|
|
|
|
x += per_cpu(memcg->vmstats_local->stat[idx], cpu);
|
2018-02-01 00:16:45 +00:00
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
if (x < 0)
|
|
|
|
x = 0;
|
|
|
|
#endif
|
|
|
|
return x;
|
2017-05-03 21:55:03 +00:00
|
|
|
}
|
|
|
|
|
2019-05-14 22:47:09 +00:00
|
|
|
void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val);
|
2017-05-03 21:55:03 +00:00
|
|
|
|
2017-09-06 23:22:09 +00:00
|
|
|
/* idx can be of type enum memcg_stat_item or node_stat_item */
|
2017-07-06 22:40:52 +00:00
|
|
|
static inline void mod_memcg_state(struct mem_cgroup *memcg,
|
2017-09-06 23:22:09 +00:00
|
|
|
int idx, int val)
|
2017-05-03 21:55:03 +00:00
|
|
|
{
|
2018-02-21 22:45:24 +00:00
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
local_irq_save(flags);
|
2018-02-01 00:16:45 +00:00
|
|
|
__mod_memcg_state(memcg, idx, val);
|
2018-02-21 22:45:24 +00:00
|
|
|
local_irq_restore(flags);
|
2017-05-03 21:55:03 +00:00
|
|
|
}
|
|
|
|
|
mm: memcontrol: fix recursive statistics correctness & scalabilty
Right now, when somebody needs to know the recursive memory statistics
and events of a cgroup subtree, they need to walk the entire subtree and
sum up the counters manually.
There are two issues with this:
1. When a cgroup gets deleted, its stats are lost. The state counters
should all be 0 at that point, of course, but the events are not.
When this happens, the event counters, which are supposed to be
monotonic, can go backwards in the parent cgroups.
2. During regular operation, we always have a certain number of lazily
freed cgroups sitting around that have been deleted, have no tasks,
but have a few cache pages remaining. These groups' statistics do not
change until we eventually hit memory pressure, but somebody
watching, say, memory.stat on an ancestor has to iterate those every
time.
This patch addresses both issues by introducing recursive counters at
each level that are propagated from the write side when stats change.
Upward propagation happens when the per-cpu caches spill over into the
local atomic counter. This is the same thing we do during charge and
uncharge, except that the latter uses atomic RMWs, which are more
expensive; stat changes happen at around the same rate. In a sparse
file test (page faults and reclaim at maximum CPU speed) with 5 cgroup
nesting levels, perf shows __mod_memcg_page state at ~1%.
Link: http://lkml.kernel.org/r/20190412151507.2769-4-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Reviewed-by: Roman Gushchin <guro@fb.com>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 22:47:12 +00:00
|
|
|
static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
|
|
|
|
enum node_stat_item idx)
|
|
|
|
{
|
|
|
|
struct mem_cgroup_per_node *pn;
|
|
|
|
long x;
|
|
|
|
|
|
|
|
if (mem_cgroup_disabled())
|
|
|
|
return node_page_state(lruvec_pgdat(lruvec), idx);
|
|
|
|
|
|
|
|
pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
|
|
|
|
x = atomic_long_read(&pn->lruvec_stat[idx]);
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
if (x < 0)
|
|
|
|
x = 0;
|
|
|
|
#endif
|
|
|
|
return x;
|
|
|
|
}
|
|
|
|
|
mm: memcontrol: make cgroup stats and events query API explicitly local
Patch series "mm: memcontrol: memory.stat cost & correctness".
The cgroup memory.stat file holds recursive statistics for the entire
subtree. The current implementation does this tree walk on-demand
whenever the file is read. This is giving us problems in production.
1. The cost of aggregating the statistics on-demand is high. A lot of
system service cgroups are mostly idle and their stats don't change
between reads, yet we always have to check them. There are also always
some lazily-dying cgroups sitting around that are pinned by a handful
of remaining page cache; the same applies to them.
In an application that periodically monitors memory.stat in our
fleet, we have seen the aggregation consume up to 5% CPU time.
2. When cgroups die and disappear from the cgroup tree, so do their
accumulated vm events. The result is that the event counters at
higher-level cgroups can go backwards and confuse some of our
automation, let alone people looking at the graphs over time.
To address both issues, this patch series changes the stat
implementation to spill counts upwards when the counters change.
The upward spilling is batched using the existing per-cpu cache. In a
sparse file stress test with 5 level cgroup nesting, the additional cost
of the flushing was negligible (a little under 1% of CPU at 100% CPU
utilization, compared to the 5% of reading memory.stat during regular
operation).
This patch (of 4):
memcg_page_state(), lruvec_page_state(), memcg_sum_events() are
currently returning the state of the local memcg or lruvec, not the
recursive state.
In practice there is a demand for both versions, although the callers
that want the recursive counts currently sum them up by hand.
Per default, cgroups are considered recursive entities and generally we
expect more users of the recursive counters, with the local counts being
special cases. To reflect that in the name, add a _local suffix to the
current implementations.
The following patch will re-incarnate these functions with recursive
semantics, but with an O(1) implementation.
[hannes@cmpxchg.org: fix bisection hole]
Link: http://lkml.kernel.org/r/20190417160347.GC23013@cmpxchg.org
Link: http://lkml.kernel.org/r/20190412151507.2769-2-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Reviewed-by: Roman Gushchin <guro@fb.com>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 22:47:06 +00:00
|
|
|
static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
|
|
|
|
enum node_stat_item idx)
|
2011-01-13 23:47:37 +00:00
|
|
|
{
|
2017-07-06 22:40:52 +00:00
|
|
|
struct mem_cgroup_per_node *pn;
|
mm: memcontrol: don't batch updates of local VM stats and events
The kernel test robot noticed a 26% will-it-scale pagefault regression
from commit 42a300353577 ("mm: memcontrol: fix recursive statistics
correctness & scalabilty"). This appears to be caused by bouncing the
additional cachelines from the new hierarchical statistics counters.
We can fix this by getting rid of the batched local counters instead.
Originally, there were *only* group-local counters, and they were fully
maintained per cpu. A reader of a stats file high up in the cgroup tree
would have to walk the entire subtree and collect each level's per-cpu
counters to get the recursive view. This was prohibitively expensive,
and so we switched to per-cpu batched updates of the local counters
during a983b5ebee57 ("mm: memcontrol: fix excessive complexity in
memory.stat reporting"), reducing the complexity from nr_subgroups *
nr_cpus to nr_subgroups.
With growing machines and cgroup trees, the tree walk itself became too
expensive for monitoring top-level groups, and this is when the culprit
patch added hierarchy counters on each cgroup level. When the per-cpu
batch size would be reached, both the local and the hierarchy counters
would get batch-updated from the per-cpu delta simultaneously.
This makes local and hierarchical counter reads blazingly fast, but it
unfortunately makes the write-side too cache line intense.
Since local counter reads were never a problem - we only centralized
them to accelerate the hierarchy walk - and use of the local counters
are becoming rarer due to replacement with hierarchical views (ongoing
rework in the page reclaim and workingset code), we can make those local
counters unbatched per-cpu counters again.
The scheme will then be as such:
when a memcg statistic changes, the writer will:
- update the local counter (per-cpu)
- update the batch counter (per-cpu). If the batch is full:
- spill the batch into the group's atomic_t
- spill the batch into all ancestors' atomic_ts
- empty out the batch counter (per-cpu)
when a local memcg counter is read, the reader will:
- collect the local counter from all cpus
when a hiearchy memcg counter is read, the reader will:
- read the atomic_t
We might be able to simplify this further and make the recursive
counters unbatched per-cpu counters as well (batch upward propagation,
but leave per-cpu collection to the readers), but that will require a
more in-depth analysis and testing of all the callsites. Deal with the
immediate regression for now.
Link: http://lkml.kernel.org/r/20190521151647.GB2870@cmpxchg.org
Fixes: 42a300353577 ("mm: memcontrol: fix recursive statistics correctness & scalabilty")
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: kernel test robot <rong.a.chen@intel.com>
Tested-by: kernel test robot <rong.a.chen@intel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-06-13 22:55:46 +00:00
|
|
|
long x = 0;
|
|
|
|
int cpu;
|
2017-07-06 22:40:52 +00:00
|
|
|
|
|
|
|
if (mem_cgroup_disabled())
|
|
|
|
return node_page_state(lruvec_pgdat(lruvec), idx);
|
|
|
|
|
|
|
|
pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
|
mm: memcontrol: don't batch updates of local VM stats and events
The kernel test robot noticed a 26% will-it-scale pagefault regression
from commit 42a300353577 ("mm: memcontrol: fix recursive statistics
correctness & scalabilty"). This appears to be caused by bouncing the
additional cachelines from the new hierarchical statistics counters.
We can fix this by getting rid of the batched local counters instead.
Originally, there were *only* group-local counters, and they were fully
maintained per cpu. A reader of a stats file high up in the cgroup tree
would have to walk the entire subtree and collect each level's per-cpu
counters to get the recursive view. This was prohibitively expensive,
and so we switched to per-cpu batched updates of the local counters
during a983b5ebee57 ("mm: memcontrol: fix excessive complexity in
memory.stat reporting"), reducing the complexity from nr_subgroups *
nr_cpus to nr_subgroups.
With growing machines and cgroup trees, the tree walk itself became too
expensive for monitoring top-level groups, and this is when the culprit
patch added hierarchy counters on each cgroup level. When the per-cpu
batch size would be reached, both the local and the hierarchy counters
would get batch-updated from the per-cpu delta simultaneously.
This makes local and hierarchical counter reads blazingly fast, but it
unfortunately makes the write-side too cache line intense.
Since local counter reads were never a problem - we only centralized
them to accelerate the hierarchy walk - and use of the local counters
are becoming rarer due to replacement with hierarchical views (ongoing
rework in the page reclaim and workingset code), we can make those local
counters unbatched per-cpu counters again.
The scheme will then be as such:
when a memcg statistic changes, the writer will:
- update the local counter (per-cpu)
- update the batch counter (per-cpu). If the batch is full:
- spill the batch into the group's atomic_t
- spill the batch into all ancestors' atomic_ts
- empty out the batch counter (per-cpu)
when a local memcg counter is read, the reader will:
- collect the local counter from all cpus
when a hiearchy memcg counter is read, the reader will:
- read the atomic_t
We might be able to simplify this further and make the recursive
counters unbatched per-cpu counters as well (batch upward propagation,
but leave per-cpu collection to the readers), but that will require a
more in-depth analysis and testing of all the callsites. Deal with the
immediate regression for now.
Link: http://lkml.kernel.org/r/20190521151647.GB2870@cmpxchg.org
Fixes: 42a300353577 ("mm: memcontrol: fix recursive statistics correctness & scalabilty")
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: kernel test robot <rong.a.chen@intel.com>
Tested-by: kernel test robot <rong.a.chen@intel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-06-13 22:55:46 +00:00
|
|
|
for_each_possible_cpu(cpu)
|
|
|
|
x += per_cpu(pn->lruvec_stat_local->count[idx], cpu);
|
2018-02-01 00:16:45 +00:00
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
if (x < 0)
|
|
|
|
x = 0;
|
|
|
|
#endif
|
|
|
|
return x;
|
2011-01-13 23:47:37 +00:00
|
|
|
}
|
|
|
|
|
mm: memcg: factor out memcg- and lruvec-level changes out of __mod_lruvec_state()
Patch series "The new cgroup slab memory controller", v7.
The patchset moves the accounting from the page level to the object level.
It allows to share slab pages between memory cgroups. This leads to a
significant win in the slab utilization (up to 45%) and the corresponding
drop in the total kernel memory footprint. The reduced number of
unmovable slab pages should also have a positive effect on the memory
fragmentation.
The patchset makes the slab accounting code simpler: there is no more need
in the complicated dynamic creation and destruction of per-cgroup slab
caches, all memory cgroups use a global set of shared slab caches. The
lifetime of slab caches is not more connected to the lifetime of memory
cgroups.
The more precise accounting does require more CPU, however in practice the
difference seems to be negligible. We've been using the new slab
controller in Facebook production for several months with different
workloads and haven't seen any noticeable regressions. What we've seen
were memory savings in order of 1 GB per host (it varied heavily depending
on the actual workload, size of RAM, number of CPUs, memory pressure,
etc).
The third version of the patchset added yet another step towards the
simplification of the code: sharing of slab caches between accounted and
non-accounted allocations. It comes with significant upsides (most
noticeable, a complete elimination of dynamic slab caches creation) but
not without some regression risks, so this change sits on top of the
patchset and is not completely merged in. So in the unlikely event of a
noticeable performance regression it can be reverted separately.
The slab memory accounting works in exactly the same way for SLAB and
SLUB. With both allocators the new controller shows significant memory
savings, with SLUB the difference is bigger. On my 16-core desktop
machine running Fedora 32 the size of the slab memory measured after the
start of the system was lower by 58% and 38% with SLUB and SLAB
correspondingly.
As an estimation of a potential CPU overhead, below are results of
slab_bulk_test01 test, kindly provided by Jesper D. Brouer. He also
helped with the evaluation of results.
The test can be found here: https://github.com/netoptimizer/prototype-kernel/
The smallest number in each row should be picked for a comparison.
SLUB-patched - bulk-API
- SLUB-patched : bulk_quick_reuse objects=1 : 187 - 90 - 224 cycles(tsc)
- SLUB-patched : bulk_quick_reuse objects=2 : 110 - 53 - 133 cycles(tsc)
- SLUB-patched : bulk_quick_reuse objects=3 : 88 - 95 - 42 cycles(tsc)
- SLUB-patched : bulk_quick_reuse objects=4 : 91 - 85 - 36 cycles(tsc)
- SLUB-patched : bulk_quick_reuse objects=8 : 32 - 66 - 32 cycles(tsc)
SLUB-original - bulk-API
- SLUB-original: bulk_quick_reuse objects=1 : 87 - 87 - 142 cycles(tsc)
- SLUB-original: bulk_quick_reuse objects=2 : 52 - 53 - 53 cycles(tsc)
- SLUB-original: bulk_quick_reuse objects=3 : 42 - 42 - 91 cycles(tsc)
- SLUB-original: bulk_quick_reuse objects=4 : 91 - 37 - 37 cycles(tsc)
- SLUB-original: bulk_quick_reuse objects=8 : 31 - 79 - 76 cycles(tsc)
SLAB-patched - bulk-API
- SLAB-patched : bulk_quick_reuse objects=1 : 67 - 67 - 140 cycles(tsc)
- SLAB-patched : bulk_quick_reuse objects=2 : 55 - 46 - 46 cycles(tsc)
- SLAB-patched : bulk_quick_reuse objects=3 : 93 - 94 - 39 cycles(tsc)
- SLAB-patched : bulk_quick_reuse objects=4 : 35 - 88 - 85 cycles(tsc)
- SLAB-patched : bulk_quick_reuse objects=8 : 30 - 30 - 30 cycles(tsc)
SLAB-original- bulk-API
- SLAB-original: bulk_quick_reuse objects=1 : 143 - 136 - 67 cycles(tsc)
- SLAB-original: bulk_quick_reuse objects=2 : 45 - 46 - 46 cycles(tsc)
- SLAB-original: bulk_quick_reuse objects=3 : 38 - 39 - 39 cycles(tsc)
- SLAB-original: bulk_quick_reuse objects=4 : 35 - 87 - 87 cycles(tsc)
- SLAB-original: bulk_quick_reuse objects=8 : 29 - 66 - 30 cycles(tsc)
This patch (of 19):
To convert memcg and lruvec slab counters to bytes there must be a way to
change these counters without touching node counters. Factor out
__mod_memcg_lruvec_state() out of __mod_lruvec_state().
Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/20200623174037.3951353-1-guro@fb.com
Link: http://lkml.kernel.org/r/20200623174037.3951353-2-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-07 06:20:32 +00:00
|
|
|
void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
|
|
|
|
int val);
|
2020-12-15 03:07:04 +00:00
|
|
|
void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val);
|
2020-08-07 06:21:37 +00:00
|
|
|
|
2020-12-15 03:07:04 +00:00
|
|
|
static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx,
|
2020-08-07 06:21:37 +00:00
|
|
|
int val)
|
|
|
|
{
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
local_irq_save(flags);
|
2020-12-15 03:07:04 +00:00
|
|
|
__mod_lruvec_kmem_state(p, idx, val);
|
2020-08-07 06:21:37 +00:00
|
|
|
local_irq_restore(flags);
|
|
|
|
}
|
|
|
|
|
mm: memcg: factor out memcg- and lruvec-level changes out of __mod_lruvec_state()
Patch series "The new cgroup slab memory controller", v7.
The patchset moves the accounting from the page level to the object level.
It allows to share slab pages between memory cgroups. This leads to a
significant win in the slab utilization (up to 45%) and the corresponding
drop in the total kernel memory footprint. The reduced number of
unmovable slab pages should also have a positive effect on the memory
fragmentation.
The patchset makes the slab accounting code simpler: there is no more need
in the complicated dynamic creation and destruction of per-cgroup slab
caches, all memory cgroups use a global set of shared slab caches. The
lifetime of slab caches is not more connected to the lifetime of memory
cgroups.
The more precise accounting does require more CPU, however in practice the
difference seems to be negligible. We've been using the new slab
controller in Facebook production for several months with different
workloads and haven't seen any noticeable regressions. What we've seen
were memory savings in order of 1 GB per host (it varied heavily depending
on the actual workload, size of RAM, number of CPUs, memory pressure,
etc).
The third version of the patchset added yet another step towards the
simplification of the code: sharing of slab caches between accounted and
non-accounted allocations. It comes with significant upsides (most
noticeable, a complete elimination of dynamic slab caches creation) but
not without some regression risks, so this change sits on top of the
patchset and is not completely merged in. So in the unlikely event of a
noticeable performance regression it can be reverted separately.
The slab memory accounting works in exactly the same way for SLAB and
SLUB. With both allocators the new controller shows significant memory
savings, with SLUB the difference is bigger. On my 16-core desktop
machine running Fedora 32 the size of the slab memory measured after the
start of the system was lower by 58% and 38% with SLUB and SLAB
correspondingly.
As an estimation of a potential CPU overhead, below are results of
slab_bulk_test01 test, kindly provided by Jesper D. Brouer. He also
helped with the evaluation of results.
The test can be found here: https://github.com/netoptimizer/prototype-kernel/
The smallest number in each row should be picked for a comparison.
SLUB-patched - bulk-API
- SLUB-patched : bulk_quick_reuse objects=1 : 187 - 90 - 224 cycles(tsc)
- SLUB-patched : bulk_quick_reuse objects=2 : 110 - 53 - 133 cycles(tsc)
- SLUB-patched : bulk_quick_reuse objects=3 : 88 - 95 - 42 cycles(tsc)
- SLUB-patched : bulk_quick_reuse objects=4 : 91 - 85 - 36 cycles(tsc)
- SLUB-patched : bulk_quick_reuse objects=8 : 32 - 66 - 32 cycles(tsc)
SLUB-original - bulk-API
- SLUB-original: bulk_quick_reuse objects=1 : 87 - 87 - 142 cycles(tsc)
- SLUB-original: bulk_quick_reuse objects=2 : 52 - 53 - 53 cycles(tsc)
- SLUB-original: bulk_quick_reuse objects=3 : 42 - 42 - 91 cycles(tsc)
- SLUB-original: bulk_quick_reuse objects=4 : 91 - 37 - 37 cycles(tsc)
- SLUB-original: bulk_quick_reuse objects=8 : 31 - 79 - 76 cycles(tsc)
SLAB-patched - bulk-API
- SLAB-patched : bulk_quick_reuse objects=1 : 67 - 67 - 140 cycles(tsc)
- SLAB-patched : bulk_quick_reuse objects=2 : 55 - 46 - 46 cycles(tsc)
- SLAB-patched : bulk_quick_reuse objects=3 : 93 - 94 - 39 cycles(tsc)
- SLAB-patched : bulk_quick_reuse objects=4 : 35 - 88 - 85 cycles(tsc)
- SLAB-patched : bulk_quick_reuse objects=8 : 30 - 30 - 30 cycles(tsc)
SLAB-original- bulk-API
- SLAB-original: bulk_quick_reuse objects=1 : 143 - 136 - 67 cycles(tsc)
- SLAB-original: bulk_quick_reuse objects=2 : 45 - 46 - 46 cycles(tsc)
- SLAB-original: bulk_quick_reuse objects=3 : 38 - 39 - 39 cycles(tsc)
- SLAB-original: bulk_quick_reuse objects=4 : 35 - 87 - 87 cycles(tsc)
- SLAB-original: bulk_quick_reuse objects=8 : 29 - 66 - 30 cycles(tsc)
This patch (of 19):
To convert memcg and lruvec slab counters to bytes there must be a way to
change these counters without touching node counters. Factor out
__mod_memcg_lruvec_state() out of __mod_lruvec_state().
Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/20200623174037.3951353-1-guro@fb.com
Link: http://lkml.kernel.org/r/20200623174037.3951353-2-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-07 06:20:32 +00:00
|
|
|
static inline void mod_memcg_lruvec_state(struct lruvec *lruvec,
|
|
|
|
enum node_stat_item idx, int val)
|
|
|
|
{
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
local_irq_save(flags);
|
|
|
|
__mod_memcg_lruvec_state(lruvec, idx, val);
|
|
|
|
local_irq_restore(flags);
|
|
|
|
}
|
|
|
|
|
2016-07-28 22:46:05 +00:00
|
|
|
unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
|
2013-09-24 22:27:41 +00:00
|
|
|
gfp_t gfp_mask,
|
|
|
|
unsigned long *total_scanned);
|
oom: badness heuristic rewrite
This a complete rewrite of the oom killer's badness() heuristic which is
used to determine which task to kill in oom conditions. The goal is to
make it as simple and predictable as possible so the results are better
understood and we end up killing the task which will lead to the most
memory freeing while still respecting the fine-tuning from userspace.
Instead of basing the heuristic on mm->total_vm for each task, the task's
rss and swap space is used instead. This is a better indication of the
amount of memory that will be freeable if the oom killed task is chosen
and subsequently exits. This helps specifically in cases where KDE or
GNOME is chosen for oom kill on desktop systems instead of a memory
hogging task.
The baseline for the heuristic is a proportion of memory that each task is
currently using in memory plus swap compared to the amount of "allowable"
memory. "Allowable," in this sense, means the system-wide resources for
unconstrained oom conditions, the set of mempolicy nodes, the mems
attached to current's cpuset, or a memory controller's limit. The
proportion is given on a scale of 0 (never kill) to 1000 (always kill),
roughly meaning that if a task has a badness() score of 500 that the task
consumes approximately 50% of allowable memory resident in RAM or in swap
space.
The proportion is always relative to the amount of "allowable" memory and
not the total amount of RAM systemwide so that mempolicies and cpusets may
operate in isolation; they shall not need to know the true size of the
machine on which they are running if they are bound to a specific set of
nodes or mems, respectively.
