From 7bdb19f67f9d5ff45174cdd09756884a4949060c Mon Sep 17 00:00:00 2001
From: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Date: Wed, 20 Jun 2018 22:32:46 +0530
Subject: [PATCH] sched/numa: Use task faults only if numa_group is not yet set
up
References: bnc#1101669 optimise numa balancing for fast migrate
Patch-mainline: v4.19-rc1
Git-commit: f03bb6760b8e5e2bcecc88d2a2ef41c09adcab39
When numa_group faults are available, task_numa_placement only uses
numa_group faults to evaluate preferred node. However it still accounts
task faults and even evaluates the preferred node just based on task
faults just to discard it in favour of preferred node chosen on the
basis of numa_group.
Instead use task faults only if numa_group is not set.
Running SPECjbb2005 on a 4 node machine and comparing bops/JVM
JVMS LAST_PATCH WITH_PATCH %CHANGE
16 25549.6 25215.7 -1.30
1 73190 72107 -1.47
Running SPECjbb2005 on a 16 node machine and comparing bops/JVM
JVMS LAST_PATCH WITH_PATCH %CHANGE
8 113437 113372 -0.05
1 196130 177403 -9.54
(numbers from v1 based on v4.17-rc5)
Testcase Time: Min Max Avg StdDev
numa01.sh Real: 506.35 794.46 599.06 104.26
numa01.sh Sys: 150.37 223.56 195.99 24.94
numa01.sh User: 43450.69 61752.04 49281.50 6635.33
numa02.sh Real: 60.33 62.40 61.31 0.90
numa02.sh Sys: 18.12 31.66 24.28 5.89
numa02.sh User: 5203.91 5325.32 5260.29 49.98
numa03.sh Real: 696.47 853.62 745.80 57.28
numa03.sh Sys: 85.68 123.71 97.89 13.48
numa03.sh User: 55978.45 66418.63 59254.94 3737.97
numa04.sh Real: 444.05 514.83 497.06 26.85
numa04.sh Sys: 230.39 375.79 316.23 48.58
numa04.sh User: 35403.12 41004.10 39720.80 2163.08
numa05.sh Real: 423.09 460.41 439.57 13.92
numa05.sh Sys: 287.38 480.15 369.37 68.52
numa05.sh User: 34732.12 38016.80 36255.85 1070.51
Testcase Time: Min Max Avg StdDev %Change
numa01.sh Real: 478.45 565.90 515.11 30.87 16.29%
numa01.sh Sys: 207.79 271.04 232.94 21.33 -15.8%
numa01.sh User: 39763.93 47303.12 43210.73 2644.86 14.04%
numa02.sh Real: 60.00 61.46 60.78 0.49 0.871%
numa02.sh Sys: 15.71 25.31 20.69 3.42 17.35%
numa02.sh User: 5175.92 5265.86 5235.97 32.82 0.464%
numa03.sh Real: 776.42 834.85 806.01 23.22 -7.47%
numa03.sh Sys: 114.43 128.75 121.65 5.49 -19.5%
numa03.sh User: 60773.93 64855.25 62616.91 1576.39 -5.36%
numa04.sh Real: 456.93 511.95 482.91 20.88 2.930%
numa04.sh Sys: 178.09 460.89 356.86 94.58 -11.3%
numa04.sh User: 36312.09 42553.24 39623.21 2247.96 0.246%
numa05.sh Real: 393.98 493.48 436.61 35.59 0.677%
numa05.sh Sys: 164.49 329.15 265.87 61.78 38.92%
numa05.sh User: 33182.65 36654.53 35074.51 1187.71 3.368%
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mel Gorman <mgorman@suse.de>
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/1529514181-9842-6-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
kernel/sched/fair.c | 20 ++++++++++----------
1 file changed, 10 insertions(+), 10 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 2da454425767..f504c18e5c92 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2138,8 +2138,8 @@ static int preferred_group_nid(struct task_struct *p, int nid)
static void task_numa_placement(struct task_struct *p)
{
- int seq, nid, max_nid = -1, max_group_nid = -1;
- unsigned long max_faults = 0, max_group_faults = 0;
+ int seq, nid, max_nid = -1;
+ unsigned long max_faults = 0;
unsigned long fault_types[2] = { 0, 0 };
unsigned long total_faults;
u64 runtime, period;
@@ -2218,15 +2218,15 @@ static void task_numa_placement(struct task_struct *p)
}
}
- if (faults > max_faults) {
- max_faults = faults;
+ if (!p->numa_group) {
+ if (faults > max_faults) {
+ max_faults = faults;
+ max_nid = nid;
+ }
+ } else if (group_faults > max_faults) {
+ max_faults = group_faults;
max_nid = nid;
}
-
- if (group_faults > max_group_faults) {
- max_group_faults = group_faults;
- max_group_nid = nid;
- }
}
update_task_scan_period(p, fault_types[0], fault_types[1]);
@@ -2234,7 +2234,7 @@ static void task_numa_placement(struct task_struct *p)
if (p->numa_group) {
numa_group_count_active_nodes(p->numa_group);
spin_unlock_irq(group_lock);
- max_nid = preferred_group_nid(p, max_group_nid);
+ max_nid = preferred_group_nid(p, max_nid);
}
if (max_faults) {