On Mon, 2014-09-01 at 14:55 +0200, Peter Zijlstra wrote: > But yes, unbounded errors here are a problem, sure relaxing the updates > makes things go fast, they also make things go skew.
Okay. In that case, would you like to take our original patch which avoids unnecessary updates? ----- Subject: [PATCH] sched: Reduce contention in update_cfs_rq_blocked_load When running workloads on 2+ socket systems, based on perf profiles, the update_cfs_rq_blocked_load function often shows up as taking up a noticeable % of run time. Much of the contention is in __update_cfs_rq_tg_load_contrib when we update the tg load contribution stats. However, it turns out that in many cases, they don't need to be updated and "tg_contrib" is 0. This patch adds a check in __update_cfs_rq_tg_load_contrib to skip updating tg load contribution stats when nothing needs to be updated. This reduces the cacheline contention that would be unnecessary. Cc: Yuyang Du <[email protected]> Cc: Aswin Chandramouleeswaran <[email protected]> Cc: Chegu Vinod <[email protected]> Cc: Scott J Norton <[email protected]> Reviewed-by: Ben Segall <[email protected]> Reviewed-by: Waiman Long <[email protected]> Signed-off-by: Jason Low <[email protected]> --- kernel/sched/fair.c | 3 +++ 1 files changed, 3 insertions(+), 0 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index d3427a8..45e346c 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2382,6 +2382,9 @@ static inline void __update_cfs_rq_tg_load_contrib(struct cfs_rq *cfs_rq, tg_contrib = cfs_rq->runnable_load_avg + cfs_rq->blocked_load_avg; tg_contrib -= cfs_rq->tg_load_contrib; + if (!tg_contrib) + return; + if (force_update || abs(tg_contrib) > cfs_rq->tg_load_contrib / 8) { atomic_long_add(tg_contrib, &tg->load_avg); cfs_rq->tg_load_contrib += tg_contrib; -- 1.7.1 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
