-----============= acceptance-small: replay-dual ============----- Tue Apr 8 15:28:34 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 oleg337-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 15:28:40 (1744140520) === Starting client oleg337-client.virtnet: -o user_xattr,flock 192.168.203.137@tcp:/lustre /mnt/lustre2 Started clients oleg337-client.virtnet: 192.168.203.137@tcp:/lustre on /mnt/lustre2 type lustre (rw,checksum,flock,user_xattr,lruresize,lazystatfs,nouser_fid2path,verbose,noencrypt,statfs_project) oleg337-client.virtnet: executing check_config_client /mnt/lustre oleg337-client.virtnet: Checking config lustre mounted on /mnt/lustre Checking servers environments Checking clients oleg337-client.virtnet environments Using TIMEOUT=20 osc.lustre-OST0000-osc-ffff8800aa270000.idle_timeout=debug osc.lustre-OST0000-osc-ffff8800b6d06800.idle_timeout=debug osc.lustre-OST0001-osc-ffff8800aa270000.idle_timeout=debug osc.lustre-OST0001-osc-ffff8800b6d06800.idle_timeout=debug disable quota as required oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all osd-ldiskfs.track_declares_assert=1 === replay-dual: finish setup 15:28:49 (1744140529) === == replay-dual test 0a: expired recovery with lost client ========================================================== 15:28:49 (1744140529) Check file is LU482_FAILED=/tmp/replay-dual.lu482.OhtEEU UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1772 1285916 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 0.54 seconds: 92.28 ops/second fail_loc=0x80000514 Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 15:28:54 (1744140534) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 15:29:08 (1744140548) targets are mounted 15:29:08 (1744140548) facet_failover done Starting client: oleg337-client.virtnet: -o user_xattr,flock 192.168.203.137@tcp:/lustre /mnt/lustre2 - unlinked 0 (time 1744140630 ; total 0 ; last 0) total: 50 unlinks in 0 seconds: inf unlinks/second PASS 0a (102s) == replay-dual test 0b: lost client during waiting for next transno ========================================================== 15:30:31 (1744140631) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1772 1285916 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 oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 15:30:35 (1744140635) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 15:30:49 (1744140649) targets are mounted 15:30:49 (1744140649) facet_failover done Starting client: oleg337-client.virtnet: -o user_xattr,flock 192.168.203.137@tcp:/lustre /mnt/lustre Starting client: oleg337-client.virtnet: -o user_xattr,flock 192.168.203.137@tcp:/lustre /mnt/lustre2 PASS 0b (94s) == replay-dual test 1: |X| simple create ================= 15:32:05 (1744140725) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1772 1285916 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 oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 15:32:08 (1744140728) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 15:32:22 (1744140742) targets are mounted 15:32:22 (1744140742) facet_failover done oleg337-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 (24s) == replay-dual test 2: |X| mkdir adir ==================== 15:32:29 (1744140749) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1772 1285916 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 oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 15:32:32 (1744140752) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 15:32:46 (1744140766) targets are mounted 15:32:46 (1744140766) facet_failover done oleg337-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 (24s) == replay-dual test 3: |X| mkdir adir, mkdir adir/bdir === 15:32:53 (1744140773) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1772 1285916 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 oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 15:32:56 (1744140776) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 15:33:10 (1744140790) targets are mounted 15:33:10 (1744140790) facet_failover done oleg337-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 (24s) == replay-dual test 4: |X| mkdir adir (-EEXIST), mkdir adir/bdir ========================================================== 15:33:18 (1744140798) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1920 1285768 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 oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 15:33:21 (1744140801) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 15:33:35 (1744140815) targets are mounted 15:33:35 (1744140815) facet_failover done oleg337-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 ============ 15:33:42 (1744140822) multiop /mnt/lustre2/a vo_tSc TMPPIPE=/tmp/multiop_open_wait_pipe.7942 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1924 1285764 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 oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 15:33:45 (1744140825) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 15:33:59 (1744140839) targets are mounted 15:33:59 (1744140839) facet_failover done oleg337-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 (24s) == replay-dual test 6: open1, open2, unlink |X| close1 [fail mds1] close2 ========================================================== 15:34:06 (1744140846) multiop /mnt/lustre2/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.7942 multiop /mnt/lustre/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.7942 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 Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 15:34:09 (1744140849) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 15:34:23 (1744140863) targets are mounted 15:34:23 (1744140863) facet_failover done oleg337-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 (24s) == replay-dual test 8: replay of resent request ========== 15:34:30 (1744140870) 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 fail_loc=0x119 fail_loc=0 Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 15:34:50 (1744140890) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 15:35:04 (1744140904) targets are mounted 15:35:04 (1744140904) facet_failover done oleg337-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 (41s) == replay-dual test 9: resending a replayed create ======= 15:35:11 (1744140911) 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 fail_loc=0x80000119 Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 15:35:15 (1744140915) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 15:35:28 (1744140928) targets are mounted 15:35:28 (1744140928) facet_failover done oleg337-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 (37s) == replay-dual test 10: resending a replayed unlink ====== 15:35:48 (1744140948) 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 fail_loc=0x80000119 Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 15:35:51 (1744140951) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 15:36:05 (1744140965) targets are mounted 15:36:05 (1744140965) facet_failover done oleg337-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 ========================================================== 15:36:28 (1744140988) 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 fail_loc=0x0119 Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 15:36:31 (1744140991) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 15:36:45 (1744141005) targets are mounted 15:36:45 (1744141005) facet_failover done oleg337-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 19 sec fail_loc=0 PASS 11 (39s) == replay-dual test 12: open resend timeout ============== 15:37:07 (1744141027) 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 multiop /mnt/lustre/f12.replay-dual vmo_c TMPPIPE=/tmp/multiop_open_wait_pipe.7942 fail_loc=0x80000302 Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 15:37:10 (1744141030) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 15:37:24 (1744141044) targets are mounted 15:37:24 (1744141044) facet_failover done fail_loc=0 /mnt/lustre/f12.replay-dual /mnt/lustre/f12.replay-dual has type file OK PASS 12 (22s) == replay-dual test 13: close resend timeout ============= 15:37:29 (1744141049) multiop /mnt/lustre/f13.replay-dual vmo_c TMPPIPE=/tmp/multiop_open_wait_pipe.7942 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 fail_loc=0x80000115 Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 15:37:33 (1744141053) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 15:37:46 (1744141066) targets are mounted 15:37:46 (1744141066) facet_failover done fail_loc=0 /mnt/lustre/f13.replay-dual /mnt/lustre/f13.replay-dual has type file OK PASS 13 (22s) SKIP: replay-dual test_14b skipping ALWAYS excluded test 14b == replay-dual test 15a: timeout waiting for lost client during replay, 1 client completes ========================================================== 15:37:52 (1744141072) 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 total: 25 open/close in 0.18 seconds: 141.23 ops/second total: 1 open/close in 0.01 seconds: 149.63 ops/second Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 15:37:55 (1744141075) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 15:38:09 (1744141089) targets are mounted 15:38:09 (1744141089) facet_failover done oleg337-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 1744141161 ; total 0 ; last 0) total: 25 unlinks in 0 seconds: inf unlinks/second Starting client: oleg337-client.virtnet: -o user_xattr,flock 192.168.203.137@tcp:/lustre /mnt/lustre2 PASS 15a (90s) == replay-dual test 15c: remove multiple OST orphans ===== 15:39:22 (1744141162) 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 Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 15:39:52 (1744141192) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 15:40:06 (1744141206) targets are mounted 15:40:06 (1744141206) facet_failover done oleg337-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: oleg337-client.virtnet: -o user_xattr,flock 192.168.203.137@tcp:/lustre /mnt/lustre2 PASS 15c (117s) == replay-dual test 16: fail MDS during recovery (3571) == 15:41:19 (1744141279) 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 total: 25 open/close in 0.19 seconds: 132.78 ops/second total: 1 open/close in 0.01 seconds: 115.85 ops/second Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 15:41:23 (1744141283) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 15:41:37 (1744141297) targets are mounted 15:41:37 (1744141297) facet_failover done Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 15:41:58 (1744141318) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 15:42:11 (1744141331) targets are mounted 15:42:11 (1744141331) facet_failover done oleg337-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 1744141405 ; total 0 ; last 0) total: 25 unlinks in 0 seconds: inf unlinks/second Starting client: oleg337-client.virtnet: -o user_xattr,flock 192.168.203.137@tcp:/lustre /mnt/lustre2 PASS 16 (127s) == replay-dual test 17: fail OST during recovery (3571) == 15:43:26 (1744141406) total: 25 open/close in 0.19 seconds: 130.77 ops/second total: 1 open/close in 0.01 seconds: 94.97 ops/second 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 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 oleg337-server Stopping /mnt/lustre-ost1 (opts:) on oleg337-server 15:43:30 (1744141410) shut down facet: ost1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover ost1 to oleg337-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 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-OST0000 15:43:44 (1744141424) targets are mounted 15:43:44 (1744141424) facet_failover done Failing ost1 on oleg337-server Stopping /mnt/lustre-ost1 (opts:) on oleg337-server 15:44:06 (1744141446) shut down facet: ost1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover ost1 to oleg337-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 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-OST0000 15:44:21 (1744141461) targets are mounted 15:44:21 (1744141461) facet_failover done oleg337-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 1744141536 ; total 0 ; last 0) total: 25 unlinks in 0 seconds: inf unlinks/second Starting client: oleg337-client.virtnet: -o user_xattr,flock 192.168.203.137@tcp:/lustre /mnt/lustre2 PASS 17 (131s) == replay-dual test 18: ldlm_handle_enqueue succeeds on evicted export (3822) ========================================================== 15:45:37 (1744141537) debug=+dlmtrace fail_loc=0x8000030b using seed 3844135475 running for 500 iterations total: 500 stats in 0 seconds: inf stats/second ldlm.namespaces.MGC192.168.203.137@tcp.