mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2026-05-12 15:08:25 -04:00
sched/fair: Ignore cache hotness for SMT migration
SMT siblings share caches, so cache hotness should be irrelevant for cross-sibling migration. Signed-off-by: Josh Don <joshdon@google.com> Proposed-by: Venkatesh Pallipadi <venki@google.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/20200804193413.510651-1-joshdon@google.com
This commit is contained in:
@@ -7402,6 +7402,10 @@ static int task_hot(struct task_struct *p, struct lb_env *env)
|
||||
if (unlikely(task_has_idle_policy(p)))
|
||||
return 0;
|
||||
|
||||
/* SMT siblings share cache */
|
||||
if (env->sd->flags & SD_SHARE_CPUCAPACITY)
|
||||
return 0;
|
||||
|
||||
/*
|
||||
* Buddy candidates are cache hot:
|
||||
*/
|
||||
|
||||
Reference in New Issue
Block a user