Root tasks are given 3% extra memory just like __vm_enough_memory()
provides in LSMs. In the event of two tasks consuming similar amounts of
memory, it is generally better to save root's task.
Because of the change in the badness() heuristic's baseline, it is also
necessary to introduce a new user interface to tune it. It's not possible
to redefine the meaning of /proc/pid/oom_adj with a new scale since the
ABI cannot be changed for backward compatability. Instead, a new tunable,
/proc/pid/oom_score_adj, is added that ranges from -1000 to +1000. It may
be used to polarize the heuristic such that certain tasks are never
considered for oom kill while others may always be considered. The value
is added directly into the badness() score so a value of -500, for
example, means to discount 50% of its memory consumption in comparison to
other tasks either on the system, bound to the mempolicy, in the cpuset,
or sharing the same memory controller.
/proc/pid/oom_adj is changed so that its meaning is rescaled into the
units used by /proc/pid/oom_score_adj, and vice versa. Changing one of
these per-task tunables will rescale the value of the other to an
equivalent meaning. Although /proc/pid/oom_adj was originally defined as
a bitshift on the badness score, it now shares the same linear growth as
/proc/pid/oom_score_adj but with different granularity. This is required
so the ABI is not broken with userspace applications and allows oom_adj to
be deprecated for future removal.
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-08-10 00:19:46 +00:00
|
|
|
|
2019-05-14 22:47:09 +00:00
|
|
|
void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx,
|
|
|
|
unsigned long count);
|
2018-02-01 00:16:37 +00:00
|
|
|
|
2017-07-06 22:40:25 +00:00
|
|
|
static inline void count_memcg_events(struct mem_cgroup *memcg,
|
2018-04-10 23:29:45 +00:00
|
|
|
enum vm_event_item idx,
|
|
|
|
unsigned long count)
|
2017-07-06 22:40:25 +00:00
|
|
|
{
|
2018-02-21 22:45:24 +00:00
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
local_irq_save(flags);
|
2018-02-01 00:16:45 +00:00
|
|
|
__count_memcg_events(memcg, idx, count);
|
2018-02-21 22:45:24 +00:00
|
|
|
local_irq_restore(flags);
|
2017-07-06 22:40:25 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline void count_memcg_page_event(struct page *page,
|
2018-04-10 23:29:45 +00:00
|
|
|
enum vm_event_item idx)
|
2017-07-06 22:40:25 +00:00
|
|
|
{
|
mm: memcontrol: Use helpers to read page's memcg data
Patch series "mm: allow mapping accounted kernel pages to userspace", v6.
Currently a non-slab kernel page which has been charged to a memory cgroup
can't be mapped to userspace. The underlying reason is simple: PageKmemcg
flag is defined as a page type (like buddy, offline, etc), so it takes a
bit from a page->mapped counter. Pages with a type set can't be mapped to
userspace.
But in general the kmemcg flag has nothing to do with mapping to
userspace. It only means that the page has been accounted by the page
allocator, so it has to be properly uncharged on release.
Some bpf maps are mapping the vmalloc-based memory to userspace, and their
memory can't be accounted because of this implementation detail.
This patchset removes this limitation by moving the PageKmemcg flag into
one of the free bits of the page->mem_cgroup pointer. Also it formalizes
accesses to the page->mem_cgroup and page->obj_cgroups using new helpers,
adds several checks and removes a couple of obsolete functions. As the
result the code became more robust with fewer open-coded bit tricks.
This patch (of 4):
Currently there are many open-coded reads of the page->mem_cgroup pointer,
as well as a couple of read helpers, which are barely used.
It creates an obstacle on a way to reuse some bits of the pointer for
storing additional bits of information. In fact, we already do this for
slab pages, where the last bit indicates that a pointer has an attached
vector of objcg pointers instead of a regular memcg pointer.
This commits uses 2 existing helpers and introduces a new helper to
converts all read sides to calls of these helpers:
struct mem_cgroup *page_memcg(struct page *page);
struct mem_cgroup *page_memcg_rcu(struct page *page);
struct mem_cgroup *page_memcg_check(struct page *page);
page_memcg_check() is intended to be used in cases when the page can be a
slab page and have a memcg pointer pointing at objcg vector. It does
check the lowest bit, and if set, returns NULL. page_memcg() contains a
VM_BUG_ON_PAGE() check for the page not being a slab page.
To make sure nobody uses a direct access, struct page's
mem_cgroup/obj_cgroups is converted to unsigned long memcg_data.
Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Link: https://lkml.kernel.org/r/20201027001657.3398190-1-guro@fb.com
Link: https://lkml.kernel.org/r/20201027001657.3398190-2-guro@fb.com
Link: https://lore.kernel.org/bpf/20201201215900.3569844-2-guro@fb.com
2020-12-01 21:58:27 +00:00
|
|
|
struct mem_cgroup *memcg = page_memcg(page);
|
|
|
|
|
|
|
|
if (memcg)
|
|
|
|
count_memcg_events(memcg, idx, 1);
|
2017-07-06 22:40:25 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline void count_memcg_event_mm(struct mm_struct *mm,
|
|
|
|
enum vm_event_item idx)
|
2012-12-12 21:51:57 +00:00
|
|
|
{
|
2015-09-08 22:01:02 +00:00
|
|
|
struct mem_cgroup *memcg;
|
|
|
|
|
2012-12-12 21:51:57 +00:00
|
|
|
if (mem_cgroup_disabled())
|
|
|
|
return;
|
2015-09-08 22:01:02 +00:00
|
|
|
|
|
|
|
rcu_read_lock();
|
|
|
|
memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
|
2018-06-14 22:28:05 +00:00
|
|
|
if (likely(memcg))
|
2018-02-01 00:16:37 +00:00
|
|
|
count_memcg_events(memcg, idx, 1);
|
2015-09-08 22:01:02 +00:00
|
|
|
rcu_read_unlock();
|
2012-12-12 21:51:57 +00:00
|
|
|
}
|
2018-02-01 00:16:37 +00:00
|
|
|
|
2018-04-10 23:29:45 +00:00
|
|
|
static inline void memcg_memory_event(struct mem_cgroup *memcg,
|
|
|
|
enum memcg_memory_event event)
|
2018-02-01 00:16:37 +00:00
|
|
|
{
|
2020-11-14 06:52:13 +00:00
|
|
|
bool swap_event = event == MEMCG_SWAP_HIGH || event == MEMCG_SWAP_MAX ||
|
|
|
|
event == MEMCG_SWAP_FAIL;
|
|
|
|
|
2019-07-12 03:55:55 +00:00
|
|
|
atomic_long_inc(&memcg->memory_events_local[event]);
|
2020-11-14 06:52:13 +00:00
|
|
|
if (!swap_event)
|
|
|
|
cgroup_file_notify(&memcg->events_local_file);
|
2019-07-12 03:55:55 +00:00
|
|
|
|
mm, memcg: consider subtrees in memory.events
memory.stat and other files already consider subtrees in their output, and
we should too in order to not present an inconsistent interface.
The current situation is fairly confusing, because people interacting with
cgroups expect hierarchical behaviour in the vein of memory.stat,
cgroup.events, and other files. For example, this causes confusion when
debugging reclaim events under low, as currently these always read "0" at
non-leaf memcg nodes, which frequently causes people to misdiagnose breach
behaviour. The same confusion applies to other counters in this file when
debugging issues.
Aggregation is done at write time instead of at read-time since these
counters aren't hot (unlike memory.stat which is per-page, so it does it
at read time), and it makes sense to bundle this with the file
notifications.
After this patch, events are propagated up the hierarchy:
[root@ktst ~]# cat /sys/fs/cgroup/system.slice/memory.events
low 0
high 0
max 0
oom 0
oom_kill 0
[root@ktst ~]# systemd-run -p MemoryMax=1 true
Running as unit: run-r251162a189fb4562b9dabfdc9b0422f5.service
[root@ktst ~]# cat /sys/fs/cgroup/system.slice/memory.events
low 0
high 0
max 7
oom 1
oom_kill 1
As this is a change in behaviour, this can be reverted to the old
behaviour by mounting with the `memory_localevents' flag set. However, we
use the new behaviour by default as there's a lack of evidence that there
are any current users of memory.events that would find this change
undesirable.
akpm: this is a behaviour change, so Cc:stable. THis is so that
forthcoming distros which use cgroup v2 are more likely to pick up the
revised behaviour.
Link: http://lkml.kernel.org/r/20190208224419.GA24772@chrisdown.name
Signed-off-by: Chris Down <chris@chrisdown.name>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Roman Gushchin <guro@fb.com>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-06-01 05:30:22 +00:00
|
|
|
do {
|
|
|
|
atomic_long_inc(&memcg->memory_events[event]);
|
2020-11-14 06:52:13 +00:00
|
|
|
if (swap_event)
|
|
|
|
cgroup_file_notify(&memcg->swap_events_file);
|
|
|
|
else
|
|
|
|
cgroup_file_notify(&memcg->events_file);
|
mm, memcg: consider subtrees in memory.events
memory.stat and other files already consider subtrees in their output, and
we should too in order to not present an inconsistent interface.
The current situation is fairly confusing, because people interacting with
cgroups expect hierarchical behaviour in the vein of memory.stat,
cgroup.events, and other files. For example, this causes confusion when
debugging reclaim events under low, as currently these always read "0" at
non-leaf memcg nodes, which frequently causes people to misdiagnose breach
behaviour. The same confusion applies to other counters in this file when
debugging issues.
Aggregation is done at write time instead of at read-time since these
counters aren't hot (unlike memory.stat which is per-page, so it does it
at read time), and it makes sense to bundle this with the file
notifications.
After this patch, events are propagated up the hierarchy:
[root@ktst ~]# cat /sys/fs/cgroup/system.slice/memory.events
low 0
high 0
max 0
oom 0
oom_kill 0
[root@ktst ~]# systemd-run -p MemoryMax=1 true
Running as unit: run-r251162a189fb4562b9dabfdc9b0422f5.service
[root@ktst ~]# cat /sys/fs/cgroup/system.slice/memory.events
low 0
high 0
max 7
oom 1
oom_kill 1
As this is a change in behaviour, this can be reverted to the old
behaviour by mounting with the `memory_localevents' flag set. However, we
use the new behaviour by default as there's a lack of evidence that there
are any current users of memory.events that would find this change
undesirable.
akpm: this is a behaviour change, so Cc:stable. THis is so that
forthcoming distros which use cgroup v2 are more likely to pick up the
revised behaviour.
Link: http://lkml.kernel.org/r/20190208224419.GA24772@chrisdown.name
Signed-off-by: Chris Down <chris@chrisdown.name>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Roman Gushchin <guro@fb.com>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-06-01 05:30:22 +00:00
|
|
|
|
mm, memcg: fix inconsistent oom event behavior
A recent commit 9852ae3fe529 ("mm, memcg: consider subtrees in
memory.events") changed the behavior of memcg events, which will now
consider subtrees in memory.events.
But oom_kill event is a special one as it is used in both cgroup1 and
cgroup2. In cgroup1, it is displayed in memory.oom_control. The file
memory.oom_control is in both root memcg and non root memcg, that is
different with memory.event as it only in non-root memcg. That commit
is okay for cgroup2, but it is not okay for cgroup1 as it will cause
inconsistent behavior between root memcg and non-root memcg.
Here's an example on why this behavior is inconsistent in cgroup1.
root memcg
/
memcg foo
/
memcg bar
Suppose there's an oom_kill in memcg bar, then the oon_kill will be
root memcg : memory.oom_control(oom_kill) 0
/
memcg foo : memory.oom_control(oom_kill) 1
/
memcg bar : memory.oom_control(oom_kill) 1
For the non-root memcg, its memory.oom_control(oom_kill) includes its
descendants' oom_kill, but for root memcg, it doesn't include its
descendants' oom_kill. That means, memory.oom_control(oom_kill) has
different meanings in different memcgs. That is inconsistent. Then the
user has to know whether the memcg is root or not.
If we can't fully support it in cgroup1, for example by adding
memory.events.local into cgroup1 as well, then let's don't touch its
original behavior.
Fixes: 9852ae3fe529 ("mm, memcg: consider subtrees in memory.events")
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Chris Down <chris@chrisdown.name>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: <stable@vger.kernel.org>
Link: http://lkml.kernel.org/r/20200502141055.7378-1-laoar.shao@gmail.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-05-14 00:50:34 +00:00
|
|
|
if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
|
|
|
|
break;
|
mm, memcg: consider subtrees in memory.events
memory.stat and other files already consider subtrees in their output, and
we should too in order to not present an inconsistent interface.
The current situation is fairly confusing, because people interacting with
cgroups expect hierarchical behaviour in the vein of memory.stat,
cgroup.events, and other files. For example, this causes confusion when
debugging reclaim events under low, as currently these always read "0" at
non-leaf memcg nodes, which frequently causes people to misdiagnose breach
behaviour. The same confusion applies to other counters in this file when
debugging issues.
Aggregation is done at write time instead of at read-time since these
counters aren't hot (unlike memory.stat which is per-page, so it does it
at read time), and it makes sense to bundle this with the file
notifications.
After this patch, events are propagated up the hierarchy:
[root@ktst ~]# cat /sys/fs/cgroup/system.slice/memory.events
low 0
high 0
max 0
oom 0
oom_kill 0
[root@ktst ~]# systemd-run -p MemoryMax=1 true
Running as unit: run-r251162a189fb4562b9dabfdc9b0422f5.service
[root@ktst ~]# cat /sys/fs/cgroup/system.slice/memory.events
low 0
high 0
max 7
oom 1
oom_kill 1
As this is a change in behaviour, this can be reverted to the old
behaviour by mounting with the `memory_localevents' flag set. However, we
use the new behaviour by default as there's a lack of evidence that there
are any current users of memory.events that would find this change
undesirable.
akpm: this is a behaviour change, so Cc:stable. THis is so that
forthcoming distros which use cgroup v2 are more likely to pick up the
revised behaviour.
Link: http://lkml.kernel.org/r/20190208224419.GA24772@chrisdown.name
Signed-off-by: Chris Down <chris@chrisdown.name>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Roman Gushchin <guro@fb.com>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-06-01 05:30:22 +00:00
|
|
|
if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS)
|
|
|
|
break;
|
|
|
|
} while ((memcg = parent_mem_cgroup(memcg)) &&
|
|
|
|
!mem_cgroup_is_root(memcg));
|
2018-02-01 00:16:37 +00:00
|
|
|
}
|
|
|
|
|
2018-06-14 22:28:05 +00:00
|
|
|
static inline void memcg_memory_event_mm(struct mm_struct *mm,
|
|
|
|
enum memcg_memory_event event)
|
|
|
|
{
|
|
|
|
struct mem_cgroup *memcg;
|
|
|
|
|
|
|
|
if (mem_cgroup_disabled())
|
|
|
|
return;
|
|
|
|
|
|
|
|
rcu_read_lock();
|
|
|
|
memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
|
|
|
|
if (likely(memcg))
|
|
|
|
memcg_memory_event(memcg, event);
|
|
|
|
rcu_read_unlock();
|
|
|
|
}
|
|
|
|
|
2011-01-20 22:44:24 +00:00
|
|
|
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
|
2012-01-13 01:18:20 +00:00
|
|
|
void mem_cgroup_split_huge_fixup(struct page *head);
|
2011-01-20 22:44:24 +00:00
|
|
|
#endif
|
|
|
|
|
2012-07-31 23:43:02 +00:00
|
|
|
#else /* CONFIG_MEMCG */
|
2016-03-15 21:57:16 +00:00
|
|
|
|
|
|
|
#define MEM_CGROUP_ID_SHIFT 0
|
|
|
|
#define MEM_CGROUP_ID_MAX 0
|
|
|
|
|
2009-01-08 02:07:48 +00:00
|
|
|
struct mem_cgroup;
|
|
|
|
|
mm: memcontrol: Use helpers to read page's memcg data
Patch series "mm: allow mapping accounted kernel pages to userspace", v6.
Currently a non-slab kernel page which has been charged to a memory cgroup
can't be mapped to userspace. The underlying reason is simple: PageKmemcg
flag is defined as a page type (like buddy, offline, etc), so it takes a
bit from a page->mapped counter. Pages with a type set can't be mapped to
userspace.
But in general the kmemcg flag has nothing to do with mapping to
userspace. It only means that the page has been accounted by the page
allocator, so it has to be properly uncharged on release.
Some bpf maps are mapping the vmalloc-based memory to userspace, and their
memory can't be accounted because of this implementation detail.
This patchset removes this limitation by moving the PageKmemcg flag into
one of the free bits of the page->mem_cgroup pointer. Also it formalizes
accesses to the page->mem_cgroup and page->obj_cgroups using new helpers,
adds several checks and removes a couple of obsolete functions. As the
result the code became more robust with fewer open-coded bit tricks.
This patch (of 4):
Currently there are many open-coded reads of the page->mem_cgroup pointer,
as well as a couple of read helpers, which are barely used.
It creates an obstacle on a way to reuse some bits of the pointer for
storing additional bits of information. In fact, we already do this for
slab pages, where the last bit indicates that a pointer has an attached
vector of objcg pointers instead of a regular memcg pointer.
This commits uses 2 existing helpers and introduces a new helper to
converts all read sides to calls of these helpers:
struct mem_cgroup *page_memcg(struct page *page);
struct mem_cgroup *page_memcg_rcu(struct page *page);
struct mem_cgroup *page_memcg_check(struct page *page);
page_memcg_check() is intended to be used in cases when the page can be a
slab page and have a memcg pointer pointing at objcg vector. It does
check the lowest bit, and if set, returns NULL. page_memcg() contains a
VM_BUG_ON_PAGE() check for the page not being a slab page.
To make sure nobody uses a direct access, struct page's
mem_cgroup/obj_cgroups is converted to unsigned long memcg_data.
Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Link: https://lkml.kernel.org/r/20201027001657.3398190-1-guro@fb.com
Link: https://lkml.kernel.org/r/20201027001657.3398190-2-guro@fb.com
Link: https://lore.kernel.org/bpf/20201201215900.3569844-2-guro@fb.com
2020-12-01 21:58:27 +00:00
|
|
|
static inline struct mem_cgroup *page_memcg(struct page *page)
|
|
|
|
{
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline struct mem_cgroup *page_memcg_rcu(struct page *page)
|
|
|
|
{
|
|
|
|
WARN_ON_ONCE(!rcu_read_lock_held());
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline struct mem_cgroup *page_memcg_check(struct page *page)
|
|
|
|
{
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2020-12-01 21:58:30 +00:00
|
|
|
static inline bool PageMemcgKmem(struct page *page)
|
|
|
|
{
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
2018-08-17 22:48:06 +00:00
|
|
|
static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg)
|
|
|
|
{
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
2016-03-15 21:57:16 +00:00
|
|
|
static inline bool mem_cgroup_disabled(void)
|
|
|
|
{
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
2018-04-10 23:29:45 +00:00
|
|
|
static inline void memcg_memory_event(struct mem_cgroup *memcg,
|
|
|
|
enum memcg_memory_event event)
|
mm: memcontrol: default hierarchy interface for memory
Introduce the basic control files to account, partition, and limit
memory using cgroups in default hierarchy mode.
This interface versioning allows us to address fundamental design
issues in the existing memory cgroup interface, further explained
below. The old interface will be maintained indefinitely, but a
clearer model and improved workload performance should encourage
existing users to switch over to the new one eventually.
The control files are thus:
- memory.current shows the current consumption of the cgroup and its
descendants, in bytes.
- memory.low configures the lower end of the cgroup's expected
memory consumption range. The kernel considers memory below that
boundary to be a reserve - the minimum that the workload needs in
order to make forward progress - and generally avoids reclaiming
it, unless there is an imminent risk of entering an OOM situation.
- memory.high configures the upper end of the cgroup's expected
memory consumption range. A cgroup whose consumption grows beyond
this threshold is forced into direct reclaim, to work off the
excess and to throttle new allocations heavily, but is generally
allowed to continue and the OOM killer is not invoked.
- memory.max configures the hard maximum amount of memory that the
cgroup is allowed to consume before the OOM killer is invoked.
- memory.events shows event counters that indicate how often the
cgroup was reclaimed while below memory.low, how often it was
forced to reclaim excess beyond memory.high, how often it hit
memory.max, and how often it entered OOM due to memory.max. This
allows users to identify configuration problems when observing a
degradation in workload performance. An overcommitted system will
have an increased rate of low boundary breaches, whereas increased
rates of high limit breaches, maximum hits, or even OOM situations
will indicate internally overcommitted cgroups.
For existing users of memory cgroups, the following deviations from
the current interface are worth pointing out and explaining:
- The original lower boundary, the soft limit, is defined as a limit
that is per default unset. As a result, the set of cgroups that
global reclaim prefers is opt-in, rather than opt-out. The costs
for optimizing these mostly negative lookups are so high that the
implementation, despite its enormous size, does not even provide
the basic desirable behavior. First off, the soft limit has no
hierarchical meaning. All configured groups are organized in a
global rbtree and treated like equal peers, regardless where they
are located in the hierarchy. This makes subtree delegation
impossible. Second, the soft limit reclaim pass is so aggressive
that it not just introduces high allocation latencies into the
system, but also impacts system performance due to overreclaim, to
the point where the feature becomes self-defeating.
The memory.low boundary on the other hand is a top-down allocated
reserve. A cgroup enjoys reclaim protection when it and all its
ancestors are below their low boundaries, which makes delegation
of subtrees possible. Secondly, new cgroups have no reserve per
default and in the common case most cgroups are eligible for the
preferred reclaim pass. This allows the new low boundary to be
efficiently implemented with just a minor addition to the generic
reclaim code, without the need for out-of-band data structures and
reclaim passes. Because the generic reclaim code considers all
cgroups except for the ones running low in the preferred first
reclaim pass, overreclaim of individual groups is eliminated as
well, resulting in much better overall workload performance.
- The original high boundary, the hard limit, is defined as a strict
limit that can not budge, even if the OOM killer has to be called.
But this generally goes against the goal of making the most out of
the available memory. The memory consumption of workloads varies
during runtime, and that requires users to overcommit. But doing
that with a strict upper limit requires either a fairly accurate
prediction of the working set size or adding slack to the limit.
Since working set size estimation is hard and error prone, and
getting it wrong results in OOM kills, most users tend to err on
the side of a looser limit and end up wasting precious resources.
The memory.high boundary on the other hand can be set much more
conservatively. When hit, it throttles allocations by forcing
them into direct reclaim to work off the excess, but it never
invokes the OOM killer. As a result, a high boundary that is
chosen too aggressively will not terminate the processes, but
instead it will lead to gradual performance degradation. The user
can monitor this and make corrections until the minimal memory
footprint that still gives acceptable performance is found.
In extreme cases, with many concurrent allocations and a complete
breakdown of reclaim progress within the group, the high boundary
can be exceeded. But even then it's mostly better to satisfy the
allocation from the slack available in other groups or the rest of
the system than killing the group. Otherwise, memory.max is there
to limit this type of spillover and ultimately contain buggy or
even malicious applications.