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffff8800a8f8c800.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffff8800aa0d1000.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0001-mdc-ffff8800a8f8c800.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0001-mdc-ffff8800aa0d1000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffff8800a8f8c800.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffff8800aa0d1000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffff8800a8f8c800.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffff8800aa0d1000.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.MGC192.168.203.137@tcp.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffff8800a8f8c800.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffff8800aa0d1000.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0001-mdc-ffff8800a8f8c800.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0001-mdc-ffff8800aa0d1000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffff8800a8f8c800.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffff8800aa0d1000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffff8800a8f8c800.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffff8800aa0d1000.early_lock_cancel=1 fail_loc=0 fail_loc=0 PASS 18 (45s) == replay-dual test 19: resend of open request =========== 15:46:22 (1744141582) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1992 1285696 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 1744141671.69 total 86.04 last 0.00) total: 1 open/close in 86.04 seconds: 0.01 ops/second fail_loc=0 Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 15:47:52 (1744141672) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 15:48:06 (1744141686) targets are mounted 15:48:06 (1744141686) facet_failover done oleg337-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 (112s) == replay-dual test 20: recovery time is not increasing == 15:48:14 (1744141694) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1992 1285696 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 oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 15:48:17 (1744141697) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 15:48:31 (1744141711) targets are mounted 15:48:31 (1744141711) facet_failover done oleg337-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: oleg337-client.virtnet: -o user_xattr,flock 192.168.203.137@tcp:/lustre /mnt/lustre2 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1992 1285696 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 oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 15:50:56 (1744141856) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 15:51:10 (1744141870) targets are mounted 15:51:10 (1744141870) facet_failover done oleg337-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: oleg337-client.virtnet: -o user_xattr,flock 192.168.203.137@tcp:/lustre /mnt/lustre2 PASS 20 (323s) == replay-dual test 21a: commit on sharing =============== 15:53:37 (1744142017) mdt.lustre-MDT0000.commit_on_sharing=1 mdt.lustre-MDT0001.commit_on_sharing=1 Replay barrier on lustre-MDT0000 Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 15:53:41 (1744142021) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 15:53:55 (1744142035) targets are mounted 15:53:55 (1744142035) facet_failover done Starting client: oleg337-client.virtnet: -o user_xattr,flock 192.168.203.137@tcp:/lustre /mnt/lustre2 mdt.lustre-MDT0000.commit_on_sharing=0 mdt.lustre-MDT0001.commit_on_sharing=0 PASS 21a (159s) 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 ========================================================== 15:56:16 (1744142176) fail_loc=0x119 Failing mds2 on oleg337-server Stopping /mnt/lustre-mds2 (opts:) on oleg337-server 15:56:19 (1744142179) shut down facet: mds2 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds2 to oleg337-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0001 15:56:32 (1744142192) targets are mounted 15:56:32 (1744142192) facet_failover done oleg337-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 2000 1285688 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1824 1285864 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: 86.46 ops/second total: 2 open/close in 0.01 seconds: 192.75 ops/second Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 15:56:42 (1744142202) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 15:56:56 (1744142216) targets are mounted 15:56:56 (1744142216) facet_failover done oleg337-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 (47s) == replay-dual test 22b: c1 lfs mkdir -i 1 d1, M1 drop reply & fail M0/M1, c2 mkdir d1/dir ========================================================== 15:57:03 (1744142223) fail_loc=0x119 Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server Failing mds2 on oleg337-server Stopping /mnt/lustre-mds2 (opts:) on oleg337-server 15:57:08 (1744142228) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server facet: mds2 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Failover mds2 to oleg337-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 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 15:57:34 (1744142254) targets are mounted 15:57:34 (1744142254) facet_failover done oleg337-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 2000 1285688 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1824 1285864 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: 83.96 ops/second total: 2 open/close in 0.01 seconds: 