From: Peter Zijlstra Date: Mon, 27 Jul 2009 12:04:49 +0000 (+0200) Subject: sched: Fix cgroup smp fairness X-Git-Tag: v2.6.32-rc1~719^2~39 X-Git-Url: http://git.openpandora.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=a5004278f0525dcb9aa43703ef77bf371ea837cd;p=pandora-kernel.git sched: Fix cgroup smp fairness Commit ec4e0e2fe018992d980910db901637c814575914 ("fix inconsistency when redistribute per-cpu tg->cfs_rq shares") broke cgroup smp fairness. In order to avoid starvation of newly placed tasks, we never quite set the share of an empty cpu group-task to 0, but instead we set it as if there's a single NICE-0 task present. If however we actually set this in cfs_rq[cpu]->shares, that means the total shares for that group will be slightly inflated every time we balance, causing the observed unfairness. Fix this by setting cfs_rq[cpu]->shares to 0 but actually setting the effective weight of the related se to the inflated number. Signed-off-by: Peter Zijlstra LKML-Reference: <1248696557.6987.1615.camel@twins> Signed-off-by: Ingo Molnar --- Reading git-diff-tree failed