- The original control file names are unwieldy and inconsistent in
many different ways. For example, the upper boundary hit count is
exported in the memory.failcnt file, but an OOM event count has to
be manually counted by listening to memory.oom_control events, and
lower boundary / soft limit events have to be counted by first
setting a threshold for that value and then counting those events.
Also, usage and limit files encode their units in the filename.
That makes the filenames very long, even though this is not
information that a user needs to be reminded of every time they
type out those names.
To address these naming issues, as well as to signal clearly that
the new interface carries a new configuration model, the naming
conventions in it necessarily differ from the old interface.
- The original limit files indicate the state of an unset limit with
a very high number, and a configured limit can be unset by echoing
-1 into those files. But that very high number is implementation
and architecture dependent and not very descriptive. And while -1
can be understood as an underflow into the highest possible value,
-2 or -10M etc. do not work, so it's not inconsistent.
memory.low, memory.high, and memory.max will use the string
"infinity" to indicate and set the highest possible value.
[akpm@linux-foundation.org: use seq_puts() for basic strings]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Cc: Greg Thelen <gthelen@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-11 23:26:06 +00:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2018-06-14 22:28:05 +00:00
|
|
|
static inline void memcg_memory_event_mm(struct mm_struct *mm,
|
|
|
|
enum memcg_memory_event event)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
mm, memcg: avoid stale protection values when cgroup is above protection
Patch series "mm, memcg: memory.{low,min} reclaim fix & cleanup", v4.
This series contains a fix for a edge case in my earlier protection
calculation patches, and a patch to make the area overall a little more
robust to hopefully help avoid this in future.
This patch (of 2):
A cgroup can have both memory protection and a memory limit to isolate it
from its siblings in both directions - for example, to prevent it from
being shrunk below 2G under high pressure from outside, but also from
growing beyond 4G under low pressure.
Commit 9783aa9917f8 ("mm, memcg: proportional memory.{low,min} reclaim")
implemented proportional scan pressure so that multiple siblings in excess
of their protection settings don't get reclaimed equally but instead in
accordance to their unprotected portion.
During limit reclaim, this proportionality shouldn't apply of course:
there is no competition, all pressure is from within the cgroup and should
be applied as such. Reclaim should operate at full efficiency.
However, mem_cgroup_protected() never expected anybody to look at the
effective protection values when it indicated that the cgroup is above its
protection. As a result, a query during limit reclaim may return stale
protection values that were calculated by a previous reclaim cycle in
which the cgroup did have siblings.
When this happens, reclaim is unnecessarily hesitant and potentially slow
to meet the desired limit. In theory this could lead to premature OOM
kills, although it's not obvious this has occurred in practice.
Workaround the problem by special casing reclaim roots in
mem_cgroup_protection. These memcgs are never participating in the
reclaim protection because the reclaim is internal.
We have to ignore effective protection values for reclaim roots because
mem_cgroup_protected might be called from racing reclaim contexts with
different roots. Calculation is relying on root -> leaf tree traversal
therefore top-down reclaim protection invariants should hold. The only
exception is the reclaim root which should have effective protection set
to 0 but that would be problematic for the following setup:
Let's have global and A's reclaim in parallel:
|
A (low=2G, usage = 3G, max = 3G, children_low_usage = 1.5G)
|\
| C (low = 1G, usage = 2.5G)
B (low = 1G, usage = 0.5G)
for A reclaim we have
B.elow = B.low
C.elow = C.low
For the global reclaim
A.elow = A.low
B.elow = min(B.usage, B.low) because children_low_usage <= A.elow
C.elow = min(C.usage, C.low)
With the effective values resetting we have A reclaim
A.elow = 0
B.elow = B.low
C.elow = C.low
and global reclaim could see the above and then
B.elow = C.elow = 0 because children_low_usage > A.elow
Which means that protected memcgs would get reclaimed.
In future we would like to make mem_cgroup_protected more robust against
racing reclaim contexts but that is likely more complex solution than this
simple workaround.
[hannes@cmpxchg.org - large part of the changelog]
[mhocko@suse.com - workaround explanation]
[chris@chrisdown.name - retitle]
Fixes: 9783aa9917f8 ("mm, memcg: proportional memory.{low,min} reclaim")
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Chris Down <chris@chrisdown.name>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Chris Down <chris@chrisdown.name>
Acked-by: Roman Gushchin <guro@fb.com>
Link: http://lkml.kernel.org/r/cover.1594638158.git.chris@chrisdown.name
Link: http://lkml.kernel.org/r/044fb8ecffd001c7905d27c0c2ad998069fdc396.1594638158.git.chris@chrisdown.name
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-07 06:22:01 +00:00
|
|
|
static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root,
|
|
|
|
struct mem_cgroup *memcg,
|
mm, memcg: make scan aggression always exclude protection
This patch is an incremental improvement on the existing
memory.{low,min} relative reclaim work to base its scan pressure
calculations on how much protection is available compared to the current
usage, rather than how much the current usage is over some protection
threshold.
This change doesn't change the experience for the user in the normal
case too much. One benefit is that it replaces the (somewhat arbitrary)
100% cutoff with an indefinite slope, which makes it easier to ballpark
a memory.low value.
As well as this, the old methodology doesn't quite apply generically to
machines with varying amounts of physical memory. Let's say we have a
top level cgroup, workload.slice, and another top level cgroup,
system-management.slice. We want to roughly give 12G to
system-management.slice, so on a 32GB machine we set memory.low to 20GB
in workload.slice, and on a 64GB machine we set memory.low to 52GB.
However, because these are relative amounts to the total machine size,
while the amount of memory we want to generally be willing to yield to
system.slice is absolute (12G), we end up putting more pressure on
system.slice just because we have a larger machine and a larger workload
to fill it, which seems fairly unintuitive. With this new behaviour, we
don't end up with this unintended side effect.
Previously the way that memory.low protection works is that if you are
50% over a certain baseline, you get 50% of your normal scan pressure.
This is certainly better than the previous cliff-edge behaviour, but it
can be improved even further by always considering memory under the
currently enforced protection threshold to be out of bounds. This means
that we can set relatively low memory.low thresholds for variable or
bursty workloads while still getting a reasonable level of protection,
whereas with the previous version we may still trivially hit the 100%
clamp. The previous 100% clamp is also somewhat arbitrary, whereas this
one is more concretely based on the currently enforced protection
threshold, which is likely easier to reason about.
There is also a subtle issue with the way that proportional reclaim
worked previously -- it promotes having no memory.low, since it makes
pressure higher during low reclaim. This happens because we base our
scan pressure modulation on how far memory.current is between memory.min
and memory.low, but if memory.low is unset, we only use the overage
method. In most cromulent configurations, this then means that we end
up with *more* pressure than with no memory.low at all when we're in low
reclaim, which is not really very usable or expected.
With this patch, memory.low and memory.min affect reclaim pressure in a
more understandable and composable way. For example, from a user
standpoint, "protected" memory now remains untouchable from a reclaim
aggression standpoint, and users can also have more confidence that
bursty workloads will still receive some amount of guaranteed
protection.
Link: http://lkml.kernel.org/r/20190322160307.GA3316@chrisdown.name
Signed-off-by: Chris Down <chris@chrisdown.name>
Reviewed-by: Roman Gushchin <guro@fb.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-10-07 00:58:38 +00:00
|
|
|
bool in_low_reclaim)
|
mm, memcg: proportional memory.{low,min} reclaim
cgroup v2 introduces two memory protection thresholds: memory.low
(best-effort) and memory.min (hard protection). While they generally do
what they say on the tin, there is a limitation in their implementation
that makes them difficult to use effectively: that cliff behaviour often
manifests when they become eligible for reclaim. This patch implements
more intuitive and usable behaviour, where we gradually mount more
reclaim pressure as cgroups further and further exceed their protection
thresholds.
This cliff edge behaviour happens because we only choose whether or not
to reclaim based on whether the memcg is within its protection limits
(see the use of mem_cgroup_protected in shrink_node), but we don't vary
our reclaim behaviour based on this information. Imagine the following
timeline, with the numbers the lruvec size in this zone:
1. memory.low=1000000, memory.current=999999. 0 pages may be scanned.
2. memory.low=1000000, memory.current=1000000. 0 pages may be scanned.
3. memory.low=1000000, memory.current=1000001. 1000001* pages may be
scanned. (?!)
* Of course, we won't usually scan all available pages in the zone even
without this patch because of scan control priority, over-reclaim
protection, etc. However, as shown by the tests at the end, these
techniques don't sufficiently throttle such an extreme change in input,
so cliff-like behaviour isn't really averted by their existence alone.
Here's an example of how this plays out in practice. At Facebook, we are
trying to protect various workloads from "system" software, like
configuration management tools, metric collectors, etc (see this[0] case
study). In order to find a suitable memory.low value, we start by
determining the expected memory range within which the workload will be
comfortable operating. This isn't an exact science -- memory usage deemed
"comfortable" will vary over time due to user behaviour, differences in
composition of work, etc, etc. As such we need to ballpark memory.low,
but doing this is currently problematic:
1. If we end up setting it too low for the workload, it won't have
*any* effect (see discussion above). The group will receive the full
weight of reclaim and won't have any priority while competing with the
less important system software, as if we had no memory.low configured
at all.
2. Because of this behaviour, we end up erring on the side of setting
it too high, such that the comfort range is reliably covered. However,
protected memory is completely unavailable to the rest of the system,
so we might cause undue memory and IO pressure there when we *know* we
have some elasticity in the workload.
3. Even if we get the value totally right, smack in the middle of the
comfort zone, we get extreme jumps between no pressure and full
pressure that cause unpredictable pressure spikes in the workload due
to the current binary reclaim behaviour.
With this patch, we can set it to our ballpark estimation without too much
worry. Any undesirable behaviour, such as too much or too little reclaim
pressure on the workload or system will be proportional to how far our
estimation is off. This means we can set memory.low much more
conservatively and thus waste less resources *without* the risk of the
workload falling off a cliff if we overshoot.
As a more abstract technical description, this unintuitive behaviour
results in having to give high-priority workloads a large protection
buffer on top of their expected usage to function reliably, as otherwise
we have abrupt periods of dramatically increased memory pressure which
hamper performance. Having to set these thresholds so high wastes
resources and generally works against the principle of work conservation.
In addition, having proportional memory reclaim behaviour has other
benefits. Most notably, before this patch it's basically mandatory to set
memory.low to a higher than desirable value because otherwise as soon as
you exceed memory.low, all protection is lost, and all pages are eligible
to scan again. By contrast, having a gradual ramp in reclaim pressure
means that you now still get some protection when thresholds are exceeded,
which means that one can now be more comfortable setting memory.low to
lower values without worrying that all protection will be lost. This is
important because workingset size is really hard to know exactly,
especially with variable workloads, so at least getting *some* protection
if your workingset size grows larger than you expect increases user
confidence in setting memory.low without a huge buffer on top being
needed.
Thanks a lot to Johannes Weiner and Tejun Heo for their advice and
assistance in thinking about how to make this work better.
In testing these changes, I intended to verify that:
1. Changes in page scanning become gradual and proportional instead of
binary.
To test this, I experimented stepping further and further down
memory.low protection on a workload that floats around 19G workingset
when under memory.low protection, watching page scan rates for the
workload cgroup:
+------------+-----------------+--------------------+--------------+
| memory.low | test (pgscan/s) | control (pgscan/s) | % of control |
+------------+-----------------+--------------------+--------------+
| 21G | 0 | 0 | N/A |
| 17G | 867 | 3799 | 23% |
| 12G | 1203 | 3543 | 34% |
| 8G | 2534 | 3979 | 64% |
| 4G | 3980 | 4147 | 96% |
| 0 | 3799 | 3980 | 95% |
+------------+-----------------+--------------------+--------------+
As you can see, the test kernel (with a kernel containing this
patch) ramps up page scanning significantly more gradually than the
control kernel (without this patch).
2. More gradual ramp up in reclaim aggression doesn't result in
premature OOMs.
To test this, I wrote a script that slowly increments the number of
pages held by stress(1)'s --vm-keep mode until a production system
entered severe overall memory contention. This script runs in a highly
protected slice taking up the majority of available system memory.
Watching vmstat revealed that page scanning continued essentially
nominally between test and control, without causing forward reclaim
progress to become arrested.
[0]: https://facebookmicrosites.github.io/cgroup2/docs/overview.html#case-study-the-fbtax2-project
[akpm@linux-foundation.org: reflow block comments to fit in 80 cols]
[chris@chrisdown.name: handle cgroup_disable=memory when getting memcg protection]
Link: http://lkml.kernel.org/r/20190201045711.GA18302@chrisdown.name
Link: http://lkml.kernel.org/r/20190124014455.GA6396@chrisdown.name
Signed-off-by: Chris Down <chris@chrisdown.name>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Roman Gushchin <guro@fb.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-10-07 00:58:32 +00:00
|
|
|
{
|
mm, memcg: make scan aggression always exclude protection
This patch is an incremental improvement on the existing
memory.{low,min} relative reclaim work to base its scan pressure
calculations on how much protection is available compared to the current
usage, rather than how much the current usage is over some protection
threshold.
This change doesn't change the experience for the user in the normal
case too much. One benefit is that it replaces the (somewhat arbitrary)
100% cutoff with an indefinite slope, which makes it easier to ballpark
a memory.low value.
As well as this, the old methodology doesn't quite apply generically to
machines with varying amounts of physical memory. Let's say we have a
top level cgroup, workload.slice, and another top level cgroup,
system-management.slice. We want to roughly give 12G to
system-management.slice, so on a 32GB machine we set memory.low to 20GB
in workload.slice, and on a 64GB machine we set memory.low to 52GB.
However, because these are relative amounts to the total machine size,
while the amount of memory we want to generally be willing to yield to
system.slice is absolute (12G), we end up putting more pressure on
system.slice just because we have a larger machine and a larger workload
to fill it, which seems fairly unintuitive. With this new behaviour, we
don't end up with this unintended side effect.
Previously the way that memory.low protection works is that if you are
50% over a certain baseline, you get 50% of your normal scan pressure.
This is certainly better than the previous cliff-edge behaviour, but it
can be improved even further by always considering memory under the
currently enforced protection threshold to be out of bounds. This means
that we can set relatively low memory.low thresholds for variable or
bursty workloads while still getting a reasonable level of protection,
whereas with the previous version we may still trivially hit the 100%
clamp. The previous 100% clamp is also somewhat arbitrary, whereas this
one is more concretely based on the currently enforced protection
threshold, which is likely easier to reason about.
There is also a subtle issue with the way that proportional reclaim
worked previously -- it promotes having no memory.low, since it makes
pressure higher during low reclaim. This happens because we base our
scan pressure modulation on how far memory.current is between memory.min
and memory.low, but if memory.low is unset, we only use the overage
method. In most cromulent configurations, this then means that we end
up with *more* pressure than with no memory.low at all when we're in low
reclaim, which is not really very usable or expected.
With this patch, memory.low and memory.min affect reclaim pressure in a
more understandable and composable way. For example, from a user
standpoint, "protected" memory now remains untouchable from a reclaim
aggression standpoint, and users can also have more confidence that
bursty workloads will still receive some amount of guaranteed
protection.
Link: http://lkml.kernel.org/r/20190322160307.GA3316@chrisdown.name
Signed-off-by: Chris Down <chris@chrisdown.name>
Reviewed-by: Roman Gushchin <guro@fb.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-10-07 00:58:38 +00:00
|
|
|
return 0;
|
mm, memcg: proportional memory.{low,min} reclaim
cgroup v2 introduces two memory protection thresholds: memory.low
(best-effort) and memory.min (hard protection). While they generally do
what they say on the tin, there is a limitation in their implementation
that makes them difficult to use effectively: that cliff behaviour often
manifests when they become eligible for reclaim. This patch implements
more intuitive and usable behaviour, where we gradually mount more
reclaim pressure as cgroups further and further exceed their protection
thresholds.
This cliff edge behaviour happens because we only choose whether or not
to reclaim based on whether the memcg is within its protection limits
(see the use of mem_cgroup_protected in shrink_node), but we don't vary
our reclaim behaviour based on this information. Imagine the following
timeline, with the numbers the lruvec size in this zone:
1. memory.low=1000000, memory.current=999999. 0 pages may be scanned.
2. memory.low=1000000, memory.current=1000000. 0 pages may be scanned.
3. memory.low=1000000, memory.current=1000001. 1000001* pages may be
scanned. (?!)
* Of course, we won't usually scan all available pages in the zone even
without this patch because of scan control priority, over-reclaim
protection, etc. However, as shown by the tests at the end, these
techniques don't sufficiently throttle such an extreme change in input,
so cliff-like behaviour isn't really averted by their existence alone.
Here's an example of how this plays out in practice. At Facebook, we are
trying to protect various workloads from "system" software, like
configuration management tools, metric collectors, etc (see this[0] case
study). In order to find a suitable memory.low value, we start by
determining the expected memory range within which the workload will be
comfortable operating. This isn't an exact science -- memory usage deemed
"comfortable" will vary over time due to user behaviour, differences in
composition of work, etc, etc. As such we need to ballpark memory.low,
but doing this is currently problematic:
1. If we end up setting it too low for the workload, it won't have
*any* effect (see discussion above). The group will receive the full
weight of reclaim and won't have any priority while competing with the
less important system software, as if we had no memory.low configured
at all.
2. Because of this behaviour, we end up erring on the side of setting
it too high, such that the comfort range is reliably covered. However,
protected memory is completely unavailable to the rest of the system,
so we might cause undue memory and IO pressure there when we *know* we
have some elasticity in the workload.
3. Even if we get the value totally right, smack in the middle of the
comfort zone, we get extreme jumps between no pressure and full
pressure that cause unpredictable pressure spikes in the workload due
to the current binary reclaim behaviour.
With this patch, we can set it to our ballpark estimation without too much
worry. Any undesirable behaviour, such as too much or too little reclaim
pressure on the workload or system will be proportional to how far our
estimation is off. This means we can set memory.low much more
conservatively and thus waste less resources *without* the risk of the
workload falling off a cliff if we overshoot.
As a more abstract technical description, this unintuitive behaviour
results in having to give high-priority workloads a large protection
buffer on top of their expected usage to function reliably, as otherwise
we have abrupt periods of dramatically increased memory pressure which
hamper performance. Having to set these thresholds so high wastes
resources and generally works against the principle of work conservation.
In addition, having proportional memory reclaim behaviour has other
benefits. Most notably, before this patch it's basically mandatory to set
memory.low to a higher than desirable value because otherwise as soon as
you exceed memory.low, all protection is lost, and all pages are eligible
to scan again. By contrast, having a gradual ramp in reclaim pressure
means that you now still get some protection when thresholds are exceeded,
which means that one can now be more comfortable setting memory.low to
lower values without worrying that all protection will be lost. This is
important because workingset size is really hard to know exactly,
especially with variable workloads, so at least getting *some* protection
if your workingset size grows larger than you expect increases user
confidence in setting memory.low without a huge buffer on top being
needed.
Thanks a lot to Johannes Weiner and Tejun Heo for their advice and
assistance in thinking about how to make this work better.
In testing these changes, I intended to verify that:
1. Changes in page scanning become gradual and proportional instead of
binary.
To test this, I experimented stepping further and further down
memory.low protection on a workload that floats around 19G workingset
when under memory.low protection, watching page scan rates for the
workload cgroup:
+------------+-----------------+--------------------+--------------+
| memory.low | test (pgscan/s) | control (pgscan/s) | % of control |
+------------+-----------------+--------------------+--------------+
| 21G | 0 | 0 | N/A |
| 17G | 867 | 3799 | 23% |
| 12G | 1203 | 3543 | 34% |
| 8G | 2534 | 3979 | 64% |
| 4G | 3980 | 4147 | 96% |
| 0 | 3799 | 3980 | 95% |
+------------+-----------------+--------------------+--------------+
As you can see, the test kernel (with a kernel containing this
patch) ramps up page scanning significantly more gradually than the
control kernel (without this patch).
2. More gradual ramp up in reclaim aggression doesn't result in
premature OOMs.
To test this, I wrote a script that slowly increments the number of
pages held by stress(1)'s --vm-keep mode until a production system
entered severe overall memory contention. This script runs in a highly
protected slice taking up the majority of available system memory.
Watching vmstat revealed that page scanning continued essentially
nominally between test and control, without causing forward reclaim
progress to become arrested.
[0]: https://facebookmicrosites.github.io/cgroup2/docs/overview.html#case-study-the-fbtax2-project
[akpm@linux-foundation.org: reflow block comments to fit in 80 cols]
[chris@chrisdown.name: handle cgroup_disable=memory when getting memcg protection]
Link: http://lkml.kernel.org/r/20190201045711.GA18302@chrisdown.name
Link: http://lkml.kernel.org/r/20190124014455.GA6396@chrisdown.name
Signed-off-by: Chris Down <chris@chrisdown.name>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Roman Gushchin <guro@fb.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-10-07 00:58:32 +00:00
|
|
|
}
|
|
|
|
|
2020-08-07 06:22:05 +00:00
|
|
|
static inline void mem_cgroup_calculate_protection(struct mem_cgroup *root,
|
|
|
|
struct mem_cgroup *memcg)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline bool mem_cgroup_below_low(struct mem_cgroup *memcg)
|
|
|
|
{
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg)
|
mm: memcontrol: default hierarchy interface for memory
Introduce the basic control files to account, partition, and limit
memory using cgroups in default hierarchy mode.
This interface versioning allows us to address fundamental design
issues in the existing memory cgroup interface, further explained
below. The old interface will be maintained indefinitely, but a
clearer model and improved workload performance should encourage
existing users to switch over to the new one eventually.
The control files are thus:
- memory.current shows the current consumption of the cgroup and its
descendants, in bytes.
- memory.low configures the lower end of the cgroup's expected
memory consumption range. The kernel considers memory below that
boundary to be a reserve - the minimum that the workload needs in
order to make forward progress - and generally avoids reclaiming
it, unless there is an imminent risk of entering an OOM situation.
- memory.high configures the upper end of the cgroup's expected
memory consumption range. A cgroup whose consumption grows beyond
this threshold is forced into direct reclaim, to work off the
excess and to throttle new allocations heavily, but is generally
allowed to continue and the OOM killer is not invoked.
- memory.max configures the hard maximum amount of memory that the
cgroup is allowed to consume before the OOM killer is invoked.
- memory.events shows event counters that indicate how often the
cgroup was reclaimed while below memory.low, how often it was
forced to reclaim excess beyond memory.high, how often it hit
memory.max, and how often it entered OOM due to memory.max. This
allows users to identify configuration problems when observing a
degradation in workload performance. An overcommitted system will
have an increased rate of low boundary breaches, whereas increased
rates of high limit breaches, maximum hits, or even OOM situations
will indicate internally overcommitted cgroups.