181.77 ops/second Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 15:57:43 (1744142263) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 15:57:58 (1744142278) targets are mounted 15:57:58 (1744142278) facet_failover done oleg337-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 (61s) == replay-dual test 22c: c1 lfs mkdir -i 1 d1, M1 drop update & fail M1, c2 mkdir d1/dir ========================================================== 15:58:05 (1744142285) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 15:58:08 (1744142288) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 15:58:20 (1744142300) targets are mounted 15:58:20 (1744142300) facet_failover done oleg337-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 2000 1285688 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1824 1285864 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: 89.81 ops/second total: 2 open/close in 0.01 seconds: 174.52 ops/second Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 15:58:30 (1744142310) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 15:58:44 (1744142324) targets are mounted 15:58:44 (1744142324) facet_failover done oleg337-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 (46s) == replay-dual test 22d: c1 lfs mkdir -i 1 d1, M1 drop update & fail M0/M1,c2 mkdir d1/dir ========================================================== 15:58:51 (1744142331) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server Failing mds2 on oleg337-server Stopping /mnt/lustre-mds2 (opts:) on oleg337-server 15:59:03 (1744142343) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server facet: mds2 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Failover mds2 to oleg337-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 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 15:59:23 (1744142363) targets are mounted 15:59:23 (1744142363) facet_failover done oleg337-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 1964 1285724 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1788 1285900 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: 78.03 ops/second total: 2 open/close in 0.01 seconds: 161.30 ops/second Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 15:59:38 (1744142378) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 15:59:52 (1744142392) targets are mounted 15:59:52 (1744142392) facet_failover done oleg337-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 (68s) == replay-dual test 23a: c1 rmdir d1, M1 drop reply and fail, client2 mkdir d1 ========================================================== 15:59:59 (1744142399) fail_loc=0x119 fail_loc=0 Failing mds2 on oleg337-server Stopping /mnt/lustre-mds2 (opts:) on oleg337-server 16:00:08 (1744142408) shut down facet: mds2 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds2 to oleg337-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0001 16:00:21 (1744142421) targets are mounted 16:00:21 (1744142421) facet_failover done oleg337-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 0.02 seconds: 110.98 ops/second Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 16:00:30 (1744142430) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 16:00:43 (1744142443) targets are mounted 16:00:43 (1744142443) facet_failover done oleg337-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 ========================================================== 16:00:51 (1744142451) fail_loc=0x119 fail_loc=0 Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server Failing mds2 on oleg337-server Stopping /mnt/lustre-mds2 (opts:) on oleg337-server 16:01:01 (1744142461) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server facet: mds2 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Failover mds2 to oleg337-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 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 16:01:21 (1744142481) targets are mounted 16:01:21 (1744142481) facet_failover done oleg337-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 0.01 seconds: 136.93 ops/second Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 16:01:30 (1744142490) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 16:01:44 (1744142504) targets are mounted 16:01:44 (1744142504) facet_failover done oleg337-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 (60s) == replay-dual test 23c: c1 rmdir d1, M0 drop update reply and fail M0, c2 mkdir d1 ========================================================== 16:01:51 (1744142511) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 16:01:54 (1744142514) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 16:02:07 (1744142527) targets are mounted 16:02:07 (1744142527) facet_failover done oleg337-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 0.01 seconds: 147.53 ops/second Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 16:02:16 (1744142536) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 16:02:29 (1744142549) targets are mounted 16:02:30 (1744142550) facet_failover done oleg337-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 ========================================================== 16:02:37 (1744142557) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server Failing mds2 on oleg337-server Stopping /mnt/lustre-mds2 (opts:) on oleg337-server 16:02:49 (1744142569) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server facet: mds2 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Failover mds2 to oleg337-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 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 16:03:10 (1744142590) targets are mounted 16:03:10 (1744142590) facet_failover done oleg337-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 1960 1285728 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1784 1285904 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 0.01 seconds: 136.97 ops/second Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 16:03:19 (1744142599) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 16:03:33 (1744142613) targets are mounted 