-----============= acceptance-small: replay-dual ============----- Mon Aug 17 00:08:24 EDT 2026 MGS_OS_ID_LIKE=rhel centos fedora rocky MGS_OS_VERSION_ID=8.10 MGS_OS_ID=rocky MGS_OS_VERSION_CODE=134873088 MDS1_OS_VERSION_ID=8.10 MDS1_OS_VERSION_CODE=134873088 MDS1_OS_ID_LIKE=rhel centos fedora rocky MDS1_OS_ID=rocky OST1_OS_VERSION_CODE=134873088 OST1_OS_ID_LIKE=rhel centos fedora rocky OST1_OS_VERSION_ID=8.10 OST1_OS_ID=rocky CLIENT_OS_ID=rocky CLIENT_OS_VERSION_CODE=134873088 CLIENT_OS_VERSION_ID=8.10 CLIENT_OS_ID_LIKE=rhel centos fedora rocky oleg113-server: ls: cannot access '/home/green/git/lustre-release/lustre/tests/except/replay-dual.*ex': No such file or directory excepting tests: 14b 21b skipping tests SLOW=no: 21b === replay-dual: start setup 00:08:36 (1786939716) === Starting client oleg113-client.virtnet: -o user_xattr,flock 192.168.201.113@tcp:/lustre /mnt/lustre2 Mount client oleg113-client.virtnet: mount -t lustre -o user_xattr,flock 192.168.201.113@tcp:/lustre /mnt/lustre2 Started clients oleg113-client.virtnet: 192.168.201.113@tcp:/lustre on /mnt/lustre2 type lustre (rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose) oleg113-client.virtnet: executing check_config_client /mnt/lustre oleg113-client.virtnet: Checking config lustre mounted on /mnt/lustre Checking servers environments Checking clients oleg113-client.virtnet environments Using TIMEOUT=20 osc.lustre-OST0000-osc-ffff897005d7f800.idle_timeout=debug osc.lustre-OST0000-osc-ffff897006706000.idle_timeout=debug osc.lustre-OST0001-osc-ffff897005d7f800.idle_timeout=debug osc.lustre-OST0001-osc-ffff897006706000.idle_timeout=debug disable quota as required oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all osd-ldiskfs.track_declares_assert=1 === replay-dual: finish setup 00:08:59 (1786939739) === == replay-dual test 0a: expired recovery with lost client ========================================================== 00:09:00 (1786939740) Check file is LU482_FAILED=/tmp/replay-dual.lu482.rMMdz9 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1708 1269596 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1532 1269772 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre total: 50 open/close in 1.13 seconds: 44.30 ops/second fail_loc=0x80000514 Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:09:08 (1786939748) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:09:26 (1786939766) targets are mounted 00:09:26 (1786939766) facet_failover done Starting client: oleg113-client.virtnet: -o user_xattr,flock 192.168.201.113@tcp:/lustre /mnt/lustre2 - unlinked 0 (time 1786939881 ; total 0 ; last 0) total: 50 unlinks in 0 seconds: inf unlinks/second PASS 0a (143s) == replay-dual test 0b: lost client during waiting for next transno ========================================================== 00:11:23 (1786939883) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1676 1269628 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1532 1269772 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:11:28 (1786939888) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:11:43 (1786939903) targets are mounted 00:11:43 (1786939903) facet_failover done Starting client: oleg113-client.virtnet: -o user_xattr,flock 192.168.201.113@tcp:/lustre /mnt/lustre Starting client: oleg113-client.virtnet: -o user_xattr,flock 192.168.201.113@tcp:/lustre /mnt/lustre2 PASS 0b (99s) == replay-dual test 1: |X| simple create ================= 00:13:02 (1786939982) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1676 1269628 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1532 1269772 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:13:07 (1786939987) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:13:22 (1786940002) targets are mounted 00:13:22 (1786940002) facet_failover done oleg113-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 PASS 1 (28s) == replay-dual test 2: |X| mkdir adir ==================== 00:13:31 (1786940011) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1676 1269628 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1532 1269772 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:13:35 (1786940015) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:13:50 (1786940030) targets are mounted 00:13:50 (1786940030) facet_failover done oleg113-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 PASS 2 (28s) == replay-dual test 3: |X| mkdir adir, mkdir adir/bdir === 00:13:59 (1786940039) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1676 1269628 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1532 1269772 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:14:03 (1786940043) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:14:18 (1786940058) targets are mounted 00:14:18 (1786940058) facet_failover done oleg113-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 PASS 3 (28s) == replay-dual test 4: |X| mkdir adir (-EEXIST), mkdir adir/bdir ========================================================== 00:14:27 (1786940067) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1848 1269456 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre mkdir: cannot create directory '/mnt/lustre/adir': File exists Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:14:37 (1786940077) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:14:52 (1786940092) targets are mounted 00:14:52 (1786940092) facet_failover done oleg113-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 PASS 4 (34s) == replay-dual test 5: open, unlink |X| close ============ 00:15:01 (1786940101) multiop /mnt/lustre2/a vo_tSc TMPPIPE=/tmp/multiop_open_wait_pipe.8229 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:15:05 (1786940105) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:15:20 (1786940120) targets are mounted 00:15:21 (1786940121) facet_failover done oleg113-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 PASS 5 (28s) == replay-dual test 6: open1, open2, unlink |X| close1 [fail mds1] close2 ========================================================== 00:15:29 (1786940129) multiop /mnt/lustre2/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8229 multiop /mnt/lustre/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8229 