linux/include
Joonsoo Kim 7cf91a98e6 mm/compaction: speed up pageblock_pfn_to_page() when zone is contiguous
There is a performance drop report due to hugepage allocation and in
there half of cpu time are spent on pageblock_pfn_to_page() in
compaction [1].

In that workload, compaction is triggered to make hugepage but most of
pageblocks are un-available for compaction due to pageblock type and
skip bit so compaction usually fails.  Most costly operations in this
case is to find valid pageblock while scanning whole zone range.  To
check if pageblock is valid to compact, valid pfn within pageblock is
required and we can obtain it by calling pageblock_pfn_to_page().  This
function checks whether pageblock is in a single zone and return valid
pfn if possible.  Problem is that we need to check it every time before
scanning pageblock even if we re-visit it and this turns out to be very
expensive in this workload.

Although we have no way to skip this pageblock check in the system where
hole exists at arbitrary position, we can use cached value for zone
continuity and just do pfn_to_page() in the system where hole doesn't
exist.  This optimization considerably speeds up in above workload.

Before vs After
  Max: 1096 MB/s vs 1325 MB/s
  Min: 635 MB/s 1015 MB/s
  Avg: 899 MB/s 1194 MB/s

Avg is improved by roughly 30% [2].

[1]: http://www.spinics.net/lists/linux-mm/msg97378.html
[2]: https://lkml.org/lkml/2015/12/9/23

[akpm@linux-foundation.org: don't forget to restore zone->contiguous on error path, per Vlastimil]
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Reported-by: Aaron Lu <aaron.lu@intel.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Tested-by: Aaron Lu <aaron.lu@intel.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-15 16:55:16 -07:00
..
acpi ACPI / CPPC: remove redundant mbox_send_message() declaration 2016-02-03 01:09:52 +01:00
asm-generic Merge branch 'mm-readonly-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2016-03-14 16:58:50 -07:00
clocksource
crypto Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6 2016-01-22 11:58:43 -08:00
drm drm/atomic: Allow for holes in connector state, v2. 2016-02-19 13:24:03 +10:00
dt-bindings clk: tegra: Add the APB2APE audio clock on Tegra210 2016-02-02 15:49:29 +01:00
keys
kvm
linux mm/compaction: speed up pageblock_pfn_to_page() when zone is contiguous 2016-03-15 16:55:16 -07:00
math-emu
media [media] vb2: fix nasty vb2_thread regression 2016-02-04 09:13:46 -02:00
memory
misc
net Another small set of fixes: 2016-02-24 16:58:12 -05:00
pcmcia
ras
rdma IB/mlx4: Enable send of RoCE QP1 packets with IP/UDP headers 2016-01-19 15:35:01 -05:00
rxrpc
scsi Initial roundup of 4.5 merge window patches 2016-01-23 18:45:06 -08:00
soc ARM: SoC driver updates for v4.5 2016-01-20 18:42:30 -08:00
sound ALSA: hda - Loop interrupt handling until really cleared 2016-02-26 08:50:31 +01:00
target target/transport: add flag to indicate CPU Affinity is observed 2016-02-10 23:08:55 -08:00
trace mm, tracing: unify mm flags handling in tracepoints and printk 2016-03-15 16:55:16 -07:00
uapi media fixes for v4.5-rc8 2016-03-11 12:32:02 -08:00
video
xen Merge branch 'for-4.5/drivers' of git://git.kernel.dk/linux-block 2016-01-21 18:19:38 -08:00
Kbuild