-----============= acceptance-small: replay-dual ============----- Wed May 28 17:49:55 EDT 2025 mgs: CentOS Linux release 7.9.2009 (Core) MGS_OS_VERSION_ID=7 MGS_OS_ID=centos MGS_OS_VERSION_CODE=117440512 MGS_OS_ID_LIKE=rhel fedora centos mds1: CentOS Linux release 7.9.2009 (Core) MDS1_OS_ID_LIKE=rhel fedora centos MDS1_OS_ID=centos MDS1_OS_VERSION_ID=7 MDS1_OS_VERSION_CODE=117440512 ost1: CentOS Linux release 7.9.2009 (Core) OST1_OS_VERSION_CODE=117440512 OST1_OS_VERSION_ID=7 OST1_OS_ID_LIKE=rhel fedora centos OST1_OS_ID=centos client: CentOS Linux release 7.9.2009 (Core) CLIENT_OS_ID=centos CLIENT_OS_ID_LIKE=rhel fedora centos CLIENT_OS_VERSION_ID=7 CLIENT_OS_VERSION_CODE=117440512 oleg256-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 17:50:00 (1748469000) === Starting client oleg256-client.virtnet: -o user_xattr,flock 192.168.202.156@tcp:/lustre /mnt/lustre2 Started clients oleg256-client.virtnet: 192.168.202.156@tcp:/lustre on /mnt/lustre2 type lustre (rw,checksum,noencrypt,flock,lazystatfs,lruresize,nolock,statfs_project,nouser_fid2path,user_xattr,verbose) oleg256-client.virtnet: executing check_config_client /mnt/lustre oleg256-client.virtnet: Checking config lustre mounted on /mnt/lustre Checking servers environments Checking clients oleg256-client.virtnet environments Using TIMEOUT=20 osc.lustre-OST0000-osc-ffff8800aaf67800.idle_timeout=debug osc.lustre-OST0000-osc-ffff8800b6618800.idle_timeout=debug osc.lustre-OST0001-osc-ffff8800aaf67800.idle_timeout=debug osc.lustre-OST0001-osc-ffff8800b6618800.idle_timeout=debug disable quota as required oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all osd-ldiskfs.track_declares_assert=1 === replay-dual: finish setup 17:50:09 (1748469009) === == replay-dual test 0a: expired recovery with lost client ========================================================== 17:50:09 (1748469009) Check file is LU482_FAILED=/tmp/replay-dual.lu482.QHR8CV UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1768 1285920 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1616 1286072 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre total: 50 open/close in 0.42 seconds: 118.71 ops/second fail_loc=0x80000514 Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 17:50:13 (1748469013) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 17:50:29 (1748469029) targets are mounted 17:50:29 (1748469029) facet_failover done Starting client: oleg256-client.virtnet: -o user_xattr,flock 192.168.202.156@tcp:/lustre /mnt/lustre2 - unlinked 0 (time 1748469144 ; total 0 ; last 0) total: 50 unlinks in 0 seconds: inf unlinks/second PASS 0a (136s) == replay-dual test 0b: lost client during waiting for next transno ========================================================== 17:52:25 (1748469145) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1768 1285920 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1616 1286072 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 17:52:29 (1748469149) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 17:52:42 (1748469162) targets are mounted 17:52:42 (1748469162) facet_failover done Starting client: oleg256-client.virtnet: -o user_xattr,flock 192.168.202.156@tcp:/lustre /mnt/lustre Starting client: oleg256-client.virtnet: -o user_xattr,flock 192.168.202.156@tcp:/lustre /mnt/lustre2 PASS 0b (94s) == replay-dual test 1: |X| simple create ================= 17:53:59 (1748469239) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1768 1285920 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1616 1286072 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 17:54:03 (1748469243) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 17:54:18 (1748469258) targets are mounted 17:54:18 (1748469258) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 1 (27s) == replay-dual test 2: |X| mkdir adir ==================== 17:54:26 (1748469266) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1768 1285920 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1616 1286072 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 17:54:30 (1748469270) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 17:54:45 (1748469285) targets are mounted 17:54:45 (1748469285) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 2 (27s) == replay-dual test 3: |X| mkdir adir, mkdir adir/bdir === 17:54:53 (1748469293) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1768 1285920 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1616 1286072 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 17:54:57 (1748469297) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 17:55:12 (1748469312) targets are mounted 17:55:12 (1748469312) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 3 (27s) == replay-dual test 4: |X| mkdir adir (-EEXIST), mkdir adir/bdir ========================================================== 17:55:20 (1748469320) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1916 1285772 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre mkdir: cannot create directory '/mnt/lustre/adir': File exists Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 17:55:24 (1748469324) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 17:55:39 (1748469339) targets are mounted 17:55:39 (1748469339) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 4 (25s) == replay-dual test 5: open, unlink |X| close ============ 17:55:45 (1748469345) multiop /mnt/lustre2/a vo_tSc TMPPIPE=/tmp/multiop_open_wait_pipe.7901 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1912 1285776 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 17:55:49 (1748469349) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 17:56:04 (1748469364) targets are mounted 17:56:04 (1748469364) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 5 (26s) == replay-dual test 6: open1, open2, unlink |X| close1 [fail mds1] close2 ========================================================== 17:56:11 (1748469371) multiop /mnt/lustre2/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.7901 multiop /mnt/lustre/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.7901 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1912 1285776 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 17:56:15 (1748469375) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 17:56:29 (1748469389) targets are mounted 17:56:29 (1748469389) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 6 (25s) == replay-dual test 8: replay of resent request ========== 17:56:36 (1748469396) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1912 1285776 