Re: [PATCH 11/19] sched/numa: Restrict migrating in parallel to the same node.
> > The commit does cause some performance regression but is needed from > > a fairness/correctness perspective. > > > > While it may cause some performance regressions, it may be due to either > a) some workloads benefit from overloading a node if the tasks idle > frequently or b) the regression may be due to delayed convergence. I'm > not 100% convinced this needs to be done from a correctness point of > view based on just this microbenchmark > I will get back with Specjbb2005 numbers as suggested by Rik.
Re: [PATCH 11/19] sched/numa: Restrict migrating in parallel to the same node.
On Mon, Jun 04, 2018 at 03:30:20PM +0530, Srikar Dronamraju wrote: > Since task migration under numa balancing can happen in parallel, more > than one task might choose to move to the same node at the same time. > This can cause load imbalances at the node level. > > The problem is more likely if there are more cores per node or more > nodes in system. > > Use a per-node variable to indicate if task migration > to the node under numa balance is currently active. > This per-node variable will not track swapping of tasks. > > Testcase Time: Min Max Avg StdDev > numa01.sh Real: 434.84 676.90 550.53 106.24 > numa01.sh Sys: 125.98 217.34 179.41 30.35 > numa01.sh User:38318.4853789.5645864.17 6620.80 > numa02.sh Real: 60.06 61.27 60.590.45 > numa02.sh Sys: 14.25 17.86 16.091.28 > numa02.sh User: 5190.13 5225.67 5209.24 13.19 > numa03.sh Real: 748.21 960.25 823.15 73.51 > numa03.sh Sys: 96.68 122.10 110.42 11.29 > numa03.sh User:58222.1672595.2763552.22 5048.87 > numa04.sh Real: 433.08 630.55 499.30 68.15 > numa04.sh Sys: 245.22 386.75 306.09 63.32 > numa04.sh User:35014.6846151.7238530.26 3924.65 > numa05.sh Real: 394.77 410.07 401.415.99 > numa05.sh Sys: 212.40 301.82 256.23 35.41 > numa05.sh User:33224.8634201.4033665.61 313.40 > > Testcase Time: Min Max Avg StdDev %Change > numa01.sh Real: 674.61 997.71 785.01 115.95 -29.86% > numa01.sh Sys: 180.87 318.88 270.13 51.32 -33.58% > numa01.sh User:54001.3071936.5060495.48 6237.55 -24.18% > numa02.sh Real: 60.62 62.30 61.460.62 -1.415% > numa02.sh Sys: 15.01 33.63 24.386.81 -34.00% > numa02.sh User: 5234.20 5325.60 5276.23 38.85 -1.269% > numa03.sh Real: 827.62 946.85 914.48 44.58 -9.987% > numa03.sh Sys: 135.55 172.40 158.46 12.75 -30.31% > numa03.sh User:64839.4273195.4470805.96 3061.20 -10.24% > numa04.sh Real: 481.01 608.76 521.14 47.28 -4.190% > numa04.sh Sys: 329.59 373.15 353.20 14.20 -13.33% > numa04.sh User:37649.0940722.9438806.32 1072.32 -0.711% > numa05.sh Real: 399.21 415.38 409.885.54 -2.066% > numa05.sh Sys: 319.46 418.57 363.31 37.62 -29.47% > numa05.sh User:33727.7734732.6834127.41 447.11 -1.353% > > The commit does cause some performance regression but is needed from > a fairness/correctness perspective. > While it may cause some performance regressions, it may be due to either a) some workloads benefit from overloading a node if the tasks idle frequently or b) the regression may be due to delayed convergence. I'm not 100% convinced this needs to be done from a correctness point of view based on just this microbenchmark -- Mel Gorman SUSE Labs
Re: [PATCH 11/19] sched/numa: Restrict migrating in parallel to the same node.
On Mon, 2018-06-04 at 15:30 +0530, Srikar Dronamraju wrote: > Since task migration under numa balancing can happen in parallel, > more > than one task might choose to move to the same node at the same time. > This can cause load imbalances at the node level. > > The problem is more likely if there are more cores per node or more > nodes in system. > > Use a per-node variable to indicate if task migration > to the node under numa balance is currently active. > This per-node variable will not track swapping of tasks. > The commit does cause some performance regression but is needed from > a fairness/correctness perspective. Does it help any "real workloads", even simple things like SpecJBB2005? If this patch only causes regressions, and does not help any workloads, I would argue that it is not in fact needed. -- All Rights Reversed. signature.asc Description: This is a digitally signed message part
[PATCH 11/19] sched/numa: Restrict migrating in parallel to the same node.