For existing users of memory cgroups, the following deviations from
the current interface are worth pointing out and explaining:
- The original lower boundary, the soft limit, is defined as a limit
that is per default unset. As a result, the set of cgroups that
global reclaim prefers is opt-in, rather than opt-out. The costs
for optimizing these mostly negative lookups are so high that the
implementation, despite its enormous size, does not even provide
the basic desirable behavior. First off, the soft limit has no
hierarchical meaning. All configured groups are organized in a
global rbtree and treated like equal peers, regardless where they
are located in the hierarchy. This makes subtree delegation
impossible. Second, the soft limit reclaim pass is so aggressive
that it not just introduces high allocation latencies into the
system, but also impacts system performance due to overreclaim, to
the point where the feature becomes self-defeating.
The memory.low boundary on the other hand is a top-down allocated
reserve. A cgroup enjoys reclaim protection when it and all its
ancestors are below their low boundaries, which makes delegation
of subtrees possible. Secondly, new cgroups have no reserve per
default and in the common case most cgroups are eligible for the
preferred reclaim pass. This allows the new low boundary to be
efficiently implemented with just a minor addition to the generic
reclaim code, without the need for out-of-band data structures and
reclaim passes. Because the generic reclaim code considers all
cgroups except for the ones running low in the preferred first
reclaim pass, overreclaim of individual groups is eliminated as
well, resulting in much better overall workload performance.
- The original high boundary, the hard limit, is defined as a strict
limit that can not budge, even if the OOM killer has to be called.
But this generally goes against the goal of making the most out of
the available memory. The memory consumption of workloads varies
during runtime, and that requires users to overcommit. But doing
that with a strict upper limit requires either a fairly accurate
prediction of the working set size or adding slack to the limit.
Since working set size estimation is hard and error prone, and
getting it wrong results in OOM kills, most users tend to err on
the side of a looser limit and end up wasting precious resources.
The memory.high boundary on the other hand can be set much more
conservatively. When hit, it throttles allocations by forcing
them into direct reclaim to work off the excess, but it never
invokes the OOM killer. As a result, a high boundary that is
chosen too aggressively will not terminate the processes, but
instead it will lead to gradual performance degradation. The user
can monitor this and make corrections until the minimal memory
footprint that still gives acceptable performance is found.
In extreme cases, with many concurrent allocations and a complete
breakdown of reclaim progress within the group, the high boundary
can be exceeded. But even then it's mostly better to satisfy the
allocation from the slack available in other groups or the rest of
the system than killing the group. Otherwise, memory.max is there
to limit this type of spillover and ultimately contain buggy or
even malicious applications.
- The original control file names are unwieldy and inconsistent in
many different ways. For example, the upper boundary hit count is
exported in the memory.failcnt file, but an OOM event count has to
be manually counted by listening to memory.oom_control events, and
lower boundary / soft limit events have to be counted by first
setting a threshold for that value and then counting those events.
Also, usage and limit files encode their units in the filename.
That makes the filenames very long, even though this is not
information that a user needs to be reminded of every time they
type out those names.
To address these naming issues, as well as to signal clearly that
the new interface carries a new configuration model, the naming
conventions in it necessarily differ from the old interface.
- The original limit files indicate the state of an unset limit with
a very high number, and a configured limit can be unset by echoing
-1 into those files. But that very high number is implementation
and architecture dependent and not very descriptive. And while -1
can be understood as an underflow into the highest possible value,
-2 or -10M etc. do not work, so it's not inconsistent.
memory.low, memory.high, and memory.max will use the string
"infinity" to indicate and set the highest possible value.
[akpm@linux-foundation.org: use seq_puts() for basic strings]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Cc: Greg Thelen <gthelen@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-11 23:26:06 +00:00
|
|
|
{
|
2020-08-07 06:22:05 +00:00
|
|
|
return false;
|
mm: memcontrol: default hierarchy interface for memory
Introduce the basic control files to account, partition, and limit
memory using cgroups in default hierarchy mode.
This interface versioning allows us to address fundamental design
issues in the existing memory cgroup interface, further explained
below. The old interface will be maintained indefinitely, but a
clearer model and improved workload performance should encourage
existing users to switch over to the new one eventually.
The control files are thus:
- memory.current shows the current consumption of the cgroup and its
descendants, in bytes.
- memory.low configures the lower end of the cgroup's expected
memory consumption range. The kernel considers memory below that
boundary to be a reserve - the minimum that the workload needs in
order to make forward progress - and generally avoids reclaiming
it, unless there is an imminent risk of entering an OOM situation.
- memory.high configures the upper end of the cgroup's expected
memory consumption range. A cgroup whose consumption grows beyond
this threshold is forced into direct reclaim, to work off the
excess and to throttle new allocations heavily, but is generally
allowed to continue and the OOM killer is not invoked.
- memory.max configures the hard maximum amount of memory that the
cgroup is allowed to consume before the OOM killer is invoked.
- memory.events shows event counters that indicate how often the
cgroup was reclaimed while below memory.low, how often it was
forced to reclaim excess beyond memory.high, how often it hit
memory.max, and how often it entered OOM due to memory.max. This
allows users to identify configuration problems when observing a
degradation in workload performance. An overcommitted system will
have an increased rate of low boundary breaches, whereas increased
rates of high limit breaches, maximum hits, or even OOM situations
will indicate internally overcommitted cgroups.
For existing users of memory cgroups, the following deviations from
the current interface are worth pointing out and explaining:
- The original lower boundary, the soft limit, is defined as a limit
that is per default unset. As a result, the set of cgroups that
global reclaim prefers is opt-in, rather than opt-out. The costs
for optimizing these mostly negative lookups are so high that the
implementation, despite its enormous size, does not even provide
the basic desirable behavior. First off, the soft limit has no
hierarchical meaning. All configured groups are organized in a
global rbtree and treated like equal peers, regardless where they
are located in the hierarchy. This makes subtree delegation
impossible. Second, the soft limit reclaim pass is so aggressive
that it not just introduces high allocation latencies into the
system, but also impacts system performance due to overreclaim, to
the point where the feature becomes self-defeating.
The memory.low boundary on the other hand is a top-down allocated
reserve. A cgroup enjoys reclaim protection when it and all its
ancestors are below their low boundaries, which makes delegation
of subtrees possible. Secondly, new cgroups have no reserve per
default and in the common case most cgroups are eligible for the
preferred reclaim pass. This allows the new low boundary to be
efficiently implemented with just a minor addition to the generic
reclaim code, without the need for out-of-band data structures and
reclaim passes. Because the generic reclaim code considers all
cgroups except for the ones running low in the preferred first
reclaim pass, overreclaim of individual groups is eliminated as
well, resulting in much better overall workload performance.
- The original high boundary, the hard limit, is defined as a strict
limit that can not budge, even if the OOM killer has to be called.
But this generally goes against the goal of making the most out of
the available memory. The memory consumption of workloads varies
during runtime, and that requires users to overcommit. But doing
that with a strict upper limit requires either a fairly accurate
prediction of the working set size or adding slack to the limit.
Since working set size estimation is hard and error prone, and
getting it wrong results in OOM kills, most users tend to err on
the side of a looser limit and end up wasting precious resources.
The memory.high boundary on the other hand can be set much more
conservatively. When hit, it throttles allocations by forcing
them into direct reclaim to work off the excess, but it never
invokes the OOM killer. As a result, a high boundary that is
chosen too aggressively will not terminate the processes, but
instead it will lead to gradual performance degradation. The user
can monitor this and make corrections until the minimal memory
footprint that still gives acceptable performance is found.
In extreme cases, with many concurrent allocations and a complete
breakdown of reclaim progress within the group, the high boundary
can be exceeded. But even then it's mostly better to satisfy the
allocation from the slack available in other groups or the rest of
the system than killing the group. Otherwise, memory.max is there
to limit this type of spillover and ultimately contain buggy or
even malicious applications.
- The original control file names are unwieldy and inconsistent in
many different ways. For example, the upper boundary hit count is
exported in the memory.failcnt file, but an OOM event count has to
be manually counted by listening to memory.oom_control events, and
lower boundary / soft limit events have to be counted by first
setting a threshold for that value and then counting those events.
Also, usage and limit files encode their units in the filename.
That makes the filenames very long, even though this is not
information that a user needs to be reminded of every time they
type out those names.
To address these naming issues, as well as to signal clearly that
the new interface carries a new configuration model, the naming
conventions in it necessarily differ from the old interface.
- The original limit files indicate the state of an unset limit with
a very high number, and a configured limit can be unset by echoing
-1 into those files. But that very high number is implementation
and architecture dependent and not very descriptive. And while -1
can be understood as an underflow into the highest possible value,
-2 or -10M etc. do not work, so it's not inconsistent.
memory.low, memory.high, and memory.max will use the string
"infinity" to indicate and set the highest possible value.
[akpm@linux-foundation.org: use seq_puts() for basic strings]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Cc: Greg Thelen <gthelen@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-11 23:26:06 +00:00
|
|
|
}
|
|
|
|
|
mm: memcontrol: convert page cache to a new mem_cgroup_charge() API
The try/commit/cancel protocol that memcg uses dates back to when pages
used to be uncharged upon removal from the page cache, and thus couldn't
be committed before the insertion had succeeded. Nowadays, pages are
uncharged when they are physically freed; it doesn't matter whether the
insertion was successful or not. For the page cache, the transaction
dance has become unnecessary.
Introduce a mem_cgroup_charge() function that simply charges a newly
allocated page to a cgroup and sets up page->mem_cgroup in one single
step. If the insertion fails, the caller doesn't have to do anything but
free/put the page.
Then switch the page cache over to this new API.
Subsequent patches will also convert anon pages, but it needs a bit more
prep work. Right now, memcg depends on page->mapping being already set up
at the time of charging, so that it can maintain its own MEMCG_CACHE and
MEMCG_RSS counters. For anon, page->mapping is set under the same pte
lock under which the page is publishd, so a single charge point that can
block doesn't work there just yet.
The following prep patches will replace the private memcg counters with
the generic vmstat counters, thus removing the page->mapping dependency,
then complete the transition to the new single-point charge API and delete
the old transactional scheme.
v2: leave shmem swapcache when charging fails to avoid double IO (Joonsoo)
v3: rebase on preceeding shmem simplification patch
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Alex Shi <alex.shi@linux.alibaba.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Link: http://lkml.kernel.org/r/20200508183105.225460-6-hannes@cmpxchg.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-03 23:01:41 +00:00
|
|
|
static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm,
|
2020-06-03 23:02:24 +00:00
|
|
|
gfp_t gfp_mask)
|
mm: memcontrol: convert page cache to a new mem_cgroup_charge() API
The try/commit/cancel protocol that memcg uses dates back to when pages
used to be uncharged upon removal from the page cache, and thus couldn't
be committed before the insertion had succeeded. Nowadays, pages are
uncharged when they are physically freed; it doesn't matter whether the
insertion was successful or not. For the page cache, the transaction
dance has become unnecessary.
Introduce a mem_cgroup_charge() function that simply charges a newly
allocated page to a cgroup and sets up page->mem_cgroup in one single
step. If the insertion fails, the caller doesn't have to do anything but
free/put the page.
Then switch the page cache over to this new API.
Subsequent patches will also convert anon pages, but it needs a bit more
prep work. Right now, memcg depends on page->mapping being already set up
at the time of charging, so that it can maintain its own MEMCG_CACHE and
MEMCG_RSS counters. For anon, page->mapping is set under the same pte
lock under which the page is publishd, so a single charge point that can
block doesn't work there just yet.
The following prep patches will replace the private memcg counters with
the generic vmstat counters, thus removing the page->mapping dependency,
then complete the transition to the new single-point charge API and delete
the old transactional scheme.
v2: leave shmem swapcache when charging fails to avoid double IO (Joonsoo)
v3: rebase on preceeding shmem simplification patch
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Alex Shi <alex.shi@linux.alibaba.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Link: http://lkml.kernel.org/r/20200508183105.225460-6-hannes@cmpxchg.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-03 23:01:41 +00:00
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
mm: memcontrol: rewrite uncharge API
The memcg uncharging code that is involved towards the end of a page's
lifetime - truncation, reclaim, swapout, migration - is impressively
complicated and fragile.
Because anonymous and file pages were always charged before they had their
page->mapping established, uncharges had to happen when the page type
could still be known from the context; as in unmap for anonymous, page
cache removal for file and shmem pages, and swap cache truncation for swap
pages. However, these operations happen well before the page is actually
freed, and so a lot of synchronization is necessary:
- Charging, uncharging, page migration, and charge migration all need
to take a per-page bit spinlock as they could race with uncharging.
- Swap cache truncation happens during both swap-in and swap-out, and
possibly repeatedly before the page is actually freed. This means
that the memcg swapout code is called from many contexts that make
no sense and it has to figure out the direction from page state to
make sure memory and memory+swap are always correctly charged.
- On page migration, the old page might be unmapped but then reused,
so memcg code has to prevent untimely uncharging in that case.
Because this code - which should be a simple charge transfer - is so
special-cased, it is not reusable for replace_page_cache().
But now that charged pages always have a page->mapping, introduce
mem_cgroup_uncharge(), which is called after the final put_page(), when we
know for sure that nobody is looking at the page anymore.
For page migration, introduce mem_cgroup_migrate(), which is called after
the migration is successful and the new page is fully rmapped. Because
the old page is no longer uncharged after migration, prevent double
charges by decoupling the page's memcg association (PCG_USED and
pc->mem_cgroup) from the page holding an actual charge. The new bits
PCG_MEM and PCG_MEMSW represent the respective charges and are transferred
to the new page during migration.
mem_cgroup_migrate() is suitable for replace_page_cache() as well,
which gets rid of mem_cgroup_replace_page_cache(). However, care
needs to be taken because both the source and the target page can
already be charged and on the LRU when fuse is splicing: grab the page
lock on the charge moving side to prevent changing pc->mem_cgroup of a
page under migration. Also, the lruvecs of both pages change as we
uncharge the old and charge the new during migration, and putback may
race with us, so grab the lru lock and isolate the pages iff on LRU to
prevent races and ensure the pages are on the right lruvec afterward.
Swap accounting is massively simplified: because the page is no longer
uncharged as early as swap cache deletion, a new mem_cgroup_swapout() can
transfer the page's memory+swap charge (PCG_MEMSW) to the swap entry
before the final put_page() in page reclaim.
Finally, page_cgroup changes are now protected by whatever protection the
page itself offers: anonymous pages are charged under the page table lock,
whereas page cache insertions, swapin, and migration hold the page lock.
Uncharging happens under full exclusion with no outstanding references.
Charging and uncharging also ensure that the page is off-LRU, which
serializes against charge migration. Remove the very costly page_cgroup
lock and set pc->flags non-atomically.
[mhocko@suse.cz: mem_cgroup_charge_statistics needs preempt_disable]
[vdavydov@parallels.com: fix flags definition]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Tested-by: Jet Chen <jet.chen@intel.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Tested-by: Felipe Balbi <balbi@ti.com>
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-08 21:19:22 +00:00
|
|
|
static inline void mem_cgroup_uncharge(struct page *page)
|
2009-12-16 00:47:03 +00:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2014-08-08 21:19:24 +00:00
|
|
|
static inline void mem_cgroup_uncharge_list(struct list_head *page_list)
|
2008-02-07 08:13:53 +00:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2016-03-15 21:57:19 +00:00
|
|
|
static inline void mem_cgroup_migrate(struct page *old, struct page *new)
|
memcg: remove refcnt from page_cgroup
memcg: performance improvements
Patch Description
1/5 ... remove refcnt fron page_cgroup patch (shmem handling is fixed)
2/5 ... swapcache handling patch
3/5 ... add helper function for shmem's memory reclaim patch
4/5 ... optimize by likely/unlikely ppatch
5/5 ... remove redundunt check patch (shmem handling is fixed.)
Unix bench result.
== 2.6.26-rc2-mm1 + memory resource controller
Execl Throughput 2915.4 lps (29.6 secs, 3 samples)
C Compiler Throughput 1019.3 lpm (60.0 secs, 3 samples)
Shell Scripts (1 concurrent) 5796.0 lpm (60.0 secs, 3 samples)
Shell Scripts (8 concurrent) 1097.7 lpm (60.0 secs, 3 samples)
Shell Scripts (16 concurrent) 565.3 lpm (60.0 secs, 3 samples)
File Read 1024 bufsize 2000 maxblocks 1022128.0 KBps (30.0 secs, 3 samples)
File Write 1024 bufsize 2000 maxblocks 544057.0 KBps (30.0 secs, 3 samples)
File Copy 1024 bufsize 2000 maxblocks 346481.0 KBps (30.0 secs, 3 samples)
File Read 256 bufsize 500 maxblocks 319325.0 KBps (30.0 secs, 3 samples)
File Write 256 bufsize 500 maxblocks 148788.0 KBps (30.0 secs, 3 samples)
File Copy 256 bufsize 500 maxblocks 99051.0 KBps (30.0 secs, 3 samples)
File Read 4096 bufsize 8000 maxblocks 2058917.0 KBps (30.0 secs, 3 samples)
File Write 4096 bufsize 8000 maxblocks 1606109.0 KBps (30.0 secs, 3 samples)
File Copy 4096 bufsize 8000 maxblocks 854789.0 KBps (30.0 secs, 3 samples)
Dc: sqrt(2) to 99 decimal places 126145.2 lpm (30.0 secs, 3 samples)
INDEX VALUES
TEST BASELINE RESULT INDEX
Execl Throughput 43.0 2915.4 678.0
File Copy 1024 bufsize 2000 maxblocks 3960.0 346481.0 875.0
File Copy 256 bufsize 500 maxblocks 1655.0 99051.0 598.5
File Copy 4096 bufsize 8000 maxblocks 5800.0 854789.0 1473.8
Shell Scripts (8 concurrent) 6.0 1097.7 1829.5
=========
FINAL SCORE 991.3
== 2.6.26-rc2-mm1 + this set ==
Execl Throughput 3012.9 lps (29.9 secs, 3 samples)
C Compiler Throughput 981.0 lpm (60.0 secs, 3 samples)
Shell Scripts (1 concurrent) 5872.0 lpm (60.0 secs, 3 samples)
Shell Scripts (8 concurrent) 1120.3 lpm (60.0 secs, 3 samples)
Shell Scripts (16 concurrent) 578.0 lpm (60.0 secs, 3 samples)
File Read 1024 bufsize 2000 maxblocks 1003993.0 KBps (30.0 secs, 3 samples)
File Write 1024 bufsize 2000 maxblocks 550452.0 KBps (30.0 secs, 3 samples)
File Copy 1024 bufsize 2000 maxblocks 347159.0 KBps (30.0 secs, 3 samples)
File Read 256 bufsize 500 maxblocks 314644.0 KBps (30.0 secs, 3 samples)
File Write 256 bufsize 500 maxblocks 151852.0 KBps (30.0 secs, 3 samples)
File Copy 256 bufsize 500 maxblocks 101000.0 KBps (30.0 secs, 3 samples)
File Read 4096 bufsize 8000 maxblocks 2033256.0 KBps (30.0 secs, 3 samples)
File Write 4096 bufsize 8000 maxblocks 1611814.0 KBps (30.0 secs, 3 samples)
File Copy 4096 bufsize 8000 maxblocks 847979.0 KBps (30.0 secs, 3 samples)
Dc: sqrt(2) to 99 decimal places 128148.7 lpm (30.0 secs, 3 samples)
INDEX VALUES
TEST BASELINE RESULT INDEX
Execl Throughput 43.0 3012.9 700.7
File Copy 1024 bufsize 2000 maxblocks 3960.0 347159.0 876.7
File Copy 256 bufsize 500 maxblocks 1655.0 101000.0 610.3
File Copy 4096 bufsize 8000 maxblocks 5800.0 847979.0 1462.0
Shell Scripts (8 concurrent) 6.0 1120.3 1867.2
=========
FINAL SCORE 1004.6
This patch:
Remove refcnt from page_cgroup().
After this,
* A page is charged only when !page_mapped() && no page_cgroup is assigned.
* Anon page is newly mapped.
* File page is added to mapping->tree.
* A page is uncharged only when
* Anon page is fully unmapped.
* File page is removed from LRU.
There is no change in behavior from user's view.
This patch also removes unnecessary calls in rmap.c which was used only for
refcnt mangement.
[akpm@linux-foundation.org: fix warning]
[hugh@veritas.com: fix shmem_unuse_inode charging]
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Pavel Emelyanov <xemul@openvz.org>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp>
Cc: Paul Menage <menage@google.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-25 08:47:14 +00:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2019-12-01 01:55:34 +00:00
|
|
|
static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg,
|
|
|
|
struct pglist_data *pgdat)
|
memcg: synchronized LRU
A big patch for changing memcg's LRU semantics.
Now,
- page_cgroup is linked to mem_cgroup's its own LRU (per zone).
- LRU of page_cgroup is not synchronous with global LRU.
- page and page_cgroup is one-to-one and statically allocated.
- To find page_cgroup is on what LRU, you have to check pc->mem_cgroup as
- lru = page_cgroup_zoneinfo(pc, nid_of_pc, zid_of_pc);
- SwapCache is handled.
And, when we handle LRU list of page_cgroup, we do following.
pc = lookup_page_cgroup(page);
lock_page_cgroup(pc); .....................(1)
mz = page_cgroup_zoneinfo(pc);
spin_lock(&mz->lru_lock);
.....add to LRU
spin_unlock(&mz->lru_lock);
unlock_page_cgroup(pc);
But (1) is spin_lock and we have to be afraid of dead-lock with zone->lru_lock.
So, trylock() is used at (1), now. Without (1), we can't trust "mz" is correct.
This is a trial to remove this dirty nesting of locks.
This patch changes mz->lru_lock to be zone->lru_lock.
Then, above sequence will be written as
spin_lock(&zone->lru_lock); # in vmscan.c or swap.c via global LRU
mem_cgroup_add/remove/etc_lru() {
pc = lookup_page_cgroup(page);
mz = page_cgroup_zoneinfo(pc);
if (PageCgroupUsed(pc)) {
....add to LRU
}
spin_lock(&zone->lru_lock); # in vmscan.c or swap.c via global LRU
This is much simpler.
(*) We're safe even if we don't take lock_page_cgroup(pc). Because..
1. When pc->mem_cgroup can be modified.
- at charge.
- at account_move().
2. at charge
the PCG_USED bit is not set before pc->mem_cgroup is fixed.
3. at account_move()
the page is isolated and not on LRU.
Pros.
- easy for maintenance.
- memcg can make use of laziness of pagevec.
- we don't have to duplicated LRU/Active/Unevictable bit in page_cgroup.
- LRU status of memcg will be synchronized with global LRU's one.
- # of locks are reduced.
- account_move() is simplified very much.
Cons.
- may increase cost of LRU rotation.
(no impact if memcg is not configured.)
