-
Bug
-
Resolution: Unresolved
-
Medium
-
None
-
None
-
None
-
3
-
9223372036854775807
CMD: trevis-155vm260.trevis.whamcloud.com grep -c /mnt/lustre' ' /proc/mounts Stopping client trevis-155vm260.trevis.whamcloud.com /mnt/lustre (opts:) CMD: trevis-155vm260.trevis.whamcloud.com lsof -t /mnt/lustre CMD: trevis-155vm260.trevis.whamcloud.com umount /mnt/lustre 2>&1 Starting client: trevis-155vm260.trevis.whamcloud.com: -o user_xattr,flock trevis-156vm273@tcp:/lustre /mnt/lustre CMD: trevis-155vm260.trevis.whamcloud.com mkdir -p /mnt/lustre CMD: trevis-155vm260.trevis.whamcloud.com mount -t lustre -o user_xattr,flock trevis-156vm273@tcp:/lustre /mnt/lustre stat: cannot statx '/mnt/lustre/d44d.sanity-flr/f44d.sanity-flr': Resource temporarily unavailable ** after mirror split & remount, file size= /usr/lib64/lustre/tests/sanity-flr.sh: line 2404: ((: 10485760 == : syntax error: operand expected (error token is "== ") sanity-flr test_44d: @@@@@@ FAIL: mirror extend should not change size, before: 10485760, after
It looks like a stat on an FLR file returns EAGAIN right after mount because the no-delay glimpse fails while the OST imports are still connecting.