For large OSTCOUNT, a small write can't take extent locks on all OSTs.
Signed-off-by: James Simmons <uja.ornl@gmail.com>
Change-Id: Ic3fb8e88444767db70545292c4b81b9fe9f1f813
Reviewed-on: http://review.whamcloud.com/1901
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Niu Yawei <niu@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
enable_lockless_truncate 1
rm -f $DIR1/$tfile
lfs setstripe -c -1 $DIR1/$tfile
- dd if=/dev/zero of=$DIR1/$tfile count=10 bs=1M > /dev/null 2>&1
+ dd if=/dev/zero of=$DIR1/$tfile count=$OSTCOUNT bs=$STRIPE_BYTES > \
+ /dev/null 2>&1
clear_osc_stats
log "checking cached lockless truncate"