From: Peter Zijlstra <a.p.zijlstra@chello.nl>
To: mingo@kernel.org, pjt@google.com, venki@google.com,
efault@gmx.de, rostedt@goodmis.org, glommer@parallels.com
Cc: linux-kernel@vger.kernel.org, Peter Zijlstra <a.p.zijlstra@chello.nl>
Subject: [RFC][PATCH 4/4] sched/fair: Optimize cgroup pick_next_task_fair
Date: Thu, 14 Jun 2012 15:29:06 +0200 [thread overview]
Message-ID: <20120614133212.810726968@chello.nl> (raw)
In-Reply-To: 20120614132902.800827488@chello.nl
[-- Attachment #1: peter_zijlstra-sched-optimize_cgroup_pick_next_task_fair_4.patch --]
[-- Type: text/plain, Size: 3335 bytes --]
Since commit 2f36825b1 ("sched: Next buddy hint on sleep and preempt
path") it is likely we pick a new task from the same cgroup, doing a put
and then set on all intermediate entities is a waste of time, so try to
avoid this.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
kernel/sched/fair.c | 75 +++++++++++++++++++++++++++++++++++++++++++++++-----
1 file changed, 68 insertions(+), 7 deletions(-)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1285,15 +1285,46 @@ wakeup_preempt_entity(struct sched_entit
*/
static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
{
- struct sched_entity *se = __pick_first_entity(cfs_rq);
- struct sched_entity *left = se;
+ struct sched_entity *left = __pick_first_entity(cfs_rq);
+ struct sched_entity *se, *curr = cfs_rq->curr;
+
+ /*
+ * Since its possible we got here without doing put_prev_entity() we
+ * also have to consider cfs_rq->curr. If it was set, and is still a
+ * runnable entity, update_curr() will update its vruntime, otherwise
+ * forget we've ever seen it.
+ */
+ if (curr) {
+ if (curr->on_rq)
+ update_curr(cfs_rq);
+ else
+ curr = NULL;
+ }
+
+ /*
+ * If curr is set we have to see if its left of the leftmost entity
+ * still in the tree, provided there was anything in the tree at all.
+ */
+ if (!left || (curr && entity_before(curr, left)))
+ left = curr;
+
+ se = left; /* ideally we run the leftmost entity */
/*
* Avoid running the skip buddy, if running something else can
* be done without getting too unfair.
*/
if (cfs_rq->skip == se) {
- struct sched_entity *second = __pick_next_entity(se);
+ struct sched_entity *second;
+
+ if (se == curr) {
+ second = __pick_first_entity(cfs_rq);
+ } else {
+ second = __pick_next_entity(se);
+ if (!second || (curr && entity_before(curr, second)))
+ second = curr;
+ }
+
if (second && wakeup_preempt_entity(second, left) < 1)
se = second;
}
@@ -2993,23 +3024,53 @@ static void check_preempt_wakeup(struct
static struct task_struct *
pick_next_task_fair(struct rq *rq, struct task_struct *prev)
{
- struct task_struct *p;
struct cfs_rq *cfs_rq = &rq->cfs;
- struct sched_entity *se;
+ struct sched_entity *se, *pse;
+ struct task_struct *p;
if (!cfs_rq->nr_running)
return NULL;
- if (prev)
+ if (prev && (prev->sched_class != &fair_sched_class)) {
prev->sched_class->put_prev_task(rq, prev);
+ prev = NULL;
+ }
do {
se = pick_next_entity(cfs_rq);
- set_next_entity(cfs_rq, se);
+ if (!prev)
+ set_next_entity(cfs_rq, se);
cfs_rq = group_cfs_rq(se);
} while (cfs_rq);
p = task_of(se);
+
+ /*
+ * If we haven't yet done put_prev_entity and the selected task is
+ * a different task than we started out with, try and touch the least
+ * amount of cfs_rq trees.
+ */
+ if (prev && prev != p) {
+ pse = &prev->se;
+
+ while (!(cfs_rq = is_same_group(se, pse))) {
+ int se_depth = se->depth;
+ int pse_depth = pse->depth;
+
+ if (se_depth <= pse_depth) {
+ put_prev_entity(cfs_rq_of(pse), pse);
+ pse = parent_entity(pse);
+ }
+ if (se_depth >= pse_depth) {
+ set_next_entity(cfs_rq_of(se), se);
+ se = parent_entity(se);
+ }
+ }
+
+ put_prev_entity(cfs_rq, pse);
+ set_next_entity(cfs_rq, se);
+ }
+
if (hrtick_enabled(rq))
hrtick_start_fair(rq, p);
next prev parent reply other threads:[~2012-06-14 13:33 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-06-14 13:29 [RFC][PATCH 0/4] sched: Optimize cgroup muck Peter Zijlstra
2012-06-14 13:29 ` [RFC][PATCH 1/4] sched/fair: track cgroup depth Peter Zijlstra
2012-06-14 13:29 ` [RFC][PATCH 2/4] sched: Push put_prev_task() into pick_next_task() Peter Zijlstra
2012-06-14 14:32 ` Steven Rostedt
2012-06-14 14:58 ` Peter Zijlstra
2012-06-15 9:49 ` Glauber Costa
2012-06-15 10:03 ` Peter Zijlstra
2012-06-15 10:01 ` Glauber Costa
2012-06-21 7:35 ` Michael Wang
2012-06-21 8:41 ` Peter Zijlstra
2012-06-21 9:23 ` Michael Wang
2012-06-14 13:29 ` [RFC][PATCH 3/4] sched/fair: clean up __clear_buddies_* Peter Zijlstra
2012-06-14 13:29 ` Peter Zijlstra [this message]
2012-06-14 21:19 ` [RFC][PATCH 4/4] sched/fair: Optimize cgroup pick_next_task_fair Peter Zijlstra
2012-06-15 14:03 ` Peter Zijlstra
2012-06-19 8:45 ` Paul Turner
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20120614133212.810726968@chello.nl \
--to=a.p.zijlstra@chello.nl \
--cc=efault@gmx.de \
--cc=glommer@parallels.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=pjt@google.com \
--cc=rostedt@goodmis.org \
--cc=venki@google.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox