Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1304830
| From | Tejun Heo <tj@kernel.org> |
|---|---|
| Newsgroups | linux.kernel |
| Subject | Re: [PATCH 5/5] cfq-iosched: Allow parent cgroup to preempt its child |
| Date | 2016-01-08 19:20 +0100 |
| Message-ID | <qOJNO-25i-45@gated-at.bofh.it> (permalink) |
| References | <qOkFI-1wu-11@gated-at.bofh.it> <qOkFI-1wu-9@gated-at.bofh.it> |
| Organization | linux.* mail to news gateway |
Hello,
On Thu, Jan 07, 2016 at 04:28:16PM +0100, Jan Kara wrote:
> From: Jan Kara <jack@suse.com>
>
> Currently we don't allow sync workload of one cgroup to preempt sync
> workload of any other cgroup. This is because we want to achieve service
> separation between cgroups. However in cases where cgroup preempting is
> ancestor of the current cgroup, there is no need of separation and
> idling introduces unnecessary overhead. This is hurts for example the
^^^
> case when workload is isolated within a cgroup but journalling threads
> are in root cgroup. Simple way to demostrate the issue is using:
>
> dbench4 -c /usr/share/dbench4/client.txt -t 10 -D /mnt 1
>
> on ext4 filesystem on plain SATA driver (mounted with barrier=0 to make
> difference more visible). When all processes are in the root cgroup,
> reported throughput is 153.132 MB/sec. When dbench process gets its own
> blkio cgroup, reported throughput drops to 26.1006 MB/sec.
>
> Fix the problem by making check in cfq_should_preempt() more benevolent
> and allow preemption by ancestor cgroup. This improves the throughput
> reported by dbench4 to 48.9106 MB/sec.
>
> Signed-off-by: Jan Kara <jack@suse.com>
Acked-by: Tejun Heo <tj@kernel.org>
Thanks.
--
tejun
Back to linux.kernel | Previous | Next — Previous in thread | Find similar | Unroll thread
[PATCH 5/5] cfq-iosched: Allow parent cgroup to preempt its child Jan Kara <jack@suse.cz> - 2016-01-07 16:30 +0100 Re: [PATCH 5/5] cfq-iosched: Allow parent cgroup to preempt its child Tejun Heo <tj@kernel.org> - 2016-01-08 19:20 +0100
csiph-web