include/linux/swap.h | 6 ++++++ mm/memcontrol.c | 8 ++++++++ mm/vmscan.c | 27 +++++++++++++++++++++++++++ 3 files changed, 41 insertions(+)
When spaces of swap devices are exhausted, only file pages can be
reclaimed. But there are still some swapcache pages in anon lru list.
This can lead to a premature out-of-memory.
The problem is found with such step:
Firstly, set a 9MB disk swap space, then create a cgroup with 10MB
memory limit, then runs an program to allocates about 15MB memory.
The problem occurs occasionally, which may need about 100 times [1].
Fix it by checking number of swapcache pages in can_reclaim_anon_pages().
If the number is not zero, return true and set swapcache_only to 1.
When scan anon lru list in swapcache_only mode, non-swapcache pages will
be skipped to isolate in order to accelerate reclaim efficiency.
However, in swapcache_only mode, the scan count still increased when scan
non-swapcache pages because there are large number of non-swapcache pages
and rare swapcache pages in swapcache_only mode, and if the non-swapcache
is skipped and do not count, the scan of pages in isolate_lru_folios() can
eventually lead to hung task, just as Sachin reported [2].
By the way, since there are enough times of memory reclaim before OOM, it
is not need to isolate too much swapcache pages in one times.
[1]. https://lore.kernel.org/lkml/CAJD7tkZAfgncV+KbKr36=eDzMnT=9dZOT0dpMWcurHLr6Do+GA@mail.gmail.com/
[2]. https://lore.kernel.org/linux-mm/CAJD7tkafz_2XAuqE8tGLPEcpLngewhUo=5US14PAtSM9tLBUQg@mail.gmail.com/
Signed-off-by: Liu Shixin <liushixin2@huawei.com>
Tested-by: Yosry Ahmed <yosryahmed@google.com>
Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
Reviewed-by: Yosry Ahmed <yosryahmed@google.com>
---
v7->v8: Reset swapcache_only at the beginning of can_reclaim_anon_pages().
v6->v7: Reset swapcache_only to zero after there are swap spaces.
v5->v6: Fix NULL pointing derefence and hung task problem reported by Sachin.
include/linux/swap.h | 6 ++++++
mm/memcontrol.c | 8 ++++++++
mm/vmscan.c | 27 +++++++++++++++++++++++++++
3 files changed, 41 insertions(+)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index f6dd6575b905..3ba146ae7cf5 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -659,6 +659,7 @@ static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_p
}
extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg);
+extern long mem_cgroup_get_nr_swapcache_pages(struct mem_cgroup *memcg);
extern bool mem_cgroup_swap_full(struct folio *folio);
#else
static inline void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry)
@@ -681,6 +682,11 @@ static inline long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg)
return get_nr_swap_pages();
}
+static inline long mem_cgroup_get_nr_swapcache_pages(struct mem_cgroup *memcg)
+{
+ return total_swapcache_pages();
+}
+
static inline bool mem_cgroup_swap_full(struct folio *folio)
{
return vm_swap_full();
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 5b009b233ab8..29e34c06ca83 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -7584,6 +7584,14 @@ long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg)
return nr_swap_pages;
}
+long mem_cgroup_get_nr_swapcache_pages(struct mem_cgroup *memcg)
+{
+ if (mem_cgroup_disabled())
+ return total_swapcache_pages();
+
+ return memcg_page_state(memcg, NR_SWAPCACHE);
+}
+
bool mem_cgroup_swap_full(struct folio *folio)
{
struct mem_cgroup *memcg;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 6f13394b112e..5d5a169ec98c 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -137,6 +137,9 @@ struct scan_control {
/* Always discard instead of demoting to lower tier memory */
unsigned int no_demotion:1;
+ /* Swap space is exhausted, only reclaim swapcache for anon LRU */
+ unsigned int swapcache_only:1;
+
/* Allocation order */
s8 order;
@@ -606,6 +609,9 @@ static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg,
int nid,
struct scan_control *sc)
{
+ if (sc)
+ sc->swapcache_only = 0;
+
if (memcg == NULL) {
/*
* For non-memcg reclaim, is there
@@ -613,10 +619,22 @@ static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg,
*/
if (get_nr_swap_pages() > 0)
return true;
+ /* Is there any swapcache pages to reclaim? */
+ if (total_swapcache_pages() > 0) {
+ if (sc)
+ sc->swapcache_only = 1;
+ return true;
+ }
} else {
/* Is the memcg below its swap limit? */
if (mem_cgroup_get_nr_swap_pages(memcg) > 0)
return true;
+ /* Is there any swapcache pages in memcg to reclaim? */
+ if (mem_cgroup_get_nr_swapcache_pages(memcg) > 0) {
+ if (sc)
+ sc->swapcache_only = 1;
+ return true;
+ }
}
/*
@@ -2342,6 +2360,15 @@ static unsigned long isolate_lru_folios(unsigned long nr_to_scan,
*/
scan += nr_pages;
+ /*
+ * Count non-swapcache too because the swapcache pages may
+ * be rare and it takes too much times here if not count
+ * the non-swapcache pages.
+ */
+ if (unlikely(sc->swapcache_only && !is_file_lru(lru) &&
+ !folio_test_swapcache(folio)))
+ goto move;
+
if (!folio_test_lru(folio))
goto move;
if (!sc->may_unmap && folio_mapped(folio))
--
2.25.1Liu Shixin <liushixin2@huawei.com> writes:
> When spaces of swap devices are exhausted, only file pages can be
> reclaimed. But there are still some swapcache pages in anon lru list.
> This can lead to a premature out-of-memory.
>
> The problem is found with such step:
>
> Firstly, set a 9MB disk swap space, then create a cgroup with 10MB
> memory limit, then runs an program to allocates about 15MB memory.
>
> The problem occurs occasionally, which may need about 100 times [1].
>
> Fix it by checking number of swapcache pages in can_reclaim_anon_pages().
> If the number is not zero, return true and set swapcache_only to 1.
> When scan anon lru list in swapcache_only mode, non-swapcache pages will
> be skipped to isolate in order to accelerate reclaim efficiency.
>
> However, in swapcache_only mode, the scan count still increased when scan
> non-swapcache pages because there are large number of non-swapcache pages
> and rare swapcache pages in swapcache_only mode, and if the non-swapcache
> is skipped and do not count, the scan of pages in isolate_lru_folios() can
> eventually lead to hung task, just as Sachin reported [2].
>
> By the way, since there are enough times of memory reclaim before OOM, it
> is not need to isolate too much swapcache pages in one times.
>
> [1]. https://lore.kernel.org/lkml/CAJD7tkZAfgncV+KbKr36=eDzMnT=9dZOT0dpMWcurHLr6Do+GA@mail.gmail.com/
> [2]. https://lore.kernel.org/linux-mm/CAJD7tkafz_2XAuqE8tGLPEcpLngewhUo=5US14PAtSM9tLBUQg@mail.gmail.com/
>
> Signed-off-by: Liu Shixin <liushixin2@huawei.com>
> Tested-by: Yosry Ahmed <yosryahmed@google.com>
> Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
> Reviewed-by: Yosry Ahmed <yosryahmed@google.com>
> ---
> v7->v8: Reset swapcache_only at the beginning of can_reclaim_anon_pages().
> v6->v7: Reset swapcache_only to zero after there are swap spaces.
> v5->v6: Fix NULL pointing derefence and hung task problem reported by Sachin.
>
> include/linux/swap.h | 6 ++++++
> mm/memcontrol.c | 8 ++++++++
> mm/vmscan.c | 27 +++++++++++++++++++++++++++
> 3 files changed, 41 insertions(+)
>
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index f6dd6575b905..3ba146ae7cf5 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -659,6 +659,7 @@ static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_p
> }
>
> extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg);
> +extern long mem_cgroup_get_nr_swapcache_pages(struct mem_cgroup *memcg);
> extern bool mem_cgroup_swap_full(struct folio *folio);
> #else
> static inline void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry)
> @@ -681,6 +682,11 @@ static inline long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg)
> return get_nr_swap_pages();
> }
>
> +static inline long mem_cgroup_get_nr_swapcache_pages(struct mem_cgroup *memcg)
> +{
> + return total_swapcache_pages();
> +}
> +
> static inline bool mem_cgroup_swap_full(struct folio *folio)
> {
> return vm_swap_full();
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 5b009b233ab8..29e34c06ca83 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -7584,6 +7584,14 @@ long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg)
> return nr_swap_pages;
> }
>
> +long mem_cgroup_get_nr_swapcache_pages(struct mem_cgroup *memcg)
> +{
> + if (mem_cgroup_disabled())
> + return total_swapcache_pages();
> +
> + return memcg_page_state(memcg, NR_SWAPCACHE);
> +}
> +
> bool mem_cgroup_swap_full(struct folio *folio)
> {
> struct mem_cgroup *memcg;
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 6f13394b112e..5d5a169ec98c 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -137,6 +137,9 @@ struct scan_control {
