mirror of https://gitee.com/openkylin/linux.git
sched/numa: Set preferred_node based on best_cpu
Currently preferred node is set to dst_nid which is the last node in the iteration whose group weight or task weight is greater than the current node. However it doesn't guarantee that dst_nid has the numa capacity to move. It also doesn't guarantee that dst_nid has the best_cpu which is the CPU/node ideal for node migration. Lets consider faults on a 4 node system with group weight numbers in different nodes being in 0 < 1 < 2 < 3 proportion. Consider the task is running on 3 and 0 is its preferred node but its capacity is full. Consider nodes 1, 2 and 3 have capacity. Then the task should be migrated to node 1. Currently the task gets moved to node 2. env.dst_nid points to the last node whose faults were greater than current node. Modify to set the preferred node based of best_cpu. Earlier setting preferred node was skipped if nr_active_nodes is 1. This could result in the task being moved out of the preferred node to a random node during regular load balancing. Also while modifying task_numa_migrate(), use sched_setnuma to set preferred node. This ensures out numa accounting is correct. Running SPECjbb2005 on a 4 node machine and comparing bops/JVM JVMS LAST_PATCH WITH_PATCH %CHANGE 16 25122.9 25549.6 1.698 1 73850 73190 -0.89 Running SPECjbb2005 on a 16 node machine and comparing bops/JVM JVMS LAST_PATCH WITH_PATCH %CHANGE 8 105930 113437 7.08676 1 178624 196130 9.80047 (numbers from v1 based on v4.17-rc5) Testcase Time: Min Max Avg StdDev numa01.sh Real: 435.78 653.81 534.58 83.20 numa01.sh Sys: 121.93 187.18 145.90 23.47 numa01.sh User: 37082.81 51402.80 43647.60 5409.75 numa02.sh Real: 60.64 61.63 61.19 0.40 numa02.sh Sys: 14.72 25.68 19.06 4.03 numa02.sh User: 5210.95 5266.69 5233.30 20.82 numa03.sh Real: 746.51 808.24 780.36 23.88 numa03.sh Sys: 97.26 108.48 105.07 4.28 numa03.sh User: 58956.30 61397.05 60162.95 1050.82 numa04.sh Real: 465.97 519.27 484.81 19.62 numa04.sh Sys: 304.43 359.08 334.68 20.64 numa04.sh User: 37544.16 41186.15 39262.44 1314.91 numa05.sh Real: 411.57 457.20 433.29 16.58 numa05.sh Sys: 230.05 435.48 339.95 67.58 numa05.sh User: 33325.54 36896.31 35637.84 1222.64 Testcase Time: Min Max Avg StdDev %Change numa01.sh Real: 506.35 794.46 599.06 104.26 -10.76% numa01.sh Sys: 150.37 223.56 195.99 24.94 -25.55% numa01.sh User: 43450.69 61752.04 49281.50 6635.33 -11.43% numa02.sh Real: 60.33 62.40 61.31 0.90 -0.195% numa02.sh Sys: 18.12 31.66 24.28 5.89 -21.49% numa02.sh User: 5203.91 5325.32 5260.29 49.98 -0.513% numa03.sh Real: 696.47 853.62 745.80 57.28 4.6339% numa03.sh Sys: 85.68 123.71 97.89 13.48 7.3347% numa03.sh User: 55978.45 66418.63 59254.94 3737.97 1.5323% numa04.sh Real: 444.05 514.83 497.06 26.85 -2.464% numa04.sh Sys: 230.39 375.79 316.23 48.58 5.8343% numa04.sh User: 35403.12 41004.10 39720.80 2163.08 -1.153% numa05.sh Real: 423.09 460.41 439.57 13.92 -1.428% numa05.sh Sys: 287.38 480.15 369.37 68.52 -7.964% numa05.sh User: 34732.12 38016.80 36255.85 1070.51 -1.704% Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Mel Gorman <mgorman@techsingularity.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> 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/1529514181-9842-5-git-send-email-srikar@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
Srikar Dronamraju
Ingo Molnar
parent
5f95ba7a43
commit
8cd45eee43
|
|
@ -1765,7 +1765,7 @@ static int task_numa_migrate(struct task_struct *p)
|
|||
* elsewhere, so there is no point in (re)trying.
|
||||
*/
|
||||
if (unlikely(!sd)) {
|
||||
p->numa_preferred_nid = task_node(p);
|
||||
sched_setnuma(p, task_node(p));
|
||||
return -EINVAL;
|
||||
}
|
||||
|
||||
|
|
@ -1824,15 +1824,13 @@ static int task_numa_migrate(struct task_struct *p)
|
|||
* trying for a better one later. Do not set the preferred node here.
|
||||
*/
|
||||
if (p->numa_group) {
|
||||
struct numa_group *ng = p->numa_group;
|
||||
|
||||
if (env.best_cpu == -1)
|
||||
nid = env.src_nid;
|
||||
else
|
||||
nid = env.dst_nid;
|
||||
nid = cpu_to_node(env.best_cpu);
|
||||
|
||||
if (ng->active_nodes > 1 && numa_is_active_node(env.dst_nid, ng))
|
||||
sched_setnuma(p, env.dst_nid);
|
||||
if (nid != p->numa_preferred_nid)
|
||||
sched_setnuma(p, nid);
|
||||
}
|
||||
|
||||
/* No better CPU than the current one was found. */
|
||||
|
|
|
|||
Loading…
Reference in New Issue