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 02:08:01 +00:00
|
|
|
{
|
2019-12-01 01:55:34 +00:00
|
|
|
return &pgdat->__lruvec;
|
memcg: synchronized LRU
A big patch for changing memcg's LRU semantics.
Now,
- page_cgroup is linked to mem_cgroup's its own LRU (per zone).
- LRU of page_cgroup is not synchronous with global LRU.
- page and page_cgroup is one-to-one and statically allocated.
- To find page_cgroup is on what LRU, you have to check pc->mem_cgroup as
- lru = page_cgroup_zoneinfo(pc, nid_of_pc, zid_of_pc);
- SwapCache is handled.
And, when we handle LRU list of page_cgroup, we do following.
pc = lookup_page_cgroup(page);
lock_page_cgroup(pc); .....................(1)
mz = page_cgroup_zoneinfo(pc);
spin_lock(&mz->lru_lock);
.....add to LRU
spin_unlock(&mz->lru_lock);
unlock_page_cgroup(pc);
But (1) is spin_lock and we have to be afraid of dead-lock with zone->lru_lock.
So, trylock() is used at (1), now. Without (1), we can't trust "mz" is correct.
This is a trial to remove this dirty nesting of locks.
This patch changes mz->lru_lock to be zone->lru_lock.
Then, above sequence will be written as
spin_lock(&zone->lru_lock); # in vmscan.c or swap.c via global LRU
mem_cgroup_add/remove/etc_lru() {
pc = lookup_page_cgroup(page);
mz = page_cgroup_zoneinfo(pc);
if (PageCgroupUsed(pc)) {
....add to LRU
}
spin_lock(&zone->lru_lock); # in vmscan.c or swap.c via global LRU
This is much simpler.
(*) We're safe even if we don't take lock_page_cgroup(pc). Because..
1. When pc->mem_cgroup can be modified.
- at charge.
- at account_move().
2. at charge
the PCG_USED bit is not set before pc->mem_cgroup is fixed.
3. at account_move()
the page is isolated and not on LRU.
Pros.
- easy for maintenance.
- memcg can make use of laziness of pagevec.
- we don't have to duplicated LRU/Active/Unevictable bit in page_cgroup.
- LRU status of memcg will be synchronized with global LRU's one.
- # of locks are reduced.
- account_move() is simplified very much.
Cons.
- may increase cost of LRU rotation.
(no impact if memcg is not configured.)
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 02:08:01 +00:00
|
|
|
}
|
|
|
|
|
2012-05-29 22:07:09 +00:00
|
|
|
static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page,
|
2016-07-28 22:45:31 +00:00
|
|
|
struct pglist_data *pgdat)
|
2008-02-07 08:13:56 +00:00
|
|
|
{
|
2019-12-01 01:55:34 +00:00
|
|
|
return &pgdat->__lruvec;
|
2008-02-07 08:13:56 +00:00
|
|
|
}
|
|
|
|
|
2020-12-15 20:34:33 +00:00
|
|
|
static inline bool lruvec_holds_page_lru_lock(struct page *page,
|
|
|
|
struct lruvec *lruvec)
|
|
|
|
{
|
|
|
|
pg_data_t *pgdat = page_pgdat(page);
|
|
|
|
|
|
|
|
return lruvec == &pgdat->__lruvec;
|
|
|
|
}
|
|
|
|
|
mm: vmscan: detect file thrashing at the reclaim root
We use refault information to determine whether the cache workingset is
stable or transitioning, and dynamically adjust the inactive:active file
LRU ratio so as to maximize protection from one-off cache during stable
periods, and minimize IO during transitions.
With cgroups and their nested LRU lists, we currently don't do this
correctly. While recursive cgroup reclaim establishes a relative LRU
order among the pages of all involved cgroups, refaults only affect the
local LRU order in the cgroup in which they are occuring. As a result,
cache transitions can take longer in a cgrouped system as the active pages
of sibling cgroups aren't challenged when they should be.
[ Right now, this is somewhat theoretical, because the siblings, under
continued regular reclaim pressure, should eventually run out of
inactive pages - and since inactive:active *size* balancing is also
done on a cgroup-local level, we will challenge the active pages
eventually in most cases. But the next patch will move that relative
size enforcement to the reclaim root as well, and then this patch
here will be necessary to propagate refault pressure to siblings. ]
This patch moves refault detection to the root of reclaim. Instead of
remembering the cgroup owner of an evicted page, remember the cgroup that
caused the reclaim to happen. When refaults later occur, they'll
correctly influence the cross-cgroup LRU order that reclaim follows.
I.e. if global reclaim kicked out pages in some subgroup A/B/C, the
refault of those pages will challenge the global LRU order, and not just
the local order down inside C.
[hannes@cmpxchg.org: use page_memcg() instead of another lookup]
Link: http://lkml.kernel.org/r/20191115160722.GA309754@cmpxchg.org
Link: http://lkml.kernel.org/r/20191107205334.158354-3-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Shakeel Butt <shakeelb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 01:55:59 +00:00
|
|
|
static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
|
|
|
|
{
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2012-10-08 23:34:12 +00:00
|
|
|
static inline bool mm_match_cgroup(struct mm_struct *mm,
|
2011-11-02 20:38:15 +00:00
|
|
|
struct mem_cgroup *memcg)
|
2008-02-07 08:14:01 +00:00
|
|
|
{
|
2012-10-08 23:34:12 +00:00
|
|
|
return true;
|
2008-02-07 08:14:01 +00:00
|
|
|
}
|
|
|
|
|
fs: fsnotify: account fsnotify metadata to kmemcg
Patch series "Directed kmem charging", v8.
The Linux kernel's memory cgroup allows limiting the memory usage of the
jobs running on the system to provide isolation between the jobs. All
the kernel memory allocated in the context of the job and marked with
__GFP_ACCOUNT will also be included in the memory usage and be limited
by the job's limit.
The kernel memory can only be charged to the memcg of the process in
whose context kernel memory was allocated. However there are cases
where the allocated kernel memory should be charged to the memcg
different from the current processes's memcg. This patch series
contains two such concrete use-cases i.e. fsnotify and buffer_head.
The fsnotify event objects can consume a lot of system memory for large
or unlimited queues if there is either no or slow listener. The events
are allocated in the context of the event producer. However they should
be charged to the event consumer. Similarly the buffer_head objects can
be allocated in a memcg different from the memcg of the page for which
buffer_head objects are being allocated.
To solve this issue, this patch series introduces mechanism to charge
kernel memory to a given memcg. In case of fsnotify events, the memcg
of the consumer can be used for charging and for buffer_head, the memcg
of the page can be charged. For directed charging, the caller can use
the scope API memalloc_[un]use_memcg() to specify the memcg to charge
for all the __GFP_ACCOUNT allocations within the scope.
This patch (of 2):
A lot of memory can be consumed by the events generated for the huge or
unlimited queues if there is either no or slow listener. This can cause
system level memory pressure or OOMs. So, it's better to account the
fsnotify kmem caches to the memcg of the listener.
However the listener can be in a different memcg than the memcg of the
producer and these allocations happen in the context of the event
producer. This patch introduces remote memcg charging API which the
producer can use to charge the allocations to the memcg of the listener.
There are seven fsnotify kmem caches and among them allocations from
dnotify_struct_cache, dnotify_mark_cache, fanotify_mark_cache and
inotify_inode_mark_cachep happens in the context of syscall from the
listener. So, SLAB_ACCOUNT is enough for these caches.
The objects from fsnotify_mark_connector_cachep are not accounted as
they are small compared to the notification mark or events and it is
unclear whom to account connector to since it is shared by all events
attached to the inode.
The allocations from the event caches happen in the context of the event
producer. For such caches we will need to remote charge the allocations
to the listener's memcg. Thus we save the memcg reference in the
fsnotify_group structure of the listener.
This patch has also moved the members of fsnotify_group to keep the size
same, at least for 64 bit build, even with additional member by filling
the holes.
[shakeelb@google.com: use GFP_KERNEL_ACCOUNT rather than open-coding it]
Link: http://lkml.kernel.org/r/20180702215439.211597-1-shakeelb@google.com
Link: http://lkml.kernel.org/r/20180627191250.209150-2-shakeelb@google.com
Signed-off-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Amir Goldstein <amir73il@gmail.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-17 22:46:39 +00:00
|
|
|
static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
|
|
|
|
{
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2018-08-17 22:46:36 +00:00
|
|
|
static inline void mem_cgroup_put(struct mem_cgroup *memcg)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2020-12-15 20:34:29 +00:00
|
|
|
static inline struct lruvec *lock_page_lruvec(struct page *page)
|
|
|
|
{
|
|
|
|
struct pglist_data *pgdat = page_pgdat(page);
|
|
|
|
|
|
|
|
spin_lock(&pgdat->__lruvec.lru_lock);
|
|
|
|
return &pgdat->__lruvec;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline struct lruvec *lock_page_lruvec_irq(struct page *page)
|
|
|
|
{
|
|
|
|
struct pglist_data *pgdat = page_pgdat(page);
|
|
|
|
|
|
|
|
spin_lock_irq(&pgdat->__lruvec.lru_lock);
|
|
|
|
return &pgdat->__lruvec;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline struct lruvec *lock_page_lruvec_irqsave(struct page *page,
|
|
|
|
unsigned long *flagsp)
|
|
|
|
{
|
|
|
|
struct pglist_data *pgdat = page_pgdat(page);
|
|
|
|
|
|
|
|
spin_lock_irqsave(&pgdat->__lruvec.lru_lock, *flagsp);
|
|
|
|
return &pgdat->__lruvec;
|
|
|
|
}
|
|
|
|
|
2012-01-13 01:17:59 +00:00
|
|
|
static inline struct mem_cgroup *
|
|
|
|
mem_cgroup_iter(struct mem_cgroup *root,
|
|
|
|
struct mem_cgroup *prev,
|
|
|
|
struct mem_cgroup_reclaim_cookie *reclaim)
|
|
|
|
{
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void mem_cgroup_iter_break(struct mem_cgroup *root,
|
|
|
|
struct mem_cgroup *prev)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2016-10-07 23:57:23 +00:00
|
|
|
static inline int mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
|
|
|
|
int (*fn)(struct task_struct *, void *), void *arg)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2016-03-15 21:57:16 +00:00
|
|
|
static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg)
|
2009-01-08 02:08:02 +00:00
|
|
|
{
|
2016-03-15 21:57:16 +00:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
|
|
|
|
{
|
|
|
|
WARN_ON_ONCE(id);
|
|
|
|
/* XXX: This should always return root_mem_cgroup */
|
|
|
|
return NULL;
|
2009-01-08 02:08:02 +00:00
|
|
|
}
|
2009-01-08 02:08:08 +00:00
|
|
|
|
2019-03-05 23:45:52 +00:00
|
|
|
static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m)
|
|
|
|
{
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2017-07-06 22:40:25 +00:00
|
|
|
static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec)
|
|
|
|
{
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2016-01-20 23:03:02 +00:00
|
|
|
static inline bool mem_cgroup_online(struct mem_cgroup *memcg)
|
2009-01-08 02:08:18 +00:00
|
|
|
{
|
2015-11-06 02:47:40 +00:00
|
|
|
return true;
|
2009-01-08 02:08:18 +00:00
|
|
|
}
|
|
|
|
|
2017-01-11 00:58:04 +00:00
|
|
|
static inline
|
|
|
|
unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec,
|
|
|
|
enum lru_list lru, int zone_idx)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
2009-01-08 02:08:19 +00:00
|
|
|
|
2018-06-08 00:06:18 +00:00
|
|
|
static inline unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg)
|
2016-10-07 23:57:23 +00:00
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
mm, memcg: proportional memory.{low,min} reclaim
cgroup v2 introduces two memory protection thresholds: memory.low
(best-effort) and memory.min (hard protection). While they generally do
what they say on the tin, there is a limitation in their implementation
that makes them difficult to use effectively: that cliff behaviour often
manifests when they become eligible for reclaim. This patch implements
more intuitive and usable behaviour, where we gradually mount more
reclaim pressure as cgroups further and further exceed their protection
thresholds.
This cliff edge behaviour happens because we only choose whether or not
to reclaim based on whether the memcg is within its protection limits
(see the use of mem_cgroup_protected in shrink_node), but we don't vary
our reclaim behaviour based on this information. Imagine the following
timeline, with the numbers the lruvec size in this zone:
1. memory.low=1000000, memory.current=999999. 0 pages may be scanned.
2. memory.low=1000000, memory.current=1000000. 0 pages may be scanned.
3. memory.low=1000000, memory.current=1000001. 1000001* pages may be
scanned. (?!)
* Of course, we won't usually scan all available pages in the zone even
without this patch because of scan control priority, over-reclaim
protection, etc. However, as shown by the tests at the end, these
techniques don't sufficiently throttle such an extreme change in input,
so cliff-like behaviour isn't really averted by their existence alone.
Here's an example of how this plays out in practice. At Facebook, we are
trying to protect various workloads from "system" software, like
configuration management tools, metric collectors, etc (see this[0] case
study). In order to find a suitable memory.low value, we start by
determining the expected memory range within which the workload will be
comfortable operating. This isn't an exact science -- memory usage deemed
"comfortable" will vary over time due to user behaviour, differences in
composition of work, etc, etc. As such we need to ballpark memory.low,
but doing this is currently problematic:
1. If we end up setting it too low for the workload, it won't have
*any* effect (see discussion above). The group will receive the full
weight of reclaim and won't have any priority while competing with the
less important system software, as if we had no memory.low configured
at all.
2. Because of this behaviour, we end up erring on the side of setting
it too high, such that the comfort range is reliably covered. However,
protected memory is completely unavailable to the rest of the system,
so we might cause undue memory and IO pressure there when we *know* we
have some elasticity in the workload.
3. Even if we get the value totally right, smack in the middle of the
comfort zone, we get extreme jumps between no pressure and full
pressure that cause unpredictable pressure spikes in the workload due
to the current binary reclaim behaviour.
With this patch, we can set it to our ballpark estimation without too much
worry. Any undesirable behaviour, such as too much or too little reclaim
pressure on the workload or system will be proportional to how far our
estimation is off. This means we can set memory.low much more
conservatively and thus waste less resources *without* the risk of the
workload falling off a cliff if we overshoot.
As a more abstract technical description, this unintuitive behaviour
results in having to give high-priority workloads a large protection
buffer on top of their expected usage to function reliably, as otherwise
we have abrupt periods of dramatically increased memory pressure which
hamper performance. Having to set these thresholds so high wastes
resources and generally works against the principle of work conservation.
In addition, having proportional memory reclaim behaviour has other
benefits. Most notably, before this patch it's basically mandatory to set
memory.low to a higher than desirable value because otherwise as soon as
you exceed memory.low, all protection is lost, and all pages are eligible
to scan again. By contrast, having a gradual ramp in reclaim pressure
means that you now still get some protection when thresholds are exceeded,
which means that one can now be more comfortable setting memory.low to
lower values without worrying that all protection will be lost. This is
important because workingset size is really hard to know exactly,
especially with variable workloads, so at least getting *some* protection
if your workingset size grows larger than you expect increases user
confidence in setting memory.low without a huge buffer on top being
needed.
Thanks a lot to Johannes Weiner and Tejun Heo for their advice and
assistance in thinking about how to make this work better.
In testing these changes, I intended to verify that:
1. Changes in page scanning become gradual and proportional instead of
binary.
To test this, I experimented stepping further and further down
memory.low protection on a workload that floats around 19G workingset
when under memory.low protection, watching page scan rates for the
workload cgroup:
+------------+-----------------+--------------------+--------------+
| memory.low | test (pgscan/s) | control (pgscan/s) | % of control |
+------------+-----------------+--------------------+--------------+
| 21G | 0 | 0 | N/A |
| 17G | 867 | 3799 | 23% |
| 12G | 1203 | 3543 | 34% |
| 8G | 2534 | 3979 | 64% |
| 4G | 3980 | 4147 | 96% |
| 0 | 3799 | 3980 | 95% |
+------------+-----------------+--------------------+--------------+
As you can see, the test kernel (with a kernel containing this
patch) ramps up page scanning significantly more gradually than the
control kernel (without this patch).
2. More gradual ramp up in reclaim aggression doesn't result in
premature OOMs.
To test this, I wrote a script that slowly increments the number of
pages held by stress(1)'s --vm-keep mode until a production system
entered severe overall memory contention. This script runs in a highly
protected slice taking up the majority of available system memory.
Watching vmstat revealed that page scanning continued essentially
nominally between test and control, without causing forward reclaim
progress to become arrested.
[0]: https://facebookmicrosites.github.io/cgroup2/docs/overview.html#case-study-the-fbtax2-project
[akpm@linux-foundation.org: reflow block comments to fit in 80 cols]
[chris@chrisdown.name: handle cgroup_disable=memory when getting memcg protection]
Link: http://lkml.kernel.org/r/20190201045711.GA18302@chrisdown.name
Link: http://lkml.kernel.org/r/20190124014455.GA6396@chrisdown.name
Signed-off-by: Chris Down <chris@chrisdown.name>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Roman Gushchin <guro@fb.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-10-07 00:58:32 +00:00
|
|
|
static inline unsigned long mem_cgroup_size(struct mem_cgroup *memcg)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2009-04-02 23:57:39 +00:00
|
|
|
static inline void
|
mm, oom: add oom victim's memcg to the oom context information
The current oom report doesn't display victim's memcg context during the
global OOM situation. While this information is not strictly needed, it
can be really helpful for containerized environments to locate which
container has lost a process. Now that we have a single line for the oom
context, we can trivially add both the oom memcg (this can be either
global_oom or a specific memcg which hits its hard limits) and task_memcg
which is the victim's memcg.
Below is the single line output in the oom report after this patch.
- global oom context information:
oom-kill:constraint=<constraint>,nodemask=<nodemask>,cpuset=<cpuset>,mems_allowed=<mems_allowed>,global_oom,task_memcg=<memcg>,task=<comm>,pid=<pid>,uid=<uid>
- memcg oom context information:
oom-kill:constraint=<constraint>,nodemask=<nodemask>,cpuset=<cpuset>,mems_allowed=<mems_allowed>,oom_memcg=<memcg>,task_memcg=<memcg>,task=<comm>,pid=<pid>,uid=<uid>
[penguin-kernel@I-love.SAKURA.ne.jp: use pr_cont() in mem_cgroup_print_oom_context()]
Link: http://lkml.kernel.org/r/201812190723.wBJ7NdkN032628@www262.sakura.ne.jp
Link: http://lkml.kernel.org/r/1542799799-36184-2-git-send-email-ufo19890607@gmail.com
Signed-off-by: yuzhoujian <yuzhoujian@didichuxing.com>
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Cc: Roman Gushchin <guro@fb.com>
Cc: Yang Shi <yang.s@alibaba-inc.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 08:36:10 +00:00
|
|
|
mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void
|
|
|
|
mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg)
|
2009-04-02 23:57:39 +00:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
mm: memcontrol: fix NULL pointer crash in test_clear_page_writeback()
Jaegeuk and Brad report a NULL pointer crash when writeback ending tries
to update the memcg stats:
BUG: unable to handle kernel NULL pointer dereference at 00000000000003b0
IP: test_clear_page_writeback+0x12e/0x2c0
[...]
RIP: 0010:test_clear_page_writeback+0x12e/0x2c0
Call Trace:
<IRQ>
end_page_writeback+0x47/0x70
f2fs_write_end_io+0x76/0x180 [f2fs]
bio_endio+0x9f/0x120
blk_update_request+0xa8/0x2f0
scsi_end_request+0x39/0x1d0
scsi_io_completion+0x211/0x690
scsi_finish_command+0xd9/0x120
scsi_softirq_done+0x127/0x150
__blk_mq_complete_request_remote+0x13/0x20
flush_smp_call_function_queue+0x56/0x110
generic_smp_call_function_single_interrupt+0x13/0x30
smp_call_function_single_interrupt+0x27/0x40
call_function_single_interrupt+0x89/0x90
RIP: 0010:native_safe_halt+0x6/0x10
(gdb) l *(test_clear_page_writeback+0x12e)
0xffffffff811bae3e is in test_clear_page_writeback (./include/linux/memcontrol.h:619).
614 mod_node_page_state(page_pgdat(page), idx, val);
615 if (mem_cgroup_disabled() || !page->mem_cgroup)
616 return;
617 mod_memcg_state(page->mem_cgroup, idx, val);
618 pn = page->mem_cgroup->nodeinfo[page_to_nid(page)];
619 this_cpu_add(pn->lruvec_stat->count[idx], val);
620 }
621
622 unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
623 gfp_t gfp_mask,
The issue is that writeback doesn't hold a page reference and the page
might get freed after PG_writeback is cleared (and the mapping is
unlocked) in test_clear_page_writeback(). The stat functions looking up
the page's node or zone are safe, as those attributes are static across
allocation and free cycles. But page->mem_cgroup is not, and it will
get cleared if we race with truncation or migration.
It appears this race window has been around for a while, but less likely
to trigger when the memcg stats were updated first thing after
PG_writeback is cleared. Recent changes reshuffled this code to update
the global node stats before the memcg ones, though, stretching the race
window out to an extent where people can reproduce the problem.
Update test_clear_page_writeback() to look up and pin page->mem_cgroup
before clearing PG_writeback, then not use that pointer afterward. It
is a partial revert of 62cccb8c8e7a ("mm: simplify lock_page_memcg()")
but leaves the pageref-holding callsites that aren't affected alone.
Link: http://lkml.kernel.org/r/20170809183825.GA26387@cmpxchg.org
Fixes: 62cccb8c8e7a ("mm: simplify lock_page_memcg()")
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: Jaegeuk Kim <jaegeuk@kernel.org>
Tested-by: Jaegeuk Kim <jaegeuk@kernel.org>
Reported-by: Bradley Bolen <bradleybolen@gmail.com>
Tested-by: Brad Bolen <bradleybolen@gmail.com>
Cc: Vladimir Davydov <vdavydov@virtuozzo.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: <stable@vger.kernel.org> [4.6+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-08-18 22:15:48 +00:00
|
|
|
static inline struct mem_cgroup *lock_page_memcg(struct page *page)
|
|
|
|
{
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void __unlock_page_memcg(struct mem_cgroup *memcg)
|
memcg: use new logic for page stat accounting
Now, page-stat-per-memcg is recorded into per page_cgroup flag by
duplicating page's status into the flag. The reason is that memcg has a
feature to move a page from a group to another group and we have race
between "move" and "page stat accounting",
Under current logic, assume CPU-A and CPU-B. CPU-A does "move" and CPU-B
does "page stat accounting".
When CPU-A goes 1st,
CPU-A CPU-B
update "struct page" info.
move_lock_mem_cgroup(memcg)
see pc->flags
copy page stat to new group
overwrite pc->mem_cgroup.
move_unlock_mem_cgroup(memcg)
move_lock_mem_cgroup(mem)
set pc->flags
update page stat accounting
move_unlock_mem_cgroup(mem)
stat accounting is guarded by move_lock_mem_cgroup() and "move" logic
(CPU-A) doesn't see changes in "struct page" information.
