summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
authorPeter Zijlstra <a.p.zijlstra@chello.nl>2008-06-27 13:41:39 +0200
committerIngo Molnar <mingo@elte.hu>2008-06-27 14:31:47 +0200
commitf5bfb7d9ff73d72ee4f2f4830a6f0c9088d00f92 (patch)
tree402e8caaef4d3f0c26a52b171e04dbb67ea08cfa /kernel
parentf1d239f73200a5803a89e5929fb3abc1596b7589 (diff)
downloadop-kernel-dev-f5bfb7d9ff73d72ee4f2f4830a6f0c9088d00f92.zip
op-kernel-dev-f5bfb7d9ff73d72ee4f2f4830a6f0c9088d00f92.tar.gz
sched: bias effective_load() error towards failing wake_affine().
Measurement shows that the difference between cgroup:/ and cgroup:/foo wake_affine() results is that the latter succeeds significantly more. Therefore bias the calculations towards failing the test. Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'kernel')
-rw-r--r--kernel/sched_fair.c28
-rw-r--r--kernel/sched_features.h1
2 files changed, 29 insertions, 0 deletions
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index e87f1a5..9bcc003 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1074,6 +1074,27 @@ static inline int wake_idle(int cpu, struct task_struct *p)
static const struct sched_class fair_sched_class;
#ifdef CONFIG_FAIR_GROUP_SCHED
+/*
+ * effective_load() calculates the load change as seen from the root_task_group
+ *
+ * Adding load to a group doesn't make a group heavier, but can cause movement
+ * of group shares between cpus. Assuming the shares were perfectly aligned one
+ * can calculate the shift in shares.
+ *
+ * The problem is that perfectly aligning the shares is rather expensive, hence
+ * we try to avoid doing that too often - see update_shares(), which ratelimits
+ * this change.
+ *
+ * We compensate this by not only taking the current delta into account, but
+ * also considering the delta between when the shares were last adjusted and
+ * now.
+ *
+ * We still saw a performance dip, some tracing learned us that between
+ * cgroup:/ and cgroup:/foo balancing the number of affine wakeups increased
+ * significantly. Therefore try to bias the error in direction of failing
+ * the affine wakeup.
+ *
+ */
static long effective_load(struct task_group *tg, int cpu,
long wl, long wg)
{
@@ -1084,6 +1105,13 @@ static long effective_load(struct task_group *tg, int cpu,
return wl;
/*
+ * By not taking the decrease of shares on the other cpu into
+ * account our error leans towards reducing the affine wakeups.
+ */
+ if (!wl && sched_feat(ASYM_EFF_LOAD))
+ return wl;
+
+ /*
* Instead of using this increment, also add the difference
* between when the shares were last updated and now.
*/
diff --git a/kernel/sched_features.h b/kernel/sched_features.h
index 7d616d2..862b06b 100644
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -10,3 +10,4 @@ SCHED_FEAT(DOUBLE_TICK, 0)
SCHED_FEAT(ASYM_GRAN, 1)
SCHED_FEAT(LB_BIAS, 0)
SCHED_FEAT(LB_WAKEUP_UPDATE, 1)
+SCHED_FEAT(ASYM_EFF_LOAD, 1)
OpenPOWER on IntegriCloud