> /* Always discard instead of demoting to lower tier memory */
> unsigned int no_demotion:1;
>
> + /* Swap space is exhausted, only reclaim swapcache for anon LRU */
> + unsigned int swapcache_only:1;
> +
> /* Allocation order */
> s8 order;
>
> @@ -606,6 +609,9 @@ static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg,
> int nid,
> struct scan_control *sc)
> {
> + if (sc)
> + sc->swapcache_only = 0;
> +
> if (memcg == NULL) {
> /*
> * For non-memcg reclaim, is there
> @@ -613,10 +619,22 @@ static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg,
> */
> if (get_nr_swap_pages() > 0)
> return true;
> + /* Is there any swapcache pages to reclaim? */
> + if (total_swapcache_pages() > 0) {
> + if (sc)
> + sc->swapcache_only = 1;
> + return true;
> + }
> } else {
> /* Is the memcg below its swap limit? */
> if (mem_cgroup_get_nr_swap_pages(memcg) > 0)
> return true;
> + /* Is there any swapcache pages in memcg to reclaim? */
> + if (mem_cgroup_get_nr_swapcache_pages(memcg) > 0) {
> + if (sc)
> + sc->swapcache_only = 1;
> + return true;
> + }
> }
I understand that this is only possible in theory. But if can_demote()
== true, get_nr_swap_pages() == 0, total_swapcache_pages() > 0, we will
demote only anonymous pages in swapcache. I think that this isn't
reasonable. So, swapcache pages should be checked after can_demote()
checking.
--
Best Regards,
Huang, Ying
> /*
> @@ -2342,6 +2360,15 @@ static unsigned long isolate_lru_folios(unsigned long nr_to_scan,
> */
> scan += nr_pages;
>
> + /*
> + * Count non-swapcache too because the swapcache pages may
> + * be rare and it takes too much times here if not count
> + * the non-swapcache pages.
> + */
> + if (unlikely(sc->swapcache_only && !is_file_lru(lru) &&
> + !folio_test_swapcache(folio)))
> + goto move;
> +
> if (!folio_test_lru(folio))
> goto move;
> if (!sc->may_unmap && folio_mapped(folio))
On 2023/11/6 14:57, Huang, Ying wrote:
> Liu Shixin <liushixin2@huawei.com> writes:
>
>> When spaces of swap devices are exhausted, only file pages can be
>> reclaimed. But there are still some swapcache pages in anon lru list.
>> This can lead to a premature out-of-memory.
>>
>> The problem is found with such step:
>>
>> Firstly, set a 9MB disk swap space, then create a cgroup with 10MB
>> memory limit, then runs an program to allocates about 15MB memory.
>>
>> The problem occurs occasionally, which may need about 100 times [1].
>>
>> Fix it by checking number of swapcache pages in can_reclaim_anon_pages().
>> If the number is not zero, return true and set swapcache_only to 1.
>> When scan anon lru list in swapcache_only mode, non-swapcache pages will
>> be skipped to isolate in order to accelerate reclaim efficiency.
>>
>> However, in swapcache_only mode, the scan count still increased when scan
>> non-swapcache pages because there are large number of non-swapcache pages
>> and rare swapcache pages in swapcache_only mode, and if the non-swapcache
>> is skipped and do not count, the scan of pages in isolate_lru_folios() can
>> eventually lead to hung task, just as Sachin reported [2].
>>
>> By the way, since there are enough times of memory reclaim before OOM, it
>> is not need to isolate too much swapcache pages in one times.
>>
>> [1]. https://lore.kernel.org/lkml/CAJD7tkZAfgncV+KbKr36=eDzMnT=9dZOT0dpMWcurHLr6Do+GA@mail.gmail.com/
>> [2]. https://lore.kernel.org/linux-mm/CAJD7tkafz_2XAuqE8tGLPEcpLngewhUo=5US14PAtSM9tLBUQg@mail.gmail.com/
>>
>> Signed-off-by: Liu Shixin <liushixin2@huawei.com>
>> Tested-by: Yosry Ahmed <yosryahmed@google.com>
>> Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
>> Reviewed-by: Yosry Ahmed <yosryahmed@google.com>
>> ---
>> v7->v8: Reset swapcache_only at the beginning of can_reclaim_anon_pages().
>> v6->v7: Reset swapcache_only to zero after there are swap spaces.
>> v5->v6: Fix NULL pointing derefence and hung task problem reported by Sachin.