But it's costly to have the same information both in 'struct page' and
'struct page_cgroup'. And, there is a potential problem.
For example, assume we have PG_dirty accounting in memcg.
PG_..is a flag for struct page.
PCG_ is a flag for struct page_cgroup.
(This is just an example. The same problem can be found in any
kind of page stat accounting.)
CPU-A CPU-B
TestSet PG_dirty
(delay) TestClear PG_dirty
if (TestClear(PCG_dirty))
memcg->nr_dirty--
if (TestSet(PCG_dirty))
memcg->nr_dirty++
Here, memcg->nr_dirty = +1, this is wrong. This race was reported by Greg
Thelen <gthelen@google.com>. Now, only FILE_MAPPED is supported but
fortunately, it's serialized by page table lock and this is not real bug,
_now_,
If this potential problem is caused by having duplicated information in
struct page and struct page_cgroup, we may be able to fix this by using
original 'struct page' information. But we'll have a problem in "move
account"
Assume we use only PG_dirty.
CPU-A CPU-B
TestSet PG_dirty
(delay) move_lock_mem_cgroup()
if (PageDirty(page))
new_memcg->nr_dirty++
pc->mem_cgroup = new_memcg;
move_unlock_mem_cgroup()
move_lock_mem_cgroup()
memcg = pc->mem_cgroup
new_memcg->nr_dirty++
accounting information may be double-counted. This was original reason to
have PCG_xxx flags but it seems PCG_xxx has another problem.
I think we need a bigger lock as
move_lock_mem_cgroup(page)
TestSetPageDirty(page)
update page stats (without any checks)
move_unlock_mem_cgroup(page)
This fixes both of problems and we don't have to duplicate page flag into
page_cgroup. Please note: move_lock_mem_cgroup() is held only when there
are possibility of "account move" under the system. So, in most path,
status update will go without atomic locks.
This patch introduces mem_cgroup_begin_update_page_stat() and
mem_cgroup_end_update_page_stat() both should be called at modifying
'struct page' information if memcg takes care of it. as
mem_cgroup_begin_update_page_stat()
modify page information
mem_cgroup_update_page_stat()
=> never check any 'struct page' info, just update counters.
mem_cgroup_end_update_page_stat().
This patch is slow because we need to call begin_update_page_stat()/
end_update_page_stat() regardless of accounted will be changed or not. A
following patch adds an easy optimization and reduces the cost.
[akpm@linux-foundation.org: s/lock/locked/]
[hughd@google.com: fix deadlock by avoiding stat lock when anon]
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Greg Thelen <gthelen@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Ying Han <yinghan@google.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-21 23:34:25 +00:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2016-03-15 21:57:22 +00:00
|
|
|
static inline void unlock_page_memcg(struct page *page)
|
memcg: use new logic for page stat accounting
Now, page-stat-per-memcg is recorded into per page_cgroup flag by
duplicating page's status into the flag. The reason is that memcg has a
feature to move a page from a group to another group and we have race
between "move" and "page stat accounting",
Under current logic, assume CPU-A and CPU-B. CPU-A does "move" and CPU-B
does "page stat accounting".
When CPU-A goes 1st,
CPU-A CPU-B
update "struct page" info.
move_lock_mem_cgroup(memcg)
see pc->flags
copy page stat to new group
overwrite pc->mem_cgroup.
move_unlock_mem_cgroup(memcg)
move_lock_mem_cgroup(mem)
set pc->flags
update page stat accounting
move_unlock_mem_cgroup(mem)
stat accounting is guarded by move_lock_mem_cgroup() and "move" logic
(CPU-A) doesn't see changes in "struct page" information.
But it's costly to have the same information both in 'struct page' and
'struct page_cgroup'. And, there is a potential problem.
For example, assume we have PG_dirty accounting in memcg.
PG_..is a flag for struct page.
PCG_ is a flag for struct page_cgroup.
(This is just an example. The same problem can be found in any
kind of page stat accounting.)
CPU-A CPU-B
TestSet PG_dirty
(delay) TestClear PG_dirty
if (TestClear(PCG_dirty))
memcg->nr_dirty--
if (TestSet(PCG_dirty))
memcg->nr_dirty++
Here, memcg->nr_dirty = +1, this is wrong. This race was reported by Greg
Thelen <gthelen@google.com>. Now, only FILE_MAPPED is supported but
fortunately, it's serialized by page table lock and this is not real bug,
_now_,
If this potential problem is caused by having duplicated information in
struct page and struct page_cgroup, we may be able to fix this by using
original 'struct page' information. But we'll have a problem in "move
account"
Assume we use only PG_dirty.
CPU-A CPU-B
TestSet PG_dirty
(delay) move_lock_mem_cgroup()
if (PageDirty(page))
new_memcg->nr_dirty++
pc->mem_cgroup = new_memcg;
move_unlock_mem_cgroup()
move_lock_mem_cgroup()
memcg = pc->mem_cgroup
new_memcg->nr_dirty++
accounting information may be double-counted. This was original reason to
have PCG_xxx flags but it seems PCG_xxx has another problem.
I think we need a bigger lock as
move_lock_mem_cgroup(page)
TestSetPageDirty(page)
update page stats (without any checks)
move_unlock_mem_cgroup(page)
This fixes both of problems and we don't have to duplicate page flag into
page_cgroup. Please note: move_lock_mem_cgroup() is held only when there
are possibility of "account move" under the system. So, in most path,
status update will go without atomic locks.
This patch introduces mem_cgroup_begin_update_page_stat() and
mem_cgroup_end_update_page_stat() both should be called at modifying
'struct page' information if memcg takes care of it. as
mem_cgroup_begin_update_page_stat()
modify page information
mem_cgroup_update_page_stat()
=> never check any 'struct page' info, just update counters.
mem_cgroup_end_update_page_stat().
This patch is slow because we need to call begin_update_page_stat()/
end_update_page_stat() regardless of accounted will be changed or not. A
following patch adds an easy optimization and reduces the cost.
[akpm@linux-foundation.org: s/lock/locked/]
[hughd@google.com: fix deadlock by avoiding stat lock when anon]
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Greg Thelen <gthelen@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Ying Han <yinghan@google.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-21 23:34:25 +00:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
memcg: punt high overage reclaim to return-to-userland path
Currently, try_charge() tries to reclaim memory synchronously when the
high limit is breached; however, if the allocation doesn't have
__GFP_WAIT, synchronous reclaim is skipped. If a process performs only
speculative allocations, it can blow way past the high limit. This is
actually easily reproducible by simply doing "find /". slab/slub
allocator tries speculative allocations first, so as long as there's
memory which can be consumed without blocking, it can keep allocating
memory regardless of the high limit.
This patch makes try_charge() always punt the over-high reclaim to the
return-to-userland path. If try_charge() detects that high limit is
breached, it adds the overage to current->memcg_nr_pages_over_high and
schedules execution of mem_cgroup_handle_over_high() which performs
synchronous reclaim from the return-to-userland path.
As long as kernel doesn't have a run-away allocation spree, this should
provide enough protection while making kmemcg behave more consistently.
It also has the following benefits.
- All over-high reclaims can use GFP_KERNEL regardless of the specific
gfp mask in use, e.g. GFP_NOFS, when the limit was breached.
- It copes with prio inversion. Previously, a low-prio task with
small memory.high might perform over-high reclaim with a bunch of
locks held. If a higher prio task needed any of these locks, it
would have to wait until the low prio task finished reclaim and
released the locks. By handing over-high reclaim to the task exit
path this issue can be avoided.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Michal Hocko <mhocko@kernel.org>
Reviewed-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-06 02:46:11 +00:00
|
|
|
static inline void mem_cgroup_handle_over_high(void)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2018-08-17 22:47:11 +00:00
|
|
|
static inline void mem_cgroup_enter_user_fault(void)
|
2013-09-12 22:13:42 +00:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2018-08-17 22:47:11 +00:00
|
|
|
static inline void mem_cgroup_exit_user_fault(void)
|
2013-09-12 22:13:42 +00:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
mm: memcg: do not trap chargers with full callstack on OOM
The memcg OOM handling is incredibly fragile and can deadlock. When a
task fails to charge memory, it invokes the OOM killer and loops right
there in the charge code until it succeeds. Comparably, any other task
that enters the charge path at this point will go to a waitqueue right
then and there and sleep until the OOM situation is resolved. The problem
is that these tasks may hold filesystem locks and the mmap_sem; locks that
the selected OOM victim may need to exit.
For example, in one reported case, the task invoking the OOM killer was
about to charge a page cache page during a write(), which holds the
i_mutex. The OOM killer selected a task that was just entering truncate()
and trying to acquire the i_mutex:
OOM invoking task:
mem_cgroup_handle_oom+0x241/0x3b0
mem_cgroup_cache_charge+0xbe/0xe0
add_to_page_cache_locked+0x4c/0x140
add_to_page_cache_lru+0x22/0x50
grab_cache_page_write_begin+0x8b/0xe0
ext3_write_begin+0x88/0x270
generic_file_buffered_write+0x116/0x290
__generic_file_aio_write+0x27c/0x480
generic_file_aio_write+0x76/0xf0 # takes ->i_mutex
do_sync_write+0xea/0x130
vfs_write+0xf3/0x1f0
sys_write+0x51/0x90
system_call_fastpath+0x18/0x1d
OOM kill victim:
do_truncate+0x58/0xa0 # takes i_mutex
do_last+0x250/0xa30
path_openat+0xd7/0x440
do_filp_open+0x49/0xa0
do_sys_open+0x106/0x240
sys_open+0x20/0x30
system_call_fastpath+0x18/0x1d
The OOM handling task will retry the charge indefinitely while the OOM
killed task is not releasing any resources.
A similar scenario can happen when the kernel OOM killer for a memcg is
disabled and a userspace task is in charge of resolving OOM situations.
In this case, ALL tasks that enter the OOM path will be made to sleep on
the OOM waitqueue and wait for userspace to free resources or increase
the group's limit. But a userspace OOM handler is prone to deadlock
itself on the locks held by the waiting tasks. For example one of the
sleeping tasks may be stuck in a brk() call with the mmap_sem held for
writing but the userspace handler, in order to pick an optimal victim,
may need to read files from /proc/<pid>, which tries to acquire the same
mmap_sem for reading and deadlocks.
This patch changes the way tasks behave after detecting a memcg OOM and
makes sure nobody loops or sleeps with locks held:
1. When OOMing in a user fault, invoke the OOM killer and restart the
fault instead of looping on the charge attempt. This way, the OOM
victim can not get stuck on locks the looping task may hold.
2. When OOMing in a user fault but somebody else is handling it
(either the kernel OOM killer or a userspace handler), don't go to
sleep in the charge context. Instead, remember the OOMing memcg in
the task struct and then fully unwind the page fault stack with
-ENOMEM. pagefault_out_of_memory() will then call back into the
memcg code to check if the -ENOMEM came from the memcg, and then
either put the task to sleep on the memcg's OOM waitqueue or just
restart the fault. The OOM victim can no longer get stuck on any
lock a sleeping task may hold.
Debugged by Michal Hocko.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: azurIt <azurit@pobox.sk>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: David Rientjes <rientjes@google.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-12 22:13:44 +00:00
|
|
|
static inline bool task_in_memcg_oom(struct task_struct *p)
|
|
|
|
{
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
2013-10-16 20:46:59 +00:00
|
|
|
static inline bool mem_cgroup_oom_synchronize(bool wait)
|
mm: memcg: do not trap chargers with full callstack on OOM
The memcg OOM handling is incredibly fragile and can deadlock. When a
task fails to charge memory, it invokes the OOM killer and loops right
there in the charge code until it succeeds. Comparably, any other task
that enters the charge path at this point will go to a waitqueue right
then and there and sleep until the OOM situation is resolved. The problem
is that these tasks may hold filesystem locks and the mmap_sem; locks that
the selected OOM victim may need to exit.
For example, in one reported case, the task invoking the OOM killer was
about to charge a page cache page during a write(), which holds the
i_mutex. The OOM killer selected a task that was just entering truncate()
and trying to acquire the i_mutex:
OOM invoking task:
mem_cgroup_handle_oom+0x241/0x3b0
mem_cgroup_cache_charge+0xbe/0xe0
add_to_page_cache_locked+0x4c/0x140
add_to_page_cache_lru+0x22/0x50
grab_cache_page_write_begin+0x8b/0xe0
ext3_write_begin+0x88/0x270
generic_file_buffered_write+0x116/0x290
__generic_file_aio_write+0x27c/0x480
generic_file_aio_write+0x76/0xf0 # takes ->i_mutex
do_sync_write+0xea/0x130
vfs_write+0xf3/0x1f0
sys_write+0x51/0x90
system_call_fastpath+0x18/0x1d
OOM kill victim:
do_truncate+0x58/0xa0 # takes i_mutex
do_last+0x250/0xa30
path_openat+0xd7/0x440
do_filp_open+0x49/0xa0
do_sys_open+0x106/0x240
sys_open+0x20/0x30
system_call_fastpath+0x18/0x1d
The OOM handling task will retry the charge indefinitely while the OOM
killed task is not releasing any resources.
A similar scenario can happen when the kernel OOM killer for a memcg is
disabled and a userspace task is in charge of resolving OOM situations.
In this case, ALL tasks that enter the OOM path will be made to sleep on
the OOM waitqueue and wait for userspace to free resources or increase
the group's limit. But a userspace OOM handler is prone to deadlock
itself on the locks held by the waiting tasks. For example one of the
sleeping tasks may be stuck in a brk() call with the mmap_sem held for
writing but the userspace handler, in order to pick an optimal victim,
may need to read files from /proc/<pid>, which tries to acquire the same
mmap_sem for reading and deadlocks.
This patch changes the way tasks behave after detecting a memcg OOM and
makes sure nobody loops or sleeps with locks held:
1. When OOMing in a user fault, invoke the OOM killer and restart the
fault instead of looping on the charge attempt. This way, the OOM
victim can not get stuck on locks the looping task may hold.
2. When OOMing in a user fault but somebody else is handling it
(either the kernel OOM killer or a userspace handler), don't go to
sleep in the charge context. Instead, remember the OOMing memcg in
the task struct and then fully unwind the page fault stack with
-ENOMEM. pagefault_out_of_memory() will then call back into the
memcg code to check if the -ENOMEM came from the memcg, and then
either put the task to sleep on the memcg's OOM waitqueue or just
restart the fault. The OOM victim can no longer get stuck on any
lock a sleeping task may hold.
Debugged by Michal Hocko.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: azurIt <azurit@pobox.sk>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: David Rientjes <rientjes@google.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-12 22:13:44 +00:00
|
|
|
{
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
2018-08-22 04:53:54 +00:00
|
|
|
static inline struct mem_cgroup *mem_cgroup_get_oom_group(
|
|
|
|
struct task_struct *victim, struct mem_cgroup *oom_domain)
|
|
|
|
{
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void mem_cgroup_print_oom_group(struct mem_cgroup *memcg)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
mm: memcontrol: fix recursive statistics correctness & scalabilty
Right now, when somebody needs to know the recursive memory statistics
and events of a cgroup subtree, they need to walk the entire subtree and
sum up the counters manually.
There are two issues with this:
1. When a cgroup gets deleted, its stats are lost. The state counters
should all be 0 at that point, of course, but the events are not.
When this happens, the event counters, which are supposed to be
monotonic, can go backwards in the parent cgroups.
2. During regular operation, we always have a certain number of lazily
freed cgroups sitting around that have been deleted, have no tasks,
but have a few cache pages remaining. These groups' statistics do not
change until we eventually hit memory pressure, but somebody
watching, say, memory.stat on an ancestor has to iterate those every
time.
This patch addresses both issues by introducing recursive counters at
each level that are propagated from the write side when stats change.
Upward propagation happens when the per-cpu caches spill over into the
local atomic counter. This is the same thing we do during charge and
uncharge, except that the latter uses atomic RMWs, which are more
expensive; stat changes happen at around the same rate. In a sparse
file test (page faults and reclaim at maximum CPU speed) with 5 cgroup
nesting levels, perf shows __mod_memcg_page state at ~1%.
Link: http://lkml.kernel.org/r/20190412151507.2769-4-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Reviewed-by: Roman Gushchin <guro@fb.com>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 22:47:12 +00:00
|
|
|
static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
mm: memcontrol: make cgroup stats and events query API explicitly local
Patch series "mm: memcontrol: memory.stat cost & correctness".
The cgroup memory.stat file holds recursive statistics for the entire
subtree. The current implementation does this tree walk on-demand
whenever the file is read. This is giving us problems in production.
1. The cost of aggregating the statistics on-demand is high. A lot of
system service cgroups are mostly idle and their stats don't change
between reads, yet we always have to check them. There are also always
some lazily-dying cgroups sitting around that are pinned by a handful
of remaining page cache; the same applies to them.
In an application that periodically monitors memory.stat in our
fleet, we have seen the aggregation consume up to 5% CPU time.
2. When cgroups die and disappear from the cgroup tree, so do their
accumulated vm events. The result is that the event counters at
higher-level cgroups can go backwards and confuse some of our
automation, let alone people looking at the graphs over time.
To address both issues, this patch series changes the stat
implementation to spill counts upwards when the counters change.
The upward spilling is batched using the existing per-cpu cache. In a
sparse file stress test with 5 level cgroup nesting, the additional cost
of the flushing was negligible (a little under 1% of CPU at 100% CPU
utilization, compared to the 5% of reading memory.stat during regular
operation).
This patch (of 4):
memcg_page_state(), lruvec_page_state(), memcg_sum_events() are
currently returning the state of the local memcg or lruvec, not the
recursive state.
In practice there is a demand for both versions, although the callers
that want the recursive counts currently sum them up by hand.
Per default, cgroups are considered recursive entities and generally we
expect more users of the recursive counters, with the local counts being
special cases. To reflect that in the name, add a _local suffix to the
current implementations.
The following patch will re-incarnate these functions with recursive
semantics, but with an O(1) implementation.
[hannes@cmpxchg.org: fix bisection hole]
Link: http://lkml.kernel.org/r/20190417160347.GC23013@cmpxchg.org
Link: http://lkml.kernel.org/r/20190412151507.2769-2-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Reviewed-by: Roman Gushchin <guro@fb.com>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 22:47:06 +00:00
|
|
|
static inline unsigned long memcg_page_state_local(struct mem_cgroup *memcg,
|
|
|
|
int idx)
|
2017-05-03 21:55:03 +00:00
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2017-07-06 22:40:52 +00:00
|
|
|
static inline void __mod_memcg_state(struct mem_cgroup *memcg,
|
2017-09-06 23:22:09 +00:00
|
|
|
int idx,
|
2017-07-06 22:40:52 +00:00
|
|
|
int nr)
|
2017-05-03 21:55:03 +00:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2017-07-06 22:40:52 +00:00
|
|
|
static inline void mod_memcg_state(struct mem_cgroup *memcg,
|
2017-09-06 23:22:09 +00:00
|
|
|
int idx,
|
2017-07-06 22:40:52 +00:00
|
|
|
int nr)
|
2017-05-03 21:55:03 +00:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
mm: memcontrol: fix recursive statistics correctness & scalabilty
Right now, when somebody needs to know the recursive memory statistics
and events of a cgroup subtree, they need to walk the entire subtree and
sum up the counters manually.
There are two issues with this:
1. When a cgroup gets deleted, its stats are lost. The state counters
should all be 0 at that point, of course, but the events are not.
When this happens, the event counters, which are supposed to be
monotonic, can go backwards in the parent cgroups.
2. During regular operation, we always have a certain number of lazily
freed cgroups sitting around that have been deleted, have no tasks,
but have a few cache pages remaining. These groups' statistics do not
change until we eventually hit memory pressure, but somebody
watching, say, memory.stat on an ancestor has to iterate those every
time.
This patch addresses both issues by introducing recursive counters at
each level that are propagated from the write side when stats change.
Upward propagation happens when the per-cpu caches spill over into the
local atomic counter. This is the same thing we do during charge and
uncharge, except that the latter uses atomic RMWs, which are more
expensive; stat changes happen at around the same rate. In a sparse
file test (page faults and reclaim at maximum CPU speed) with 5 cgroup
nesting levels, perf shows __mod_memcg_page state at ~1%.
Link: http://lkml.kernel.org/r/20190412151507.2769-4-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Reviewed-by: Roman Gushchin <guro@fb.com>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 22:47:12 +00:00
|
|
|
static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
|
|
|
|
enum node_stat_item idx)
|
|
|
|
{
|
|
|
|
return node_page_state(lruvec_pgdat(lruvec), idx);
|
|
|
|
}
|
|
|
|
|
mm: memcontrol: make cgroup stats and events query API explicitly local
Patch series "mm: memcontrol: memory.stat cost & correctness".
The cgroup memory.stat file holds recursive statistics for the entire
subtree. The current implementation does this tree walk on-demand
whenever the file is read. This is giving us problems in production.
1. The cost of aggregating the statistics on-demand is high. A lot of
system service cgroups are mostly idle and their stats don't change
between reads, yet we always have to check them. There are also always
some lazily-dying cgroups sitting around that are pinned by a handful
of remaining page cache; the same applies to them.
In an application that periodically monitors memory.stat in our
fleet, we have seen the aggregation consume up to 5% CPU time.
2. When cgroups die and disappear from the cgroup tree, so do their
accumulated vm events. The result is that the event counters at
higher-level cgroups can go backwards and confuse some of our
automation, let alone people looking at the graphs over time.
To address both issues, this patch series changes the stat
implementation to spill counts upwards when the counters change.
The upward spilling is batched using the existing per-cpu cache. In a
sparse file stress test with 5 level cgroup nesting, the additional cost
of the flushing was negligible (a little under 1% of CPU at 100% CPU
utilization, compared to the 5% of reading memory.stat during regular
operation).
This patch (of 4):
memcg_page_state(), lruvec_page_state(), memcg_sum_events() are
currently returning the state of the local memcg or lruvec, not the
recursive state.
In practice there is a demand for both versions, although the callers
that want the recursive counts currently sum them up by hand.
Per default, cgroups are considered recursive entities and generally we
expect more users of the recursive counters, with the local counts being
special cases. To reflect that in the name, add a _local suffix to the
current implementations.
The following patch will re-incarnate these functions with recursive
semantics, but with an O(1) implementation.
[hannes@cmpxchg.org: fix bisection hole]
Link: http://lkml.kernel.org/r/20190417160347.GC23013@cmpxchg.org
Link: http://lkml.kernel.org/r/20190412151507.2769-2-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Reviewed-by: Roman Gushchin <guro@fb.com>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 22:47:06 +00:00
|
|
|
static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
|
|
|
|
enum node_stat_item idx)
|
2011-01-13 23:47:37 +00:00
|
|
|
{
|
2017-07-06 22:40:52 +00:00
|
|
|
return node_page_state(lruvec_pgdat(lruvec), idx);
|
2011-01-13 23:47:37 +00:00
|
|
|
}
|
|
|
|
|
mm: memcg: factor out memcg- and lruvec-level changes out of __mod_lruvec_state()
Patch series "The new cgroup slab memory controller", v7.