16:03:33 (1744142613) facet_failover done oleg337-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 (63s) == replay-dual test 24: reconstruct on non-existing object ========================================================== 16:03:40 (1744142620) 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 ==================== 16:05:07 (1744142707) 1+0 records in 1+0 records out 512 bytes (512 B) copied, 0.00256232 s, 200 kB/s fail_loc=0x304 fail_loc=0x80000325 Failing ost1 on oleg337-server Stopping /mnt/lustre-ost1 (opts:) on oleg337-server 16:05:10 (1744142710) shut down facet: ost1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover ost1 to oleg337-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 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-OST0000 16:05:23 (1744142723) targets are mounted 16:05:23 (1744142723) facet_failover done oleg337-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 6811: 3449 Terminated LUSTRE="/home/green/git/lustre-release/lustre" bash -c "multiop /mnt/lustre2/f25.replay-dual Ow512" fail_loc=0 PASS 25 (21s) == replay-dual test 26: dbench and tar with mds failover ========================================================== 16:05:28 (1744142728) Starting client oleg337-client.virtnet: -o user_xattr,flock 192.168.203.137@tcp:/lustre /mnt/lustre Started clients oleg337-client.virtnet: 192.168.203.137@tcp:/lustre on /mnt/lustre type lustre (rw,checksum,flock,user_xattr,lruresize,lazystatfs,nouser_fid2path,verbose,noencrypt,statfs_project) Started tar loop with pid 4989 Started dbench loop with 4990 striped dir -i0 -c2 -H crush2 /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 Tue Apr 8 16:05:29 EDT 2025 waiting for dbench pid 5031 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 1 247 9.40 MB/sec warmup 1 sec latency 23.481 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2292 1285396 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2088 1285600 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 26112 3555904 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 27656 7161380 1% /mnt/lustre 1 503 8.73 MB/sec warmup 2 sec latency 21.444 ms 1 758 7.12 MB/sec warmup 3 sec latency 286.255 ms 1 1061 5.72 MB/sec warmup 4 sec latency 15.943 ms test_26 fail mds1 1 times 1 1457 5.21 MB/sec warmup 5 sec latency 15.751 ms Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 1 1655 4.37 MB/sec warmup 6 sec latency 374.416 ms 16:05:36 (1744142736) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server 1 1655 3.74 MB/sec warmup 7 sec latency 1374.610 ms 1 1655 3.28 MB/sec warmup 8 sec latency 2374.762 ms 1 1655 2.91 MB/sec warmup 9 sec latency 3374.923 ms 1 1655 2.62 MB/sec warmup 10 sec latency 4375.053 ms 1 1655 2.38 MB/sec warmup 11 sec latency 5375.171 ms 1 1655 2.18 MB/sec warmup 12 sec latency 6375.312 ms 1 1655 2.02 MB/sec warmup 13 sec latency 7375.487 ms 1 1655 1.87 MB/sec warmup 14 sec latency 8375.650 ms 1 1655 1.75 MB/sec warmup 15 sec latency 9375.795 ms 1 1655 1.64 MB/sec warmup 16 sec latency 10375.910 ms Failover mds1 to oleg337-server mount facets: mds1 1 1655 1.54 MB/sec warmup 17 sec latency 11376.013 ms 1 1655 1.46 MB/sec warmup 18 sec latency 12376.159 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 1655 1.38 MB/sec warmup 19 sec latency 13376.262 ms oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 16:05:49 (1744142749) targets are mounted 16:05:49 (1744142749) facet_failover done 1 1655 0.00 MB/sec execute 1 sec latency 15376.483 ms 1 1655 0.00 MB/sec execute 2 sec latency 16376.650 ms 1 1655 0.00 MB/sec execute 3 sec latency 17376.844 ms 1 1655 0.00 MB/sec execute 4 sec latency 18376.961 ms oleg337-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 1840 0.03 MB/sec execute 5 sec latency 18787.906 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 2174 0.09 MB/sec execute 6 sec latency 19.364 ms 1 2559 0.39 MB/sec execute 7 sec latency 15.909 ms 1 3209 1.01 MB/sec execute 8 sec latency 16.576 ms 1 3705 1.40 MB/sec execute 9 sec latency 16.741 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 3044 1284644 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2596 1285092 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 5840 3591028 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 30320 3570484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 36160 7161512 1% /mnt/lustre 1 3970 1.39 MB/sec execute 10 sec latency 20.979 ms 1 4260 1.28 MB/sec execute 11 sec latency 41.903 ms 1 4538 1.23 MB/sec execute 12 sec latency 20.596 ms test_26 fail mds2 2 times 1 4851 1.23 MB/sec execute 13 sec latency 17.137 ms Failing mds2 on oleg337-server Stopping /mnt/lustre-mds2 (opts:) on oleg337-server 1 5180 1.36 MB/sec execute 14 sec latency 27.112 ms 16:06:04 (1744142764) shut down facet: mds2 facet_host: oleg337-server facet_failover_host: oleg337-server 1 5449 1.29 MB/sec execute 15 sec latency 21.596 ms 1 5820 1.23 MB/sec execute 16 sec latency 12.485 ms 1 5820 1.16 MB/sec execute 17 sec latency 1007.263 ms 1 5820 1.09 MB/sec execute 18 sec latency 2007.354 ms 1 5820 1.04 MB/sec execute 19 sec latency 3007.469 ms 1 5820 0.98 MB/sec execute 20 sec latency 4007.584 ms 1 5820 0.94 MB/sec execute 21 sec latency 5007.693 ms 1 5820 0.90 MB/sec execute 22 sec latency 6007.845 ms 1 5820 0.86 MB/sec execute 23 sec latency 7007.957 ms 1 5820 0.82 MB/sec execute 24 sec latency 8008.061 ms Failover mds2 to oleg337-server mount facets: mds2 1 5820 0.79 MB/sec execute 25 sec latency 9008.221 ms 1 5820 0.76 MB/sec execute 26 sec latency 10008.346 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 5820 0.73 MB/sec execute 27 sec latency 11008.458 ms oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 1 5820 0.70 MB/sec execute 28 sec latency 12008.555 ms Started lustre-MDT0001 16:06:17 (1744142777) targets are mounted 16:06:17 (1744142777) facet_failover done 1 5820 0.68 MB/sec execute 29 sec latency 13008.701 ms 1 5820 0.66 MB/sec execute 30 sec latency 14008.835 ms 1 5820 0.64 MB/sec execute 31 sec latency 15008.946 ms 1 5820 0.62 MB/sec execute 32 sec latency 16009.081 ms oleg337-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 6061 0.66 MB/sec execute 33 sec latency 16177.392 ms 1 6722 0.80 MB/sec execute 34 sec latency 23.732 ms 1 7185 0.90 MB/sec execute 35 sec latency 16.133 ms 1 7434 0.91 MB/sec execute 36 sec latency 18.772 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 4672 1283016 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2568 1285120 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 13608 3580064 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 36464 3558448 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 50072 7138512 1% /mnt/lustre 1 7584 0.89 MB/sec execute 37 sec latency 40.364 ms 1 7820 0.87 MB/sec execute 38 sec latency 20.302 ms 1 8000 0.86 MB/sec execute 39 sec latency 253.705 ms 1 8308 0.88 MB/sec execute 40 sec latency 17.341 ms test_26 fail mds1 3 times 1 8595 0.93 MB/sec execute 41 sec latency 37.425 ms Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 1 8732 0.91 MB/sec execute 42 sec latency 53.858 ms 1 8732 0.89 MB/sec execute 43 sec latency 1054.046 ms 1 8732 0.87 MB/sec execute 44 sec latency 2054.309 ms 1 8732 0.85 MB/sec execute 45 sec latency 3054.525 ms 1 8732 0.83 MB/sec execute 46 sec latency 4054.753 ms 1 8732 0.81 MB/sec execute 47 sec latency 5054.975 ms 1 8732 0.80 MB/sec execute 48 sec latency 6055.168 ms 16:06:38 (1744142798) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server 1 8732 0.78 MB/sec execute 49 sec latency 7055.394 ms 1 8732 0.76 MB/sec execute 50 sec latency 8055.611 ms 1 8732 0.75 MB/sec execute 51 sec latency 9055.828 ms 1 8732 0.73 MB/sec execute 52 sec latency 10056.023 ms 1 8732 0.72 MB/sec execute 53 sec latency 11056.197 ms 1 8732 0.71 MB/sec execute 54 sec latency 12056.381 ms 1 8732 0.69 MB/sec execute 55 sec latency 13056.577 ms 1 8732 0.68 MB/sec execute 56 sec latency 14056.791 ms 1 8732 0.67 MB/sec execute 57 sec latency 15057.008 ms 1 8732 0.66 MB/sec execute 58 sec latency 16057.208 ms Failover mds1 to oleg337-server mount facets: mds1 1 8732 0.65 MB/sec execute 59 sec latency 17057.422 ms 1 8732 0.64 MB/sec execute 60 sec latency 18057.597 ms 1 8732 0.63 MB/sec execute 61 sec latency 19057.893 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 8732 0.62 MB/sec execute 62 sec latency 20058.131 ms oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all 1 8732 0.61 MB/sec execute 63 sec latency 21058.296 ms pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 16:06:53 (1744142813) targets are mounted 16:06:53 (1744142813) facet_failover done 1 8732 0.60 MB/sec execute 64 sec latency 22058.448 ms 1 8732 0.59 MB/sec execute 65 sec latency 23058.683 ms 1 8732 0.58 MB/sec execute 66 sec latency 24058.858 ms 1 8732 0.57 MB/sec execute 67 sec latency 25058.993 ms 1 8751 0.56 MB/sec execute 68 sec latency 25950.516 ms oleg337-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 8970 0.56 MB/sec execute 69 sec latency 20.203 ms 1 9254 0.55 MB/sec execute 70 sec latency 18.293 ms 1 9499 0.56 MB/sec execute 71 sec latency 19.992 ms 1 10000 0.62 MB/sec execute 72 sec latency 17.464 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 5172 1282516 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 3132 1284556 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 31960 3571836 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 46380 3556064 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 78340 7127900 2% /mnt/lustre 1 10377 0.65 MB/sec execute 73 sec latency 23.598 ms 1 10665 0.68 MB/sec execute 74 sec latency 22.506 ms 1 10737 0.68 MB/sec execute 75 sec latency 553.852 ms 1 10897 0.68 MB/sec execute 76 sec latency 560.409 ms 1 11048 0.68 MB/sec execute 77 sec latency 25.051 ms test_26 fail mds2 4 times Failing mds2 on oleg337-server 1 11169 0.67 MB/sec execute 78 sec latency 28.454 ms Stopping /mnt/lustre-mds2 (opts:) on oleg337-server 1 11381 0.66 MB/sec execute 79 sec latency 29.149 ms 1 11532 0.66 MB/sec execute 80 sec latency 29.151 ms 1 11653 0.65 MB/sec execute 81 sec latency 30.707 ms 1 11653 0.65 MB/sec execute 82 sec latency 1021.540 ms 1 11653 0.64 MB/sec execute 83 sec latency 2021.778 ms 1 11653 0.63 MB/sec execute 84 sec latency 3022.116 ms 16:07:14 (1744142834) shut down facet: mds2 facet_host: oleg337-server facet_failover_host: oleg337-server 1 11653 0.62 MB/sec execute 85 sec latency 4022.362 ms 1 11653 0.62 MB/sec execute 86 sec latency 5022.701 ms 1 11653 0.61 MB/sec execute 87 sec latency 6022.951 ms 1 11653 0.60 MB/sec execute 88 sec latency 7023.191 ms 1 11653 0.60 MB/sec execute 89 sec latency 8023.342 ms 1 11653 0.59 MB/sec execute 90 sec latency 9023.494 ms 1 11653 0.58 MB/sec execute 91 sec latency 10023.683 ms 1 11653 0.58 MB/sec execute 92 sec latency 11023.841 ms 1 11653 0.57 MB/sec execute 93 sec latency 12024.044 ms 1 11653 0.56 MB/sec execute 94 sec latency 13024.244 ms Failover mds2 to oleg337-server mount facets: mds2 1 11653 0.56 MB/sec execute 95 sec latency 14024.400 ms 1 11653 0.55 MB/sec execute 96 sec latency 15024.591 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 11653 0.55 MB/sec execute 97 sec latency 16024.782 ms oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all 1 11653 0.54 MB/sec execute 98 sec latency 17024.935 ms pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0001 16:07:28 (1744142848) targets are mounted 16:07:28 (1744142848) facet_failover done 1 11653 0.54 MB/sec execute 99 sec latency 18025.102 ms 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec 1 cleanup 103 sec oleg337-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 0 cleanup 104 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 1726 43.298 21988.288 Close 1267 22.803 25950.496 Rename 72 15.443 30.681 Unlink 361 5.104 20.069 Qpathinfo 1572 2.734 18.760 Qfileinfo 270 0.449 2.856 Qfsinfo 290 0.995 7.063 Sfileinfo 134 9.304 24.578 Find 608 2.102 14.460 WriteX 848 2.153 10.960 ReadX 2713 0.084 3.142 LockX 6 1.379 1.668 UnlockX 6 1.414 1.622 Flush 126 11.085 253.686 Throughput 0.535884 MB/sec 1 clients 1 procs max_latency=25950.516 ms stopping dbench on /mnt/lustre at Tue Apr 8 16:07:33 EDT 2025 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec striped dir -i0 -c2 -H all_char /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 Tue Apr 8 16:07:34 EDT 2025 waiting for dbench pid 9492 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 1 165 6.80 MB/sec warmup 1 sec latency 48.669 ms 1 357 6.39 MB/sec warmup 2 sec latency 31.825 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 5400 1282288 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 3364 1284324 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 45652 3558432 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 13332 3588484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 58984 7146916 1% /mnt/lustre 1 539 6.32 MB/sec warmup 3 sec latency 35.253 ms 1 779 5.34 MB/sec warmup 4 sec latency 28.270 ms 1 949 4.36 MB/sec warmup 5 sec latency 33.446 ms 1 1134 3.83 MB/sec warmup 6 sec latency 26.813 ms 1 1277 3.31 MB/sec warmup 7 sec latency 30.911 ms test_26 fail mds1 5 times Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 1 1622 3.27 MB/sec warmup 8 sec latency 33.250 ms 16:07:43 (1744142863) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server 1 1641 2.91 MB/sec warmup 9 sec latency 954.088 ms 1 1641 2.62 MB/sec warmup 10 sec latency 1954.247 ms 1 1641 2.38 MB/sec warmup 11 sec latency 2954.377 ms 1 1641 2.18 MB/sec warmup 12 sec latency 3954.544 ms 1 1641 2.01 MB/sec warmup 13 sec latency 4954.680 ms 1 1641 1.87 MB/sec warmup 14 sec latency 5954.815 ms 1 1641 1.75 MB/sec warmup 15 sec latency 6954.946 ms 1 1641 1.64 MB/sec warmup 16 sec latency 7955.082 ms 1 1641 1.54 MB/sec warmup 17 sec latency 8955.239 ms 1 1641 1.45 MB/sec warmup 18 sec latency 9955.376 ms Failover mds1 to oleg337-server mount facets: mds1 1 1641 1.38 MB/sec warmup 19 sec latency 10955.535 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 1641 0.00 MB/sec execute 1 sec latency 12955.699 ms oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all 1 1641 0.00 MB/sec execute 2 sec latency 13955.836 ms pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 16:07:57 (1744142877) targets are mounted 16:07:57 (1744142877) facet_failover done 1 1641 0.00 MB/sec execute 3 sec latency 14955.973 ms 1 1641 0.00 MB/sec execute 4 sec latency 15956.136 ms 1 1641 0.00 MB/sec execute 5 sec latency 16956.269 ms 1 1641 0.00 MB/sec execute 6 sec latency 17956.422 ms 1 1686 0.01 MB/sec execute 7 sec latency 18784.329 ms oleg337-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 2040 0.05 MB/sec execute 8 sec latency 16.959 ms 1 2297 0.18 MB/sec execute 9 sec latency 53.533 ms 1 2490 0.25 MB/sec execute 10 sec latency 52.725 ms 1 2997 0.67 MB/sec execute 11 sec latency 20.272 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 4588 1283100 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 3104 1284584 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 43424 3554952 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 12480 3581716 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 55904 7136668 1% /mnt/lustre 1 3584 1.02 MB/sec execute 12 sec latency 23.629 ms 1 3897 1.07 MB/sec execute 13 sec latency 15.592 ms 1 4148 0.99 MB/sec execute 14 sec latency 16.539 ms 1 4415 0.97 MB/sec execute 15 sec latency 22.144 ms test_26 fail mds2 6 times Failing mds2 on oleg337-server Stopping /mnt/lustre-mds2 (opts:) on oleg337-server 1 4701 1.00 MB/sec execute 16 sec latency 20.484 ms 16:08:11 (1744142891) shut down facet: mds2 facet_host: oleg337-server facet_failover_host: oleg337-server 1 4702 0.94 MB/sec execute 17 sec latency 996.787 ms 1 4702 0.88 MB/sec execute 18 sec latency 1996.876 ms 1 4702 0.84 MB/sec execute 19 sec latency 2996.981 ms 1 4702 0.80 MB/sec execute 20 sec latency 3997.111 ms 1 4702 0.76 MB/sec execute 21 sec latency 4997.217 ms 1 4702 0.72 MB/sec execute 22 sec latency 5997.319 ms 1 4702 0.69 MB/sec execute 23 sec latency 6997.508 ms 1 4702 0.66 MB/sec execute 24 sec latency 7997.665 ms 1 4702 0.64 MB/sec execute 25 sec latency 8997.890 ms 1 4702 0.61 MB/sec execute 26 sec latency 9998.095 ms Failover mds2 to oleg337-server mount facets: mds2 1 4702 0.59 MB/sec execute 27 sec latency 10998.232 ms 1 4702 0.57 MB/sec execute 28 sec latency 11998.352 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 4702 0.55 MB/sec execute 29 sec latency 12998.549 ms oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all 1 4702 0.53 MB/sec execute 30 sec latency 13998.733 ms pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0001 16:08:25 (1744142905) targets are mounted 16:08:25 (1744142905) facet_failover done 1 4702 0.51 MB/sec execute 31 sec latency 14998.851 ms 1 4702 0.50 MB/sec execute 32 sec latency 15999.010 ms 1 4702 0.48 MB/sec execute 33 sec latency 16999.200 ms 1 4702 0.47 MB/sec execute 34 sec latency 17999.315 ms oleg337-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1 4862 0.47 MB/sec execute 35 sec latency 18447.117 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 5174 0.53 MB/sec execute 36 sec latency 18.584 ms 1 5426 0.52 MB/sec execute 37 sec latency 26.192 ms 1 5763 0.52 MB/sec execute 38 sec latency 23.134 ms 1 5997 0.54 MB/sec execute 39 sec latency 47.235 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2688 1285000 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2364 1285324 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 38376 3567440 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 13488 3592852 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 51864 7160292 1% /mnt/lustre 1 6534 0.66 MB/sec execute 40 sec latency 20.934 ms 1 6832 0.69 MB/sec execute 41 sec latency 437.065 ms 1 7171 0.75 MB/sec execute 42 sec latency 20.802 ms striped dir -i0 -c2 -H all_char /mnt/lustre/d26.replay-dual/run_tar 1 7343 0.76 MB/sec execute 43 sec latency 63.268 ms test_26 fail mds1 7 times Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 1 7531 0.75 MB/sec execute 44 sec latency 32.528 ms 1 7531 0.73 MB/sec execute 45 sec latency 1014.502 ms 1 7531 0.72 MB/sec execute 46 sec