mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-14 06:35:12 +00:00
408587baee
With memcg v2 enabled, memcg->memory.usage is a very hot member for the workloads doing memcg charging on multiple CPUs concurrently. Particularly the network intensive workloads. In addition, there is a false cache sharing between memory.usage and memory.high on the charge path. This patch moves the usage into a separate cacheline and move all the read most fields into separate cacheline. To evaluate the impact of this optimization, on a 72 CPUs machine, we ran the following workload in a three level of cgroup hierarchy. $ netserver -6 # 36 instances of netperf with following params $ netperf -6 -H ::1 -l 60 -t TCP_SENDFILE -- -m 10K Results (average throughput of netperf): Without (6.0-rc1) 10482.7 Mbps With patch 12413.7 Mbps (18.4% improvement) With the patch, the throughput improved by 18.4%. One side-effect of this patch is the increase in the size of struct mem_cgroup. For example with this patch on 64 bit build, the size of struct mem_cgroup increased from 4032 bytes to 4416 bytes. However for the performance improvement, this additional size is worth it. In addition there are opportunities to reduce the size of struct mem_cgroup like deprecation of kmem and tcpmem page counters and better packing. Link: https://lkml.kernel.org/r/20220825000506.239406-3-shakeelb@google.com Signed-off-by: Shakeel Butt <shakeelb@google.com> Reported-by: kernel test robot <oliver.sang@intel.com> Reviewed-by: Feng Tang <feng.tang@intel.com> Acked-by: Soheil Hassas Yeganeh <soheil@google.com> Acked-by: Roman Gushchin <roman.gushchin@linux.dev> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Michal Koutný" <mkoutny@suse.com> Cc: Muchun Song <songmuchun@bytedance.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
93 lines
2.6 KiB
C
93 lines
2.6 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _LINUX_PAGE_COUNTER_H
|
|
#define _LINUX_PAGE_COUNTER_H
|
|
|
|
#include <linux/atomic.h>
|
|
#include <linux/cache.h>
|
|
#include <linux/kernel.h>
|
|
#include <asm/page.h>
|
|
|
|
#if defined(CONFIG_SMP)
|
|
struct pc_padding {
|
|
char x[0];
|
|
} ____cacheline_internodealigned_in_smp;
|
|
#define PC_PADDING(name) struct pc_padding name
|
|
#else
|
|
#define PC_PADDING(name)
|
|
#endif
|
|
|
|
struct page_counter {
|
|
/*
|
|
* Make sure 'usage' does not share cacheline with any other field. The
|
|
* memcg->memory.usage is a hot member of struct mem_cgroup.
|
|
*/
|
|
atomic_long_t usage;
|
|
PC_PADDING(_pad1_);
|
|
|
|
/* effective memory.min and memory.min usage tracking */
|
|
unsigned long emin;
|
|
atomic_long_t min_usage;
|
|
atomic_long_t children_min_usage;
|
|
|
|
/* effective memory.low and memory.low usage tracking */
|
|
unsigned long elow;
|
|
atomic_long_t low_usage;
|
|
atomic_long_t children_low_usage;
|
|
|
|
unsigned long watermark;
|
|
unsigned long failcnt;
|
|
|
|
/* Keep all the read most fields in a separete cacheline. */
|
|
PC_PADDING(_pad2_);
|
|
|
|
unsigned long min;
|
|
unsigned long low;
|
|
unsigned long high;
|
|
unsigned long max;
|
|
struct page_counter *parent;
|
|
} ____cacheline_internodealigned_in_smp;
|
|
|
|
#if BITS_PER_LONG == 32
|
|
#define PAGE_COUNTER_MAX LONG_MAX
|
|
#else
|
|
#define PAGE_COUNTER_MAX (LONG_MAX / PAGE_SIZE)
|
|
#endif
|
|
|
|
static inline void page_counter_init(struct page_counter *counter,
|
|
struct page_counter *parent)
|
|
{
|
|
atomic_long_set(&counter->usage, 0);
|
|
counter->max = PAGE_COUNTER_MAX;
|
|
counter->parent = parent;
|
|
}
|
|
|
|
static inline unsigned long page_counter_read(struct page_counter *counter)
|
|
{
|
|
return atomic_long_read(&counter->usage);
|
|
}
|
|
|
|
void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages);
|
|
void page_counter_charge(struct page_counter *counter, unsigned long nr_pages);
|
|
bool page_counter_try_charge(struct page_counter *counter,
|
|
unsigned long nr_pages,
|
|
struct page_counter **fail);
|
|
void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages);
|
|
void page_counter_set_min(struct page_counter *counter, unsigned long nr_pages);
|
|
void page_counter_set_low(struct page_counter *counter, unsigned long nr_pages);
|
|
|
|
static inline void page_counter_set_high(struct page_counter *counter,
|
|
unsigned long nr_pages)
|
|
{
|
|
WRITE_ONCE(counter->high, nr_pages);
|
|
}
|
|
|
|
int page_counter_set_max(struct page_counter *counter, unsigned long nr_pages);
|
|
int page_counter_memparse(const char *buf, const char *max,
|
|
unsigned long *nr_pages);
|
|
|
|
static inline void page_counter_reset_watermark(struct page_counter *counter)
|
|
{
|
|
counter->watermark = page_counter_read(counter);
|
|
}
|
|
|
|
#endif /* _LINUX_PAGE_COUNTER_H */
|