From: Chris Down <chris-6Bi1550iOqEnzZ6mRAm98g@public.gmane.org>
To: "Bruno Prémont"
<bonbons-ud5FBsm0p/xEiooADzr8i9i2O/JbrIOy@public.gmane.org>
Cc: Michal Hocko <mhocko-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>,
cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org,
Johannes Weiner <hannes-druUgvl0LCNAfugRpC6u6w@public.gmane.org>,
Vladimir Davydov
<vdavydov.dev-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
Subject: Re: Memory CG and 5.1 to 5.6 uprade slows backup
Date: Thu, 9 Apr 2020 18:50:44 +0100 [thread overview]
Message-ID: <20200409175044.GC1040020@chrisdown.name> (raw)
In-Reply-To: <20200409174042.2a3389ba-pDZhbqX7CfkoGc32E1+a2S4z1YicLaQ4@public.gmane.org>
Bruno Prémont writes:
>On Thu, 9 Apr 2020 16:24:17 +0100 wrote:
>
>> Bruno Prémont writes:
>> >Could it be that cache is being prevented from being reclaimed by a task
>> >in another cgroup?
>> >
>> >e.g.
>> > cgroup/system/backup
>> > first reads $files (reads each once)
>> > cgroup/workload/bla
>> > second&more reads $files
>> >
>> >Would $files remain associated to cgroup/system/backup and not
>> >reclaimed there instead of being reassigned to cgroup/workload/bla?
>>
>> Yes, that's entirely possible. The first cgroup to fault in the pages is
>> charged for the memory. Other cgroups may use them, but they are not accounted
>> for as part of that other cgroup. They may also still be "active" as a result
>> of use by another cgroup.
>
>But the memory would then be 'active' in the original cgroup? which is
>not the case here I feel.
Yes, that's correct. I don't think it's the case here (since active_file is not
that large in the affected cgroup), but it's certainly generally a possibility.
WARNING: multiple messages have this Message-ID (diff)
From: Chris Down <chris@chrisdown.name>
To: "Bruno Prémont" <bonbons@linux-vserver.org>
Cc: Michal Hocko <mhocko@kernel.org>,
cgroups@vger.kernel.org, linux-mm@kvack.org,
Johannes Weiner <hannes@cmpxchg.org>,
Vladimir Davydov <vdavydov.dev@gmail.com>
Subject: Re: Memory CG and 5.1 to 5.6 uprade slows backup
Date: Thu, 9 Apr 2020 18:50:44 +0100 [thread overview]
Message-ID: <20200409175044.GC1040020@chrisdown.name> (raw)
In-Reply-To: <20200409174042.2a3389ba@hemera.lan.sysophe.eu>
Bruno Prémont writes:
>On Thu, 9 Apr 2020 16:24:17 +0100 wrote:
>
>> Bruno Prémont writes:
>> >Could it be that cache is being prevented from being reclaimed by a task
>> >in another cgroup?
>> >
>> >e.g.
>> > cgroup/system/backup
>> > first reads $files (reads each once)
>> > cgroup/workload/bla
>> > second&more reads $files
>> >
>> >Would $files remain associated to cgroup/system/backup and not
>> >reclaimed there instead of being reassigned to cgroup/workload/bla?
>>
>> Yes, that's entirely possible. The first cgroup to fault in the pages is
>> charged for the memory. Other cgroups may use them, but they are not accounted
>> for as part of that other cgroup. They may also still be "active" as a result
>> of use by another cgroup.
>
>But the memory would then be 'active' in the original cgroup? which is
>not the case here I feel.
