diff options
| author | Dan Williams <dan.j.williams@intel.com> | 2008-04-28 11:15:53 +0200 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2008-04-28 17:58:42 +0200 |
| commit | 8b3e6cdc53b7f29f7026955d6cb6902a49322a15 (patch) | |
| tree | 69d9f22a526e687fe2892d327caa3fa6ddd65cf6 /Documentation | |
| parent | md: replace remaining __FUNCTION__ occurrences (diff) | |
| download | linux-8b3e6cdc53b7f29f7026955d6cb6902a49322a15.tar.xz linux-8b3e6cdc53b7f29f7026955d6cb6902a49322a15.zip | |
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>
Diffstat (limited to 'Documentation')
| -rw-r--r-- | Documentation/md.txt | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/Documentation/md.txt b/Documentation/md.txt index 396cdd982c26..a8b430627473 100644 --- a/Documentation/md.txt +++ b/Documentation/md.txt @@ -450,3 +450,9 @@ These currently include there are upper and lower limits (32768, 16). Default is 128. strip_cache_active (currently raid5 only) number of active entries in the stripe cache + preread_bypass_threshold (currently raid5 only) + number of times a stripe requiring preread will be bypassed by + a stripe that does not require preread. For fairness defaults + to 1. Setting this to 0 disables bypass accounting and + requires preread stripes to wait until all full-width stripe- + writes are complete. Valid values are 0 to stripe_cache_size. |