On Fri, 22 Apr 2011 14:39:24 +0900 (JST)
KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx> wrote:
> > +bool mem_cgroup_kswapd_can_sleep(void)
> > +{
> > + return list_empty(&memcg_kswapd_control.list);
> > +}
>
> and,
>
> > @@ -2583,40 +2585,46 @@ static void kswapd_try_to_sleep(struct kswapd *kswapd_p, int order,
> > } else {
> > + /* For now, we just check the remaining works.*/
> > + if (mem_cgroup_kswapd_can_sleep())
> > + schedule();
>
> has bad assumption. If freeable memory is very little and kswapds are
> contended, memcg-kswap also have to give up and go into sleep as global
> kswapd.
>
> Otherwise, We are going to see kswapd cpu 100% consumption issue again.
>
Hmm, ok. need to add more logics. Is it ok to have add-on patch like this ?
I'll consider some more smart and fair....
==
Because memcg-kswapd push back memcg to the list when there is remaining work,
it may consume too much cpu when it finds hard-to-reclaim-memcg.
This patch adds a penalty to hard-to-reclaim memcg and reduces chance to
be scheduled again.
---
include/linux/memcontrol.h | 2 +-
mm/memcontrol.c | 14 +++++++++++---
mm/vmscan.c | 4 ++--
3 files changed, 14 insertions(+), 6 deletions(-)
Index: mmotm-Apr14/include/linux/memcontrol.h
===================================================================
--- mmotm-Apr14.orig/include/linux/memcontrol.h
+++ mmotm-Apr14/include/linux/memcontrol.h
@@ -96,7 +96,7 @@ extern int mem_cgroup_select_victim_node
extern bool mem_cgroup_kswapd_can_sleep(void);
extern struct mem_cgroup *mem_cgroup_get_shrink_target(void);
-extern void mem_cgroup_put_shrink_target(struct mem_cgroup *mem);
+extern void mem_cgroup_put_shrink_target(struct mem_cgroup *mem, int pages);
extern wait_queue_head_t *mem_cgroup_kswapd_waitq(void);
extern int mem_cgroup_kswapd_bonus(struct mem_cgroup *mem);
Index: mmotm-Apr14/mm/memcontrol.c
===================================================================
--- mmotm-Apr14.orig/mm/memcontrol.c
+++ mmotm-Apr14/mm/memcontrol.c
@@ -4739,6 +4739,10 @@ struct mem_cgroup *mem_cgroup_get_shrink
memcg_kswapd_wait_list);
list_del_init(&mem->memcg_kswapd_wait_list);
}
+ if (mem && mem->stalled) {
+ mem->stalled--; /* This memcg was cpu hog */
+ continue;
+ }
} while (mem && !css_tryget(&mem->css));
if (mem)
atomic_inc(&mem->kswapd_running);
@@ -4747,7 +4751,7 @@ struct mem_cgroup *mem_cgroup_get_shrink
return mem;
}
-void mem_cgroup_put_shrink_target(struct mem_cgroup *mem)
+void mem_cgroup_put_shrink_target(struct mem_cgroup *mem, int nr_pages)
{
if (!mem)
return;
@@ -4755,8 +4759,12 @@ void mem_cgroup_put_shrink_target(struct
if (!mem_cgroup_watermark_ok(mem, CHARGE_WMARK_HIGH)) {
spin_lock(&memcg_kswapd_control.lock);
if (list_empty(&mem->memcg_kswapd_wait_list)) {
- list_add_tail(&mem->memcg_kswapd_wait_list,
- &memcg_kswapd_control.list);
+ /* If memory reclaim was smooth, resched it */
+ if (nr_pages >= SWAP_CLUSTER_MAX/2)
+ list_add_tail(&mem->memcg_kswapd_wait_list,
+ &memcg_kswapd_control.list);
+ else
+ mem->stalled += 1; /* ignore this memcg for a while */
}
spin_unlock(&memcg_kswapd_control.lock);
}
Index: mmotm-Apr14/mm/vmscan.c
===================================================================
--- mmotm-Apr14.orig/mm/vmscan.c
+++ mmotm-Apr14/mm/vmscan.c
@@ -2892,8 +2892,8 @@ int kswapd(void *p)
} else {
mem = mem_cgroup_get_shrink_target();
if (mem)
- shrink_mem_cgroup(mem, order);
- mem_cgroup_put_shrink_target(mem);
+ ret = shrink_mem_cgroup(mem, order);
+ mem_cgroup_put_shrink_target(mem, ret);
}
}
return 0;
==
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxxx For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>