sched/numa: Use group_weights to identify if migration degrades locality
On NUMA_BACKPLANE and NUMA_GLUELESS_MESH systems, tasks/memory should be consolidated to the closest group of nodes. In such a case, relying on group_fault metric may not always help to consolidate. There can always be a case where a node closer to the preferred node may have lesser faults than a node further away from the preferred node. In such a case, moving to node with more faults might avoid numa consolidation. Using group_weight would help to consolidate task/memory around the preferred_node. While here, to be on the conservative side, don't override migrate thread degrades locality logic for CPU_NEWLY_IDLE load balancing. Note: Similar problems exist with should_numa_migrate_memory and will be dealt separately. Running SPECjbb2005 on a 4 node machine and comparing bops/JVM JVMS LAST_PATCH WITH_PATCH %CHANGE 16 25645.4 25960 1.22 1 72142 73550 1.95 Running SPECjbb2005 on a 16 node machine and comparing bops/JVM JVMS LAST_PATCH WITH_PATCH %CHANGE 8 110199 120071 8.958 1 176303 176249 -0.03 (numbers from v1 based on v4.17-rc5) Testcase Time: Min Max Avg StdDev numa01.sh Real: 490.04 774.86 596.26 96.46 numa01.sh Sys: 151.52 242.88 184.82 31.71 numa01.sh User: 41418.41 60844.59 48776.09 6564.27 numa02.sh Real: 60.14 62.94 60.98 1.00 numa02.sh Sys: 16.11 30.77 21.20 5.28 numa02.sh User: 5184.33 5311.09 5228.50 44.24 numa03.sh Real: 790.95 856.35 826.41 24.11 numa03.sh Sys: 114.93 118.85 117.05 1.63 numa03.sh User: 60990.99 64959.28 63470.43 1415.44 numa04.sh Real: 434.37 597.92 504.87 59.70 numa04.sh Sys: 237.63 397.40 289.74 55.98 numa04.sh User: 34854.87 41121.83 38572.52 2615.84 numa05.sh Real: 386.77 448.90 417.22 22.79 numa05.sh Sys: 149.23 379.95 303.04 79.55 numa05.sh User: 32951.76 35959.58 34562.18 1034.05 Testcase Time: Min Max Avg StdDev %Change numa01.sh Real: 493.19 672.88 597.51 59.38 -0.20% numa01.sh Sys: 150.09 245.48 207.76 34.26 -11.0% numa01.sh User: 41928.51 53779.17 48747.06 3901.39 0.059% numa02.sh Real: 60.63 62.87 61.22 0.83 -0.39% numa02.sh Sys: 16.64 27.97 20.25 4.06 4.691% numa02.sh User: 5222.92 5309.60 5254.03 29.98 -0.48% numa03.sh Real: 821.52 902.15 863.60 32.41 -4.30% numa03.sh Sys: 112.04 130.66 118.35 7.08 -1.09% numa03.sh User: 62245.16 69165.14 66443.04 2450.32 -4.47% numa04.sh Real: 414.53 519.57 476.25 37.00 6.009% numa04.sh Sys: 181.84 335.67 280.41 54.07 3.327% numa04.sh User: 33924.50 39115.39 37343.78 1934.26 3.290% numa05.sh Real: 408.30 441.45 417.90 12.05 -0.16% numa05.sh Sys: 233.41 381.60 295.58 57.37 2.523% numa05.sh User: 33301.31 35972.50 34335.19 938.94 0.661% Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@surriel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1529514181-9842-16-git-send-email-srikar@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
parent
30619c89b1
commit
f35678b6a1
|
@ -6899,8 +6899,8 @@ static int task_hot(struct task_struct *p, struct lb_env *env)
|
||||||
static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
|
static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
|
||||||
{
|
{
|
||||||
struct numa_group *numa_group = rcu_dereference(p->numa_group);
|
struct numa_group *numa_group = rcu_dereference(p->numa_group);
|
||||||
unsigned long src_faults, dst_faults;
|
unsigned long src_weight, dst_weight;
|
||||||
int src_nid, dst_nid;
|
int src_nid, dst_nid, dist;
|
||||||
|
|
||||||
if (!static_branch_likely(&sched_numa_balancing))
|
if (!static_branch_likely(&sched_numa_balancing))
|
||||||
return -1;
|
return -1;
|
||||||
|
@ -6927,18 +6927,19 @@ static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
|
||||||
return 0;
|
return 0;
|
||||||
|
|
||||||
/* Leaving a core idle is often worse than degrading locality. */
|
/* Leaving a core idle is often worse than degrading locality. */
|
||||||
if (env->idle != CPU_NOT_IDLE)
|
if (env->idle == CPU_IDLE)
|
||||||
return -1;
|
return -1;
|
||||||
|
|
||||||
|
dist = node_distance(src_nid, dst_nid);
|
||||||
if (numa_group) {
|
if (numa_group) {
|
||||||
src_faults = group_faults(p, src_nid);
|
src_weight = group_weight(p, src_nid, dist);
|
||||||
dst_faults = group_faults(p, dst_nid);
|
dst_weight = group_weight(p, dst_nid, dist);
|
||||||
} else {
|
} else {
|
||||||
src_faults = task_faults(p, src_nid);
|
src_weight = task_weight(p, src_nid, dist);
|
||||||
dst_faults = task_faults(p, dst_nid);
|
dst_weight = task_weight(p, dst_nid, dist);
|
||||||
}
|
}
|
||||||
|
|
||||||
return dst_faults < src_faults;
|
return dst_weight < src_weight;
|
||||||
}
|
}
|
||||||
|
|
||||||
#else
|
#else
|
||||||
|
|
Loading…
Reference in New Issue