Whamcloud - gitweb
LU-11290 osc: Batch gang_lookup cbs 89/33089/10
authorPatrick Farrell <paf@cray.com>
Wed, 3 Mar 2021 06:50:04 +0000 (09:50 +0300)
committerOleg Drokin <green@whamcloud.com>
Wed, 2 Jun 2021 17:47:55 +0000 (17:47 +0000)
commit0d6d0b7bc95a82dee02d35d0a8a41d24692cad45
tree4141f3366ad9384432e669dc6a73710768586b18
parent79372d86cd64c097cb4f46cb166ba716795619f6
LU-11290 osc: Batch gang_lookup cbs

The osc_page_gang_lookup call backs can be trivially
converted to operate in batches rather than one page at a
time.  This improves cancellation time for locks protecting
large numbers of pages by about 10% (after landing
another optimization (LU-11290 ldlm: page discard speedup)
it shows 6% for canceling a lock for 30GB cached file ).

Truncate to zero time (with one lock protecting many pages)
was improved by about 5-10% as well.  Lock weighing
performance should be improved slightly as well, but is
tricky to benchmark.

HPE-bug-id: LUS-6432
Change-Id: Ib30594ae97182cbeb18051d6cee860c97ae7e119
Signed-off-by: Patrick Farrell <paf@cray.com>
Signed-off-by: Alexander Zarochentsev <alexander.zarochentsev@hpe.com>
Reviewed-on: https://review.whamcloud.com/33089
Tested-by: jenkins <devops@whamcloud.com>
Reviewed-by: Bobi Jam <bobijam@hotmail.com>
Reviewed-by: Wang Shilong <wshilong@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
lustre/include/lustre_osc.h
lustre/mdc/mdc_dev.c
lustre/osc/osc_cache.c
lustre/osc/osc_io.c
lustre/osc/osc_lock.c