Thread: Newer kernels and CFS scheduler again
Hi All,
As I'll soon be looking at migrating some of our debian servers onto the new stable release, I've started doing a bit of basic pgbench testing.
Initially I've seen a little performance regression with higher concurrent clients when going from the 2.6.32 kernel to 3.2.14 (select only and tpc-b). After trying the suggestions made by Shaun Thomas a while back (here: http://www.postgresql.org/message-id/50E4AAB1.9040902@optionshouse.com) and getting nowhere, I'm seeing big improvements instead increasing the
defaults for sched_min_granularity_ns and sched_wakeup_granularity_ns (As described here: https://www.kernel.org/doc/Documentation/scheduler/sched-design-CFS.txt) from debians defaults of 3000000 and 4000000 respectively.
On my initial test setup (which admittedly is far from cutting edge) of 2xE5320 / 32Gb the following seem pretty optimal:
kernel.sched_min_granularity_ns=9000000
kernel.sched_wakeup_granularity_ns=12000000
kernel.sched_wakeup_granularity_ns=12000000
I've yet to do any testing on our larger machines, but as there have been a few posts here about performance vs newer kernels I was just wondering what other peoples findings are regarding CFS?
Glyn
>________________________________ > From: Glyn Astill <glynastill@yahoo.co.uk> >To: "pgsql-general@postgresql.org" <pgsql-general@postgresql.org> >Sent: Tuesday, 30 April 2013, 16:58 >Subject: [GENERAL] Newer kernels and CFS scheduler again > >Hi All, > > >As I'll soon be looking at migrating some of our debian servers onto the new stable release, I've started doing a bit ofbasic pgbench testing. > > >Initially I've seen a little performance regression with higher concurrent clients when going from the 2.6.32 kernel to3.2.14 (select only and tpc-b). After trying the suggestions made by Shaun Thomas a while back (here: http://www.postgresql.org/message-id/50E4AAB1.9040902@optionshouse.com)and getting nowhere, I'm seeing big improvements insteadincreasing the > Slight correction, I meant 3.2.41 >defaults for sched_min_granularity_ns and sched_wakeup_granularity_ns (As described here: https://www.kernel.org/doc/Documentation/scheduler/sched-design-CFS.txt)from debians defaults of 3000000 and 4000000 respectively. > > > >On my initial test setup (which admittedly is far from cutting edge) of 2xE5320 / 32Gb the following seem pretty optimal: > > >kernel.sched_min_granularity_ns=9000000 >kernel.sched_wakeup_granularity_ns=12000000 > > >I've yet to do any testing on our larger machines, but as there have been a few posts here about performance vs newer kernelsI was just wondering what other peoples findings are regarding CFS? > > >Glyn > >
On 04/30/2013 10:58 AM, Glyn Astill wrote: > kernel.sched_min_granularity_ns=9000000 > kernel.sched_wakeup_granularity_ns=12000000 I'll keep this in mind and do some testing when I get a chance. I think I tried tweaking these and didn't get much of a return compared to the migration cost, but that was back on kernel 3.2.31, so maybe that'll change. Thanks for the info! -- Shaun Thomas OptionsHouse | 141 W. Jackson Blvd. | Suite 500 | Chicago IL, 60604 312-676-8870 sthomas@optionshouse.com ______________________________________________ See http://www.peak6.com/email_disclaimer/ for terms and conditions related to this email