summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorVaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>2008-12-18 23:26:16 +0530
committerIngo Molnar <mingo@elte.hu>2008-12-19 09:21:48 +0100
commitd5679bd11916eba5c8ee9033003e1a5ce56ece9a (patch)
treebb7c1bef4446e606ea23e4e6711a48013fed3666
parentafb8a9b70b86866a60e08b2956ae4e1406390336 (diff)
downloadop-kernel-dev-d5679bd11916eba5c8ee9033003e1a5ce56ece9a.zip
op-kernel-dev-d5679bd11916eba5c8ee9033003e1a5ce56ece9a.tar.gz
sched: favour lower logical cpu number for sched_mc balance
Impact: change load-balancing direction to match that of irqbalanced Just in case two groups have identical load, prefer to move load to lower logical cpu number rather than the present logic of moving to higher logical number. find_busiest_group() tries to look for a group_leader that has spare capacity to take more tasks and freeup an appropriate least loaded group. Just in case there is a tie and the load is equal, then the group with higher logical number is favoured. This conflicts with user space irqbalance daemon that will move interrupts to lower logical number if the system utilisation is very low. Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
-rw-r--r--kernel/sched.c4
1 files changed, 2 insertions, 2 deletions
diff --git a/kernel/sched.c b/kernel/sched.c
index 56b285c..94b9d11 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3241,7 +3241,7 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
*/
if ((sum_nr_running < min_nr_running) ||
(sum_nr_running == min_nr_running &&
- cpumask_first(sched_group_cpus(group)) <
+ cpumask_first(sched_group_cpus(group)) >
cpumask_first(sched_group_cpus(group_min)))) {
group_min = group;
min_nr_running = sum_nr_running;
@@ -3257,7 +3257,7 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
if (sum_nr_running <= group_capacity - 1) {
if (sum_nr_running > leader_nr_running ||
(sum_nr_running == leader_nr_running &&
- cpumask_first(sched_group_cpus(group)) >
+ cpumask_first(sched_group_cpus(group)) <
cpumask_first(sched_group_cpus(group_leader)))) {
group_leader = group;
leader_nr_running = sum_nr_running;
OpenPOWER on IntegriCloud