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:15:33 (1786940133) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:15:49 (1786940149) targets are mounted 00:15:49 (1786940149) facet_failover done oleg113-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 PASS 6 (28s) == replay-dual test 8: replay of resent request ========== 00:15:57 (1786940157) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre fail_loc=0x119 fail_loc=0 Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:16:18 (1786940178) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:16:33 (1786940193) targets are mounted 00:16:33 (1786940193) facet_failover done oleg113-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 PASS 8 (45s) == replay-dual test 9: resending a replayed create ======= 00:16:42 (1786940202) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre fail_loc=0x80000119 Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:16:46 (1786940206) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:17:01 (1786940221) targets are mounted 00:17:01 (1786940221) facet_failover done oleg113-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 fail_loc=0 PASS 9 (42s) == replay-dual test 10: resending a replayed unlink ====== 00:17:24 (1786940244) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre fail_loc=0x80000119 Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:17:29 (1786940249) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:17:44 (1786940264) targets are mounted 00:17:44 (1786940264) facet_failover done oleg113-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 fail_loc=0 PASS 10 (40s) == replay-dual test 11: both clients timeout during replay ========================================================== 00:18:04 (1786940284) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre fail_loc=0x0119 Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:18:09 (1786940289) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:18:24 (1786940304) targets are mounted 00:18:24 (1786940304) facet_failover done oleg113-client.virtnet: executing wait_import_state_mount FULL mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 14 sec fail_loc=0 PASS 11 (38s) == replay-dual test 12: open resend timeout ============== 00:18:42 (1786940322) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre multiop /mnt/lustre/f12.replay-dual vmo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8229 fail_loc=0x80000302 Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:18:47 (1786940327) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:19:02 (1786940342) targets are mounted 00:19:02 (1786940342) facet_failover done fail_loc=0 /mnt/lustre/f12.replay-dual /mnt/lustre/f12.replay-dual has type file OK PASS 12 (25s) == replay-dual test 13: close resend timeout ============= 00:19:07 (1786940347) multiop /mnt/lustre/f13.replay-dual vmo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8229 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre fail_loc=0x80000115 Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:19:11 (1786940351) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:19:26 (1786940366) targets are mounted 00:19:26 (1786940366) facet_failover done fail_loc=0 /mnt/lustre/f13.replay-dual /mnt/lustre/f13.replay-dual has type file OK PASS 13 (25s) SKIP: replay-dual test_14b skipping ALWAYS excluded test 14b == replay-dual test 15a: timeout waiting for lost client during replay, 1 client completes ========================================================== 00:19:32 (1786940372) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre total: 25 open/close in 0.21 seconds: 119.11 ops/second total: 1 open/close in 0.01 seconds: 100.81 ops/second Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:19:37 (1786940377) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:19:52 (1786940392) targets are mounted 00:19:52 (1786940392) facet_failover done oleg113-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 - unlinked 0 (time 1786940466 ; total 0 ; last 0) total: 25 unlinks in 0 seconds: inf unlinks/second Starting client: oleg113-client.virtnet: -o user_xattr,flock 192.168.201.113@tcp:/lustre /mnt/lustre2 PASS 15a (96s) == replay-dual test 15c: remove multiple OST orphans ===== 00:21:08 (1786940468) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:21:42 (1786940502) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:21:57 (1786940517) targets are mounted 00:21:57 (1786940517) facet_failover done oleg113-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 Starting client: oleg113-client.virtnet: -o user_xattr,flock 192.168.201.113@tcp:/lustre /mnt/lustre2 PASS 15c (126s) == replay-dual test 16: fail MDS during recovery (3571) == 00:23:14 (1786940594) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre total: 25 open/close in 0.50 seconds: 50.08 ops/second total: 1 open/close in 0.02 seconds: 46.10 ops/second Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:23:20 (1786940600) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:23:58 (1786940638) targets are mounted 00:23:58 (1786940638) facet_failover done Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:24:20 (1786940660) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:24:36 (1786940676) targets are mounted 00:24:36 (1786940676) facet_failover done oleg113-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 - unlinked 0 (time 1786940750 ; total 0 ; last 0) total: 25 unlinks in 0 seconds: inf unlinks/second Starting client: oleg113-client.virtnet: -o user_xattr,flock 192.168.201.113@tcp:/lustre /mnt/lustre2 PASS 16 (159s) == replay-dual test 17: fail OST during recovery (3571) == 00:25:53 (1786940753) total: 25 open/close in 0.58 seconds: 43.43 ops/second total: 1 open/close in 0.03 seconds: 29.03 ops/second UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1916 1269388 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing ost1 on oleg113-server Stopping /mnt/lustre-ost1 (opts:) on oleg113-server 00:26:01 (1786940761) shut down facet: ost1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover ost1 to oleg113-server mount facets: ost1 Start ost1: mount -t lustre -o localrecov /dev/mapper/ost1_flakey /mnt/lustre-ost1 seq.cli-lustre-OST0000-super.width=65536 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-OST0000 00:26:24 (1786940784) targets are mounted 00:26:24 (1786940784) facet_failover done Failing ost1 on oleg113-server Stopping /mnt/lustre-ost1 (opts:) on oleg113-server 00:26:50 (1786940810) shut down facet: ost1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover ost1 to oleg113-server mount facets: ost1 Start ost1: mount -t lustre -o localrecov /dev/mapper/ost1_flakey /mnt/lustre-ost1 seq.cli-lustre-OST0000-super.width=65536 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-OST0000 00:27:20 (1786940840) targets are mounted 00:27:20 (1786940840) facet_failover done oleg113-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid 1475 0 osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in FULL state after 0 sec - unlinked 0 (time 1786940909 ; total 0 ; last 0) total: 25 unlinks in 1 seconds: 25.000000 unlinks/second Starting client: oleg113-client.virtnet: -o user_xattr,flock 192.168.201.113@tcp:/lustre /mnt/lustre2 PASS 17 (161s) == replay-dual test 18: ldlm_handle_enqueue succeeds on evicted export (3822) ========================================================== 00:28:34 (1786940914) debug=+dlmtrace fail_loc=0x8000030b using seed 4208194185 running for 500 iterations total: 500 stats in 1 seconds: 500.000000 stats/second ldlm.namespaces.MGC192.168.201.113@tcp.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffff897006409800.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffff8970064cf000.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0001-mdc-ffff897006409800.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0001-mdc-ffff8970064cf000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffff897006409800.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffff8970064cf000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffff897006409800.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffff8970064cf000.early_lock_cancel=0 fail_loc=0x80000305 Error in opening file "/mnt/lustre2/d18.replay-dual/f18.replay-dual"(flags=O_RDONLY) 2: No such file or directory ldlm.namespaces.MGC192.168.201.113@tcp.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffff897006409800.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffff8970064cf000.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0001-mdc-ffff897006409800.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0001-mdc-ffff8970064cf000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffff897006409800.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffff8970064cf000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffff897006409800.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffff8970064cf000.early_lock_cancel=1 fail_loc=0 fail_loc=0 PASS 18 (55s) == replay-dual test 19: resend of open request =========== 00:29:30 (1786940970) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1920 1269384 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre fail_loc=0x157 - open/close 0 (time 1786941065.85 total 86.71 last 0.00) total: 1 open/close in 86.71 seconds: 0.01 ops/second fail_loc=0 Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:31:11 (1786941071) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:31:43 (1786941103) targets are mounted 00:31:43 (1786941103) facet_failover done oleg113-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 PASS 19 (152s) == replay-dual test 20: recovery time is not increasing == 00:32:02 (1786941122) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1896 1269408 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:32:16 (1786941136) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:32:52 (1786941172) targets are mounted 00:32:52 (1786941172) facet_failover done oleg113-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 Starting client: oleg113-client.virtnet: -o user_xattr,flock 192.168.201.113@tcp:/lustre /mnt/lustre2 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1896 1269408 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:35:22 (1786941322) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:35:54 (1786941354) targets are mounted 00:35:54 (1786941354) facet_failover done oleg113-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 Starting client: oleg113-client.virtnet: -o user_xattr,flock 192.168.201.113@tcp:/lustre /mnt/lustre2 PASS 20 (378s) == replay-dual test 21a: commit on sharing =============== 00:38:20 (1786941500) mdt.lustre-MDT0000.commit_on_sharing=1 mdt.lustre-MDT0001.commit_on_sharing=1 Replay barrier on lustre-MDT0000 Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:38:29 (1786941509) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:39:04 (1786941544) targets are mounted 00:39:04 (1786941544) facet_failover done Starting client: oleg113-client.virtnet: -o user_xattr,flock 192.168.201.113@tcp:/lustre /mnt/lustre2 mdt.lustre-MDT0000.commit_on_sharing=0 mdt.lustre-MDT0001.commit_on_sharing=0 PASS 21a (185s) SKIP: replay-dual test_21b skipping SLOW test 21b == replay-dual test 22a: c1 lfs mkdir -i 1 dir1, M1 drop reply & fail, c2 mkdir dir1/dir ========================================================== 00:41:27 (1786941687) fail_loc=0x119 Failing mds2 on oleg113-server Stopping /mnt/lustre-mds2 (opts:) on oleg113-server 00:41:35 (1786941695) shut down facet: mds2 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds2 to oleg113-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0001 00:42:00 (1786941720) targets are mounted 00:42:00 (1786941720) facet_failover done oleg113-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1904 1269400 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1744 1269560 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.15 seconds: 12.92 ops/second total: 2 open/close in 0.07 seconds: 27.75 ops/second Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:42:29 (1786941749) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:43:00 (1786941780) targets are mounted 00:43:00 (1786941780) facet_failover done oleg113-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 PASS 22a (112s) == replay-dual test 22b: c1 lfs mkdir -i 1 d1, M1 drop reply & fail M0/M1, c2 mkdir d1/dir ========================================================== 00:43:19 (1786941799) fail_loc=0x119 Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server Failing mds2 on oleg113-server Stopping /mnt/lustre-mds2 (opts:) on oleg113-server 00:43:34 (1786941814) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server facet: mds2 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Failover mds2 to oleg113-server mount facets: mds2 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 00:44:06 (1786941846) targets are mounted 00:44:06 (1786941846) facet_failover done oleg113-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1904 1269400 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1744 1269560 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.16 seconds: 12.64 ops/second total: 2 open/close in 0.06 seconds: 32.94 ops/second Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:44:33 (1786941873) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:45:10 (1786941910) targets are mounted 00:45:10 (1786941910) facet_failover done oleg113-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 PASS 22b (132s) == replay-dual test 22c: c1 lfs mkdir -i 1 d1, M1 drop update & fail M1, c2 mkdir d1/dir ========================================================== 00:45:31 (1786941931) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:45:43 (1786941943) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:46:19 (1786941979) targets are mounted 00:46:20 (1786941980) facet_failover done oleg113-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 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1904 1269400 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1756 1269548 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.17 seconds: 11.58 ops/second total: 2 open/close in 0.06 seconds: 31.49 ops/second Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:46:50 (1786942010) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:47:25 (1786942045) targets are mounted 00:47:25 (1786942045) facet_failover done oleg113-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 PASS 22c (133s) == replay-dual test 22d: c1 lfs mkdir -i 1 d1, M1 drop update & fail M0/M1,c2 mkdir d1/dir ========================================================== 00:47:44 (1786942064) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server Failing mds2 on oleg113-server Stopping /mnt/lustre-mds2 (opts:) on oleg113-server 00:48:09 (1786942089) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server facet: mds2 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Failover mds2 to oleg113-server mount facets: mds2 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 Started lustre-MDT0001 00:48:53 (1786942133) targets are mounted 00:48:53 (1786942133) facet_failover done oleg113-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1868 1269436 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1708 1269596 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.13 seconds: 15.32 ops/second total: 2 open/close in 0.04 seconds: 52.65 ops/second Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:49:35 (1786942175) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:50:08 (1786942208) targets are mounted 00:50:08 (1786942208) facet_failover done oleg113-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 PASS 22d (163s) == replay-dual test 23a: c1 rmdir d1, M1 drop reply and fail, client2 mkdir d1 ========================================================== 00:50:27 (1786942227) fail_loc=0x119 fail_loc=0 Failing mds2 on oleg113-server Stopping /mnt/lustre-mds2 (opts:) on oleg113-server 00:50:41 (1786942241) shut down facet: mds2 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds2 to oleg113-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0001 00:51:05 (1786942265) targets are mounted 00:51:05 (1786942265) facet_failover done oleg113-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1900 1269404 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.06 seconds: 35.66 ops/second Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:51:29 (1786942289) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:52:02 (1786942322) targets are mounted 00:52:02 (1786942322) facet_failover done oleg113-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 PASS 23a (113s) == replay-dual test 23b: c1 rmdir d1, M1 drop reply and fail M0/M1, c2 mkdir d1 ========================================================== 00:52:20 (1786942340) fail_loc=0x119 fail_loc=0 Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server Failing mds2 on oleg113-server Stopping /mnt/lustre-mds2 (opts:) on oleg113-server 00:52:32 (1786942352) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server facet: mds2 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Failover mds2 to oleg113-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 00:53:02 (1786942382) targets are mounted 00:53:02 (1786942382) facet_failover done oleg113-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1900 1269404 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.07 seconds: 29.84 ops/second Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:53:32 (1786942412) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:54:06 (1786942446) targets are mounted 00:54:06 (1786942446) facet_failover done oleg113-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 PASS 23b (121s) == replay-dual test 23c: c1 rmdir d1, M0 drop update reply and fail M0, c2 mkdir d1 ========================================================== 00:54:21 (1786942461) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:54:29 (1786942469) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:54:51 (1786942491) targets are mounted 00:54:51 (1786942491) facet_failover done oleg113-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 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1900 1269404 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1752 1269552 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.07 seconds: 26.95 ops/second Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:55:10 (1786942510) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:55:44 (1786942544) targets are mounted 00:55:44 (1786942544) facet_failover done oleg113-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 PASS 23c (98s) == replay-dual test 23d: c1 rmdir d1, M0 drop update reply and fail M0/M1, c2 mkdir d1 ========================================================== 00:55:59 (1786942559) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server Failing mds2 on oleg113-server Stopping /mnt/lustre-mds2 (opts:) on oleg113-server 00:56:19 (1786942579) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server facet: mds2 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Failover mds2 to oleg113-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 Started lustre-MDT0001 00:56:44 (1786942604) targets are mounted 00:56:44 (1786942604) facet_failover done oleg113-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1864 1269440 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1704 1269600 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.07 seconds: 29.77 ops/second Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 00:57:15 (1786942635) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 00:57:40 (1786942660) targets are mounted 00:57:40 (1786942660) facet_failover done oleg113-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 PASS 23d (115s) == replay-dual test 24: reconstruct on non-existing object ========================================================== 00:57:54 (1786942674) fail_loc=0x119 fail_loc=0 truncate: cannot truncate '/mnt/lustre/f24.replay-dual' to length 100: No such file or directory PASS 24 (91s) == replay-dual test 25: replay|resend ==================== 00:59:25 (1786942765) 1+0 records in 1+0 records out 512 bytes copied, 0.0100047 s, 51.2 kB/s fail_loc=0x304 fail_loc=0x80000325 Failing ost1 on oleg113-server Stopping /mnt/lustre-ost1 (opts:) on oleg113-server 00:59:30 (1786942770) shut down facet: ost1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover ost1 to oleg113-server mount facets: ost1 Start ost1: mount -t lustre -o localrecov /dev/mapper/ost1_flakey /mnt/lustre-ost1 seq.cli-lustre-OST0000-super.width=65536 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-OST0000 00:59:50 (1786942790) targets are mounted 00:59:50 (1786942790) facet_failover done oleg113-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid 1475 0 osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in FULL state after 0 sec /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 6982: 64113 Terminated LUSTRE="/home/green/git/lustre-release/lustre" bash -c "multiop /mnt/lustre2/f25.replay-dual Ow512" fail_loc=0 PASS 25 (39s) == replay-dual test 26: dbench and tar with mds failover ========================================================== 01:00:04 (1786942804) Starting client oleg113-client.virtnet: -o user_xattr,flock 192.168.201.113@tcp:/lustre /mnt/lustre Started clients oleg113-client.virtnet: 192.168.201.113@tcp:/lustre on /mnt/lustre type lustre (rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose) Started tar loop with pid 65553 Started dbench loop with 65554 striped dir -i0 -c2 -H crush /mnt/lustre2/d26.replay-dual/run_dbench striped dir -i0 -c2 -H crush2 /mnt/lustre/d26.replay-dual/run_tar looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt '/usr/share/dbench/client.txt' -> 'client.txt' running 'dbench 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100' on /mnt/lustre at Mon Aug 17 01:00:08 EDT 2026 waiting for dbench pid 65605 dbench version 4.00 - Copyright Andrew Tridgell 1999-2004 Running for 100 seconds with load 'client.txt' and minimum warmup 20 secs failed to create barrier semaphore 0 of 1 processes prepared for launch 0 sec 1 of 1 processes prepared for launch 0 sec releasing clients UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2004 1269300 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1840 1269464 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1564 3605456 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 26120 3579736 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 27684 7185192 1% /mnt/lustre 1 34 1.04 MB/sec warmup 1 sec latency 74.552 ms 1 113 2.61 MB/sec warmup 2 sec latency 148.929 ms 1 155 2.18 MB/sec warmup 3 sec latency 134.205 ms 1 189 1.89 MB/sec warmup 4 sec latency 380.576 ms 1 237 1.81 MB/sec warmup 5 sec latency 98.611 ms 1 290 1.78 MB/sec warmup 6 sec latency 115.441 ms 1 356 1.82 MB/sec warmup 7 sec latency 83.461 ms test_26 fail mds1 1 times 1 421 1.86 MB/sec warmup 8 sec latency 85.176 ms Failing mds1 on oleg113-server 1 469 1.82 MB/sec warmup 9 sec latency 105.950 ms Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 1 522 1.80 MB/sec warmup 10 sec latency 87.282 ms 1 606 1.90 MB/sec warmup 11 sec latency 304.870 ms 1 606 1.74 MB/sec warmup 12 sec latency 1307.050 ms 01:00:20 (1786942820) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server 1 606 1.61 MB/sec warmup 13 sec latency 2310.167 ms 1 606 1.50 MB/sec warmup 14 sec latency 3312.183 ms 1 606 1.40 MB/sec warmup 15 sec latency 4312.357 ms 1 606 1.31 MB/sec warmup 16 sec latency 5313.099 ms 1 606 1.23 MB/sec warmup 17 sec latency 6315.514 ms 1 606 1.16 MB/sec warmup 18 sec latency 7315.728 ms 1 606 1.10 MB/sec warmup 19 sec latency 8315.942 ms 1 606 0.00 MB/sec execute 1 sec latency 10318.512 ms 1 606 0.00 MB/sec execute 2 sec latency 11318.953 ms Failover mds1 to oleg113-server mount facets: mds1 1 606 0.00 MB/sec execute 3 sec latency 12319.165 ms 1 606 0.00 MB/sec execute 4 sec latency 13319.350 ms 1 606 0.00 MB/sec execute 5 sec latency 14319.632 ms 1 606 0.00 MB/sec execute 6 sec latency 15319.789 ms 1 606 0.00 MB/sec execute 7 sec latency 16320.014 ms 1 606 0.00 MB/sec execute 8 sec latency 17320.216 ms 1 606 0.00 MB/sec execute 9 sec latency 18320.628 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 606 0.00 MB/sec execute 10 sec latency 19321.759 ms 1 606 0.00 MB/sec execute 11 sec latency 20322.364 ms 1 606 0.00 MB/sec execute 12 sec latency 21322.557 ms 1 606 0.00 MB/sec execute 13 sec latency 22322.888 ms 1 606 0.00 MB/sec execute 14 sec latency 23323.113 ms 1 606 0.00 MB/sec execute 15 sec latency 24323.342 ms 1 606 0.00 MB/sec execute 16 sec latency 25323.551 ms 1 606 