The patchset moves the accounting from the page level to the object level.
It allows to share slab pages between memory cgroups. This leads to a
significant win in the slab utilization (up to 45%) and the corresponding
drop in the total kernel memory footprint. The reduced number of
unmovable slab pages should also have a positive effect on the memory
fragmentation.
The patchset makes the slab accounting code simpler: there is no more need
in the complicated dynamic creation and destruction of per-cgroup slab
caches, all memory cgroups use a global set of shared slab caches. The
lifetime of slab caches is not more connected to the lifetime of memory
cgroups.
The more precise accounting does require more CPU, however in practice the
difference seems to be negligible. We've been using the new slab
controller in Facebook production for several months with different
workloads and haven't seen any noticeable regressions. What we've seen
were memory savings in order of 1 GB per host (it varied heavily depending
on the actual workload, size of RAM, number of CPUs, memory pressure,
etc).
The third version of the patchset added yet another step towards the
simplification of the code: sharing of slab caches between accounted and
non-accounted allocations. It comes with significant upsides (most
noticeable, a complete elimination of dynamic slab caches creation) but
not without some regression risks, so this change sits on top of the
patchset and is not completely merged in. So in the unlikely event of a
noticeable performance regression it can be reverted separately.
The slab memory accounting works in exactly the same way for SLAB and
SLUB. With both allocators the new controller shows significant memory
savings, with SLUB the difference is bigger. On my 16-core desktop
machine running Fedora 32 the size of the slab memory measured after the
start of the system was lower by 58% and 38% with SLUB and SLAB
correspondingly.
As an estimation of a potential CPU overhead, below are results of
slab_bulk_test01 test, kindly provided by Jesper D. Brouer. He also
helped with the evaluation of results.
The test can be found here: https://github.com/netoptimizer/prototype-kernel/
The smallest number in each row should be picked for a comparison.
SLUB-patched - bulk-API
- SLUB-patched : bulk_quick_reuse objects=1 : 187 - 90 - 224 cycles(tsc)
- SLUB-patched : bulk_quick_reuse objects=2 : 110 - 53 - 133 cycles(tsc)
- SLUB-patched : bulk_quick_reuse objects=3 : 88 - 95 - 42 cycles(tsc)
- SLUB-patched : bulk_quick_reuse objects=4 : 91 - 85 - 36 cycles(tsc)
- SLUB-patched : bulk_quick_reuse objects=8 : 32 - 66 - 32 cycles(tsc)
SLUB-original - bulk-API
- SLUB-original: bulk_quick_reuse objects=1 : 87 - 87 - 142 cycles(tsc)
- SLUB-original: bulk_quick_reuse objects=2 : 52 - 53 - 53 cycles(tsc)
- SLUB-original: bulk_quick_reuse objects=3 : 42 - 42 - 91 cycles(tsc)
- SLUB-original: bulk_quick_reuse objects=4 : 91 - 37 - 37 cycles(tsc)
- SLUB-original: bulk_quick_reuse objects=8 : 31 - 79 - 76 cycles(tsc)
SLAB-patched - bulk-API
- SLAB-patched : bulk_quick_reuse objects=1 : 67 - 67 - 140 cycles(tsc)
- SLAB-patched : bulk_quick_reuse objects=2 : 55 - 46 - 46 cycles(tsc)
- SLAB-patched : bulk_quick_reuse objects=3 : 93 - 94 - 39 cycles(tsc)
- SLAB-patched : bulk_quick_reuse objects=4 : 35 - 88 - 85 cycles(tsc)
- SLAB-patched : bulk_quick_reuse objects=8 : 30 - 30 - 30 cycles(tsc)
SLAB-original- bulk-API
- SLAB-original: bulk_quick_reuse objects=1 : 143 - 136 - 67 cycles(tsc)
- SLAB-original: bulk_quick_reuse objects=2 : 45 - 46 - 46 cycles(tsc)
- SLAB-original: bulk_quick_reuse objects=3 : 38 - 39 - 39 cycles(tsc)
- SLAB-original: bulk_quick_reuse objects=4 : 35 - 87 - 87 cycles(tsc)
- SLAB-original: bulk_quick_reuse objects=8 : 29 - 66 - 30 cycles(tsc)
This patch (of 19):
To convert memcg and lruvec slab counters to bytes there must be a way to
change these counters without touching node counters. Factor out
__mod_memcg_lruvec_state() out of __mod_lruvec_state().
Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/20200623174037.3951353-1-guro@fb.com
Link: http://lkml.kernel.org/r/20200623174037.3951353-2-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-07 06:20:32 +00:00
|
|
|
static inline void __mod_memcg_lruvec_state(struct lruvec *lruvec,
|
|
|
|
enum node_stat_item idx, int val)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2020-12-15 03:07:04 +00:00
|
|
|
static inline void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx,
|
2019-08-13 22:37:41 +00:00
|
|
|
int val)
|
|
|
|
{
|
|
|
|
struct page *page = virt_to_head_page(p);
|
|
|
|
|
|
|
|
__mod_node_page_state(page_pgdat(page), idx, val);
|
|
|
|
}
|
|
|
|
|
2020-12-15 03:07:04 +00:00
|
|
|
static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx,
|
2020-08-07 06:21:37 +00:00
|
|
|
int val)
|
|
|
|
{
|
|
|
|
struct page *page = virt_to_head_page(p);
|
|
|
|
|
|
|
|
mod_node_page_state(page_pgdat(page), idx, val);
|
|
|
|
}
|
|
|
|
|
2009-09-23 22:56:39 +00:00
|
|
|
static inline
|
2016-07-28 22:46:05 +00:00
|
|
|
unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
|
2013-09-24 22:27:41 +00:00
|
|
|
gfp_t gfp_mask,
|
|
|
|
unsigned long *total_scanned)
|
2009-09-23 22:56:39 +00:00
|
|
|
{
|
2013-09-24 22:27:41 +00:00
|
|
|
return 0;
|
2009-09-23 22:56:39 +00:00
|
|
|
}
|
|
|
|
|
2012-01-13 01:18:20 +00:00
|
|
|
static inline void mem_cgroup_split_huge_fixup(struct page *head)
|
2011-01-20 22:44:24 +00:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2017-07-06 22:40:25 +00:00
|
|
|
static inline void count_memcg_events(struct mem_cgroup *memcg,
|
|
|
|
enum vm_event_item idx,
|
|
|
|
unsigned long count)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2019-05-14 00:16:54 +00:00
|
|
|
static inline void __count_memcg_events(struct mem_cgroup *memcg,
|
|
|
|
enum vm_event_item idx,
|
|
|
|
unsigned long count)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2017-07-06 22:40:25 +00:00
|
|
|
static inline void count_memcg_page_event(struct page *page,
|
2017-09-06 23:22:09 +00:00
|
|
|
int idx)
|
2017-07-06 22:40:25 +00:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2011-05-26 23:25:38 +00:00
|
|
|
static inline
|
2017-07-06 22:40:25 +00:00
|
|
|
void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx)
|
2011-05-26 23:25:38 +00:00
|
|
|
{
|
|
|
|
}
|
2020-12-15 20:34:29 +00:00
|
|
|
|
|
|
|
static inline void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page)
|
|
|
|
{
|
|
|
|
}
|
2012-07-31 23:43:02 +00:00
|
|
|
#endif /* CONFIG_MEMCG */
|
2008-02-07 08:13:51 +00:00
|
|
|
|
2020-12-15 03:07:04 +00:00
|
|
|
static inline void __inc_lruvec_kmem_state(void *p, enum node_stat_item idx)
|
2019-08-13 22:37:41 +00:00
|
|
|
{
|
2020-12-15 03:07:04 +00:00
|
|
|
__mod_lruvec_kmem_state(p, idx, 1);
|
2019-08-13 22:37:41 +00:00
|
|
|
}
|
|
|
|
|
2020-12-15 03:07:04 +00:00
|
|
|
static inline void __dec_lruvec_kmem_state(void *p, enum node_stat_item idx)
|
2019-08-13 22:37:41 +00:00
|
|
|
{
|
2020-12-15 03:07:04 +00:00
|
|
|
__mod_lruvec_kmem_state(p, idx, -1);
|
2019-08-13 22:37:41 +00:00
|
|
|
}
|
|
|
|
|
mm: vmscan: determine anon/file pressure balance at the reclaim root
We split the LRU lists into anon and file, and we rebalance the scan
pressure between them when one of them begins thrashing: if the file cache
experiences workingset refaults, we increase the pressure on anonymous
pages; if the workload is stalled on swapins, we increase the pressure on
the file cache instead.
With cgroups and their nested LRU lists, we currently don't do this
correctly. While recursive cgroup reclaim establishes a relative LRU
order among the pages of all involved cgroups, LRU pressure balancing is
done on an individual cgroup LRU level. As a result, when one cgroup is
thrashing on the filesystem cache while a sibling may have cold anonymous
pages, pressure doesn't get equalized between them.
This patch moves LRU balancing decision to the root of reclaim - the same
level where the LRU order is established.
It does this by tracking LRU cost recursively, so that every level of the
cgroup tree knows the aggregate LRU cost of all memory within its domain.
When the page scanner calculates the scan balance for any given individual
cgroup's LRU list, it uses the values from the ancestor cgroup that
initiated the reclaim cycle.
If one sibling is then thrashing on the cache, it will tip the pressure
balance inside its ancestors, and the next hierarchical reclaim iteration
will go more after the anon pages in the tree.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Rik van Riel <riel@surriel.com>
Link: http://lkml.kernel.org/r/20200520232525.798933-13-hannes@cmpxchg.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-03 23:03:06 +00:00
|
|
|
static inline struct lruvec *parent_lruvec(struct lruvec *lruvec)
|
|
|
|
{
|
|
|
|
struct mem_cgroup *memcg;
|
|
|
|
|
|
|
|
memcg = lruvec_memcg(lruvec);
|
|
|
|
if (!memcg)
|
|
|
|
return NULL;
|
|
|
|
memcg = parent_mem_cgroup(memcg);
|
|
|
|
if (!memcg)
|
|
|
|
return NULL;
|
|
|
|
return mem_cgroup_lruvec(memcg, lruvec_pgdat(lruvec));
|
|
|
|
}
|
|
|
|
|
2020-12-15 20:34:29 +00:00
|
|
|
static inline void unlock_page_lruvec(struct lruvec *lruvec)
|
|
|
|
{
|
|
|
|
spin_unlock(&lruvec->lru_lock);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void unlock_page_lruvec_irq(struct lruvec *lruvec)
|
|
|
|
{
|
|
|
|
spin_unlock_irq(&lruvec->lru_lock);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void unlock_page_lruvec_irqrestore(struct lruvec *lruvec,
|
|
|
|
unsigned long flags)
|
|
|
|
{
|
|
|
|
spin_unlock_irqrestore(&lruvec->lru_lock, flags);
|
|
|
|
}
|
|
|
|
|
2020-12-15 20:34:33 +00:00
|
|
|
/* Don't lock again iff page's lruvec locked */
|
|
|
|
static inline struct lruvec *relock_page_lruvec_irq(struct page *page,
|
|
|
|
struct lruvec *locked_lruvec)
|
|
|
|
{
|
|
|
|
if (locked_lruvec) {
|
|
|
|
if (lruvec_holds_page_lru_lock(page, locked_lruvec))
|
|
|
|
return locked_lruvec;
|
|
|
|
|
|
|
|
unlock_page_lruvec_irq(locked_lruvec);
|
|
|
|
}
|
|
|
|
|
|
|
|
return lock_page_lruvec_irq(page);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Don't lock again iff page's lruvec locked */
|
|
|
|
static inline struct lruvec *relock_page_lruvec_irqsave(struct page *page,
|
|
|
|
struct lruvec *locked_lruvec, unsigned long *flags)
|
|
|
|
{
|
|
|
|
if (locked_lruvec) {
|
|
|
|
if (lruvec_holds_page_lru_lock(page, locked_lruvec))
|
|
|
|
return locked_lruvec;
|
|
|
|
|
|
|
|
unlock_page_lruvec_irqrestore(locked_lruvec, *flags);
|
|
|
|
}
|
|
|
|
|
|
|
|
return lock_page_lruvec_irqsave(page, flags);
|
|
|
|
}
|
|
|
|
|
2015-05-22 21:13:37 +00:00
|
|
|
#ifdef CONFIG_CGROUP_WRITEBACK
|
2015-05-22 22:23:33 +00:00
|
|
|
|
|
|
|
struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb);
|
writeback: fix incorrect calculation of available memory for memcg domains
For memcg domains, the amount of available memory was calculated as
min(the amount currently in use + headroom according to memcg,
total clean memory)
This isn't quite correct as what should be capped by the amount of
clean memory is the headroom, not the sum of memory in use and
headroom. For example, if a memcg domain has a significant amount of
dirty memory, the above can lead to a value which is lower than the
current amount in use which doesn't make much sense. In most
circumstances, the above leads to a number which is somewhat but not
drastically lower.
As the amount of memory which can be readily allocated to the memcg
domain is capped by the amount of system-wide clean memory which is
not already assigned to the memcg itself, the number we want is
the amount currently in use +
min(headroom according to memcg, clean memory elsewhere in the system)
This patch updates mem_cgroup_wb_stats() to return the number of
filepages and headroom instead of the calculated available pages.
mdtc_cap_avail() is renamed to mdtc_calc_avail() and performs the
above calculation from file, headroom, dirty and globally clean pages.
v2: Dummy mem_cgroup_wb_stats() implementation wasn't updated leading
to build failure when !CGROUP_WRITEBACK. Fixed.
Signed-off-by: Tejun Heo <tj@kernel.org>
Fixes: c2aa723a6093 ("writeback: implement memcg writeback domain based throttling")
Signed-off-by: Jens Axboe <axboe@fb.com>
2015-09-29 17:04:26 +00:00
|
|
|
void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
|
|
|
|
unsigned long *pheadroom, unsigned long *pdirty,
|
|
|
|
unsigned long *pwriteback);
|
2015-05-22 22:23:33 +00:00
|
|
|
|
writeback, memcg: Implement foreign dirty flushing
There's an inherent mismatch between memcg and writeback. The former
trackes ownership per-page while the latter per-inode. This was a
deliberate design decision because honoring per-page ownership in the
writeback path is complicated, may lead to higher CPU and IO overheads
and deemed unnecessary given that write-sharing an inode across
different cgroups isn't a common use-case.
Combined with inode majority-writer ownership switching, this works
well enough in most cases but there are some pathological cases. For
example, let's say there are two cgroups A and B which keep writing to
different but confined parts of the same inode. B owns the inode and
A's memory is limited far below B's. A's dirty ratio can rise enough
to trigger balance_dirty_pages() sleeps but B's can be low enough to
avoid triggering background writeback. A will be slowed down without
a way to make writeback of the dirty pages happen.
This patch implements foreign dirty recording and foreign mechanism so
that when a memcg encounters a condition as above it can trigger
flushes on bdi_writebacks which can clean its pages. Please see the
comment on top of mem_cgroup_track_foreign_dirty_slowpath() for
details.
A reproducer follows.
write-range.c::
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <fcntl.h>
#include <sys/types.h>
static const char *usage = "write-range FILE START SIZE\n";
int main(int argc, char **argv)
{
int fd;
unsigned long start, size, end, pos;
char *endp;
char buf[4096];
if (argc < 4) {
fprintf(stderr, usage);
return 1;
}
fd = open(argv[1], O_WRONLY);
if (fd < 0) {
perror("open");
return 1;
}
start = strtoul(argv[2], &endp, 0);
if (*endp != '\0') {
fprintf(stderr, usage);
return 1;
}
size = strtoul(argv[3], &endp, 0);
if (*endp != '\0') {
fprintf(stderr, usage);
return 1;
}
end = start + size;
while (1) {
for (pos = start; pos < end; ) {
long bread, bwritten = 0;
if (lseek(fd, pos, SEEK_SET) < 0) {
perror("lseek");
return 1;
}
bread = read(0, buf, sizeof(buf) < end - pos ?
sizeof(buf) : end - pos);
if (bread < 0) {
perror("read");
return 1;
}
if (bread == 0)
return 0;
while (bwritten < bread) {
long this;
this = write(fd, buf + bwritten,
bread - bwritten);
if (this < 0) {
perror("write");
return 1;
}
bwritten += this;
pos += bwritten;
}
}
}
}
repro.sh::
#!/bin/bash
set -e
set -x
sysctl -w vm.dirty_expire_centisecs=300000
sysctl -w vm.dirty_writeback_centisecs=300000
sysctl -w vm.dirtytime_expire_seconds=300000
echo 3 > /proc/sys/vm/drop_caches
TEST=/sys/fs/cgroup/test
A=$TEST/A
B=$TEST/B
mkdir -p $A $B
echo "+memory +io" > $TEST/cgroup.subtree_control
echo $((1<<30)) > $A/memory.high
echo $((32<<30)) > $B/memory.high
rm -f testfile
touch testfile
fallocate -l 4G testfile
echo "Starting B"
(echo $BASHPID > $B/cgroup.procs
pv -q --rate-limit 70M < /dev/urandom | ./write-range testfile $((2<<30)) $((2<<30))) &
echo "Waiting 10s to ensure B claims the testfile inode"
sleep 5
sync
sleep 5
sync
echo "Starting A"
(echo $BASHPID > $A/cgroup.procs
pv < /dev/urandom | ./write-range testfile 0 $((2<<30)))
v2: Added comments explaining why the specific intervals are being used.
v3: Use 0 @nr when calling cgroup_writeback_by_id() to use best-effort
flushing while avoding possible livelocks.
v4: Use get_jiffies_64() and time_before/after64() instead of raw
jiffies_64 and arthimetic comparisons as suggested by Jan.
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-08-26 16:06:56 +00:00
|
|
|
void mem_cgroup_track_foreign_dirty_slowpath(struct page *page,
|
|
|
|
struct bdi_writeback *wb);
|
|
|
|
|
|
|
|
static inline void mem_cgroup_track_foreign_dirty(struct page *page,
|
|
|
|
struct bdi_writeback *wb)
|
|
|
|
{
|
2019-10-07 00:58:15 +00:00
|
|
|
if (mem_cgroup_disabled())
|
|
|
|
return;
|
|
|
|
|
mm: memcontrol: Use helpers to read page's memcg data
Patch series "mm: allow mapping accounted kernel pages to userspace", v6.
Currently a non-slab kernel page which has been charged to a memory cgroup
can't be mapped to userspace. The underlying reason is simple: PageKmemcg
flag is defined as a page type (like buddy, offline, etc), so it takes a
bit from a page->mapped counter. Pages with a type set can't be mapped to
userspace.
But in general the kmemcg flag has nothing to do with mapping to
userspace. It only means that the page has been accounted by the page
allocator, so it has to be properly uncharged on release.
Some bpf maps are mapping the vmalloc-based memory to userspace, and their
memory can't be accounted because of this implementation detail.
This patchset removes this limitation by moving the PageKmemcg flag into
one of the free bits of the page->mem_cgroup pointer. Also it formalizes
accesses to the page->mem_cgroup and page->obj_cgroups using new helpers,
adds several checks and removes a couple of obsolete functions. As the
result the code became more robust with fewer open-coded bit tricks.
This patch (of 4):
Currently there are many open-coded reads of the page->mem_cgroup pointer,
as well as a couple of read helpers, which are barely used.
It creates an obstacle on a way to reuse some bits of the pointer for
storing additional bits of information. In fact, we already do this for
slab pages, where the last bit indicates that a pointer has an attached
vector of objcg pointers instead of a regular memcg pointer.
This commits uses 2 existing helpers and introduces a new helper to
converts all read sides to calls of these helpers:
struct mem_cgroup *page_memcg(struct page *page);
struct mem_cgroup *page_memcg_rcu(struct page *page);
struct mem_cgroup *page_memcg_check(struct page *page);
page_memcg_check() is intended to be used in cases when the page can be a
slab page and have a memcg pointer pointing at objcg vector. It does
check the lowest bit, and if set, returns NULL. page_memcg() contains a
VM_BUG_ON_PAGE() check for the page not being a slab page.
To make sure nobody uses a direct access, struct page's
mem_cgroup/obj_cgroups is converted to unsigned long memcg_data.
Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Link: https://lkml.kernel.org/r/20201027001657.3398190-1-guro@fb.com
Link: https://lkml.kernel.org/r/20201027001657.3398190-2-guro@fb.com
Link: https://lore.kernel.org/bpf/20201201215900.3569844-2-guro@fb.com
2020-12-01 21:58:27 +00:00
|
|
|
if (unlikely(&page_memcg(page)->css != wb->memcg_css))
|
writeback, memcg: Implement foreign dirty flushing
There's an inherent mismatch between memcg and writeback. The former
trackes ownership per-page while the latter per-inode. This was a
deliberate design decision because honoring per-page ownership in the
writeback path is complicated, may lead to higher CPU and IO overheads
and deemed unnecessary given that write-sharing an inode across
different cgroups isn't a common use-case.
Combined with inode majority-writer ownership switching, this works
well enough in most cases but there are some pathological cases. For
example, let's say there are two cgroups A and B which keep writing to
different but confined parts of the same inode. B owns the inode and
A's memory is limited far below B's. A's dirty ratio can rise enough
to trigger balance_dirty_pages() sleeps but B's can be low enough to
avoid triggering background writeback. A will be slowed down without
a way to make writeback of the dirty pages happen.
This patch implements foreign dirty recording and foreign mechanism so
that when a memcg encounters a condition as above it can trigger
flushes on bdi_writebacks which can clean its pages. Please see the
comment on top of mem_cgroup_track_foreign_dirty_slowpath() for
details.
