'll
submit this to Ubuntu and linux-stable once it gets accepted.
Thanks again,
On Tue, Jul 23, 2019 at 12:13 PM Phil Auld wrote:
>
> Hi Dave,
>
> On Tue, Jul 23, 2019 at 11:44:26AM -0500 Dave Chiluk wrote:
> > It has been observed, that highly-threaded, non-cp
Changelog v6
- Added back missing call to lsub_positive(&cfs_b->runtime, runtime);
- Added Reviewed-by: Ben Segall
- Fix some grammar in the Documentation, and change some wording.
- Updated documentation due to the .rst change
Changelog v5
- Based on this comment from Ben Segall's comment on v4
ile still maintaining correct cpu quota restrictions.
That testcase is available at https://github.com/indeedeng/fibtest.
Fixes: 512ac999d275 ("sched/fair: Fix bandwidth timer clock drift condition")
Signed-off-by: Dave Chiluk
Reviewed-by: Ben Segall
---
Documentation/scheduler/sched-
On Fri, Jul 12, 2019 at 5:10 PM wrote:
> Ugh. Maybe we /do/ just give up and say that most people don't seem to
> be using cfs_b in a way that expiration of the leftover 1ms matters.
That was my conclusion as well. Does this mean you want to proceed
with my patch set? Do you have any changes yo
aining correct cpu quota restrictions.
That testcase is available at https://github.com/indeedeng/fibtest.
Fixes: 512ac999d275 ("sched/fair: Fix bandwidth timer clock drift condition")
Signed-off-by: Dave Chiluk
---
Documentation/scheduler/sched-bwc.txt | 73 +
Changelog v5
- Based on this comment from Ben Segall's comment on v4
> If the cost of taking this global lock across all cpus without a
> ratelimit was somehow not a problem, I'd much prefer to just set
> min_cfs_rq_runtime = 0. (Assuming it is, I definitely prefer the "lie
> and sorta have 2x peri
aining correct cpu quota restrictions.
That testcase is available at https://github.com/indeedeng/fibtest.
Fixes: 512ac999d275 ("sched/fair: Fix bandwidth timer clock drift condition")
Signed-off-by: Dave Chiluk
---
Documentation/scheduler/sched-bwc.txt | 73 +
On Wed, May 29, 2019 at 02:05:55PM -0700, bseg...@google.com wrote:
> Dave Chiluk writes:
>
> Yeah, having run the test, stranding only 1 ms per cpu rather than 5
> doesn't help if you only have 10 ms of quota and even 10 threads/cpus.
> The slack timer isn't importa
Changelog v3
- Reworked documentation to better describe behavior of slice expiration
per feedback from Peter Oskolkov
Changelog v2
- Fixed some checkpatch errors in the commit message.
erformance
discrepancy has been observed to be almost 30x performance improvement,
while still maintaining correct cpu quota restrictions albeit over
longer time intervals than cpu.cfs_period_us. That testcase is
available at https://github.com/indeedeng/fibtest.
Fixes: 512ac999d275 ("sched/fair: F
On Fri, May 24, 2019 at 5:07 PM Peter Oskolkov wrote:
> Linux CPU scheduling tail latency is a well-known issue and a major
> pain point in some workloads:
> https://www.google.com/search?q=linux+cpu+scheduling+tail+latency
>
> Even assuming that nobody noticed this particular cause
> of CPU sched
On Fri, May 24, 2019 at 11:28 AM Peter Oskolkov wrote:
>
> On Fri, May 24, 2019 at 8:15 AM Dave Chiluk wrote:
> >
> > On Fri, May 24, 2019 at 9:32 AM Phil Auld wrote:
> > > On Thu, May 23, 2019 at 02:01:58PM -0700 Peter Oskolkov wrote:
> >
> > > > If
single fast thread taskset to cpu 0, and 7 slow threads taskset
to cpus 1-7. This run is expected to show less iterations, but the
worse problem is that the cpu usage is far less than the 500ms that it
should have received.
Thanks for the engagement on this,
Dave Chiluk
erformance
discrepancy has been observed to be almost 30x performance improvement,
while still maintaining correct cpu quota restrictions albeit over
longer time intervals than cpu.cfs_period_us. That testcase is
available at https://github.com/indeedeng/fibtest.
Fixes: 512ac999d275 ("sched/fair: F
Changelog v2
- Fixed some checkpatch errors in the commit message.
cy has been observed to be almost 30x performance improvement,
while still maintaining correct cpu quota restrictions albeit over
longer time intervals than cpu.cfs_period_us. That testcase is available
at https://github.com/indeedeng/fibtest.
Fixes: 512ac999d275 ("sched/fair: Fix bandwidth timer c
16 matches
Mail list logo