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre fail_loc=0x119 fail_loc=0 Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 17:56:56 (1748469416) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 17:57:11 (1748469431) targets are mounted 17:57:11 (1748469431) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 8 (42s) == replay-dual test 9: resending a replayed create ======= 17:57:18 (1748469438) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1912 1285776 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre fail_loc=0x80000119 Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 17:57:22 (1748469442) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 17:57:36 (1748469456) targets are mounted 17:57:36 (1748469456) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 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 ====== 17:58:00 (1748469480) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1912 1285776 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre fail_loc=0x80000119 Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 17:58:05 (1748469485) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 17:58:20 (1748469500) targets are mounted 17:58:20 (1748469500) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 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 ========================================================== 17:58:40 (1748469520) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1912 1285776 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre fail_loc=0x0119 Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 17:58:45 (1748469525) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 17:59:00 (1748469540) targets are mounted 17:59:00 (1748469540) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount FULL mdc.lustre-MDT0000-mdc-*.mds_server_uuid 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 ============== 17:59:18 (1748469558) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1912 1285776 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre multiop /mnt/lustre/f12.replay-dual vmo_c TMPPIPE=/tmp/multiop_open_wait_pipe.7901 fail_loc=0x80000302 Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 17:59:23 (1748469563) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 17:59:39 (1748469579) targets are mounted 17:59:39 (1748469579) facet_failover done fail_loc=0 /mnt/lustre/f12.replay-dual /mnt/lustre/f12.replay-dual has type file OK PASS 12 (26s) == replay-dual test 13: close resend timeout ============= 17:59:44 (1748469584) multiop /mnt/lustre/f13.replay-dual vmo_c TMPPIPE=/tmp/multiop_open_wait_pipe.7901 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1912 1285776 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre fail_loc=0x80000115 Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 17:59:49 (1748469589) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 18:00:04 (1748469604) targets are mounted 18:00:04 (1748469604) 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 ========================================================== 18:00:10 (1748469610) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1912 1285776 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre total: 25 open/close in 0.32 seconds: 77.68 ops/second total: 1 open/close in 0.01 seconds: 75.22 ops/second Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 18:00:15 (1748469615) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 18:00:30 (1748469630) targets are mounted 18:00:30 (1748469630) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec - unlinked 0 (time 1748469702 ; total 0 ; last 0) total: 25 unlinks in 0 seconds: inf unlinks/second Starting client: oleg256-client.virtnet: -o user_xattr,flock 192.168.202.156@tcp:/lustre /mnt/lustre2 PASS 15a (93s) == replay-dual test 15c: remove multiple OST orphans ===== 18:01:44 (1748469704) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1912 1285776 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 18:02:25 (1748469745) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 18:02:40 (1748469760) targets are mounted 18:02:40 (1748469760) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec Starting client: oleg256-client.virtnet: -o user_xattr,flock 192.168.202.156@tcp:/lustre /mnt/lustre2 PASS 15c (133s) == replay-dual test 16: fail MDS during recovery (3571) == 18:03:56 (1748469836) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1912 1285776 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre total: 25 open/close in 0.34 seconds: 73.66 ops/second total: 1 open/close in 0.01 seconds: 90.59 ops/second Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 18:04:01 (1748469841) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 18:04:16 (1748469856) targets are mounted 18:04:16 (1748469856) facet_failover done Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 18:04:37 (1748469877) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 18:04:51 (1748469891) targets are mounted 18:04:51 (1748469891) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec - unlinked 0 (time 1748469964 ; total 0 ; last 0) total: 25 unlinks in 0 seconds: inf unlinks/second Starting client: oleg256-client.virtnet: -o user_xattr,flock 192.168.202.156@tcp:/lustre /mnt/lustre2 PASS 16 (130s) == replay-dual test 17: fail OST during recovery (3571) == 18:06:06 (1748469966) total: 25 open/close in 0.22 seconds: 115.00 ops/second total: 1 open/close in 0.02 seconds: 55.98 ops/second UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1984 1285704 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre Failing ost1 on oleg256-server Stopping /mnt/lustre-ost1 (opts:) on oleg256-server 18:06:10 (1748469970) shut down facet: ost1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover ost1 to oleg256-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 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-OST0000 18:06:26 (1748469986) targets are mounted 18:06:26 (1748469986) facet_failover done Failing ost1 on oleg256-server Stopping /mnt/lustre-ost1 (opts:) on oleg256-server 18:06:47 (1748470007) shut down facet: ost1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover ost1 to oleg256-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 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-OST0000 18:07:02 (1748470022) targets are mounted 18:07:02 (1748470022) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in FULL state after 0 sec - unlinked 0 (time 1748470097 ; total 0 ; last 0) total: 25 unlinks in 0 seconds: inf unlinks/second Starting client: oleg256-client.virtnet: -o user_xattr,flock 192.168.202.156@tcp:/lustre /mnt/lustre2 PASS 17 (133s) == replay-dual test 18: ldlm_handle_enqueue succeeds on evicted export (3822) ========================================================== 18:08:19 (1748470099) debug=+dlmtrace fail_loc=0x8000030b using seed 1280239126 running for 500 iterations total: 500 stats in 0 seconds: inf stats/second ldlm.namespaces.MGC192.168.202.156@tcp.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffff8800b37b1000.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffff8800b3c30800.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0001-mdc-ffff8800b37b1000.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0001-mdc-ffff8800b3c30800.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffff8800b37b1000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffff8800b3c30800.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffff8800b37b1000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffff8800b3c30800.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.MGC192.168.202.156@tcp.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffff8800b37b1000.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffff8800b3c30800.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0001-mdc-ffff8800b37b1000.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0001-mdc-ffff8800b3c30800.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffff8800b37b1000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffff8800b3c30800.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffff8800b37b1000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffff8800b3c30800.early_lock_cancel=1 fail_loc=0 fail_loc=0 PASS 18 (46s) == replay-dual test 19: resend of open request =========== 18:09:05 (1748470145) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1988 1285700 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1540 3605480 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3076 7210964 1% /mnt/lustre fail_loc=0x157 - open/close 0 (time 1748470234.58 total 86.03 last 0.00) total: 1 open/close in 86.03 seconds: 0.01 ops/second fail_loc=0 Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 18:10:36 (1748470236) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 18:10:51 (1748470251) targets are mounted 18:10:51 (1748470251) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 19 (113s) == replay-dual test 20: recovery time is not increasing == 18:10:59 (1748470259) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1988 1285700 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1540 3605480 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3076 7210964 1% /mnt/lustre Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 18:11:03 (1748470263) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 18:11:18 (1748470278) targets are mounted 18:11:18 (1748470278) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec Starting client: oleg256-client.virtnet: -o user_xattr,flock 192.168.202.156@tcp:/lustre /mnt/lustre2 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1988 1285700 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1540 3605480 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3076 7210964 1% /mnt/lustre Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 18:13:42 (1748470422) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 18:13:58 (1748470438) targets are mounted 18:13:58 (1748470438) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec Starting client: oleg256-client.virtnet: -o user_xattr,flock 192.168.202.156@tcp:/lustre /mnt/lustre2 PASS 20 (324s) == replay-dual test 21a: commit on sharing =============== 18:16:22 (1748470582) mdt.lustre-MDT0000.commit_on_sharing=1 mdt.lustre-MDT0001.commit_on_sharing=1 Replay barrier on lustre-MDT0000 Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 18:16:25 (1748470585) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 18:16:39 (1748470599) targets are mounted 18:16:39 (1748470599) facet_failover done Starting client: oleg256-client.virtnet: -o user_xattr,flock 192.168.202.156@tcp:/lustre /mnt/lustre2 mdt.lustre-MDT0000.commit_on_sharing=0 mdt.lustre-MDT0001.commit_on_sharing=0 PASS 21a (162s) 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 ========================================================== 18:19:04 (1748470744) fail_loc=0x119 Failing mds2 on oleg256-server Stopping /mnt/lustre-mds2 (opts:) on oleg256-server 18:19:09 (1748470749) shut down facet: mds2 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds2 to oleg256-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0001 18:19:26 (1748470766) targets are mounted 18:19:26 (1748470766) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 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 1996 1285692 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1820 1285868 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1540 3605480 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3076 7210964 1% /mnt/lustre total: 2 open/close in 0.06 seconds: 31.73 ops/second total: 2 open/close in 0.04 seconds: 47.48 ops/second Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 18:19:40 (1748470780) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 18:19:56 (1748470796) targets are mounted 18:19:56 (1748470796) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 22a (61s) == replay-dual test 22b: c1 lfs mkdir -i 1 d1, M1 drop reply & fail M0/M1, c2 mkdir d1/dir ========================================================== 18:20:05 (1748470805) fail_loc=0x119 Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server Failing mds2 on oleg256-server Stopping /mnt/lustre-mds2 (opts:) on oleg256-server 18:20:11 (1748470811) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server facet: mds2 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Failover mds2 to oleg256-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 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 18:20:38 (1748470838) targets are mounted 18:20:38 (1748470838) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid 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 1996 1285692 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1820 1285868 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1540 3605480 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3076 7210964 1% /mnt/lustre total: 2 open/close in 0.07 seconds: 30.27 ops/second total: 2 open/close in 0.02 seconds: 103.10 ops/second Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 18:20:51 (1748470851) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 18:21:07 (1748470867) targets are mounted 18:21:07 (1748470867) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 22b (70s) == replay-dual test 22c: c1 lfs mkdir -i 1 d1, M1 drop update & fail M1, c2 mkdir d1/dir ========================================================== 18:21:16 (1748470876) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 18:21:19 (1748470879) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 18:21:34 (1748470894) targets are mounted 18:21:35 (1748470895) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 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 1996 1285692 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1820 1285868 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1540 3605480 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3076 7210964 1% /mnt/lustre total: 2 open/close in 0.04 seconds: 56.36 ops/second total: 2 open/close in 0.02 seconds: 111.21 ops/second Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 18:21:45 (1748470905) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 18:21:59 (1748470919) targets are mounted 18:21:59 (1748470919) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 22c (53s) == replay-dual test 22d: c1 lfs mkdir -i 1 d1, M1 drop update & fail M0/M1,c2 mkdir d1/dir ========================================================== 18:22:08 (1748470928) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server Failing mds2 on oleg256-server Stopping /mnt/lustre-mds2 (opts:) on oleg256-server 18:22:17 (1748470937) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server facet: mds2 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Failover mds2 to oleg256-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 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 18:22:43 (1748470963) targets are mounted 18:22:43 (1748470963) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid 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 1996 1285692 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1820 1285868 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1540 3605480 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3076 7210964 1% /mnt/lustre total: 2 open/close in 0.03 seconds: 66.25 ops/second total: 2 open/close in 0.01 seconds: 158.34 ops/second Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 18:22:52 (1748470972) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 18:23:06 (1748470986) targets are mounted 18:23:06 (1748470986) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 22d (65s) == replay-dual test 23a: c1 rmdir d1, M1 drop reply and fail, client2 mkdir d1 ========================================================== 18:23:13 (1748470993) fail_loc=0x119 fail_loc=0 Failing mds2 on oleg256-server Stopping /mnt/lustre-mds2 (opts:) on oleg256-server 18:23:22 (1748471002) shut down facet: mds2 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds2 to oleg256-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0001 18:23:35 (1748471015) targets are mounted 18:23:35 (1748471015) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 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 1992 1285696 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1816 1285872 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1540 3605480 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3076 7210964 1% /mnt/lustre total: 2 open/close in 0.02 seconds: 106.03 ops/second Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 18:23:44 (1748471024) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 18:23:58 (1748471038) targets are mounted 18:23:58 (1748471038) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 23a (52s) == replay-dual test 23b: c1 rmdir d1, M1 drop reply and fail M0/M1, c2 mkdir d1 ========================================================== 18:24:05 (1748471045) fail_loc=0x119 fail_loc=0 Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server Failing mds2 on oleg256-server Stopping /mnt/lustre-mds2 (opts:) on oleg256-server 18:24:15 (1748471055) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server facet: mds2 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Failover mds2 to oleg256-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 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 18:24:36 (1748471076) targets are mounted 18:24:36 (1748471076) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid 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 1992 1285696 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1816 1285872 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1540 3605480 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3076 7210964 1% /mnt/lustre total: 2 open/close in 0.02 seconds: 131.23 ops/second Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 18:24:45 (1748471085) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 18:24:58 (1748471098) targets are mounted 18:24:58 (1748471098) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 23b (61s) == replay-dual test 23c: c1 rmdir d1, M0 drop update reply and fail M0, c2 mkdir d1 ========================================================== 18:25:06 (1748471106) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 18:25:08 (1748471108) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 18:25:21 (1748471121) targets are mounted 18:25:21 (1748471121) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 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 1992 1285696 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1816 1285872 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1540 3605480 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3076 7210964 1% /mnt/lustre total: 2 open/close in 0.02 seconds: 123.86 ops/second Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 18:25:30 (1748471130) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 18:25:44 (1748471144) targets are mounted 18:25:44 (1748471144) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 23c (46s) == replay-dual test 23d: c1 rmdir d1, M0 drop update reply and fail M0/M1, c2 mkdir d1 ========================================================== 18:25:52 (1748471152) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server Failing mds2 on oleg256-server Stopping /mnt/lustre-mds2 (opts:) on oleg256-server 18:26:04 (1748471164) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server facet: mds2 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Failover mds2 to oleg256-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 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 