On Fri 23-03-18 12:04:16, Li,Rongqing wrote:
[...]
> shrink_slab does not reclaim any memory, but take lots of time to
> count lru
>
> maybe we can use the returning of shrink_slab to control if next
> shrink_slab should be called?
How? Different memcgs might have different amount of shrinkable me
> > 发送时间: 2018年3月19日 18:52
> > > 收件人: Michal Hocko
> > > 抄送: linux-kernel@vger.kernel.org; linux...@kvack.org;
> > > cgro...@vger.kernel.org; han...@cmpxchg.org; Andrey Ryabinin
> > >
> > > 主题: 答复: 答复: [PATCH] mm/memcontrol.c: speed up to force
> empty
r.kernel.org; linux...@kvack.org;
> > cgro...@vger.kernel.org; han...@cmpxchg.org; Andrey Ryabinin
> >
> > 主题: 答复: 答复: [PATCH] mm/memcontrol.c: speed up to force empty a
> > memory cgroup
> >
> >
> >
> > > -邮件原件-
> > > 发件人: Michal
Ryabinin
>
> 主题: 答复: 答复: [PATCH] mm/memcontrol.c: speed up to force empty a
> memory cgroup
>
>
>
> > -邮件原件-
> > 发件人: Michal Hocko [mailto:mho...@kernel.org]
> > 发送时间: 2018年3月19日 18:38
> > 收件人: Li,Rongqing
> > 抄送: linux-kernel@
On Wed 21-03-18 01:35:05, Andrey Ryabinin wrote:
> On 03/21/2018 01:15 AM, David Rientjes wrote:
> > On Wed, 21 Mar 2018, Andrey Ryabinin wrote:
> >
> > It would probably be best to limit the
> > nr_pages to the amount that needs to be reclaimed, though, rather than
> > over reclaimi
On Wed, 21 Mar 2018, Andrey Ryabinin wrote:
> > Is SWAP_CLUSTER_MAX the best answer if I'm lowering the limit by 1GB?
> >
>
> Absolutely not. I completely on your side here.
> I've tried to fix this recently -
> http://lkml.kernel.org/r/20180119132544.19569-2-aryabi...@virtuozzo.com
> I guess
On 03/21/2018 01:15 AM, David Rientjes wrote:
> On Wed, 21 Mar 2018, Andrey Ryabinin wrote:
>
> It would probably be best to limit the
> nr_pages to the amount that needs to be reclaimed, though, rather than
> over reclaiming.
How do you achieve that? The charging path is n
On Wed, 21 Mar 2018, Andrey Ryabinin wrote:
> >>> It would probably be best to limit the
> >>> nr_pages to the amount that needs to be reclaimed, though, rather than
> >>> over reclaiming.
> >>
> >> How do you achieve that? The charging path is not synchornized with the
> >> shrinking one at all
On 03/20/2018 11:29 PM, David Rientjes wrote:
> On Tue, 20 Mar 2018, Michal Hocko wrote:
>
>> Although SWAP_CLUSTER_MAX is used at the lower level, but the call
>> stack of try_to_free_mem_cgroup_pages is too long, increase the
>> nr_to_reclaim can reduce times of calling
>> func
On Tue, 20 Mar 2018, Michal Hocko wrote:
> > > > > Although SWAP_CLUSTER_MAX is used at the lower level, but the call
> > > > > stack of try_to_free_mem_cgroup_pages is too long, increase the
> > > > > nr_to_reclaim can reduce times of calling
> > > > > function[do_try_to_free_pages, shrink_zones,
On Mon 19-03-18 10:51:57, David Rientjes wrote:
> On Mon, 19 Mar 2018, Li,Rongqing wrote:
>
> > > > Although SWAP_CLUSTER_MAX is used at the lower level, but the call
> > > > stack of try_to_free_mem_cgroup_pages is too long, increase the
> > > > nr_to_reclaim can reduce times of calling
> > > > f
On Mon, 19 Mar 2018, Li,Rongqing wrote:
> > > Although SWAP_CLUSTER_MAX is used at the lower level, but the call
> > > stack of try_to_free_mem_cgroup_pages is too long, increase the
> > > nr_to_reclaim can reduce times of calling
> > > function[do_try_to_free_pages, shrink_zones, hrink_node ]
> >
> -邮件原件-
> 发件人: Michal Hocko [mailto:mho...@kernel.org]
> 发送时间: 2018年3月19日 18:38
> 收件人: Li,Rongqing
> 抄送: linux-kernel@vger.kernel.org; linux...@kvack.org;
> cgro...@vger.kernel.org; han...@cmpxchg.org; Andrey Ryabinin
>
> 主题: Re: 答复: [PATCH] mm/memcontrol.c: speed up to force empty a
>
13 matches
Mail list logo