0.00 MB/sec execute 17 sec latency 26323.790 ms 1 606 0.00 MB/sec execute 18 sec latency 27324.866 ms 1 606 0.00 MB/sec execute 19 sec latency 28325.136 ms 1 606 0.00 MB/sec execute 20 sec latency 29325.380 ms 1 606 0.00 MB/sec execute 21 sec latency 30326.728 ms 1 606 0.00 MB/sec execute 22 sec latency 31326.886 ms oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 1 606 0.00 MB/sec execute 23 sec latency 32327.780 ms Started lustre-MDT0000 01:00:51 (1786942851) targets are mounted 01:00:51 (1786942851) facet_failover done 1 606 0.00 MB/sec execute 24 sec latency 33328.125 ms 1 606 0.00 MB/sec execute 25 sec latency 34328.459 ms 1 606 0.00 MB/sec execute 26 sec latency 35328.618 ms 1 612 0.00 MB/sec execute 27 sec latency 36172.942 ms 1 674 0.01 MB/sec execute 28 sec latency 76.481 ms 1 718 0.01 MB/sec execute 29 sec latency 102.957 ms 1 728 0.01 MB/sec execute 30 sec latency 650.171 ms oleg113-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 770 0.01 MB/sec execute 31 sec latency 124.382 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 806 0.02 MB/sec execute 32 sec latency 95.040 ms 1 856 0.02 MB/sec execute 33 sec latency 129.461 ms 1 890 0.02 MB/sec execute 34 sec latency 101.716 ms 1 921 0.02 MB/sec execute 35 sec latency 124.243 ms 1 976 0.03 MB/sec execute 36 sec latency 89.177 ms 1 1050 0.05 MB/sec execute 37 sec latency 78.134 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2168 1269136 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1948 1269356 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 11672 3595096 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 47316 3553308 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 58988 7148404 1% /mnt/lustre 1 1102 0.05 MB/sec execute 38 sec latency 98.667 ms 1 1145 0.05 MB/sec execute 39 sec latency 66.664 ms 1 1182 0.05 MB/sec execute 40 sec latency 116.178 ms 1 1224 0.05 MB/sec execute 41 sec latency 82.111 ms 1 1268 0.05 MB/sec execute 42 sec latency 106.934 ms 1 1285 0.05 MB/sec execute 43 sec latency 757.397 ms 1 1378 0.11 MB/sec execute 44 sec latency 1195.645 ms 1 1421 0.11 MB/sec execute 45 sec latency 141.737 ms 1 1486 0.11 MB/sec execute 46 sec latency 81.951 ms test_26 fail mds2 2 times 1 1523 0.11 MB/sec execute 47 sec latency 93.237 ms 1 1566 0.11 MB/sec execute 48 sec latency 95.511 ms Failing mds2 on oleg113-server 1 1597 0.11 MB/sec execute 49 sec latency 120.673 ms Stopping /mnt/lustre-mds2 (opts:) on oleg113-server 1 1642 0.10 MB/sec execute 50 sec latency 94.644 ms 1 1686 0.10 MB/sec execute 51 sec latency 124.863 ms 01:01:20 (1786942880) shut down facet: mds2 facet_host: oleg113-server facet_failover_host: oleg113-server 1 1775 0.10 MB/sec execute 52 sec latency 78.984 ms 1 1842 0.10 MB/sec execute 53 sec latency 77.454 ms 1 1888 0.10 MB/sec execute 54 sec latency 128.746 ms 1 1974 0.10 MB/sec execute 55 sec latency 84.644 ms 1 2024 0.10 MB/sec execute 56 sec latency 132.938 ms 1 2068 0.10 MB/sec execute 57 sec latency 96.382 ms 1 2139 0.10 MB/sec execute 58 sec latency 113.657 ms 1 2164 0.10 MB/sec execute 59 sec latency 144.738 ms 1 2209 0.10 MB/sec execute 60 sec latency 113.699 ms 1 2251 0.10 MB/sec execute 61 sec latency 156.674 ms Failover mds2 to oleg113-server 1 2259 0.09 MB/sec execute 62 sec latency 809.193 ms mount facets: mds2 1 2259 0.09 MB/sec execute 63 sec latency 1811.280 ms 1 2259 0.09 MB/sec execute 64 sec latency 2816.553 ms 1 2259 0.09 MB/sec execute 65 sec latency 3816.772 ms 1 2259 0.09 MB/sec execute 66 sec latency 4817.798 ms 1 2259 0.09 MB/sec execute 67 sec latency 5818.300 ms 1 2259 0.09 MB/sec execute 68 sec latency 6820.733 ms 1 2259 0.08 MB/sec execute 69 sec latency 7820.974 ms 1 2259 0.08 MB/sec execute 70 sec latency 8821.412 ms 1 2259 0.08 MB/sec execute 71 sec latency 9822.184 ms 1 2259 0.08 MB/sec execute 72 sec latency 10823.858 ms 1 2259 0.08 MB/sec execute 73 sec latency 11824.326 ms 1 2259 0.08 MB/sec execute 74 sec latency 12827.955 ms 1 2259 0.08 MB/sec execute 75 sec latency 13828.308 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 2259 0.08 MB/sec execute 76 sec latency 14828.549 ms 1 2259 0.08 MB/sec execute 77 sec latency 15830.004 ms 1 2259 0.07 MB/sec execute 78 sec latency 16830.401 ms 1 2259 0.07 MB/sec execute 79 sec latency 17832.758 ms 1 2259 0.07 MB/sec execute 80 sec latency 18833.024 ms 1 2259 0.07 MB/sec execute 81 sec latency 19833.920 ms 1 2259 0.07 MB/sec execute 82 sec latency 20834.176 ms 1 2259 0.07 MB/sec execute 83 sec latency 21835.396 ms oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all 1 2259 0.07 MB/sec execute 84 sec latency 22836.419 ms pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 1 2259 0.07 MB/sec execute 85 sec latency 23836.663 ms 1 2259 0.07 MB/sec execute 86 sec latency 24837.610 ms Started lustre-MDT0001 01:01:55 (1786942915) targets are mounted 01:01:55 (1786942915) facet_failover done 1 2286 0.07 MB/sec execute 87 sec latency 25292.592 ms 1 2345 0.08 MB/sec execute 88 sec latency 87.652 ms 1 2369 0.08 MB/sec execute 89 sec latency 124.568 ms 1 2396 0.08 MB/sec execute 90 sec latency 128.509 ms 1 2428 0.08 MB/sec execute 91 sec latency 148.739 ms 1 2453 0.08 MB/sec execute 92 sec latency 174.535 ms 1 2478 0.08 MB/sec execute 93 sec latency 185.171 ms 1 2551 0.08 MB/sec execute 94 sec latency 125.334 ms 1 2571 0.08 MB/sec execute 95 sec latency 156.017 ms 1 2596 0.08 MB/sec execute 96 sec latency 172.633 ms oleg113-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 1 2750 0.11 MB/sec execute 97 sec latency 138.817 ms 1 2779 0.11 MB/sec execute 98 sec latency 170.126 ms 1 2891 0.12 MB/sec execute 99 sec latency 160.141 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec 1 cleanup 103 sec 1 cleanup 104 sec 1 cleanup 105 sec 0 cleanup 106 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 381 120.195 25292.577 Close 319 12.045 66.860 Rename 18 92.531 174.502 Unlink 43 30.644 104.721 Qpathinfo 366 118.432 36172.914 Qfileinfo 77 3.050 16.124 Qfsinfo 51 4.102 28.433 Sfileinfo 50 62.038 125.317 Find 127 12.564 40.766 WriteX 229 15.271 125.844 ReadX 614 2.165 96.360 LockX 2 22.457 28.135 UnlockX 2 10.323 11.830 Flush 35 63.770 251.267 Throughput 0.117881 MB/sec 1 clients 1 procs