18:26:24 (1748471184) targets are mounted 18:26:24 (1748471184) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid 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 1956 1285732 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1780 1285908 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1540 3605480 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3076 7210964 1% /mnt/lustre total: 2 open/close in 0.02 seconds: 112.66 ops/second Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 18:26:33 (1748471193) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 18:26:47 (1748471207) targets are mounted 18:26:47 (1748471207) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 23d (62s) == replay-dual test 24: reconstruct on non-existing object ========================================================== 18:26:54 (1748471214) fail_loc=0x119 fail_loc=0 truncate: cannot truncate '/mnt/lustre/f24.replay-dual' to length 100: No such file or directory PASS 24 (87s) == replay-dual test 25: replay|resend ==================== 18:28:21 (1748471301) 1+0 records in 1+0 records out 512 bytes (512 B) copied, 0.00380297 s, 135 kB/s fail_loc=0x304 fail_loc=0x80000325 Failing ost1 on oleg256-server Stopping /mnt/lustre-ost1 (opts:) on oleg256-server 18:28:24 (1748471304) shut down facet: ost1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover ost1 to oleg256-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 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-OST0000 18:28:37 (1748471317) targets are mounted 18:28:37 (1748471317) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid 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 6829: 3460 Terminated LUSTRE="/home/green/git/lustre-release/lustre" bash -c "multiop /mnt/lustre2/f25.replay-dual Ow512" fail_loc=0 PASS 25 (22s) == replay-dual test 26: dbench and tar with mds failover ========================================================== 18:28:43 (1748471323) Starting client oleg256-client.virtnet: -o user_xattr,flock 192.168.202.156@tcp:/lustre /mnt/lustre Started clients oleg256-client.virtnet: 192.168.202.156@tcp:/lustre on /mnt/lustre type lustre (rw,checksum,noencrypt,flock,lazystatfs,lruresize,nolock,statfs_project,nouser_fid2path,user_xattr,verbose) Started tar loop with pid 5001 Started dbench loop with 5003 striped dir -i0 -c2 -H all_char /mnt/lustre2/d26.replay-dual/run_dbench striped dir -i0 -c2 -H crush /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 Wed May 28 18:28:44 EDT 2025 waiting for dbench pid 5043 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 2228 1285460 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2024 1285664 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 26120 3580704 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 27656 7186188 1% /mnt/lustre 1 193 7.65 MB/sec warmup 1 sec latency 40.055 ms 1 344 6.13 MB/sec warmup 2 sec latency 41.008 ms 1 511 5.91 MB/sec warmup 3 sec latency 37.249 ms 1 710 5.30 MB/sec warmup 4 sec latency 43.836 ms 1 864 4.31 MB/sec warmup 5 sec latency 33.002 ms test_26 fail mds1 1 times Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 1 1042 3.81 MB/sec warmup 6 sec latency 29.411 ms 18:28:51 (1748471331) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server 1 1088 3.28 MB/sec warmup 7 sec latency 793.224 ms 1 1088 2.87 MB/sec warmup 8 sec latency 1793.414 ms 1 1088 2.55 MB/sec warmup 9 sec latency 2793.986 ms 1 1088 2.29 MB/sec warmup 10 sec latency 3794.174 ms 1 1088 2.08 MB/sec warmup 11 sec latency 4794.335 ms 1 1088 1.91 MB/sec warmup 12 sec latency 5794.503 ms 1 1088 1.76 MB/sec warmup 13 sec latency 6794.656 ms 1 1088 1.64 MB/sec warmup 14 sec latency 7795.629 ms 1 1088 1.53 MB/sec warmup 15 sec latency 8795.784 ms 1 1088 1.43 MB/sec warmup 16 sec latency 9796.242 ms Failover mds1 to oleg256-server mount facets: mds1 1 1088 1.35 MB/sec warmup 17 sec latency 10796.364 ms 1 1088 1.27 MB/sec warmup 18 sec latency 11796.500 ms 1 1088 1.21 MB/sec warmup 19 sec latency 12796.694 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 1088 0.00 MB/sec execute 1 sec latency 14797.406 ms oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 1 1088 0.00 MB/sec execute 2 sec latency 15798.190 ms Started lustre-MDT0000 18:29:06 (1748471346) targets are mounted 18:29:06 (1748471346) facet_failover done 1 1088 0.00 MB/sec execute 3 sec latency 16798.343 ms 1 1088 0.00 MB/sec execute 4 sec latency 17798.669 ms 1 1088 0.00 MB/sec execute 5 sec latency 18798.855 ms 1 1088 0.00 MB/sec execute 6 sec latency 19799.278 ms oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 1252 0.02 MB/sec execute 7 sec latency 19909.487 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 1485 0.39 MB/sec execute 8 sec latency 55.859 ms 1 1687 0.36 MB/sec execute 9 sec latency 24.095 ms 1 1924 0.35 MB/sec execute 10 sec latency 32.147 ms 1 2150 0.34 MB/sec execute 11 sec latency 23.906 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2796 1284892 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2528 1285160 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 32748 3564896 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 6520 3593468 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 39268 7158364 1% /mnt/lustre 1 2388 0.42 MB/sec execute 12 sec latency 30.164 ms 1 2600 0.47 MB/sec execute 13 sec latency 23.203 ms 1 3177 0.80 MB/sec execute 14 sec latency 17.960 ms 1 3570 1.03 MB/sec execute 15 sec latency 19.002 ms test_26 fail mds2 2 times Failing mds2 on oleg256-server Stopping /mnt/lustre-mds2 (opts:) on oleg256-server 1 3812 1.05 MB/sec execute 16 sec latency 21.376 ms 18:29:21 (1748471361) shut down facet: mds2 facet_host: oleg256-server facet_failover_host: oleg256-server 1 4002 1.01 MB/sec execute 17 sec latency 21.964 ms 1 4083 0.95 MB/sec execute 18 sec latency 616.628 ms 1 4083 0.90 MB/sec execute 19 sec latency 1616.728 ms 1 4083 0.86 MB/sec execute 20 sec latency 2616.982 ms 1 4083 0.82 MB/sec execute 21 sec latency 3617.075 ms 1 4083 0.78 MB/sec execute 22 sec latency 4617.173 ms 1 4083 0.75 MB/sec execute 23 sec latency 5617.275 ms 1 4083 0.71 MB/sec execute 24 sec latency 6617.435 ms 1 4083 0.69 MB/sec execute 25 sec latency 7617.553 ms 1 4083 0.66 MB/sec execute 26 sec latency 8617.656 ms Failover mds2 to oleg256-server mount facets: mds2 1 4083 0.64 MB/sec execute 27 sec latency 9617.769 ms 1 4083 0.61 MB/sec execute 28 sec latency 10617.904 ms 1 4083 0.59 MB/sec execute 29 sec latency 11618.010 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 4083 0.57 MB/sec execute 30 sec latency 12618.114 