>>
>> include/linux/swap.h | 6 ++++++
>> mm/memcontrol.c | 8 ++++++++
>> mm/vmscan.c | 27 +++++++++++++++++++++++++++
>> 3 files changed, 41 insertions(+)
>>
>> diff --git a/include/linux/swap.h b/include/linux/swap.h
>> index f6dd6575b905..3ba146ae7cf5 100644
>> --- a/include/linux/swap.h
>> +++ b/include/linux/swap.h
>> @@ -659,6 +659,7 @@ static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_p
>> }
>>
>> extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg);
>> +extern long mem_cgroup_get_nr_swapcache_pages(struct mem_cgroup *memcg);
>> extern bool mem_cgroup_swap_full(struct folio *folio);
>> #else
>> static inline void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry)
>> @@ -681,6 +682,11 @@ static inline long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg)
>> return get_nr_swap_pages();
>> }
>>
>> +static inline long mem_cgroup_get_nr_swapcache_pages(struct mem_cgroup *memcg)
>> +{
>> + return total_swapcache_pages();
>> +}
>> +
>> static inline bool mem_cgroup_swap_full(struct folio *folio)
>> {
>> return vm_swap_full();
>> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
>> index 5b009b233ab8..29e34c06ca83 100644
>> --- a/mm/memcontrol.c
>> +++ b/mm/memcontrol.c
>> @@ -7584,6 +7584,14 @@ long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg)
>> return nr_swap_pages;
>> }
>>
>> +long mem_cgroup_get_nr_swapcache_pages(struct mem_cgroup *memcg)
>> +{
>> + if (mem_cgroup_disabled())
>> + return total_swapcache_pages();
>> +
>> + return memcg_page_state(memcg, NR_SWAPCACHE);
>> +}
>> +
>> bool mem_cgroup_swap_full(struct folio *folio)
>> {
>> struct mem_cgroup *memcg;
>> diff --git a/mm/vmscan.c b/mm/vmscan.c
>> index 6f13394b112e..5d5a169ec98c 100644
>> --- a/mm/vmscan.c
>> +++ b/mm/vmscan.c
>> @@ -137,6 +137,9 @@ struct scan_control {
>> /* Always discard instead of demoting to lower tier memory */
>> unsigned int no_demotion:1;
>>
>> + /* Swap space is exhausted, only reclaim swapcache for anon LRU */
>> + unsigned int swapcache_only:1;
>> +
>> /* Allocation order */
>> s8 order;
>>
>> @@ -606,6 +609,9 @@ static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg,
>> int nid,
>> struct scan_control *sc)
>> {
>> + if (sc)
>> + sc->swapcache_only = 0;
>> +
>> if (memcg == NULL) {
>> /*
>> * For non-memcg reclaim, is there
>> @@ -613,10 +619,22 @@ static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg,
>> */
>> if (get_nr_swap_pages() > 0)
>> return true;
>> + /* Is there any swapcache pages to reclaim? */
>> + if (total_swapcache_pages() > 0) {
>> + if (sc)
>> + sc->swapcache_only = 1;
>> + return true;
>> + }
>> } else {
>> /* Is the memcg below its swap limit? */
>> if (mem_cgroup_get_nr_swap_pages(memcg) > 0)
>> return true;
>> + /* Is there any swapcache pages in memcg to reclaim? */
>> + if (mem_cgroup_get_nr_swapcache_pages(memcg) > 0) {
>> + if (sc)
>> + sc->swapcache_only = 1;
>> + return true;
>> + }
>> }
> I understand that this is only possible in theory. But if can_demote()
> == true, get_nr_swap_pages() == 0, total_swapcache_pages() > 0, we will
> demote only anonymous pages in swapcache. I think that this isn't
> reasonable. So, swapcache pages should be checked after can_demote()
> checking.
>
> --
> Best Regards,
> Huang, Ying
Thanks for your advise, that sounds more reasonable. I will modify it soon.
>
>> /*
>> @@ -2342,6 +2360,15 @@ static unsigned long isolate_lru_folios(unsigned long nr_to_scan,
>> */
>> scan += nr_pages;
>>
>> + /*
>> + * Count non-swapcache too because the swapcache pages may
>> + * be rare and it takes too much times here if not count
>> + * the non-swapcache pages.
>> + */
>> + if (unlikely(sc->swapcache_only && !is_file_lru(lru) &&
>> + !folio_test_swapcache(folio)))
>> + goto move;
>> +
>> if (!folio_test_lru(folio))
>> goto move;
>> if (!sc->may_unmap && folio_mapped(folio))
> .
>
© 2016 - 2025 Red Hat, Inc.