A reproducer follows.
write-range.c::
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <fcntl.h>
#include <sys/types.h>
static const char *usage = "write-range FILE START SIZE\n";
int main(int argc, char **argv)
{
int fd;
unsigned long start, size, end, pos;
char *endp;
char buf[4096];
if (argc < 4) {
fprintf(stderr, usage);
return 1;
}
fd = open(argv[1], O_WRONLY);
if (fd < 0) {
perror("open");
return 1;
}
start = strtoul(argv[2], &endp, 0);
if (*endp != '\0') {
fprintf(stderr, usage);
return 1;
}
size = strtoul(argv[3], &endp, 0);
if (*endp != '\0') {
fprintf(stderr, usage);
return 1;
}
end = start + size;
while (1) {
for (pos = start; pos < end; ) {
long bread, bwritten = 0;
if (lseek(fd, pos, SEEK_SET) < 0) {
perror("lseek");
return 1;
}
bread = read(0, buf, sizeof(buf) < end - pos ?
sizeof(buf) : end - pos);
if (bread < 0) {
perror("read");
return 1;
}
if (bread == 0)
return 0;
while (bwritten < bread) {
long this;
this = write(fd, buf + bwritten,
bread - bwritten);
if (this < 0) {
perror("write");
return 1;
}
bwritten += this;
pos += bwritten;
}
}
}
}
repro.sh::
#!/bin/bash
set -e
set -x
sysctl -w vm.dirty_expire_centisecs=300000
sysctl -w vm.dirty_writeback_centisecs=300000
sysctl -w vm.dirtytime_expire_seconds=300000
echo 3 > /proc/sys/vm/drop_caches
TEST=/sys/fs/cgroup/test
A=$TEST/A
B=$TEST/B
mkdir -p $A $B
echo "+memory +io" > $TEST/cgroup.subtree_control
echo $((1<<30)) > $A/memory.high
echo $((32<<30)) > $B/memory.high
rm -f testfile
touch testfile
fallocate -l 4G testfile
echo "Starting B"
(echo $BASHPID > $B/cgroup.procs
pv -q --rate-limit 70M < /dev/urandom | ./write-range testfile $((2<<30)) $((2<<30))) &
echo "Waiting 10s to ensure B claims the testfile inode"
sleep 5
sync
sleep 5
sync
echo "Starting A"
(echo $BASHPID > $A/cgroup.procs
pv < /dev/urandom | ./write-range testfile 0 $((2<<30)))
v2: Added comments explaining why the specific intervals are being used.
v3: Use 0 @nr when calling cgroup_writeback_by_id() to use best-effort
flushing while avoding possible livelocks.
v4: Use get_jiffies_64() and time_before/after64() instead of raw
jiffies_64 and arthimetic comparisons as suggested by Jan.
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-08-26 16:06:56 +00:00
|
|
|
mem_cgroup_track_foreign_dirty_slowpath(page, wb);
|
|
|
|
}
|
|
|
|
|
|
|
|
void mem_cgroup_flush_foreign(struct bdi_writeback *wb);
|
|
|
|
|
2015-05-22 22:23:33 +00:00
|
|
|
#else /* CONFIG_CGROUP_WRITEBACK */
|
|
|
|
|
|
|
|
static inline struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb)
|
|
|
|
{
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2015-05-22 22:23:35 +00:00
|
|
|
static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb,
|
writeback: fix incorrect calculation of available memory for memcg domains
For memcg domains, the amount of available memory was calculated as
min(the amount currently in use + headroom according to memcg,
total clean memory)
This isn't quite correct as what should be capped by the amount of
clean memory is the headroom, not the sum of memory in use and
headroom. For example, if a memcg domain has a significant amount of
dirty memory, the above can lead to a value which is lower than the
current amount in use which doesn't make much sense. In most
circumstances, the above leads to a number which is somewhat but not
drastically lower.
As the amount of memory which can be readily allocated to the memcg
domain is capped by the amount of system-wide clean memory which is
not already assigned to the memcg itself, the number we want is
the amount currently in use +
min(headroom according to memcg, clean memory elsewhere in the system)
This patch updates mem_cgroup_wb_stats() to return the number of
filepages and headroom instead of the calculated available pages.
mdtc_cap_avail() is renamed to mdtc_calc_avail() and performs the
above calculation from file, headroom, dirty and globally clean pages.
v2: Dummy mem_cgroup_wb_stats() implementation wasn't updated leading
to build failure when !CGROUP_WRITEBACK. Fixed.
Signed-off-by: Tejun Heo <tj@kernel.org>
Fixes: c2aa723a6093 ("writeback: implement memcg writeback domain based throttling")
Signed-off-by: Jens Axboe <axboe@fb.com>
2015-09-29 17:04:26 +00:00
|
|
|
unsigned long *pfilepages,
|
|
|
|
unsigned long *pheadroom,
|
2015-05-22 22:23:35 +00:00
|
|
|
unsigned long *pdirty,
|
|
|
|
unsigned long *pwriteback)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
writeback, memcg: Implement foreign dirty flushing
There's an inherent mismatch between memcg and writeback. The former
trackes ownership per-page while the latter per-inode. This was a
deliberate design decision because honoring per-page ownership in the
writeback path is complicated, may lead to higher CPU and IO overheads
and deemed unnecessary given that write-sharing an inode across
different cgroups isn't a common use-case.
Combined with inode majority-writer ownership switching, this works
well enough in most cases but there are some pathological cases. For
example, let's say there are two cgroups A and B which keep writing to
different but confined parts of the same inode. B owns the inode and
A's memory is limited far below B's. A's dirty ratio can rise enough
to trigger balance_dirty_pages() sleeps but B's can be low enough to
avoid triggering background writeback. A will be slowed down without
a way to make writeback of the dirty pages happen.
This patch implements foreign dirty recording and foreign mechanism so
that when a memcg encounters a condition as above it can trigger
flushes on bdi_writebacks which can clean its pages. Please see the
comment on top of mem_cgroup_track_foreign_dirty_slowpath() for
details.
A reproducer follows.
write-range.c::
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <fcntl.h>
#include <sys/types.h>
static const char *usage = "write-range FILE START SIZE\n";
int main(int argc, char **argv)
{
int fd;
unsigned long start, size, end, pos;
char *endp;
char buf[4096];
if (argc < 4) {
fprintf(stderr, usage);
return 1;
}
fd = open(argv[1], O_WRONLY);
if (fd < 0) {
perror("open");
return 1;
}
start = strtoul(argv[2], &endp, 0);
if (*endp != '\0') {
fprintf(stderr, usage);
return 1;
}
size = strtoul(argv[3], &endp, 0);
if (*endp != '\0') {
fprintf(stderr, usage);
return 1;
}
end = start + size;
while (1) {
for (pos = start; pos < end; ) {
long bread, bwritten = 0;
if (lseek(fd, pos, SEEK_SET) < 0) {
perror("lseek");
return 1;
}
bread = read(0, buf, sizeof(buf) < end - pos ?
sizeof(buf) : end - pos);
if (bread < 0) {
perror("read");
return 1;
}
if (bread == 0)
return 0;
while (bwritten < bread) {
long this;
this = write(fd, buf + bwritten,
bread - bwritten);
if (this < 0) {
perror("write");
return 1;
}
bwritten += this;
pos += bwritten;
}
}
}
}
repro.sh::
#!/bin/bash
set -e
set -x
sysctl -w vm.dirty_expire_centisecs=300000
sysctl -w vm.dirty_writeback_centisecs=300000
sysctl -w vm.dirtytime_expire_seconds=300000
echo 3 > /proc/sys/vm/drop_caches
TEST=/sys/fs/cgroup/test
A=$TEST/A
B=$TEST/B
mkdir -p $A $B
echo "+memory +io" > $TEST/cgroup.subtree_control
echo $((1<<30)) > $A/memory.high
echo $((32<<30)) > $B/memory.high
rm -f testfile
touch testfile
fallocate -l 4G testfile
echo "Starting B"
(echo $BASHPID > $B/cgroup.procs
pv -q --rate-limit 70M < /dev/urandom | ./write-range testfile $((2<<30)) $((2<<30))) &
echo "Waiting 10s to ensure B claims the testfile inode"
sleep 5
sync
sleep 5
sync
echo "Starting A"
(echo $BASHPID > $A/cgroup.procs
pv < /dev/urandom | ./write-range testfile 0 $((2<<30)))
v2: Added comments explaining why the specific intervals are being used.
v3: Use 0 @nr when calling cgroup_writeback_by_id() to use best-effort
flushing while avoding possible livelocks.
v4: Use get_jiffies_64() and time_before/after64() instead of raw
jiffies_64 and arthimetic comparisons as suggested by Jan.
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-08-26 16:06:56 +00:00
|
|
|
static inline void mem_cgroup_track_foreign_dirty(struct page *page,
|
|
|
|
struct bdi_writeback *wb)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void mem_cgroup_flush_foreign(struct bdi_writeback *wb)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2015-05-22 22:23:33 +00:00
|
|
|
#endif /* CONFIG_CGROUP_WRITEBACK */
|
2015-05-22 21:13:37 +00:00
|
|
|
|
2011-12-11 21:47:03 +00:00
|
|
|
struct sock;
|
2016-01-14 23:21:17 +00:00
|
|
|
bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages);
|
|
|
|
void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages);
|
2016-01-20 23:02:47 +00:00
|
|
|
#ifdef CONFIG_MEMCG
|
2016-01-14 23:21:34 +00:00
|
|
|
extern struct static_key_false memcg_sockets_enabled_key;
|
|
|
|
#define mem_cgroup_sockets_enabled static_branch_unlikely(&memcg_sockets_enabled_key)
|
2016-10-08 00:00:58 +00:00
|
|
|
void mem_cgroup_sk_alloc(struct sock *sk);
|
|
|
|
void mem_cgroup_sk_free(struct sock *sk);
|
2016-01-14 23:21:17 +00:00
|
|
|
static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
|
net: tcp_memcontrol: sanitize tcp memory accounting callbacks
There won't be a tcp control soft limit, so integrating the memcg code
into the global skmem limiting scheme complicates things unnecessarily.
Replace this with simple and clear charge and uncharge calls--hidden
behind a jump label--to account skb memory.
Note that this is not purely aesthetic: as a result of shoehorning the
per-memcg code into the same memory accounting functions that handle the
global level, the old code would compare the per-memcg consumption
against the smaller of the per-memcg limit and the global limit. This
allowed the total consumption of multiple sockets to exceed the global
limit, as long as the individual sockets stayed within bounds. After
this change, the code will always compare the per-memcg consumption to
the per-memcg limit, and the global consumption to the global limit, and
thus close this loophole.
Without a soft limit, the per-memcg memory pressure state in sockets is
generally questionable. However, we did it until now, so we continue to
enter it when the hard limit is hit, and packets are dropped, to let
other sockets in the cgroup know that they shouldn't grow their transmit
windows, either. However, keep it simple in the new callback model and
leave memory pressure lazily when the next packet is accepted (as
opposed to doing it synchroneously when packets are processed). When
packets are dropped, network performance will already be in the toilet,
so that should be a reasonable trade-off.
As described above, consumption is now checked on the per-memcg level
and the global level separately. Likewise, memory pressure states are
maintained on both the per-memcg level and the global level, and a
socket is considered under pressure when either level asserts as much.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-14 23:21:14 +00:00
|
|
|
{
|
2016-01-20 23:02:50 +00:00
|
|
|
if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_pressure)
|
2016-01-14 23:21:32 +00:00
|
|
|
return true;
|
|
|
|
do {
|
|
|
|
if (time_before(jiffies, memcg->socket_pressure))
|
|
|
|
return true;
|
|
|
|
} while ((memcg = parent_mem_cgroup(memcg)));
|
|
|
|
return false;
|
net: tcp_memcontrol: sanitize tcp memory accounting callbacks
There won't be a tcp control soft limit, so integrating the memcg code
into the global skmem limiting scheme complicates things unnecessarily.
Replace this with simple and clear charge and uncharge calls--hidden
behind a jump label--to account skb memory.
Note that this is not purely aesthetic: as a result of shoehorning the
per-memcg code into the same memory accounting functions that handle the
global level, the old code would compare the per-memcg consumption
against the smaller of the per-memcg limit and the global limit. This
allowed the total consumption of multiple sockets to exceed the global
limit, as long as the individual sockets stayed within bounds. After
this change, the code will always compare the per-memcg consumption to
the per-memcg limit, and the global consumption to the global limit, and
thus close this loophole.
Without a soft limit, the per-memcg memory pressure state in sockets is
generally questionable. However, we did it until now, so we continue to
enter it when the hard limit is hit, and packets are dropped, to let
other sockets in the cgroup know that they shouldn't grow their transmit
windows, either. However, keep it simple in the new callback model and
leave memory pressure lazily when the next packet is accepted (as
opposed to doing it synchroneously when packets are processed). When
packets are dropped, network performance will already be in the toilet,
so that should be a reasonable trade-off.
As described above, consumption is now checked on the per-memcg level
and the global level separately. Likewise, memory pressure states are
maintained on both the per-memcg level and the global level, and a
socket is considered under pressure when either level asserts as much.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-14 23:21:14 +00:00
|
|
|
}
|
2019-09-23 22:38:12 +00:00
|
|
|
|
|
|
|
extern int memcg_expand_shrinker_maps(int new_id);
|
|
|
|
|
|
|
|
extern void memcg_set_shrinker_bit(struct mem_cgroup *memcg,
|
|
|
|
int nid, int shrinker_id);
|
net: tcp_memcontrol: sanitize tcp memory accounting callbacks
There won't be a tcp control soft limit, so integrating the memcg code
into the global skmem limiting scheme complicates things unnecessarily.
Replace this with simple and clear charge and uncharge calls--hidden
behind a jump label--to account skb memory.
Note that this is not purely aesthetic: as a result of shoehorning the
per-memcg code into the same memory accounting functions that handle the
global level, the old code would compare the per-memcg consumption
against the smaller of the per-memcg limit and the global limit. This
allowed the total consumption of multiple sockets to exceed the global
limit, as long as the individual sockets stayed within bounds. After
this change, the code will always compare the per-memcg consumption to
the per-memcg limit, and the global consumption to the global limit, and
thus close this loophole.
Without a soft limit, the per-memcg memory pressure state in sockets is
generally questionable. However, we did it until now, so we continue to
enter it when the hard limit is hit, and packets are dropped, to let
other sockets in the cgroup know that they shouldn't grow their transmit
windows, either. However, keep it simple in the new callback model and
leave memory pressure lazily when the next packet is accepted (as
opposed to doing it synchroneously when packets are processed). When
packets are dropped, network performance will already be in the toilet,
so that should be a reasonable trade-off.
As described above, consumption is now checked on the per-memcg level
and the global level separately. Likewise, memory pressure states are
maintained on both the per-memcg level and the global level, and a
socket is considered under pressure when either level asserts as much.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-14 23:21:14 +00:00
|
|
|
#else
|
2016-01-14 23:21:20 +00:00
|
|
|
#define mem_cgroup_sockets_enabled 0
|
2016-10-08 00:00:58 +00:00
|
|
|
static inline void mem_cgroup_sk_alloc(struct sock *sk) { };
|
|
|
|
static inline void mem_cgroup_sk_free(struct sock *sk) { };
|
2016-01-14 23:21:17 +00:00
|
|
|
static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
|
net: tcp_memcontrol: sanitize tcp memory accounting callbacks
There won't be a tcp control soft limit, so integrating the memcg code
into the global skmem limiting scheme complicates things unnecessarily.
Replace this with simple and clear charge and uncharge calls--hidden
behind a jump label--to account skb memory.
Note that this is not purely aesthetic: as a result of shoehorning the
per-memcg code into the same memory accounting functions that handle the
global level, the old code would compare the per-memcg consumption
against the smaller of the per-memcg limit and the global limit. This
allowed the total consumption of multiple sockets to exceed the global
limit, as long as the individual sockets stayed within bounds. After
this change, the code will always compare the per-memcg consumption to
the per-memcg limit, and the global consumption to the global limit, and
thus close this loophole.
Without a soft limit, the per-memcg memory pressure state in sockets is
generally questionable. However, we did it until now, so we continue to
enter it when the hard limit is hit, and packets are dropped, to let
other sockets in the cgroup know that they shouldn't grow their transmit
windows, either. However, keep it simple in the new callback model and
leave memory pressure lazily when the next packet is accepted (as
opposed to doing it synchroneously when packets are processed). When
packets are dropped, network performance will already be in the toilet,
so that should be a reasonable trade-off.
As described above, consumption is now checked on the per-memcg level
and the global level separately. Likewise, memory pressure states are
maintained on both the per-memcg level and the global level, and a
socket is considered under pressure when either level asserts as much.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-14 23:21:14 +00:00
|
|
|
{
|
|
|
|
return false;
|
|
|
|
}
|
2019-09-23 22:38:12 +00:00
|
|
|
|
|
|
|
static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg,
|
|
|
|
int nid, int shrinker_id)
|
|
|
|
{
|
|
|
|
}
|
net: tcp_memcontrol: sanitize tcp memory accounting callbacks
There won't be a tcp control soft limit, so integrating the memcg code
into the global skmem limiting scheme complicates things unnecessarily.
Replace this with simple and clear charge and uncharge calls--hidden
behind a jump label--to account skb memory.
Note that this is not purely aesthetic: as a result of shoehorning the
per-memcg code into the same memory accounting functions that handle the
global level, the old code would compare the per-memcg consumption
against the smaller of the per-memcg limit and the global limit. This
allowed the total consumption of multiple sockets to exceed the global
limit, as long as the individual sockets stayed within bounds. After
this change, the code will always compare the per-memcg consumption to
the per-memcg limit, and the global consumption to the global limit, and
thus close this loophole.
Without a soft limit, the per-memcg memory pressure state in sockets is
generally questionable. However, we did it until now, so we continue to
enter it when the hard limit is hit, and packets are dropped, to let
other sockets in the cgroup know that they shouldn't grow their transmit
windows, either. However, keep it simple in the new callback model and
leave memory pressure lazily when the next packet is accepted (as
opposed to doing it synchroneously when packets are processed). When
packets are dropped, network performance will already be in the toilet,
so that should be a reasonable trade-off.
As described above, consumption is now checked on the per-memcg level
and the global level separately. Likewise, memory pressure states are
maintained on both the per-memcg level and the global level, and a
socket is considered under pressure when either level asserts as much.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-14 23:21:14 +00:00
|
|
|
#endif
|
2012-12-18 22:21:56 +00:00
|
|
|
|
2018-10-26 22:03:19 +00:00
|
|
|
#ifdef CONFIG_MEMCG_KMEM
|
2020-04-02 04:06:46 +00:00
|
|
|
int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order);
|
|
|
|
void __memcg_kmem_uncharge_page(struct page *page, int order);
|
2016-07-26 22:24:21 +00:00
|
|
|
|
2020-08-07 06:20:49 +00:00
|
|
|
struct obj_cgroup *get_obj_cgroup_from_current(void);
|
|
|
|
|
|
|
|
int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size);
|
|
|
|
void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size);
|
|
|
|
|
2016-01-14 23:21:34 +00:00
|
|
|
extern struct static_key_false memcg_kmem_enabled_key;
|
2012-12-18 22:23:01 +00:00
|
|
|
|
2015-02-12 22:58:57 +00:00
|
|
|
extern int memcg_nr_cache_ids;
|
2015-09-08 22:01:07 +00:00
|
|
|
void memcg_get_cache_ids(void);
|
|
|
|
void memcg_put_cache_ids(void);
|
2012-12-18 22:23:10 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Helper macro to loop through all memcg-specific caches. Callers must still
|
|
|
|
* check if the cache is valid (it is either valid or NULL).
|
|
|
|
* the slab_mutex must be held when looping through those caches
|
|
|
|
*/
|
2012-12-18 22:23:01 +00:00
|
|
|
#define for_each_memcg_cache_index(_idx) \
|
2015-02-12 22:58:57 +00:00
|
|
|
for ((_idx) = 0; (_idx) < memcg_nr_cache_ids; (_idx)++)
|
2012-12-18 22:23:01 +00:00
|
|
|
|
2012-12-18 22:21:56 +00:00
|
|
|
static inline bool memcg_kmem_enabled(void)
|
|
|
|
{
|
2020-08-07 06:21:47 +00:00
|
|
|
return static_branch_likely(&memcg_kmem_enabled_key);
|
2012-12-18 22:21:56 +00:00
|
|
|
}
|
|
|
|
|
2020-04-02 04:06:46 +00:00
|
|
|
static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp,
|
|
|
|
int order)
|
2019-03-05 23:43:13 +00:00
|
|
|
{
|
|
|
|
if (memcg_kmem_enabled())
|
2020-04-02 04:06:46 +00:00
|
|
|
return __memcg_kmem_charge_page(page, gfp, order);
|
2019-03-05 23:43:13 +00:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2020-04-02 04:06:46 +00:00
|
|
|
static inline void memcg_kmem_uncharge_page(struct page *page, int order)
|
2019-03-05 23:43:13 +00:00
|
|
|
{
|
|
|
|
if (memcg_kmem_enabled())
|
2020-04-02 04:06:46 +00:00
|
|
|
__memcg_kmem_uncharge_page(page, order);
|
2019-03-05 23:43:13 +00:00
|
|
|
}
|
|
|
|
|
2015-09-08 22:01:02 +00:00
|
|
|
/*
|
2020-12-15 03:06:45 +00:00
|
|
|
* A helper for accessing memcg's kmem_id, used for getting
|
|
|
|
* corresponding LRU lists.
|
2015-09-08 22:01:02 +00:00
|
|
|
*/
|
|
|
|
static inline int memcg_cache_id(struct mem_cgroup *memcg)
|
|
|
|
{
|
|
|
|
return memcg ? memcg->kmemcg_id : -1;
|
|
|
|
}
|
2014-04-07 22:39:24 +00:00
|
|
|
|
2020-03-29 02:17:25 +00:00
|
|
|
struct mem_cgroup *mem_cgroup_from_obj(void *p);
|
|
|
|
|
2012-12-18 22:21:56 +00:00
|
|
|
#else
|
2018-10-26 22:03:19 +00:00
|
|
|
|
2020-04-02 04:06:46 +00:00
|
|
|
static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp,
|
|
|
|
int order)
|
2018-10-26 22:03:19 +00:00
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2020-04-02 04:06:46 +00:00
|
|
|
static inline void memcg_kmem_uncharge_page(struct page *page, int order)
|
2018-10-26 22:03:19 +00:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2020-04-02 04:06:46 +00:00
|
|
|
static inline int __memcg_kmem_charge_page(struct page *page, gfp_t gfp,
|
|
|
|
int order)
|
2019-03-05 23:43:13 +00:00
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2020-04-02 04:06:46 +00:00
|
|
|
static inline void __memcg_kmem_uncharge_page(struct page *page, int order)
|
2019-03-05 23:43:13 +00:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2012-12-18 22:23:01 +00:00
|
|
|
#define for_each_memcg_cache_index(_idx) \
|
|
|
|
for (; NULL; )
|
|
|
|
|
2012-12-18 22:22:46 +00:00
|
|
|
static inline bool memcg_kmem_enabled(void)
|
|
|
|
{
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
2012-12-18 22:22:34 +00:00
|
|
|
static inline int memcg_cache_id(struct mem_cgroup *memcg)
|
|
|
|
{
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
2015-02-12 22:59:01 +00:00
|
|
|
static inline void memcg_get_cache_ids(void)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void memcg_put_cache_ids(void)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2020-03-29 02:17:25 +00:00
|
|
|
static inline struct mem_cgroup *mem_cgroup_from_obj(void *p)
|
|
|
|
{
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2018-08-17 22:47:25 +00:00
|
|
|
#endif /* CONFIG_MEMCG_KMEM */
|
2016-01-20 23:02:32 +00:00
|
|
|
|
2008-02-07 08:13:50 +00:00
|
|
|
#endif /* _LINUX_MEMCONTROL_H */
|