ms oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0001 18:29:35 (1748471375) targets are mounted 18:29:35 (1748471375) facet_failover done 1 4083 0.55 MB/sec execute 31 sec latency 13618.223 ms 1 4083 0.54 MB/sec execute 32 sec latency 14618.317 ms 1 4083 0.52 MB/sec execute 33 sec latency 15618.435 ms 1 4083 0.50 MB/sec execute 34 sec latency 16618.538 ms 1 4214 0.49 MB/sec execute 35 sec latency 17215.410 ms oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 4505 0.50 MB/sec execute 36 sec latency 19.639 ms 1 4840 0.52 MB/sec execute 37 sec latency 16.357 ms 1 5251 0.59 MB/sec execute 38 sec latency 15.467 ms 1 5581 0.58 MB/sec execute 39 sec latency 18.405 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 4640 1283048 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2648 1285040 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 39020 3562024 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 10840 3587528 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 49860 7149552 1% /mnt/lustre 1 5928 0.60 MB/sec execute 40 sec latency 28.379 ms 1 6150 0.61 MB/sec execute 41 sec latency 298.647 ms 1 6787 0.73 MB/sec execute 42 sec latency 16.960 ms test_26 fail mds1 3 times 1 7242 0.81 MB/sec execute 43 sec latency 12.033 ms Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 1 7470 0.82 MB/sec execute 44 sec latency 142.699 ms 1 7470 0.81 MB/sec execute 45 sec latency 1142.838 ms 1 7470 0.79 MB/sec execute 46 sec latency 2142.999 ms 1 7470 0.77 MB/sec execute 47 sec latency 3143.164 ms 1 7470 0.76 MB/sec execute 48 sec latency 4143.385 ms 1 7470 0.74 MB/sec execute 49 sec latency 5143.633 ms 1 7470 0.72 MB/sec execute 50 sec latency 6143.769 ms 18:29:55 (1748471395) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server 1 7470 0.71 MB/sec execute 51 sec latency 7143.940 ms 1 7470 0.70 MB/sec execute 52 sec latency 8144.099 ms 1 7470 0.68 MB/sec execute 53 sec latency 9144.263 ms 1 7470 0.67 MB/sec execute 54 sec latency 10144.447 ms 1 7470 0.66 MB/sec execute 55 sec latency 11144.620 ms 1 7470 0.65 MB/sec execute 56 sec latency 12144.786 ms 1 7470 0.64 MB/sec execute 57 sec latency 13144.961 ms 1 7470 0.62 MB/sec execute 58 sec latency 14145.112 ms 1 7470 0.61 MB/sec execute 59 sec latency 15145.285 ms 1 7470 0.60 MB/sec execute 60 sec latency 16145.575 ms Failover mds1 to oleg256-server mount facets: mds1 1 7470 0.59 MB/sec execute 61 sec latency 17145.805 ms 1 7470 0.58 MB/sec execute 62 sec latency 18145.948 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 7470 0.58 MB/sec execute 63 sec latency 19146.101 ms 1 7470 0.57 MB/sec execute 64 sec latency 20146.408 ms oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 18:30:09 (1748471409) targets are mounted 18:30:09 (1748471409) facet_failover done 1 7470 0.56 MB/sec execute 65 sec latency 21146.578 ms 1 7470 0.55 MB/sec execute 66 sec latency 22146.728 ms 1 7470 0.54 MB/sec execute 67 sec latency 23147.307 ms 1 7470 0.53 MB/sec execute 68 sec latency 24147.483 ms 1 7470 0.53 MB/sec execute 69 sec latency 25147.605 ms 1 7480 0.52 MB/sec execute 70 sec latency 26015.368 ms oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 7623 0.51 MB/sec execute 71 sec latency 26.614 ms 1 7825 0.51 MB/sec execute 72 sec latency 61.343 ms 1 8039 0.51 MB/sec execute 73 sec latency 27.907 ms 1 8265 0.52 MB/sec execute 74 sec latency 22.351 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 5012 1282676 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 3032 1284656 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 47192 3556968 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 30500 3565308 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 77692 7122276 2% /mnt/lustre 1 8583 0.55 MB/sec execute 75 sec latency 35.956 ms 1 8829 0.55 MB/sec execute 76 sec latency 17.456 ms 1 9115 0.54 MB/sec execute 77 sec latency 15.572 ms 1 9407 0.55 MB/sec execute 78 sec latency 20.465 ms test_26 fail mds2 4 times 1 9587 0.56 MB/sec execute 79 sec latency 25.326 ms Failing mds2 on oleg256-server Stopping /mnt/lustre-mds2 (opts:) on oleg256-server 1 9999 0.60 MB/sec execute 80 sec latency 25.767 ms 18:30:25 (1748471425) shut down facet: mds2 facet_host: oleg256-server facet_failover_host: oleg256-server 1 10413 0.63 MB/sec execute 81 sec latency 19.926 ms 1 10787 0.66 MB/sec execute 82 sec latency 14.052 ms 1 11049 0.67 MB/sec execute 83 sec latency 13.647 ms 1 11174 0.66 MB/sec execute 84 sec latency 432.234 ms 1 11174 0.65 MB/sec execute 85 sec latency 1432.401 ms 1 11174 0.64 MB/sec execute 86 sec latency 2432.563 ms 1 11174 0.64 MB/sec execute 87 sec latency 3432.701 ms 1 11174 0.63 MB/sec execute 88 sec latency 4432.883 ms 1 11174 0.62 MB/sec execute 89 sec latency 5433.029 ms 1 11174 0.62 MB/sec execute 90 sec latency 6433.187 ms Failover mds2 to oleg256-server mount facets: mds2 1 11174 0.61 MB/sec execute 91 sec latency 7433.370 ms 1 11174 0.60 MB/sec execute 92 sec latency 8433.501 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 11174 0.60 MB/sec execute 93 sec latency 9433.601 ms oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0001 18:30:38 (1748471438) targets are mounted 18:30:38 (1748471438) facet_failover done 1 11174 0.59 MB/sec execute 94 sec latency 10433.895 ms 1 11174 0.58 MB/sec execute 95 sec latency 11434.009 ms 1 11174 0.58 MB/sec execute 96 sec latency 12434.139 ms 1 11174 0.57 MB/sec execute 97 sec latency 13434.295 ms 1 11174 0.57 MB/sec execute 98 sec latency 14434.400 ms oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1 11381 0.56 MB/sec execute 99 sec latency 14691.934 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 cleanup 100 sec 0 cleanup 101 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 1826 9.906 61.330 Close 1337 1.847 6.936 Rename 77 15.731 30.021 Unlink 370 75.090 26015.346 Qpathinfo 1675 21.967 17215.393 Qfileinfo 289 0.474 2.996 Qfsinfo 300 0.863 4.347 Sfileinfo 146 9.849 20.194 Find 639 34.145 19909.471 WriteX 889 2.191 12.415 ReadX 2863 0.125 48.463 LockX 6 2.032 3.034 UnlockX 6 1.835 2.803 Flush 128 10.792 298.633 Throughput 0.562704 MB/sec 1 clients 1 procs max_latency=26015.368 ms stopping dbench on /mnt/lustre at Wed May 28 18:30:45 EDT 2025 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished striped dir -i0 -c2 -H crush /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 Wed May 28 18:30:46 EDT 2025 waiting for dbench pid 9566 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 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 5436 1282252 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 3500 1284188 