From 0132c3e1777ceabc24c7d209b7cbe78c28c03c09 Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Mon, 23 Jun 2014 11:46:16 -0400 Subject: [PATCH] sched/numa: Examine a task move when examining a task swap Running "perf bench numa mem -0 -m -P 1000 -p 8 -t 20" on a 4 node system results in 160 runnable threads on a system with 80 CPU threads. Once a process has nearly converged, with 39 threads on one node and 1 thread on another node, the remaining thread will be unable to migrate to its preferred node through a task swap. However, a simple task move would make the workload converge, witout causing an imbalance. Test for this unlikely occurrence, and attempt a task move to the preferred nid when it happens. # Running main, "perf bench numa mem -p 8 -t 20 -0 -m -P 1000" ### # 160 tasks will execute (on 4 nodes, 80 CPUs): # -1x 0MB global shared mem operations # -1x 1000MB process shared mem operations # -1x 0MB thread local mem operations ### ### # # 0.0% [0.2 mins] 0/0 1/1 36/2 0/0 [36/3 ] l: 0-0 ( 0) {0-2} # 0.0% [0.3 mins] 43/3 37/2 39/2 41/3 [ 6/10] l: 0-1 ( 1) {1-2} # 0.0% [0.4 mins] 42/3 38/2 40/2 40/2 [ 4/9 ] l: 1-2 ( 1) [50.0%] {1-2} # 0.0% [0.6 mins] 41/3 39/2 40/2 40/2 [ 2/9 ] l: 2-4 ( 2) [50.0%] {1-2} # 0.0% [0.7 mins] 40/2 40/2 40/2 40/2 [ 0/8 ] l: 3-5 ( 2) [40.0%] ( 41.8s converged) Without this patch, this same perf bench numa mem run had to rely on the scheduler load balancer to first balance out the load (moving a random task), before a task swap could complete the NUMA convergence. The load balancer does not normally take action unless the load difference exceeds 25%. Convergence times of over half an hour have been observed without this patch. With this patch, the NUMA balancing code will simply migrate the task, if that does not cause an imbalance. Also skip examining a CPU in detail if the improvement on that CPU is no more than the best we already have. Signed-off-by: Rik van Riel Cc: chegu_vinod@hp.com Cc: mgorman@suse.de Cc: Linus Torvalds Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-ggthh0rnh0yua6o5o3p6cr1o@git.kernel.org Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index cebb312e874b..9d1734a724a8 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1155,6 +1155,7 @@ static void task_numa_compare(struct task_numa_env *env, long src_load, dst_load; long load; long imp = env->p->numa_group ? groupimp : taskimp; + long moveimp = imp; rcu_read_lock(); cur = ACCESS_ONCE(dst_rq->curr); @@ -1201,7 +1202,7 @@ static void task_numa_compare(struct task_numa_env *env, } } - if (imp < env->best_imp) + if (imp <= env->best_imp && moveimp <= env->best_imp) goto unlock; if (!cur) { @@ -1214,7 +1215,8 @@ static void task_numa_compare(struct task_numa_env *env, } /* Balance doesn't matter much if we're running a task per cpu */ - if (src_rq->nr_running == 1 && dst_rq->nr_running == 1) + if (imp > env->best_imp && src_rq->nr_running == 1 && + dst_rq->nr_running == 1) goto assign; /* @@ -1230,6 +1232,23 @@ balance: src_load += effective_load(tg, env->src_cpu, -load, -load); dst_load += effective_load(tg, env->dst_cpu, load, load); + if (moveimp > imp && moveimp > env->best_imp) { + /* + * If the improvement from just moving env->p direction is + * better than swapping tasks around, check if a move is + * possible. Store a slightly smaller score than moveimp, + * so an actually idle CPU will win. + */ + if (!load_too_imbalanced(src_load, dst_load, env)) { + imp = moveimp - 1; + cur = NULL; + goto assign; + } + } + + if (imp <= env->best_imp) + goto unlock; + if (cur) { /* Cur moves in the opposite direction. */ load = cur->se.load.weight; -- 2.30.2