lkml.org 
[lkml]   [2019]   [Jul]   [28]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Subject[PATCH RFC] mm/memcontrol: reclaim severe usage over high limit in get_user_pages loop
From
Date
High memory limit in memory cgroup allows to batch memory reclaiming and
defer it until returning into userland. This moves it out of any locks.

Fixed gap between high and max limit works pretty well (we are using
64 * NR_CPUS pages) except cases when one syscall allocates tons of
memory. This affects all other tasks in cgroup because they might hit
max memory limit in unhandy places and\or under hot locks.

For example mmap with MAP_POPULATE or MAP_LOCKED might allocate a lot
of pages and push memory cgroup usage far ahead high memory limit.

This patch uses halfway between high and max limits as threshold and
in this case starts memory reclaiming if mem_cgroup_handle_over_high()
called with argument only_severe = true, otherwise reclaim is deferred
till returning into userland. If high limits isn't set nothing changes.

Now long running get_user_pages will periodically reclaim cgroup memory.
Other possible targets are generic file read/write iter loops.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
---
include/linux/memcontrol.h | 4 ++--
include/linux/tracehook.h | 2 +-
mm/gup.c | 5 ++++-
mm/memcontrol.c | 17 ++++++++++++++++-
4 files changed, 23 insertions(+), 5 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 44c41462be33..eca2bf9560f2 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -512,7 +512,7 @@ unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec,
return mz->lru_zone_size[zone_idx][lru];
}

-void mem_cgroup_handle_over_high(void);
+void mem_cgroup_handle_over_high(bool only_severe);

unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg);

@@ -969,7 +969,7 @@ static inline void unlock_page_memcg(struct page *page)
{
}

-static inline void mem_cgroup_handle_over_high(void)
+static inline void mem_cgroup_handle_over_high(bool only_severe)
{
}

diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h
index 36fb3bbed6b2..8845fb65353f 100644
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -194,7 +194,7 @@ static inline void tracehook_notify_resume(struct pt_regs *regs)
}
#endif

- mem_cgroup_handle_over_high();
+ mem_cgroup_handle_over_high(false);
blkcg_maybe_throttle_current();
}

diff --git a/mm/gup.c b/mm/gup.c
index 98f13ab37bac..42b93fffe824 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -847,8 +847,11 @@ static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
ret = -ERESTARTSYS;
goto out;
}
- cond_resched();

+ /* Reclaim memory over high limit before stocking too much */
+ mem_cgroup_handle_over_high(true);
+
+ cond_resched();
page = follow_page_mask(vma, start, foll_flags, &ctx);
if (!page) {
ret = faultin_page(tsk, vma, start, &foll_flags,
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index cdbb7a84cb6e..15fa664ce98c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2317,11 +2317,16 @@ static void high_work_func(struct work_struct *work)
reclaim_high(memcg, MEMCG_CHARGE_BATCH, GFP_KERNEL);
}

+#define MEMCG_SEVERE_OVER_HIGH (1 << 31)
+
/*
* Scheduled by try_charge() to be executed from the userland return path
* and reclaims memory over the high limit.
+ *
+ * Long allocation loops should call periodically with only_severe = true
+ * to reclaim memory if usage already over halfway to the max limit.
*/
-void mem_cgroup_handle_over_high(void)
+void mem_cgroup_handle_over_high(bool only_severe)
{
unsigned int nr_pages = current->memcg_nr_pages_over_high;
struct mem_cgroup *memcg;
@@ -2329,6 +2334,11 @@ void mem_cgroup_handle_over_high(void)
if (likely(!nr_pages))
return;

+ if (nr_pages & MEMCG_SEVERE_OVER_HIGH)
+ nr_pages -= MEMCG_SEVERE_OVER_HIGH;
+ else if (only_severe)
+ return;
+
memcg = get_mem_cgroup_from_mm(current->mm);
reclaim_high(memcg, nr_pages, GFP_KERNEL);
css_put(&memcg->css);
@@ -2493,6 +2503,11 @@ static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
schedule_work(&memcg->high_work);
break;
}
+ /* Mark as severe if over halfway to the max limit */
+ if (page_counter_read(&memcg->memory) >
+ (memcg->high >> 1) + (memcg->memory.max >> 1))
+ current->memcg_nr_pages_over_high |=
+ MEMCG_SEVERE_OVER_HIGH;
current->memcg_nr_pages_over_high += batch;
set_notify_resume(current);
break;
\
 
 \ /
  Last update: 2019-07-28 14:34    [W:0.145 / U:3.448 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site