Since task migration under numa balancing can happen in parallel, more than one task might choose to move to the same node at the same time. This can cause load imbalances at the node level. The problem is more likely if there are more cores per node or more nodes in system. Use a per-node variable to indicate if task migration to the node under numa balance is currently active. This per-node variable will not track swapping of tasks. Testcase Time: Min Max Avg StdDev numa01.sh Real: 434.84 676.90 550.53 106.24 numa01.sh Sys: 125.98 217.34 179.41 30.35 numa01.sh User:38318.4853789.5645864.17 6620.80 numa02.sh Real: 60.06 61.27 60.590.45 numa02.sh Sys: 14.25 17.86 16.091.28 numa02.sh User: 5190.13 5225.67 5209.24 13.19 numa03.sh Real: 748.21 960.25 823.15 73.51 numa03.sh Sys: 96.68 122.10 110.42 11.29 numa03.sh User:58222.1672595.2763552.22 5048.87 numa04.sh Real: 433.08 630.55 499.30 68.15 numa04.sh Sys: 245.22 386.75 306.09 63.32 numa04.sh User:35014.6846151.7238530.26 3924.65 numa05.sh Real: 394.77 410.07 401.415.99 numa05.sh Sys: 212.40 301.82 256.23 35.41 numa05.sh User:33224.8634201.4033665.61 313.40 Testcase Time: Min Max Avg StdDev %Change numa01.sh Real: 674.61 997.71 785.01 115.95 -29.86% numa01.sh Sys: 180.87 318.88 270.13 51.32 -33.58% numa01.sh User:54001.3071936.5060495.48 6237.55 -24.18% numa02.sh Real: 60.62 62.30 61.460.62 -1.415% numa02.sh Sys: 15.01 33.63 24.386.81 -34.00% numa02.sh User: 5234.20 5325.60 5276.23 38.85 -1.269% numa03.sh Real: 827.62 946.85 914.48 44.58 -9.987% numa03.sh Sys: 135.55 172.40 158.46 12.75 -30.31% numa03.sh User:64839.4273195.4470805.96 3061.20 -10.24% numa04.sh Real: 481.01 608.76 521.14 47.28 -4.190% numa04.sh Sys: 329.59 373.15 353.20 14.20 -13.33% numa04.sh User:37649.0940722.9438806.32 1072.32 -0.711% numa05.sh Real: 399.21 415.38 409.885.54 -2.066% numa05.sh Sys: 319.46 418.57 363.31 37.62 -29.47% numa05.sh User:33727.7734732.6834127.41 447.11 -1.353% The commit does cause some performance regression but is needed from a fairness/correctness perspective. Signed-off-by: Srikar Dronamraju --- include/linux/mmzone.h | 1 + kernel/sched/fair.c| 14 ++ mm/page_alloc.c| 1 + 3 files changed, 16 insertions(+) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 32699b2..b0767703 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -677,6 +677,7 @@ struct zonelist { /* Number of pages migrated during the rate limiting time interval */ unsigned long numabalancing_migrate_nr_pages; + int active_node_migrate; #endif /* * This is a per-node reserve of pages that are not available diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 3e19e32..259c343 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1478,11 +1478,22 @@ struct task_numa_env { static void task_numa_assign(struct task_numa_env *env, struct task_struct *p, long imp) { + pg_data_t *pgdat = NODE_DATA(cpu_to_node(env->dst_cpu)); struct rq *rq = cpu_rq(env->dst_cpu); if (xchg(&rq->numa_migrate_on, 1)) return; + if (!env->best_task && env->best_cpu != -1) + WRITE_ONCE(pgdat->active_node_migrate, 0); + + if (!p) { + if (xchg(&pgdat->active_node_migrate, 1)) { + WRITE_ONCE(rq->numa_migrate_on, 0); + return; + } + } + if (env->best_cpu != -1) { rq = cpu_rq(env->best_cpu); WRITE_ONCE(rq->numa_migrate_on, 0); @@ -1819,8 +1830,11 @@ static int task_numa_migrate(struct task_struct *p) best_rq = cpu_rq(env.best_cpu); if (env.best_task == NULL) { + pg_data_t *pgdat = NODE_DATA(cpu_to_node(env.dst_cpu)); + ret = migrate_task_to(p, env.best_cpu); WRITE_ONCE(best_rq->numa_migrate_on, 0); + WRITE_ONCE(pgdat->active_node_migrate, 0); if (ret != 0) trace_sched_stick_numa(p, env.src_cpu,