From: Christoph Lameter <clameter@sgi.com>
To: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
miklos@szeredi.hu, akpm@linux-foundation.org, neilb@suse.de,
dgc@sgi.com, tomoki.sekiyama.qu@hitachi.com,
nikita@clusterfs.com, trond.myklebust@fys.uio.no,
yingchao.zhou@gmail.com, richard@rsk.demon.co.uk,
torvalds@linux-foundation.org, pj@sgi.com
Subject: Re: [PATCH 00/23] per device dirty throttling -v9
Date: Fri, 17 Aug 2007 13:37:05 -0700 (PDT) [thread overview]
Message-ID: <Pine.LNX.4.64.0708171333370.9404@schroedinger.engr.sgi.com> (raw)
In-Reply-To: <1187335158.6114.119.camel@twins>
On Fri, 17 Aug 2007, Peter Zijlstra wrote:
> Currently we do:
> dirty = total_dirty * bdi_completions_p * task_dirty_p
>
> As dgc pointed out before, there is the issue of bdi/task correlation,
> that is, we do not track task dirty rates per bdi, so now a task that
> heavily dirties on one bdi will also get penalised on the others (and
> similar issues).
I think that is tolerable.
>
> If we were to change it so:
> dirty = cpuset_dirty * bdi_completions_p * task_dirty_p
>
> We get additional correlation issues: cpuset/bdi, cpuset/task.
> Which could yield surprising results if some bdis are strictly per
> cpuset.
If we do not do the above then the dirty page calculation for a small
cpuset (F.e. 1 node of a 128 node system) could allow an amount of dirty
pages that will fill up all the node.
> The cpuset/task correlation has a strict mapping and could be solved by
> keeping the vm_dirties counter per cpuset. However, this would seriously
> complicate the code and I'm not sure if it would gain us much.
The patchset that I referred to has code to calculate the dirty count and
ratio per cpuset by looping over the nodes. Currently we are having
trouble with small cpusets not performing writeout correctly. This
sometimes may result in OOM conditions because the whole node is full of
dirty pages. If the cpu boundaries are enforced in a strict way then the
application may fail with an OOM.
We can compensate by recalculating the dirty_ratio based on the smallest
cpuset but then larger cpusets are penalized. Also one cannot set the
dirty_ratio below a certain mininum.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
prev parent reply other threads:[~2007-08-17 20:37 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-08-16 7:45 Peter Zijlstra
2007-08-16 7:45 ` [PATCH 01/23] nfs: remove congestion_end() Peter Zijlstra
2007-08-16 7:45 ` [PATCH 02/23] lib: percpu_counter_add Peter Zijlstra
2007-08-17 15:48 ` Josef Sipek
2007-08-16 7:45 ` [PATCH 03/23] lib: percpu_counter_sub Peter Zijlstra
2007-08-16 7:45 ` [PATCH 04/23] lib: percpu_counter variable batch Peter Zijlstra
2007-08-16 7:45 ` [PATCH 05/23] lib: make percpu_counter_add take s64 Peter Zijlstra
2007-08-16 7:45 ` [PATCH 06/23] lib: percpu_counter_set Peter Zijlstra
2007-08-16 7:45 ` [PATCH 07/23] lib: percpu_counter_sum_positive Peter Zijlstra
2007-08-16 7:45 ` [PATCH 08/23] lib: percpu_count_sum() Peter Zijlstra
2007-08-16 7:45 ` [PATCH 09/23] lib: percpu_counter_init error handling Peter Zijlstra
2007-08-17 15:56 ` Josef Sipek
2007-08-17 16:03 ` Peter Zijlstra
2007-08-18 8:09 ` Peter Zijlstra
2007-08-23 18:24 ` Josef Sipek
2007-08-16 7:45 ` [PATCH 10/23] lib: percpu_counter_init_irq Peter Zijlstra
2007-08-16 7:45 ` [PATCH 11/23] mm: bdi init hooks Peter Zijlstra
2007-08-17 16:10 ` Josef Sipek
2007-08-17 16:15 ` Peter Zijlstra
2007-08-16 7:45 ` [PATCH 12/23] containers: " Peter Zijlstra
2007-08-16 7:45 ` [PATCH 13/23] mtd: " Peter Zijlstra
2007-08-16 7:45 ` [PATCH 14/23] mtd: clean up the backing_dev_info usage Peter Zijlstra
2007-08-16 7:45 ` [PATCH 15/23] mtd: give mtdconcat devices their own backing_dev_info Peter Zijlstra
2007-08-16 7:45 ` [PATCH 16/23] mm: scalable bdi statistics counters Peter Zijlstra
2007-08-17 16:20 ` Josef Sipek
2007-08-17 16:23 ` Peter Zijlstra
2007-08-16 7:45 ` [PATCH 17/23] mm: count reclaimable pages per BDI Peter Zijlstra
2007-08-17 16:23 ` Josef Sipek
2007-08-16 7:45 ` [PATCH 18/23] mm: count writeback " Peter Zijlstra
2007-08-16 7:45 ` [PATCH 19/23] mm: expose BDI statistics in sysfs Peter Zijlstra
2007-08-16 7:45 ` [PATCH 20/23] lib: floating proportions Peter Zijlstra
2007-08-16 7:45 ` [PATCH 21/23] mm: per device dirty threshold Peter Zijlstra
2007-08-16 7:45 ` [PATCH 22/23] mm: dirty balancing for tasks Peter Zijlstra
2007-08-16 7:45 ` [PATCH 23/23] debug: sysfs files for the current ratio/size/total Peter Zijlstra
2007-08-16 21:29 ` [PATCH 00/23] per device dirty throttling -v9 Christoph Lameter
2007-08-17 7:19 ` Peter Zijlstra
2007-08-17 20:37 ` Christoph Lameter [this message]
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=Pine.LNX.4.64.0708171333370.9404@schroedinger.engr.sgi.com \
--to=clameter@sgi.com \
--cc=a.p.zijlstra@chello.nl \
--cc=akpm@linux-foundation.org \
--cc=dgc@sgi.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=miklos@szeredi.hu \
--cc=neilb@suse.de \
--cc=nikita@clusterfs.com \
--cc=pj@sgi.com \
--cc=richard@rsk.demon.co.uk \
--cc=tomoki.sekiyama.qu@hitachi.com \
--cc=torvalds@linux-foundation.org \
--cc=trond.myklebust@fys.uio.no \
--cc=yingchao.zhou@gmail.com \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox