sched, numa, mm: Implement slow start for working set sampling

Add a 1 second delay before starting to scan the working set of
a task and starting to balance it amongst nodes.

[ note that before the constant per task WSS sampling rate patch
  the initial scan would happen much later still, in effect that
  patch caused this regression. ]

The theory is that short-run tasks benefit very little from NUMA
placement: they come and go, and they better stick to the node
they were started on. As tasks mature and rebalance to other CPUs
and nodes, so does their NUMA placement have to change and so
does it start to matter more and more.

In practice this change fixes an observable kbuild regression:

   # [ a perf stat --null --repeat 10 test of ten bzImage builds to /dev/shm ]

   !NUMA:
   45.291088843 seconds time elapsed                                          ( +-  0.40% )
   45.154231752 seconds time elapsed                                          ( +-  0.36% )

   +NUMA, no slow start:
   46.172308123 seconds time elapsed                                          ( +-  0.30% )
   46.343168745 seconds time elapsed                                          ( +-  0.25% )

   +NUMA, 1 sec slow start:
   45.224189155 seconds time elapsed                                          ( +-  0.25% )
   45.160866532 seconds time elapsed                                          ( +-  0.17% )

and it also fixes an observable perf bench (hackbench) regression:

   # perf stat --null --repeat 10 perf bench sched messaging

   -NUMA:

   -NUMA:                  0.246225691 seconds time elapsed                   ( +-  1.31% )
   +NUMA no slow start:    0.252620063 seconds time elapsed                   ( +-  1.13% )

   +NUMA 1sec delay:       0.248076230 seconds time elapsed                   ( +-  1.35% )

The implementation is simple and straightforward, most of the patch
deals with adding the /proc/sys/kernel/sched_numa_scan_delay_ms tunable
knob.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Link: http://lkml.kernel.org/n/tip-vn7p3ynbwqt3qqewhdlvjltc@git.kernel.org
[ Wrote the changelog, ran measurements, tuned the default. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9007119b231000884aa508d18140b568bce845a9..2eedef9d18ecbf1983377f73e9f6528c7cc20cf1 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2020,6 +2020,7 @@ enum sched_tunable_scaling {
 };
 extern enum sched_tunable_scaling sysctl_sched_tunable_scaling;
 
+extern unsigned int sysctl_sched_numa_scan_delay;
 extern unsigned int sysctl_sched_numa_scan_period_min;
 extern unsigned int sysctl_sched_numa_scan_period_max;
 extern unsigned int sysctl_sched_numa_scan_size;

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b607bc8b833b17a1c5fb05ae4dc7d5a7b409eb41..407fd65f6b8cc24664ab1d9e02aa018d3cbd9853 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1545,7 +1545,7 @@ static void __sched_fork(struct task_struct *p)
        p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0;
        p->numa_migrate_seq = p->mm ? p->mm->numa_scan_seq - 1 : 0;
        p->numa_faults = NULL;
-       p->numa_scan_period = sysctl_sched_numa_scan_period_min;
+       p->numa_scan_period = sysctl_sched_numa_scan_delay;
        p->numa_work.next = &p->numa_work;
 #endif /* CONFIG_SCHED_NUMA */
 }

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e5186fe75912bba1ba13321031553b05c02dc69b..c0a2e0ad2acb57020e614e49bb9dff057d8c72be 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -827,11 +827,12 @@ static void account_numa_dequeue(struct rq *rq, struct task_struct *p)
 }
 
 /*
- * numa task sample period in ms: 5s
+ * Scan @scan_size MB every @scan_period after an initial @scan_delay.
  */
-unsigned int sysctl_sched_numa_scan_period_min = 100;
-unsigned int sysctl_sched_numa_scan_period_max = 100*16;
-unsigned int sysctl_sched_numa_scan_size = 256;   /* MB */
+unsigned int sysctl_sched_numa_scan_delay = 1000;      /* ms */
+unsigned int sysctl_sched_numa_scan_period_min = 100;  /* ms */
+unsigned int sysctl_sched_numa_scan_period_max = 100*16;/* ms */
+unsigned int sysctl_sched_numa_scan_size = 256;                /* MB */
 
 /*
  * Wait for the 2-sample stuff to settle before migrating again
@@ -985,6 +986,8 @@ void task_tick_numa(struct rq *rq, struct task_struct *curr)
        period = (u64)curr->numa_scan_period * NSEC_PER_MSEC;
 
        if (now - curr->node_stamp > period) {
+               if (!curr->node_stamp)
+                       curr->numa_scan_period = sysctl_sched_numa_scan_period_min;
                curr->node_stamp = now;
 
                /*

diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index f33866acb8811cecce7c2d6e802bf5f1782e0f9a..b769d25e20e7bfd18eeedd03b886715965d5dbbb 100644 (file)
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -352,6 +352,13 @@ static struct ctl_table kern_table[] = {
        },
 #endif /* CONFIG_SMP */
 #ifdef CONFIG_SCHED_NUMA
+       {
+               .procname       = "sched_numa_scan_delay_ms",
+               .data           = &sysctl_sched_numa_scan_delay,
+               .maxlen         = sizeof(unsigned int),
+               .mode           = 0644,
+               .proc_handler   = proc_dointvec,
+       },
        {
                .procname       = "sched_numa_scan_period_min_ms",
                .data           = &sysctl_sched_numa_scan_period_min,