leandrof/linux
1
0
Fork 0
forked from Minki/linux
Code Issues Pull Requests Packages Projects Releases Wiki Activity
4b96a29ba8
linux/kernel/sched
History
Peter Zijlstra 4b96a29ba8 mm: sched: numa: 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/numa_balancing_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>
[ Wrote the changelog, ran measurements, tuned the default. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
2012-12-11 14:42:47 +00:00
..
auto_group.c sched: Clean up parameter passing of proc_sched_autogroup_set_nice() 2012-03-02 12:23:49 +01:00
auto_group.h
clock.c
core.c mm: sched: numa: Implement slow start for working set sampling 2012-12-11 14:42:47 +00:00
cpupri.c sched: Fix minor code style issues 2012-07-26 11:47:00 +02:00
cpupri.h
cputime.c vtime: Consolidate system/idle context detection 2012-09-25 15:42:37 +02:00
debug.c sched/debug: Fix printing large integers on 32-bit platforms 2012-05-14 15:05:28 +02:00
fair.c mm: sched: numa: Implement slow start for working set sampling 2012-12-11 14:42:47 +00:00
features.h mm: numa: Add fault driven placement and migration 2012-12-11 14:42:45 +00:00
idle_task.c sched/nohz: Rewrite and fix load-avg computation -- again 2012-07-05 20:58:13 +02:00
Makefile sched: Move cputime code to its own file 2012-08-20 13:05:17 +02:00
rt.c sched: Remove __ARCH_WANT_INTERRUPTS_ON_CTXSW 2012-09-13 16:52:04 +02:00
sched.h mm: numa: Add fault driven placement and migration 2012-12-11 14:42:45 +00:00
stats.c sched: Remove sched_switch 2012-01-27 13:28:53 +01:00
stats.h
stop_task.c sched: Fix migration thread runtime bogosity 2012-08-13 18:41:55 +02:00