== sanity-quota test 18: MDS failover while writing, no watchdog triggered (b14840) ========================================================== 03:06:23 (1790924783) sleep 5 for ZFS MDS Waiting for MDT destroys to complete Creating test directory fail_val=0 fail_loc=0 User quota (limit: 200) Disk quotas for usr quota_usr (uid 60000): Filesystem kbytes bquota blimit bgrace files iquota ilimit igrace /mnt/lustre 0 0 204800 - 0 0 0 - lustre-MDT0000 0 - 0 - 0 - 0 - lustre-OST0000 0 - 0 - 0 - 0 - lustre-OST0001 0 - 0 - 0 - 0 - Total allocated inode limit: 0, total allocated block limit: 0 -u quota_usr space:0 Write 100M (buffered) ... running as uid/gid/euid/egid 60000/60000/60000/60000, groups: 60000 [dd] [if=/dev/urandom] [bs=1M] [of=/mnt/lustre/d18.sanity-quota/f18.sanity-quota] [count=100] UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210432 2688 2205696 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3770368 2048 3739648 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:1] filesystem_summary: 7541760 4096 7506944 1% /mnt/lustre Fail mds for 40 seconds Failing mds1 on oleg603-server Stopping /mnt/lustre-mds1 (opts:) on oleg603-server 100+0 records in 100+0 records out 104857600 bytes (105 MB, 100 MiB) copied, 7.27417 s, 14.4 MB/s 03:06:58 (1790924818) shut down facet: mds1 facet_host: oleg603-server facet_failover_host: oleg603-server Failover mds1 to oleg603-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg603-server: oleg603-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg603-client: oleg603-server: ssh exited with exit code 1 Started lustre-MDT0000 03:07:20 (1790924840) targets are mounted 03:07:20 (1790924840) facet_failover done oleg603-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec (dd_pid=118081, time=0, timeout=600) Disk quotas for usr quota_usr (uid 60000): Filesystem kbytes bquota blimit bgrace files iquota ilimit igrace /mnt/lustre 102412 0 204800 - 1 0 0 - lustre-MDT0000 1* - 1 - 1* - 0 - lustre-OST0000 102412 - 114688 - 1 - 0 - lustre-OST0001 0 - 0 - 0 - 0 - Total allocated inode limit: 0, total allocated block limit: 114688 Delete files... Wait for unlink objects finished... sleep 5 for ZFS MDS sleep 5 for ZFS OST Waiting for MDT destroys to complete sleep 5 for ZFS MDS Waiting for MDT destroys to complete Creating test directory fail_val=0 fail_loc=0 User quota (limit: 200) Disk quotas for usr quota_usr (uid 60000): Filesystem kbytes bquota blimit bgrace files iquota ilimit igrace /mnt/lustre 0 0 204800 - 0 0 0 - lustre-MDT0000 0 - 0 - 0 - 0 - lustre-OST0000 0 - 0 - 0 - 0 - lustre-OST0001 0 - 0 - 0 - 0 - Total allocated inode limit: 0, total allocated block limit: 0 -u quota_usr space:0 Write 100M (directio) ... running as uid/gid/euid/egid 60000/60000/60000/60000, groups: 60000 [dd] [if=/dev/urandom] [bs=1M] [of=/mnt/lustre/d18.sanity-quota/f18.sanity-quota] [count=100] [oflag=direct] UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210432 2560 2205824 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3770368 2048 3761152 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:1] filesystem_summary: 7541760 4096 7528448 1% /mnt/lustre Fail mds for 40 seconds Failing mds1 on oleg603-server Stopping /mnt/lustre-mds1 (opts:) on oleg603-server 03:08:33 (1790924913) shut down facet: mds1 facet_host: oleg603-server facet_failover_host: oleg603-server Failover mds1 to oleg603-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg603-server: oleg603-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg603-client: oleg603-server: ssh exited with exit code 1 Started lustre-MDT0000 03:08:57 (1790924937) targets are mounted 03:08:57 (1790924937) facet_failover done oleg603-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 100+0 records in 100+0 records out 104857600 bytes (105 MB, 100 MiB) copied, 47.8174 s, 2.2 MB/s (dd_pid=120469, time=4, timeout=600) Disk quotas for usr quota_usr (uid 60000): Filesystem kbytes bquota blimit bgrace files iquota ilimit igrace /mnt/lustre 102412 0 204800 - 1 0 0 - lustre-MDT0000 1* - 1 - 1* - 0 - lustre-OST0000 102412 - 114688 - 1 - 0 - lustre-OST0001 0 - 0 - 0 - 0 - Total allocated inode limit: 0, total allocated block limit: 114688 Delete files... Wait for unlink objects finished... sleep 5 for ZFS MDS sleep 5 for ZFS OST Waiting for MDT destroys to complete Delete files... Wait for unlink objects finished... sleep 5 for ZFS MDS Waiting for MDT destroys to complete Delete files... Wait for unlink objects finished... sleep 5 for ZFS MDS Waiting for MDT destroys to complete