Re: [PATCH v3] vm_swappiness=0 should still try to avoid swapping anon memory

From: Nico Pache <npache@redhat.com>
To: Johannes Weiner <hannes@cmpxchg.org>
Cc: linux-mm@kvack.org, akpm@linux-foundation.org,
	linux-kernel@vger.kernel.org, aquini@redhat.com,
	shakeelb@google.com, llong@redhat.com, mhocko@suse.com,
	hakavlad@inbox.lv
Subject: Re: [PATCH v3] vm_swappiness=0 should still try to avoid swapping anon memory
Date: Tue, 19 Apr 2022 15:37:51 -0400	[thread overview]
Message-ID: <001bf379-9026-fd7a-3fff-c1b2cea35348@redhat.com> (raw)
In-Reply-To: <Yl8Dk+a1YDwupLMv@cmpxchg.org>

Hi Johannes,

On 4/19/22 14:46, Johannes Weiner wrote:
> Hi Nico,
> 
> On Tue, Apr 19, 2022 at 02:11:53PM -0400, Nico Pache wrote:
>> I think its is important to note the issue we are seeing has greatly improved
>> since the initial posting. However we have noticed that the issue is still
>> present (and significantly worse) when cgroupV1 is set.
>>
>> We were initially testing with CgroupV1 and later found that the issue was not
>> as bad in CgroupV2 (but was still an noticeable issue). This is also resulting
>> in the splitting of THPs in the host kernel.
> 
> When swappiness is 0, cgroup limit reclaim has a fixed SCAN_FILE
> branch, so it shouldn't ever look at anon. I'm assuming you're getting
> global reclaim mixed in. Indeed, I think we can try harder not to swap
> for global reclaim if the user asks for that.
We aren't actually utilizing the cgroup mechanism; however, switching between
the two has a noticeable affect on the global reclaim of the system. This is not
a writeback case either-- The reproducer simply reads. So I think we can rule
out the v2 writeback controller being involved. My initial patch was also
targeting swappiness=0 but this also occurs when >0.
> 
> Can you try the below patch?
of course thanks for that :) I'll let you know how it goes!

Cheers,
-- Nico