iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

sched/fair: Don't double balance_interval for migrate_misfit

Browse Source 
It is not necessarily an indication of the system being busy and
requires a backoff of the load balancer activities. But pushing it high
could mean generally delaying other misfit activities or other type of
imbalances.

Also don't pollute nr_balance_failed because of misfit failures. The
value is used for enabling cache hot migration and in migrate_util/load
types. None of which should be impacted (skewed) by misfit failures.

Signed-off-by: Qais Yousef <qyousef@layalina.io>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20240324004552.999936-5-qyousef@layalina.io
This commit is contained in:
Qais Yousef 2024-03-24 00:45:52 +00:00 committed by Ingo Molnar
parent fa427e8e53
commit 58eeb2d79b
1 changed files with 11 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
kernel/sched/fair.c
View File

@ -11449,8 +11449,12 @@ more_balance:
* We do not want newidle balance, which can be very * We do not want newidle balance, which can be very
* frequent, pollute the failure counter causing * frequent, pollute the failure counter causing
* excessive cache_hot migrations and active balances. * excessive cache_hot migrations and active balances.
*
* Similarly for migration_misfit which is not related to
* load/util migration, don't pollute nr_balance_failed.
*/ */
if (idle != CPU_NEWLY_IDLE) if (idle != CPU_NEWLY_IDLE &&
env.migration_type != migrate_misfit)
sd->nr_balance_failed++; sd->nr_balance_failed++;
if (need_active_balance(&env)) { if (need_active_balance(&env)) {
@ -11533,8 +11537,13 @@ out_one_pinned:
* repeatedly reach this code, which would lead to balance_interval * repeatedly reach this code, which would lead to balance_interval
* skyrocketing in a short amount of time. Skip the balance_interval * skyrocketing in a short amount of time. Skip the balance_interval
* increase logic to avoid that. * increase logic to avoid that.
*
* Similarly misfit migration which is not necessarily an indication of
* the system being busy and requires lb to backoff to let it settle
* down.
*/ */
if (env.idle == CPU_NEWLY_IDLE) if (env.idle == CPU_NEWLY_IDLE ||
env.migration_type == migrate_misfit)
goto out; goto out;
/* tune up the balancing interval */ /* tune up the balancing interval */