linux/include
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
..
acpi Merge branch 'release' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux 2012-10-08 07:14:06 +09:00
asm-generic mm: numa: pte_numa() and pmd_numa() 2012-12-11 14:42:36 +00:00
clocksource
crypto Merge branch 'modules-next' of git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux 2012-10-14 13:39:34 -07:00
drm drm/radeon: add some new SI PCI ids 2012-10-23 10:23:49 -04:00
keys KEYS: Asymmetric key pluggable data parsers 2012-10-08 13:50:13 +10:30
linux mm: sched: numa: Implement slow start for working set sampling 2012-12-11 14:42:47 +00:00
math-emu
media Merge branch 'exynos-drm-next' of git://git.infradead.org/users/kmpark/linux-samsung into drm-next 2012-10-07 21:06:33 +10:00
memory
misc
net Merge branch 'for-john' of git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211 2012-10-29 14:14:48 -04:00
pcmcia
ras
rdma infiniband: pass rdma_cm module to netlink_dump_start 2012-10-07 00:30:56 -04:00
rxrpc
scsi SCSI misc on 20121012 2012-10-13 10:57:01 +09:00
sound ALSA: Add a reference counter to card instance 2012-10-30 11:07:10 +01:00
target target: Add target_submit_cmd_map_sgls for SGL fabric memory passthrough 2012-10-02 14:16:08 -07:00
trace mm: migrate: Add a tracepoint for migrate_pages 2012-12-11 14:28:35 +00:00
uapi mm: mempolicy: Hide MPOL_NOOP and MPOL_MF_LAZY from userspace for now 2012-12-11 14:42:44 +00:00
video fbdev updates for 3.7 2012-10-12 10:21:02 +09:00
xen Bug-fixes: 2012-11-10 06:56:21 +01:00
Kbuild UAPI: Remove empty non-UAPI Kbuild files 2012-10-17 12:31:15 +01:00