From: Nick Piggin Remove the special casing for idle CPU balancing. Things like this are hurting for example on SMT, where are single sibling being idle doesn't really warrant a really aggressive pull over the NUMA domain, for example. Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton --- 25-akpm/kernel/sched.c | 6 ------ 1 files changed, 6 deletions(-) diff -puN kernel/sched.c~sched-no-aggressive-idle-balancing kernel/sched.c --- 25/kernel/sched.c~sched-no-aggressive-idle-balancing 2005-02-24 19:54:49.000000000 -0800 +++ 25-akpm/kernel/sched.c 2005-02-24 19:54:49.000000000 -0800 @@ -1877,15 +1877,9 @@ nextgroup: /* Get rid of the scaling factor, rounding down as we divide */ *imbalance = *imbalance / SCHED_LOAD_SCALE; - return busiest; out_balanced: - if (busiest && (idle == NEWLY_IDLE || - (idle == SCHED_IDLE && max_load > SCHED_LOAD_SCALE)) ) { - *imbalance = 1; - return busiest; - } *imbalance = 0; return NULL; _