Whamcloud - gitweb
LU-7988 hsm: added coordinator housekeeping flag 82/19582/38
authorFrank Zago <fzago@cray.com>
Fri, 8 Apr 2016 17:59:06 +0000 (13:59 -0400)
committerOleg Drokin <oleg.drokin@intel.com>
Thu, 31 Aug 2017 19:15:34 +0000 (19:15 +0000)
commitafc9ff6caff7d572041cabf0a957dc8749fce49d
tree0bba44aacd777da31fd30894d149786d4c668bee
parent0fedb017c12629d145fa0577451d43adc757eb36
LU-7988 hsm: added coordinator housekeeping flag

When the coordinator is not performing housekeeping, only the requests
in the ARS_WAITING state will be processed as they are new
requests. The other requests, in states ARS_FAILED, ARS_CANCELED,
ARS_SUCCEED and ARS_STARTED can wait a few more seconds until the
housekeeping starts.

Also, when not performing housekeeping, as soon as hsd.request is
full, exit from the loop as there is enough potential work queued;
there's no need to examine all the HSM records, thus shortening the
time spent in cdt_llog_process() holding the critical lock
cdt_llog_lock.

Test-Parameters: trivial testlist=sanity-hsm
Signed-off-by: frank zago <fzago@cray.com>
Change-Id: Ib73c97d29ca2f86b912aeb8d055c004cff14d5cf
Reviewed-on: https://review.whamcloud.com/19582
Tested-by: Jenkins
Reviewed-by: Quentin Bouget <quentin.bouget@cea.fr>
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Patrick Farrell <paf@cray.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
lustre/mdt/mdt_coordinator.c