linux/include
Dan Williams 8b3e6cdc53 md: introduce get_priority_stripe() to improve raid456 write performance
Improve write performance by preventing the delayed_list from dumping all its
stripes onto the handle_list in one shot.  Delayed stripes are now further
delayed by being held on the 'hold_list'.  The 'hold_list' is bypassed when:

  * a STRIPE_IO_STARTED stripe is found at the head of 'handle_list'
  * 'handle_list' is empty and i/o is being done to satisfy full stripe-width
    write requests
  * 'bypass_count' is less than 'bypass_threshold'.  By default the threshold
    is 1, i.e. every other stripe handled is a preread stripe provided the
    top two conditions are false.

Benchmark data:
System: 2x Xeon 5150, 4x SATA, mem=1GB
Baseline: 2.6.24-rc7
Configuration: mdadm --create /dev/md0 /dev/sd[b-e] -n 4 -l 5 --assume-clean
Test1: dd if=/dev/zero of=/dev/md0 bs=1024k count=2048
  * patched:  +33% (stripe_cache_size = 256), +25% (stripe_cache_size = 512)

Test2: tiobench --size 2048 --numruns 5 --block 4096 --block 131072 (XFS)
  * patched: +13%
  * patched + preread_bypass_threshold = 0: +37%

Changes since v1:
* reduce bypass_threshold from (chunk_size / sectors_per_chunk) to (1) and
  make it configurable.  This defaults to fairness and modest performance
  gains out of the box.
Changes since v2:
* [neilb@suse.de]: kill STRIPE_PRIO_HI and preread_needed as they are not
  necessary, the important change was clearing STRIPE_DELAYED in
  add_stripe_bio and this has been moved out to make_request for the hang
  fix.
* [neilb@suse.de]: simplify get_priority_stripe
* [dan.j.williams@intel.com]: reset the bypass_count when ->hold_list is
  sampled empty (+11%)
* [dan.j.williams@intel.com]: decrement the bypass_count at the detection
  of stripes being naturally promoted off of hold_list +2%.  Note, resetting
  bypass_count instead of decrementing on these events yields +4% but that is
  probably too aggressive.
Changes since v3:
* cosmetic fixups

Tested-by: James W. Laferriere <babydr@baby-dragons.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 08:58:42 -07:00
..
acpi
asm-alpha alpha: teach the compiler that BUG doesn't return 2008-04-28 08:58:27 -07:00
asm-arm mm: introduce pte_special pte bit 2008-04-28 08:58:23 -07:00
asm-avr32 mm: introduce pte_special pte bit 2008-04-28 08:58:23 -07:00
asm-blackfin
asm-cris cris: add constfy to pgd_offset() 2008-04-28 08:58:28 -07:00
asm-frv mm: introduce pte_special pte bit 2008-04-28 08:58:23 -07:00
asm-generic gpiochip_reserve() 2008-04-28 08:58:34 -07:00
asm-h8300
asm-ia64 hugetlbfs: common code update for s390 2008-04-28 08:58:25 -07:00
asm-m32r mm: introduce pte_special pte bit 2008-04-28 08:58:23 -07:00
asm-m68k mm: introduce pte_special pte bit 2008-04-28 08:58:23 -07:00
asm-m68knommu
asm-mips serial: add VR41xx SIU setup for serial console 2008-04-28 08:58:30 -07:00
asm-mn10300 mm: introduce pte_special pte bit 2008-04-28 08:58:23 -07:00
asm-parisc mm: introduce pte_special pte bit 2008-04-28 08:58:23 -07:00
asm-powerpc hugetlbfs: common code update for s390 2008-04-28 08:58:25 -07:00
asm-ppc mm: introduce pte_special pte bit 2008-04-28 08:58:23 -07:00
asm-s390 s390: implement pte special bit 2008-04-28 08:58:23 -07:00
asm-sh hugetlbfs: common code update for s390 2008-04-28 08:58:25 -07:00
asm-sparc mm: introduce pte_special pte bit 2008-04-28 08:58:23 -07:00
asm-sparc64 hugetlbfs: common code update for s390 2008-04-28 08:58:25 -07:00
asm-um mm: introduce pte_special pte bit 2008-04-28 08:58:23 -07:00
asm-v850
asm-x86 gxfb/lxfb: detect framebuffer size using an MSR if VSA2 isn't available 2008-04-28 08:58:40 -07:00
asm-xtensa mm: introduce pte_special pte bit 2008-04-28 08:58:23 -07:00
crypto
keys
linux md: introduce get_priority_stripe() to improve raid456 write performance 2008-04-28 08:58:42 -07:00
math-emu
media
mtd
net
pcmcia
rdma
rxrpc
scsi
sound
video fbdev: platforming hecubafb and n411 2008-04-28 08:58:41 -07:00
xen
Kbuild