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 9932 3592520 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 27092 3549748 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 37024 7142268 1% /mnt/lustre 1 254 9.66 MB/sec warmup 1 sec latency 23.722 ms 1 517 8.90 MB/sec warmup 2 sec latency 20.234 ms 1 845 7.19 MB/sec warmup 3 sec latency 67.324 ms 1 1157 5.75 MB/sec warmup 4 sec latency 17.252 ms test_26 fail mds1 5 times 1 1540 5.22 MB/sec warmup 5 sec latency 25.943 ms Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 1 1715 4.37 MB/sec warmup 6 sec latency 502.456 ms 18:30:53 (1748471453) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server 1 1715 3.75 MB/sec warmup 7 sec latency 1502.632 ms 1 1715 3.28 MB/sec warmup 8 sec latency 2502.783 ms 1 1715 2.92 MB/sec warmup 9 sec latency 3503.059 ms 1 1715 2.62 MB/sec warmup 10 sec latency 4503.201 ms 1 1715 2.39 MB/sec warmup 11 sec latency 5503.332 ms 1 1715 2.19 MB/sec warmup 12 sec latency 6503.490 ms 1 1715 2.02 MB/sec warmup 13 sec latency 7503.644 ms 1 1715 1.87 MB/sec warmup 14 sec latency 8503.803 ms 1 1715 1.75 MB/sec warmup 15 sec latency 9503.967 ms 1 1715 1.64 MB/sec warmup 16 sec latency 10504.141 ms Failover mds1 to oleg256-server mount facets: mds1 1 1715 1.54 MB/sec warmup 17 sec latency 11504.309 ms 1 1715 1.46 MB/sec warmup 18 sec latency 12504.468 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 1715 1.38 MB/sec warmup 19 sec latency 13504.554 ms oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 18:31:07 (1748471467) targets are mounted 18:31:07 (1748471467) facet_failover done 1 1715 0.00 MB/sec execute 1 sec latency 15504.888 ms 1 1715 0.00 MB/sec execute 2 sec latency 16505.076 ms 1 1715 0.00 MB/sec execute 3 sec latency 17505.236 ms 1 1715 0.00 MB/sec execute 4 sec latency 18505.382 ms 1 1753 0.01 MB/sec execute 5 sec latency 19275.112 ms oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 2010 0.05 MB/sec execute 6 sec latency 21.390 ms 1 2373 0.24 MB/sec execute 7 sec latency 14.376 ms 1 2906 0.82 MB/sec execute 8 sec latency 14.204 ms 1 3549 1.35 MB/sec execute 9 sec latency 15.888 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 4368 1283320 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2872 1284816 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 12596 3583844 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 40676 3556380 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 53272 7140224 1% /mnt/lustre 1 3841 1.35 MB/sec execute 10 sec latency 45.616 ms 1 4068 1.26 MB/sec execute 11 sec latency 14.995 ms 1 4340 1.19 MB/sec execute 12 sec latency 31.188 ms 1 4639 1.21 MB/sec execute 13 sec latency 21.387 ms test_26 fail mds2 6 times Failing mds2 on oleg256-server 1 5004 1.35 MB/sec execute 14 sec latency 17.743 ms Stopping /mnt/lustre-mds2 (opts:) on oleg256-server 18:31:21 (1748471481) shut down facet: mds2 facet_host: oleg256-server facet_failover_host: oleg256-server 1 5254 1.27 MB/sec execute 15 sec latency 25.281 ms 1 5551 1.21 MB/sec execute 16 sec latency 24.997 ms 1 5820 1.16 MB/sec execute 17 sec latency 231.294 ms 1 5820 1.09 MB/sec execute 18 sec latency 1231.388 ms 1 5820 1.03 MB/sec execute 19 sec latency 2231.474 ms 1 5820 0.98 MB/sec execute 20 sec latency 3231.638 ms 1 5820 0.94 MB/sec execute 21 sec latency 4231.800 ms 1 5820 0.89 MB/sec execute 22 sec latency 5231.970 ms 1 5820 0.85 MB/sec execute 23 sec latency 6232.138 ms 1 5820 0.82 MB/sec execute 24 sec latency 7232.308 ms 1 5820 0.79 MB/sec execute 25 sec latency 8232.456 ms Failover mds2 to oleg256-server mount facets: mds2 1 5820 0.76 MB/sec execute 26 sec latency 9232.564 ms 1 5820 0.73 MB/sec execute 27 sec latency 10232.711 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 5820 0.70 MB/sec execute 28 sec latency 11232.835 ms oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0001 18:31:35 (1748471495) targets are mounted 18:31:35 (1748471495) facet_failover done 1 5820 0.68 MB/sec execute 29 sec latency 12232.986 ms 1 5820 0.66 MB/sec execute 30 sec latency 13233.070 ms 1 5820 0.63 MB/sec execute 31 sec latency 14233.231 ms 1 5820 0.61 MB/sec execute 32 sec latency 15233.388 ms 1 5849 0.62 MB/sec execute 33 sec latency 16167.741 ms oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 6111 0.64 MB/sec execute 34 sec latency 23.554 ms 1 6557 0.75 MB/sec execute 35 sec latency 19.012 ms 1 7079 0.87 MB/sec execute 36 sec latency 19.899 ms 1 7345 0.88 MB/sec execute 37 sec latency 17.647 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2624 1285064 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2252 1285436 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 12396 3593276 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 37480 3566824 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 49876 7160100 1% /mnt/lustre 1 7527 0.87 MB/sec execute 38 sec latency 55.234 ms striped dir -i0 -c2 -H fnv_1a_64 /mnt/lustre/d26.replay-dual/run_tar 1 7775 0.85 MB/sec execute 39 sec latency 29.785 ms 1 7894 0.83 MB/sec execute 40 sec latency 467.422 ms 1 8151 0.85 MB/sec execute 41 sec latency 18.797 ms test_26 fail mds1 7 times 1 8382 0.84 MB/sec execute 42 sec latency 22.455 ms Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 1 8643 0.89 MB/sec execute 43 sec latency 281.181 ms 18:31:50 (1748471510) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server 1 8643 0.87 MB/sec execute 44 sec latency 1281.342 ms 1 8643 0.85 MB/sec execute 45 sec latency 2281.491 ms 1 8643 0.83 MB/sec execute 46 sec latency 3281.661 ms 1 8643 0.81 MB/sec execute 47 sec latency 4281.806 ms 1 8643 0.79 MB/sec execute 48 sec latency 5281.930 ms 1 8643 0.78 MB/sec execute 49 sec latency 6282.094 ms 1 8643 0.76 MB/sec execute 50 sec latency 7282.314 ms 1 8643 0.75 MB/sec execute 51 sec latency 8282.508 ms 1 8643 0.73 MB/sec execute 52 sec latency 9282.719 ms 1 8643 0.72 MB/sec execute 53 sec latency 10282.871 ms Failover mds1 to oleg256-server mount facets: mds1 1 8643 0.71 MB/sec execute 54 sec latency 11283.013 ms 1 8643 0.69 MB/sec execute 55 sec latency 12283.144 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 8643 0.68 MB/sec execute 56 sec latency 13283.321 ms oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 1 8643 0.67 MB/sec execute 57 sec latency 14283.484 ms Started lustre-MDT0000 18:32:04 (1748471524) targets are mounted 18:32:04 (1748471524) facet_failover done 1 8643 0.66 MB/sec execute 58 sec latency 15283.698 ms 1 8643 0.65 MB/sec execute 59 sec latency 16283.885 ms 1 8643 0.63 MB/sec execute 60 sec latency 17284.039 ms 1 8643 0.62 MB/sec execute 