sched/fair: tweak pick_next_entity
PATCH 1/1 sched/fair: tweak pick_next_entity
Currently, pick_next_entity(...) has the following structure (simplified):
[...]
if (last_buddy_ok())
result = last_buddy;
if (next_buddy_ok())
result = next_buddy;
[...]
The intended behavior is to prefer next buddy over last buddy; the current code somewhat obfuscates this, and also wastes cycles checking the last buddy when eventually the next buddy is picked up.
So this patch refactors two 'ifs' above into
[...]
if (next_buddy_ok())
result = next_buddy;
else if (last_buddy_ok())
result = last_buddy;[...]
--- kernel/sched/fair.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-)
kernel/sched/fair.c +10 -10
@@ -4465,17 +4465,17 @@ pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr) se = second; } -/* -* Prefer last buddy, try to return the CPU to a preempted task. -*/ -if (cfs_rq->last &&wakeup_preempt_entity (cfs_rq->last, left) <1 ) - se = cfs_rq->last; - -/* -* Someone really wants this to run. If it's not unfair, run it. -*/ -if (cfs_rq->next &&wakeup_preempt_entity (cfs_rq->next, left) <1 ) +if (cfs_rq->next &&wakeup_preempt_entity (cfs_rq->next, left) <1 ) { +/* +* Someone really wants this to run. If it's not unfair, run it. +*/ se = cfs_rq->next; + }else if (cfs_rq->last &&wakeup_preempt_entity (cfs_rq->last, left) <1 ) { +/* +* Prefer last buddy, try to return the CPU to a preempted task. +*/ + se = cfs_rq->last; + }clear_buddies (cfs_rq, se);
Signature · 1 line
2.28.0.709.gb0816b6eb0-goog
Quoted 18 lines · Peter Oskolkov
Currently,
pick_next_entity(...)has the following structure (simplified):[...]
if (last_buddy_ok())
result =last_buddy;
if (next_buddy_ok())
result =next_buddy;
[...]The intended behavior is to prefer next buddy over last buddy; the current code somewhat obfuscates this, and also wastes cycles checking the last buddy when eventually the next buddy is picked up.
So this patch refactors two 'ifs' above into
Quoted 8 lines
[...]
if (next_buddy_ok())result = next_buddy; else if (last_buddy_ok()) result = last_buddy;[...]
Signed-off-by Peter Oskolkov <[email protected]>
Quoted 39 lines
--- kernel/sched/fair.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-)kernel/sched/fair.c +10
-11@@ -4465,17 +4465,17 @@ pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr) se = second; } -/* -* Prefer last buddy, try to return the CPU to a preempted task. -*/ -if (cfs_rq->last &&wakeup_preempt_entity (cfs_rq->last, left) <1 ) - se = cfs_rq->last; - -/* -* Someone really wants this to run. If it's not unfair, run it. -*/ -if (cfs_rq->next &&wakeup_preempt_entity (cfs_rq->next, left) <1 ) +if (cfs_rq->next &&wakeup_preempt_entity (cfs_rq->next, left) <1 ) { +/* +* Someone really wants this to run. If it's not unfair, run it. +*/ se = cfs_rq->next; + }else if (cfs_rq->last &&wakeup_preempt_entity (cfs_rq->last, left) <1 ) { +/* +* Prefer last buddy, try to return the CPU to a preempted task. +*/ + se = cfs_rq->last; + }clear_buddies (cfs_rq, se); --2.28.0.709.gb0816b6eb0-goog
Peter Zijlstra
maintainerQuoted 26 lines · Vincent Guittot
Quoted 25 lines · Peter Oskolkov
Currently,
pick_next_entity(...)has the following structure (simplified):[...]
if (last_buddy_ok())
result =last_buddy;
if (next_buddy_ok())
result =next_buddy;
[...]The intended behavior is to prefer next buddy over last buddy; the current code somewhat obfuscates this, and also wastes cycles checking the last buddy when eventually the next buddy is picked up.
So this patch refactors two 'ifs' above into
[...]
if (next_buddy_ok())result = next_buddy; else if (last_buddy_ok()) result = last_buddy;[...]
Quoted 3 lines
Quoted 1 line
Signed-off-by Peter Oskolkov <[email protected]>Reviewed-by Vincent Guittot <[email protected]>
Thanks!
[tip: sched/core] sched/fair: Tweak pick_next_entity()
In reply to Peter OskolkovThe following commit has been merged into the sched/core branch of tip:
The following commit has been merged into the sched/core branch of tip:
Commit-ID: 9abb897345ce1d41257567f571a78137c961c405 Gitweb: https://git.kernel.org/tip/9abb897345ce1d41257567f571a78137c961c405 Author: Peter Oskolkov <[email protected]> AuthorDate: Wed, 30 Sep 2020 10:35:32 -07:00 Committer: Peter Zijlstra <[email protected]> CommitterDate: Sat, 03 Oct 2020 16:30:52 +02:00
sched/fair: Tweak pick_next_entity()
Currently, pick_next_entity(...) has the following structure (simplified):
[...]
if (last_buddy_ok())
result = last_buddy;
if (next_buddy_ok())
result = next_buddy;
[...]The intended behavior is to prefer next buddy over last buddy; the current code somewhat obfuscates this, and also wastes cycles checking the last buddy when eventually the next buddy is picked up.
So this patch refactors two 'ifs' above into
[...]
if (next_buddy_ok())
result = next_buddy;
else if (last_buddy_ok())
result = last_buddy;
[...]--- kernel/sched/fair.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-)
kernel/sched/fair.c +10 -10
@@ -4465,17 +4465,17 @@ pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr) se = second; } -/* -* Prefer last buddy, try to return the CPU to a preempted task. -*/ -if (cfs_rq->last &&wakeup_preempt_entity (cfs_rq->last, left) <1 ) - se = cfs_rq->last; - -/* -* Someone really wants this to run. If it's not unfair, run it. -*/ -if (cfs_rq->next &&wakeup_preempt_entity (cfs_rq->next, left) <1 ) +if (cfs_rq->next &&wakeup_preempt_entity (cfs_rq->next, left) <1 ) { +/* +* Someone really wants this to run. If it's not unfair, run it. +*/ se = cfs_rq->next; + }else if (cfs_rq->last &&wakeup_preempt_entity (cfs_rq->last, left) <1 ) { +/* +* Prefer last buddy, try to return the CPU to a preempted task. +*/ + se = cfs_rq->last; + }clear_buddies (cfs_rq, se);