mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-10-31 16:38:12 +00:00
6d4675e601
The rmap locks(i_mmap_rwsem and anon_vma->root->rwsem) could be contended
under memory pressure if processes keep working on their vmas(e.g., fork,
mmap, munmap). It makes reclaim path stuck. In our real workload traces,
we see kswapd is waiting the lock for 300ms+(worst case, a sec) and it
makes other processes entering direct reclaim, which were also stuck on
the lock.
This patch makes lru aging path try_lock mode like shink_page_list so the
reclaim context will keep working with next lru pages without being stuck.
if it found the rmap lock contended, it rotates the page back to head of
lru in both active/inactive lrus to make them consistent behavior, which
is basic starting point rather than adding more heristic.
Since this patch introduces a new "contended" field as out-param along
with try_lock in-param in rmap_walk_control, it's not immutable any longer
if the try_lock is set so remove const keywords on rmap related functions.
Since rmap walking is already expensive operation, I doubt the const
would help sizable benefit( And we didn't have it until 5.17).
In a heavy app workload in Android, trace shows following statistics. It
almost removes rmap lock contention from reclaim path.
Martin Liu reported:
Before:
max_dur(ms) min_dur(ms) max-min(dur)ms avg_dur(ms) sum_dur(ms) count blocked_function
1632 0 1631 151.542173 31672 209 page_lock_anon_vma_read
601 0 601 145.544681 28817 198 rmap_walk_file
After:
max_dur(ms) min_dur(ms) max-min(dur)ms avg_dur(ms) sum_dur(ms) count blocked_function
NaN NaN NaN NaN NaN 0.0 NaN
0 0 0 0.127645 1 12 rmap_walk_file
[minchan@kernel.org: add comment, per Matthew]
Link: https://lkml.kernel.org/r/YnNqeB5tUf6LZ57b@google.com
Link: https://lkml.kernel.org/r/20220510215423.164547-1-minchan@kernel.org
Signed-off-by: Minchan Kim <minchan@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: John Dias <joaodias@google.com>
Cc: Tim Murray <timmurray@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Martin Liu <liumartin@google.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
92 lines
2.5 KiB
C
92 lines
2.5 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef __LINUX_KSM_H
|
|
#define __LINUX_KSM_H
|
|
/*
|
|
* Memory merging support.
|
|
*
|
|
* This code enables dynamic sharing of identical pages found in different
|
|
* memory areas, even if they are not shared by fork().
|
|
*/
|
|
|
|
#include <linux/bitops.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/rmap.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/sched/coredump.h>
|
|
|
|
struct stable_node;
|
|
struct mem_cgroup;
|
|
|
|
#ifdef CONFIG_KSM
|
|
int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
|
|
unsigned long end, int advice, unsigned long *vm_flags);
|
|
int __ksm_enter(struct mm_struct *mm);
|
|
void __ksm_exit(struct mm_struct *mm);
|
|
|
|
static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
|
|
{
|
|
if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags))
|
|
return __ksm_enter(mm);
|
|
return 0;
|
|
}
|
|
|
|
static inline void ksm_exit(struct mm_struct *mm)
|
|
{
|
|
if (test_bit(MMF_VM_MERGEABLE, &mm->flags))
|
|
__ksm_exit(mm);
|
|
}
|
|
|
|
/*
|
|
* When do_swap_page() first faults in from swap what used to be a KSM page,
|
|
* no problem, it will be assigned to this vma's anon_vma; but thereafter,
|
|
* it might be faulted into a different anon_vma (or perhaps to a different
|
|
* offset in the same anon_vma). do_swap_page() cannot do all the locking
|
|
* needed to reconstitute a cross-anon_vma KSM page: for now it has to make
|
|
* a copy, and leave remerging the pages to a later pass of ksmd.
|
|
*
|
|
* We'd like to make this conditional on vma->vm_flags & VM_MERGEABLE,
|
|
* but what if the vma was unmerged while the page was swapped out?
|
|
*/
|
|
struct page *ksm_might_need_to_copy(struct page *page,
|
|
struct vm_area_struct *vma, unsigned long address);
|
|
|
|
void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc);
|
|
void folio_migrate_ksm(struct folio *newfolio, struct folio *folio);
|
|
|
|
#else /* !CONFIG_KSM */
|
|
|
|
static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void ksm_exit(struct mm_struct *mm)
|
|
{
|
|
}
|
|
|
|
#ifdef CONFIG_MMU
|
|
static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
|
|
unsigned long end, int advice, unsigned long *vm_flags)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline struct page *ksm_might_need_to_copy(struct page *page,
|
|
struct vm_area_struct *vma, unsigned long address)
|
|
{
|
|
return page;
|
|
}
|
|
|
|
static inline void rmap_walk_ksm(struct folio *folio,
|
|
struct rmap_walk_control *rwc)
|
|
{
|
|
}
|
|
|
|
static inline void folio_migrate_ksm(struct folio *newfolio, struct folio *old)
|
|
{
|
|
}
|
|
#endif /* CONFIG_MMU */
|
|
#endif /* !CONFIG_KSM */
|
|
|
|
#endif /* __LINUX_KSM_H */
|