61 sec latency 18284.162 ms 1 8733 0.62 MB/sec execute 62 sec latency 18896.326 ms oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 8989 0.61 MB/sec execute 63 sec latency 19.204 ms 1 9315 0.61 MB/sec execute 64 sec latency 12.879 ms 1 9676 0.63 MB/sec execute 65 sec latency 15.907 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 10306 0.70 MB/sec execute 66 sec latency 16.330 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Wed May 28 18:32:13 EDT 2025 with return code 0 9566 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 9566 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished PASS 26 (215s) == replay-dual test 28: lock replay should be ordered: waiting after granted ========================================================== 18:32:18 (1748471538) Waiting for MDT destroys to complete 1+0 records in 1+0 records out 4096 bytes (4.1 kB) copied, 0.00277911 s, 1.5 MB/s fail_loc=0x80000324 fail_loc=0x32a Failing ost1 on oleg256-server Stopping /mnt/lustre-ost1 (opts:) on oleg256-server 18:32:31 (1748471551) shut down facet: ost1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover ost1 to oleg256-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 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-OST0000 18:32:44 (1748471564) targets are mounted 18:32:44 (1748471564) facet_failover done 1+0 records in 1+0 records out 4096 bytes (4.1 kB) copied, 0.00348858 s, 1.2 MB/s oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in FULL state after 0 sec PASS 28 (33s) == replay-dual test 29: replay vs update with the same xid ========================================================== 18:32:51 (1748471571) SKIP: replay-dual test_29 needs >= 2 clients SKIP 29 (0s) == replay-dual test 30: layout lock replay is not blocked on IO ========================================================== 18:32:51 (1748471571) 10+0 records in 10+0 records out 40960 bytes (41 kB) copied, 0.00865272 s, 4.7 MB/s 10+0 records in 10+0 records out 40960 bytes (41 kB) copied, 0.00951766 s, 4.3 MB/s fail_loc=0x32e fail_val=4 Failing mds1 on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server 18:32:54 (1748471574) shut down facet: mds1 facet_host: oleg256-server facet_failover_host: oleg256-server Failover mds1 to oleg256-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 18:33:07 (1748471587) targets are mounted 18:33:07 (1748471587) facet_failover done 160+0 records in 160+0 records out 81920 bytes (82 kB) copied, 19.001 s, 4.3 kB/s oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 30 (23s) == replay-dual test 31: deadlock on file_remove_privs and occupied mod rpc slots ========================================================== 18:33:14 (1748471594) Failing ost1 on oleg256-server Stopping /mnt/lustre-ost1 (opts:) on oleg256-server 18:33:16 (1748471596) shut down facet: ost1 facet_host: oleg256-server facet_failover_host: oleg256-server Creating to objid 3201 on ost lustre-OST0000... total: 32 open/close in 0.16 seconds: 195.49 ops/second at_max=0 fail_loc=0x80001420 file /mnt/lustre2/d31.replay-dual/mdtdir/f31.replay-dual is ready Failover ost1 to oleg256-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 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-OST0000 18:33:29 (1748471609) targets are mounted 18:33:29 (1748471609) facet_failover done oleg256-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in FULL IDLE state after 0 sec pids: 17587 17588 17594 17595 17596 17597 17598 17599 17600 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2412 1285276 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1988 1285700 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3084 7210956 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 258 1023742 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 262144 477 261667 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 262144 411 261733 1% /mnt/lustre[OST:1] filesystem_summary: 523999 599 523400 1% /mnt/lustre at_max=600 PASS 31 (20s) == replay-dual test 32: gap in update llog shouldn't break recovery ========================================================== 18:33:34 (1748471614) fail_loc=0x0000131d fail_val=10 fail_loc=0x726 Stopping /mnt/lustre-mds2 (opts:) on oleg256-server Stopping /mnt/lustre-mds1 (opts:) on oleg256-server fail_loc=0 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0000 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0001 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2516 1285172 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2056 1285632 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3084 7210956 1% /mnt/lustre PASS 32 (15s) == replay-dual test 33: Check for OBD_INCOMPAT_MULTI_RPCS in last_rcvd after abort_recovery ========================================================== 18:33:49 (1748471629) at_min=60 Stopping /mnt/lustre-mds2 (opts:) on oleg256-server last_rcvd in /dev/mapper/mds2_flakey: incompat = 0x61c Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0001 oleg256-client.virtnet: executing wait_import_state_mount REPLAY_WAIT mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0001-mdc-*.mds_server_uuid in REPLAY_WAIT state after 0 sec oleg256-client.virtnet: executing wait_import_state_mount FULL mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec affected facets: mds2 oleg256-server: oleg256-server.virtnet: executing _wait_recovery_complete *.lustre-MDT0001.recovery_status 1475 oleg256-server: *.lustre-MDT0001.recovery_status status: COMPLETE Stopping /mnt/lustre-mds2 (opts:) on oleg256-server last_rcvd in /dev/mapper/mds2_flakey: incompat = 0x61c Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg256-server: oleg256-server.virtnet: executing set_default_debug -1 all pdsh@oleg256-client: oleg256-server: ssh exited with exit code 1 Started lustre-MDT0001 Starting client: oleg256-client.virtnet: -o user_xattr,flock 192.168.202.156@tcp:/lustre /mnt/lustre2 oleg256-client.virtnet: executing wait_import_state_mount FULL mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL DISCONN state after 3 sec affected facets: mds2 oleg256-server: oleg256-server.virtnet: executing _wait_recovery_complete *.lustre-MDT0001.recovery_status 1475 oleg256-server: *.lustre-MDT0001.recovery_status status: COMPLETE at_min=5 PASS 33 (35s) == replay-dual test complete, duration 2668 sec ========== 18:34:24 (1748471664) === replay-dual: start cleanup 18:34:25 (1748471665) === Stopping clients: oleg256-client.virtnet /mnt/lustre2 (opts:) Stopping client oleg256-client.virtnet /mnt/lustre2 opts: === replay-dual: finish cleanup 18:34:27 (1748471667) ===