max_latency=36172.942 ms stopping dbench on /mnt/lustre at Mon Aug 17 01:02:14 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2380 1268924 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2144 1269160 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 6248 3599832 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 51152 3554664 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 57400 7154496 1% /mnt/lustre striped dir -i0 -c2 -H fnv_1a_64 /mnt/lustre2/d26.replay-dual/run_dbench looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt '/usr/share/dbench/client.txt' -> 'client.txt' running 'dbench 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100' on /mnt/lustre at Mon Aug 17 01:02:27 EDT 2026 waiting for dbench pid 67860 dbench version 4.00 - Copyright Andrew Tridgell 1999-2004 Running for 100 seconds with load 'client.txt' and minimum warmup 20 secs 0 of 1 processes prepared for launch 0 sec 1 of 1 processes prepared for launch 0 sec releasing clients test_26 fail mds1 3 times 0 11 0.00 MB/sec warmup 1 sec latency 21.869 ms 1 52 1.04 MB/sec warmup 2 sec latency 137.096 ms 1 91 1.39 MB/sec warmup 3 sec latency 137.342 ms Failing mds1 on oleg113-server 1 121 1.37 MB/sec warmup 4 sec latency 236.913 ms Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 1 139 1.20 MB/sec warmup 5 sec latency 291.266 ms 1 165 1.13 MB/sec warmup 6 sec latency 365.047 ms 1 172 1.01 MB/sec warmup 7 sec latency 767.230 ms 1 172 0.88 MB/sec warmup 8 sec latency 1769.742 ms 1 172 0.78 MB/sec warmup 9 sec latency 2772.064 ms 1 172 0.70 MB/sec warmup 10 sec latency 3772.343 ms 1 172 0.64 MB/sec warmup 11 sec latency 4772.966 ms 1 172 0.59 MB/sec warmup 12 sec latency 5773.909 ms 1 172 0.54 MB/sec warmup 13 sec latency 6774.075 ms 1 172 0.50 MB/sec warmup 14 sec latency 7774.581 ms 01:02:42 (1786942962) shut down 1 172 0.47 MB/sec warmup 15 sec latency 8774.896 ms facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server 1 172 0.44 MB/sec warmup 16 sec latency 9775.438 ms 1 172 0.41 MB/sec warmup 17 sec latency 10777.292 ms 1 172 0.39 MB/sec warmup 18 sec latency 11777.602 ms 1 172 0.37 MB/sec warmup 19 sec latency 12777.786 ms 1 172 0.00 MB/sec execute 1 sec latency 14778.237 ms 1 172 0.00 MB/sec execute 2 sec latency 15778.673 ms 1 172 0.00 MB/sec execute 3 sec latency 16780.632 ms 1 172 0.00 MB/sec execute 4 sec latency 17780.797 ms 1 172 0.00 MB/sec execute 5 sec latency 18780.964 ms Failover mds1 to oleg113-server mount facets: mds1 1 172 0.00 MB/sec execute 6 sec latency 19793.327 ms 1 172 0.00 MB/sec execute 7 sec latency 20793.822 ms 1 172 0.00 MB/sec execute 8 sec latency 21798.141 ms 1 172 0.00 MB/sec execute 9 sec latency 22798.398 ms 1 172 0.00 MB/sec execute 10 sec latency 23807.002 ms 1 172 0.00 MB/sec execute 11 sec latency 24821.154 ms 1 172 0.00 MB/sec execute 12 sec latency 25821.434 ms 1 172 0.00 MB/sec execute 13 sec latency 26825.232 ms 1 172 0.00 MB/sec execute 14 sec latency 27827.547 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 172 0.00 MB/sec execute 15 sec latency 28827.832 ms 1 172 0.00 MB/sec execute 16 sec latency 29828.205 ms 1 172 0.00 MB/sec execute 17 sec latency 30828.838 ms 1 172 0.00 MB/sec execute 18 sec latency 31830.239 ms 1 172 0.00 MB/sec execute 19 sec latency 32830.695 ms 1 172 0.00 MB/sec execute 20 sec latency 33832.012 ms 1 172 0.00 MB/sec execute 21 sec latency 34832.392 ms 1 172 0.00 MB/sec execute 22 sec latency 35832.691 ms 1 172 0.00 MB/sec execute 23 sec latency 36835.964 ms 1 172 0.00 MB/sec execute 24 sec latency 37836.442 ms 1 172 0.00 MB/sec execute 25 sec latency 38836.668 ms oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all 1 172 0.00 MB/sec execute 26 sec latency 39836.979 ms pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 1 172 0.00 MB/sec execute 27 sec latency 40839.996 ms Started lustre-MDT0000 01:03:15 (1786942995) targets are mounted 01:03:15 (1786942995) facet_failover done 1 172 0.00 MB/sec execute 28 sec latency 41840.181 ms 1 187 0.02 MB/sec execute 29 sec latency 41978.027 ms 1 223 0.05 MB/sec execute 30 sec latency 128.145 ms 1 255 0.08 MB/sec execute 31 sec latency 151.808 ms 1 294 0.12 MB/sec execute 32 sec latency 110.790 ms 1 335 0.15 MB/sec execute 33 sec latency 155.770 ms 1 373 0.18 MB/sec execute 34 sec latency 152.048 ms oleg113-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 413 0.22 MB/sec execute 35 sec latency 117.756 ms 1 445 0.24 MB/sec execute 36 sec latency 148.133 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 478 0.26 MB/sec execute 37 sec latency 171.966 ms 1 503 0.27 MB/sec execute 38 sec latency 239.689 ms 1 575 0.31 MB/sec execute 39 sec latency 246.545 ms 1 637 0.35 MB/sec execute 40 sec latency 112.216 ms 1 680 0.34 MB/sec execute 41 sec latency 94.307 ms 1 713 0.34 MB/sec execute 42 sec latency 127.553 ms 1 759 0.33 MB/sec execute 43 sec latency 106.367 ms 1 786 0.33 MB/sec execute 44 sec latency 151.984 ms 1 845 0.32 MB/sec execute 45 sec latency 120.340 ms 1 884 0.32 MB/sec execute 46 sec latency 113.710 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 884 0.31 MB/sec execute 47 sec latency 1021.765 ms 1 913 0.31 MB/sec execute 48 sec latency 1062.207 ms 1 948 0.30 MB/sec execute 49 sec latency 117.710 ms 1 977 0.30 MB/sec execute 50 sec latency 119.970 ms 1 1041 0.31 MB/sec execute 51 sec latency 92.038 ms 1 1099 0.30 MB/sec execute 52 sec latency 67.265 ms 1 1145 0.30 MB/sec execute 53 sec latency 82.296 ms 1 1179 0.29 MB/sec execute 54 sec latency 146.456 ms 1 1225 0.29 MB/sec execute 55 sec latency 76.550 ms 1 1262 0.29 MB/sec execute 56 sec latency 100.923 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Mon Aug 17 01:03:44 EDT 2026 with return code 0 67860 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 67860 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished PASS 26 (257s) == replay-dual test 28: lock replay should be ordered: waiting after granted ========================================================== 01:04:21 (1786943061) Waiting for MDT destroys to complete 1+0 records in 1+0 records out 4096 bytes (4.1 kB, 4.0 KiB) copied, 0.0169523 s, 242 kB/s fail_loc=0x80000324 fail_loc=0x32a Failing ost1 on oleg113-server Stopping /mnt/lustre-ost1 (opts:) on oleg113-server 01:04:41 (1786943081) shut down facet: ost1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover ost1 to oleg113-server mount facets: ost1 Start ost1: mount -t lustre -o localrecov /dev/mapper/ost1_flakey /mnt/lustre-ost1 1+0 records in 1+0 records out 4096 bytes (4.1 kB, 4.0 KiB) copied, 0.0226895 s, 181 kB/s seq.cli-lustre-OST0000-super.width=65536 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-OST0000 01:05:06 (1786943106) targets are mounted 01:05:06 (1786943106) facet_failover done oleg113-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid 1475 0 osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in FULL state after 0 sec PASS 28 (64s) == replay-dual test 29: replay vs update with the same xid ========================================================== 01:05:26 (1786943126) SKIP: replay-dual test_29 needs >= 2 clients SKIP 29 (4s) == replay-dual test 30: layout lock replay is not blocked on IO ========================================================== 01:05:29 (1786943129) 10+0 records in 10+0 records out 40960 bytes (41 kB, 40 KiB) copied, 0.0384825 s, 1.1 MB/s 10+0 records in 10+0 records out 40960 bytes (41 kB, 40 KiB) copied, 0.0425529 s, 963 kB/s fail_loc=0x32e fail_val=4 Failing mds1 on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server 01:05:36 (1786943136) shut down facet: mds1 facet_host: oleg113-server facet_failover_host: oleg113-server Failover mds1 to oleg113-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 160+0 records in 160+0 records out 81920 bytes (82 kB, 80 KiB) copied, 28.617 s, 2.9 kB/s Started lustre-MDT0000 01:06:00 (1786943160) targets are mounted 01:06:00 (1786943160) facet_failover done oleg113-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 PASS 30 (47s) == replay-dual test 31: deadlock on file_remove_privs and occupied mod rpc slots ========================================================== 01:06:16 (1786943176) Failing ost1 on oleg113-server Stopping /mnt/lustre-ost1 (opts:) on oleg113-server Creating to objid 2401 on ost lustre-OST0000... total: 32 open/close in 1.03 seconds: 30.92 ops/second 01:06:25 (1786943185) shut down facet: ost1 facet_host: oleg113-server facet_failover_host: oleg113-server at_max=0 fail_loc=0x80001420 file /mnt/lustre2/d31.replay-dual/mdtdir/f31.replay-dual is ready Failover ost1 to oleg113-server mount facets: ost1 Start ost1: mount -t lustre -o localrecov /dev/mapper/ost1_flakey /mnt/lustre-ost1 seq.cli-lustre-OST0000-super.width=65536 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-OST0000 01:06:48 (1786943208) targets are mounted 01:06:48 (1786943208) facet_failover done oleg113-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid 1475 0 osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in FULL IDLE state after 0 sec pids: 73033 73034 73039 73040 73041 73042 73043 73044 73045 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2188 1269116 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1868 1269436 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1568 3605452 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3112 7210928 1% /mnt/lustre UUID Inodes IUsed IFree IUse% Mounted on lustre-MDT0000_UUID 1024000 341 1023659 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1024000 259 1023741 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 262144 516 261628 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 262144 417 261727 1% /mnt/lustre[OST:1] filesystem_summary: 523955 600 523355 1% /mnt/lustre at_max=600 PASS 31 (50s) == replay-dual test 32: gap in update llog shouldn't break recovery ========================================================== 01:07:06 (1786943226) fail_loc=0x0000131d fail_val=10 fail_loc=0x726 Stopping /mnt/lustre-mds2 (opts:) on oleg113-server Stopping /mnt/lustre-mds1 (opts:) on oleg113-server fail_loc=0 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0000 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0001 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2296 1269008 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1940 1269364 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1568 3605452 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3112 7210928 1% /mnt/lustre PASS 32 (42s) == replay-dual test 33: Check for OBD_INCOMPAT_MULTI_RPCS in last_rcvd after abort_recovery ========================================================== 01:07:49 (1786943269) at_min=60 Stopping /mnt/lustre-mds2 (opts:) on oleg113-server last_rcvd in /dev/mapper/mds2_flakey: incompat = 0x61c Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0001 oleg113-client.virtnet: executing wait_import_state_mount REPLAY_WAIT mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0001-mdc-*.mds_server_uuid in REPLAY_WAIT state after 0 sec oleg113-client.virtnet: executing wait_import_state_mount FULL mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec affected facets: mds2 oleg113-server: oleg113-server.virtnet: executing _wait_recovery_complete *.lustre-MDT0001.recovery_status 1475 oleg113-server: *.lustre-MDT0001.recovery_status status: COMPLETE Stopping /mnt/lustre-mds2 (opts:) on oleg113-server last_rcvd in /dev/mapper/mds2_flakey: incompat = 0x61c Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg113-server: oleg113-server.virtnet: executing set_default_debug -1 all pdsh@oleg113-client: oleg113-server: ssh exited with exit code 1 Started lustre-MDT0001 Starting client: oleg113-client.virtnet: -o user_xattr,flock 192.168.201.113@tcp:/lustre /mnt/lustre2 oleg113-client.virtnet: executing wait_import_state_mount FULL mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec affected facets: mds2 oleg113-server: oleg113-server.virtnet: executing _wait_recovery_complete *.lustre-MDT0001.recovery_status 1475 oleg113-server: *.lustre-MDT0001.recovery_status status: COMPLETE at_min=5 PASS 33 (90s) == replay-dual test complete, duration 3654 sec ========== 01:09:19 (1786943359) === replay-dual: start cleanup 01:09:20 (1786943360) === Stopping clients: oleg113-client.virtnet /mnt/lustre2 (opts:) Stopping client oleg113-client.virtnet /mnt/lustre2 opts: === replay-dual: finish cleanup 01:09:30 (1786943370) ===