Yes, that's correct. I don't think it's the case here (since active_file is not
that large in the affected cgroup), but it's certainly generally a possibility.
next prev parent reply other threads:[~2020-04-09 17:50 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-04-09 9:25 Memory CG and 5.1 to 5.6 uprade slows backup Bruno Prémont
2020-04-09 9:25 ` Bruno Prémont
[not found] ` <20200409112505.2e1fc150-pDZhbqX7CfkoGc32E1+a2S4z1YicLaQ4@public.gmane.org>
2020-04-09 9:46 ` Michal Hocko
2020-04-09 9:46 ` Michal Hocko
[not found] ` <20200409094615.GE18386-2MMpYkNvuYDjFM9bn6wA6Q@public.gmane.org>
2020-04-09 10:17 ` Bruno Prémont
2020-04-09 10:17 ` Bruno Prémont
[not found] ` <20200409121733.1a5ba17c-pDZhbqX7CfkoGc32E1+a2S4z1YicLaQ4@public.gmane.org>
2020-04-09 10:34 ` Michal Hocko
2020-04-09 10:34 ` Michal Hocko
[not found] ` <20200409103400.GF18386-2MMpYkNvuYDjFM9bn6wA6Q@public.gmane.org>
2020-04-09 15:09 ` Bruno Prémont
2020-04-09 15:09 ` Bruno Prémont
[not found] ` <20200409170926.182354c3-pDZhbqX7CfkoGc32E1+a2S4z1YicLaQ4@public.gmane.org>
2020-04-09 15:24 ` Chris Down
2020-04-09 15:24 ` Chris Down
[not found] ` <20200409152417.GB1040020-6Bi1550iOqEnzZ6mRAm98g@public.gmane.org>
2020-04-09 15:40 ` Bruno Prémont
2020-04-09 15:40 ` Bruno Prémont
[not found] ` <20200409174042.2a3389ba-pDZhbqX7CfkoGc32E1+a2S4z1YicLaQ4@public.gmane.org>
2020-04-09 17:50 ` Chris Down [this message]
2020-04-09 17:50 ` Chris Down
[not found] ` <20200409175044.GC1040020-6Bi1550iOqEnzZ6mRAm98g@public.gmane.org>
2020-04-09 17:56 ` Chris Down
2020-04-09 17:56 ` Chris Down
2020-04-09 15:25 ` Michal Hocko
2020-04-09 15:25 ` Michal Hocko
2020-04-10 7:15 ` Bruno Prémont
[not found] ` <20200410091525.287062fa-pDZhbqX7CfkoGc32E1+a2S4z1YicLaQ4@public.gmane.org>
2020-04-10 8:43 ` Bruno Prémont
2020-04-10 8:43 ` Bruno Prémont
[not found] ` <20200410115010.1d9f6a3f@hemera.lan.sysophe.eu>
[not found] ` <20200414163134.GQ4629@dhcp22.suse.cz>
[not found] ` <20200414163134.GQ4629-2MMpYkNvuYDjFM9bn6wA6Q@public.gmane.org>
2020-04-15 10:17 ` Bruno Prémont
2020-04-15 10:17 ` Bruno Prémont
[not found] ` <20200415121753.3c8d700b-pDZhbqX7CfkoGc32E1+a2S4z1YicLaQ4@public.gmane.org>
2020-04-15 10:24 ` Michal Hocko
2020-04-15 10:24 ` Michal Hocko
[not found] ` <20200415102442.GE4629-2MMpYkNvuYDjFM9bn6wA6Q@public.gmane.org>
2020-04-15 11:37 ` Bruno Prémont
2020-04-15 11:37 ` Bruno Prémont
[not found] ` <20200409152540.GP18386-2MMpYkNvuYDjFM9bn6wA6Q@public.gmane.org>
2020-04-14 15:09 ` Bruno Prémont
2020-04-14 15:09 ` Bruno Prémont
2020-04-09 10:50 ` Chris Down
2020-04-09 10:50 ` Chris Down
[not found] ` <20200409105048.GA1040020-6Bi1550iOqEnzZ6mRAm98g@public.gmane.org>
2020-04-09 11:58 ` Bruno Prémont
2020-04-09 11:58 ` Bruno Prémont
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200409175044.GC1040020@chrisdown.name \
--to=chris-6bi1550ioqenzz6mram98g@public.gmane.org \
--cc=bonbons-ud5FBsm0p/xEiooADzr8i9i2O/JbrIOy@public.gmane.org \
--cc=cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=hannes-druUgvl0LCNAfugRpC6u6w@public.gmane.org \
--cc=linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org \
--cc=mhocko-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org \
--cc=vdavydov.dev-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.