* [patch] sched domain: increase the SMT busy rebalance interval
@ 2006-11-14 22:35 Siddha, Suresh B
0 siblings, 0 replies; only message in thread
From: Siddha, Suresh B @ 2006-11-14 22:35 UTC (permalink / raw)
To: mingo, nickpiggin, akpm; +Cc: linux-kernel, clameter, kenneth.w.chen
With SMT, if the logical processor is busy, load balance happens for every
8msec(min)-16msec(max). There is no need to do this often, as this is
just for fairness(to maintain uniform runqueue lengths) and default time slice
anyhow is 100msec.
Appended patch increases this interval to 64msec(min)-128msec(max) when the
logical processor is busy.
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
---
diff --git a/include/linux/topology.h b/include/linux/topology.h
index da508d1..b93bb6c 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -93,7 +93,7 @@ #define SD_SIBLING_INIT (struct sched_do
.groups = NULL, \
.min_interval = 1, \
.max_interval = 2, \
- .busy_factor = 8, \
+ .busy_factor = 64, \
.imbalance_pct = 110, \
.cache_nice_tries = 0, \
.per_cpu_gain = 25, \
^ permalink raw reply related [flat|nested] only message in thread
only message in thread, other threads:[~2006-11-14 22:58 UTC | newest]
Thread overview: (only message) (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2006-11-14 22:35 [patch] sched domain: increase the SMT busy rebalance interval Siddha, Suresh B
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.