Re: [PATCH v2] sched/core: Don't mix isolcpus and housekeeping CPUs

From: Srikar Dronamraju
Date: Fri Oct 26 2018 - 05:31:08 EST


* Peter Zijlstra <peterz@xxxxxxxxxxxxx> [2018-10-26 10:41:05]:

> > #
> > # ./hist.sh
> > 10:35:21 IST UID TGID TID %usr %system %guest %CPU CPU Command
> > 10:35:21 IST 0 2645 - 8.70 0.01 0.00 8.71 1 ebizzy
> > 10:35:21 IST 0 - 2645 0.01 0.00 0.00 0.01 1 |__ebizzy
> > 10:35:21 IST 0 - 2647 0.14 0.00 0.00 0.14 1 |__ebizzy
> > 10:35:21 IST 0 - 2648 0.13 0.00 0.00 0.13 1 |__ebizzy
> > 10:35:21 IST 0 - 2649 0.13 0.00 0.00 0.13 1 |__ebizzy
> > 10:35:21 IST 0 - 2650 0.13 0.00 0.00 0.13 1 |__ebizzy
> > 10:35:21 IST 0 - 2651 0.13 0.00 0.00 0.13 1 |__ebizzy
> > 10:35:21 IST 0 - 2652 0.13 0.00 0.00 0.13 1 |__ebizzy
> > 10:35:21 IST 0 - 2653 0.13 0.00 0.00 0.13 1 |__ebizzy
> > 10:35:23 IST UID TGID TID %usr %system %guest %CPU CPU Command
> > 10:35:23 IST 0 2642 - 0.00 0.00 0.00 0.00 1 hist.sh
> > 10:35:23 IST 0 - 2642 0.00 0.00 0.00 0.00 1 |__hist.sh
> > #
>
> That's correct and specified behaviour.
>
> cpu1 has no sched domain (or the singleton domaon, which is the same)
> and thus its tasks will not be migrated.
>

As I mentioned, If every run was the same, then it would have been good.
However if we increase the cpuset from 1-8 to 1-31 then we seen spreading
more often but not always.

./hist.sh
02:59:10 IST UID TGID TID %usr %system %guest %CPU CPU Command
02:59:10 IST 0 2244 - 100.00 0.13 0.00 100.00 30 ebizzy
02:59:10 IST 0 - 2244 0.00 0.02 0.00 0.02 30 |__ebizzy
02:59:10 IST 0 - 2246 4.37 0.00 0.00 4.37 21 |__ebizzy
02:59:10 IST 0 - 2247 2.14 0.00 0.00 2.14 8 |__ebizzy
02:59:10 IST 0 - 2248 3.13 0.00 0.00 3.13 28 |__ebizzy
02:59:10 IST 0 - 2249 5.57 0.00 0.00 5.57 18 |__ebizzy
02:59:10 IST 0 - 2250 4.29 0.00 0.00 4.29 11 |__ebizzy
02:59:10 IST 0 - 2251 5.32 0.00 0.00 5.32 19 |__ebizzy
02:59:10 IST 0 - 2252 5.62 0.00 0.00 5.62 17 |__ebizzy
02:59:11 IST UID TGID TID %usr %system %guest %CPU CPU Command
02:59:11 IST 0 2241 - 0.00 0.00 0.00 0.00 29 hist.sh
02:59:11 IST 0 - 2241 0.00 0.00 0.00 0.00 29 |__hist.sh


> If there is a problem, it is with cpuset and its interaction with
> isolcpus. I still have to look at the last version of cpuset-v2, but
> iirc that was better in this regard.

Okay.

--
Thanks and Regards
Srikar Dronamraju