[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <165510981202.4207.14005671845758536625.tip-bot2@tip-bot2>
Date: Mon, 13 Jun 2022 08:43:32 -0000
From: "tip-bot2 for Mel Gorman" <tip-bot2@...utronix.de>
To: linux-tip-commits@...r.kernel.org
Cc: Mel Gorman <mgorman@...hsingularity.net>,
"Peter Zijlstra (Intel)" <peterz@...radead.org>,
K Prateek Nayak <kprateek.nayak@....com>, x86@...nel.org,
linux-kernel@...r.kernel.org
Subject: [tip: sched/core] sched/numa: Initialise numa_migrate_retry
The following commit has been merged into the sched/core branch of tip:
Commit-ID: 70ce3ea9aa4ed901c8a90de667df5ef307766e71
Gitweb: https://git.kernel.org/tip/70ce3ea9aa4ed901c8a90de667df5ef307766e71
Author: Mel Gorman <mgorman@...hsingularity.net>
AuthorDate: Fri, 20 May 2022 11:35:16 +01:00
Committer: Peter Zijlstra <peterz@...radead.org>
CommitterDate: Mon, 13 Jun 2022 10:29:59 +02:00
sched/numa: Initialise numa_migrate_retry
On clone, numa_migrate_retry is inherited from the parent which means
that the first NUMA placement of a task is non-deterministic. This
affects when load balancing recognises numa tasks and whether to
migrate "regular", "remote" or "all" tasks between NUMA scheduler
domains.
Signed-off-by: Mel Gorman <mgorman@...hsingularity.net>
Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
Tested-by: K Prateek Nayak <kprateek.nayak@....com>
Link: https://lore.kernel.org/r/20220520103519.1863-2-mgorman@techsingularity.net
---
kernel/sched/fair.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 77b2048..51836ef 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2885,6 +2885,7 @@ void init_numa_balancing(unsigned long clone_flags, struct task_struct *p)
p->node_stamp = 0;
p->numa_scan_seq = mm ? mm->numa_scan_seq : 0;
p->numa_scan_period = sysctl_numa_balancing_scan_delay;
+ p->numa_migrate_retry = 0;
/* Protect against double add, see task_tick_numa and task_numa_work */
p->numa_work.next = &p->numa_work;
p->numa_faults = NULL;
Powered by blists - more mailing lists