From: Nick Piggin <piggin@cyberone.com.au>

I was able to reproduce the half-load kernbench problems on the non-NUMA
stp 8-way.

I made a pretty simple "lessidle" patch which tweaks some sched domain
parameters to be more inclined to move tasks, especially when idle.  That
brought performance to nearly exactly the same as 2.6.3.

Context switches are still up, but user and system time is down a bit.  So
indicates it is still less balance-happy but is obviously enough to bring
the idle time down.

2.6.3:                http://khack.osdl.org/stp/288459/
2.6.3-mm4-lessidle:   http://khack.osdl.org/stp/288995/

So it is more a matter of tuning than anything fundamental.  It may be that
the patch now makes balancing too aggressive, but it is probably better to
err on the side that is closer to 2.6 behaviour.

I haven't tested this on much else.


---

 25-akpm/include/linux/sched.h |   16 ++++++++--------
 25-akpm/kernel/sched.c        |    5 +++++
 2 files changed, 13 insertions(+), 8 deletions(-)

diff -puN include/linux/sched.h~sched-domains-improvements include/linux/sched.h
--- 25/include/linux/sched.h~sched-domains-improvements	Mon Mar  1 16:00:10 2004
+++ 25-akpm/include/linux/sched.h	Mon Mar  1 16:00:10 2004
@@ -565,11 +565,11 @@ struct sched_domain {
 	.parent			= NULL,			\
 	.groups			= NULL,			\
 	.min_interval		= 1,			\
-	.max_interval		= 8,			\
-	.busy_factor		= 32,			\
+	.max_interval		= 4,			\
+	.busy_factor		= 64,			\
 	.imbalance_pct		= 125,			\
-	.cache_hot_time		= (5*1000000),		\
-	.cache_nice_tries	= 2,			\
+	.cache_hot_time		= (5*1000000/2),	\
+	.cache_nice_tries	= 1,			\
 	.flags			= SD_FLAG_FASTMIGRATE | SD_FLAG_NEWIDLE,\
 	.balance_interval	= 1,			\
 	.nr_balance_failed	= 0,			\
@@ -581,11 +581,11 @@ struct sched_domain {
 	.span			= CPU_MASK_NONE,	\
 	.parent			= NULL,			\
 	.groups			= NULL,			\
-	.min_interval		= 20,			\
-	.max_interval		= 1000*fls(num_online_cpus()),\
-	.busy_factor		= 4,			\
+	.min_interval		= 8,			\
+	.max_interval		= 256*fls(num_online_cpus()),\
+	.busy_factor		= 8,			\
 	.imbalance_pct		= 125,			\
-	.cache_hot_time		= (5*1000000),		\
+	.cache_hot_time		= (10*1000000),		\
 	.cache_nice_tries	= 1,			\
 	.flags			= SD_FLAG_EXEC,		\
 	.balance_interval	= 1,			\
diff -puN kernel/sched.c~sched-domains-improvements kernel/sched.c
--- 25/kernel/sched.c~sched-domains-improvements	Mon Mar  1 16:00:10 2004
+++ 25-akpm/kernel/sched.c	Mon Mar  1 16:00:10 2004
@@ -1476,6 +1476,11 @@ nextgroup:
 	return busiest;
 
 out_balanced:
+	if (busiest && idle == NEWLY_IDLE) {
+		*imbalance = 1;
+		return busiest;
+	}
+
 	*imbalance = 0;
 	return NULL;
 }

_