latency 2014.650 ms 1 7531 0.70 MB/sec execute 47 sec latency 3014.780 ms 1 7531 0.69 MB/sec execute 48 sec latency 4014.894 ms 1 7531 0.67 MB/sec execute 49 sec latency 5014.988 ms 1 7531 0.66 MB/sec execute 50 sec latency 6015.116 ms 16:08:45 (1744142925) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server 1 7531 0.65 MB/sec execute 51 sec latency 7015.266 ms 1 7531 0.63 MB/sec execute 52 sec latency 8015.411 ms 1 7531 0.62 MB/sec execute 53 sec latency 9015.530 ms 1 7531 0.61 MB/sec execute 54 sec latency 10015.691 ms 1 7531 0.60 MB/sec execute 55 sec latency 11015.858 ms 1 7531 0.59 MB/sec execute 56 sec latency 12015.995 ms 1 7531 0.58 MB/sec execute 57 sec latency 13016.107 ms 1 7531 0.57 MB/sec execute 58 sec latency 14016.221 ms 1 7531 0.56 MB/sec execute 59 sec latency 15016.326 ms 1 7531 0.55 MB/sec execute 60 sec latency 16016.481 ms Failover mds1 to oleg337-server mount facets: mds1 1 7531 0.54 MB/sec execute 61 sec latency 17016.625 ms 1 7531 0.53 MB/sec execute 62 sec latency 18016.703 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 7531 0.52 MB/sec execute 63 sec latency 19016.862 ms oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all 1 7531 0.52 MB/sec execute 64 sec latency 20017.047 ms pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 16:08:59 (1744142939) targets are mounted 16:08:59 (1744142939) facet_failover done 1 7531 0.51 MB/sec execute 65 sec latency 21017.185 ms 1 7531 0.50 MB/sec execute 66 sec latency 22017.345 ms 1 7531 0.49 MB/sec execute 67 sec latency 23017.538 ms 1 7531 0.49 MB/sec execute 68 sec latency 24017.694 ms oleg337-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 7642 0.48 MB/sec execute 69 sec latency 24505.589 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 7899 0.48 MB/sec execute 70 sec latency 16.744 ms 1 8169 0.49 MB/sec execute 71 sec latency 17.454 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 8527 0.53 MB/sec execute 72 sec latency 15.693 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Tue Apr 8 16:09:07 EDT 2025 with return code 0 9492 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 9492 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished PASS 26 (223s) == replay-dual test 28: lock replay should be ordered: waiting after granted ========================================================== 16:09:11 (1744142951) Waiting for MDT destroys to complete 1+0 records in 1+0 records out 4096 bytes (4.1 kB) copied, 0.00414561 s, 988 kB/s fail_loc=0x80000324 fail_loc=0x32a Failing ost1 on oleg337-server Stopping /mnt/lustre-ost1 (opts:) on oleg337-server 16:09:27 (1744142967) shut down facet: ost1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover ost1 to oleg337-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 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 1+0 records in 1+0 records out 4096 bytes (4.1 kB) copied, 0.00303945 s, 1.3 MB/s Started lustre-OST0000 16:09:41 (1744142981) targets are mounted 16:09:41 (1744142981) facet_failover done oleg337-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 (36s) == replay-dual test 29: replay vs update with the same xid ========================================================== 16:09:48 (1744142988) SKIP: replay-dual test_29 needs >= 2 clients SKIP 29 (0s) == replay-dual test 30: layout lock replay is not blocked on IO ========================================================== 16:09:48 (1744142988) 10+0 records in 10+0 records out 40960 bytes (41 kB) copied, 0.0082624 s, 5.0 MB/s 10+0 records in 10+0 records out 40960 bytes (41 kB) copied, 0.00956815 s, 4.3 MB/s fail_loc=0x32e fail_val=4 Failing mds1 on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server 16:09:51 (1744142991) shut down facet: mds1 facet_host: oleg337-server facet_failover_host: oleg337-server Failover mds1 to oleg337-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 16:10:04 (1744143004) targets are mounted 16:10:04 (1744143004) facet_failover done 160+0 records in 160+0 records out 81920 bytes (82 kB) copied, 20.8237 s, 3.9 kB/s oleg337-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 (25s) == replay-dual test 31: deadlock on file_remove_privs and occupied mod rpc slots ========================================================== 16:10:13 (1744143013) Failing ost1 on oleg337-server Stopping /mnt/lustre-ost1 (opts:) on oleg337-server 16:10:15 (1744143015) shut down facet: ost1 facet_host: oleg337-server facet_failover_host: oleg337-server Creating to objid 3105 on ost lustre-OST0000... total: 32 open/close in 0.28 seconds: 113.99 ops/second at_max=0 fail_loc=0x80001420 file /mnt/lustre2/d31.replay-dual/mdtdir/f31.replay-dual is ready Failover ost1 to oleg337-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 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-OST0000 16:10:28 (1744143028) targets are mounted 16:10:28 (1744143028) facet_failover done oleg337-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: 17735 17736 17742 17743 17744 17745 17746 17747 17748 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2376 1285312 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1952 1285736 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 475 261669 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 262144 409 261735 1% /mnt/lustre[OST:1] filesystem_summary: 524003 599 523404 1% /mnt/lustre at_max=600 PASS 31 (20s) == replay-dual test 32: gap in update llog shouldn't break recovery ========================================================== 16:10:33 (1744143033) fail_loc=0x0000131d fail_val=10 fail_loc=0x726 Stopping /mnt/lustre-mds2 (opts:) on oleg337-server Stopping /mnt/lustre-mds1 (opts:) on oleg337-server fail_loc=0 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0000 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0001 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2480 1285180 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2032 1285656 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 (21s) == replay-dual test 33: Check for OBD_INCOMPAT_MULTI_RPCS in last_rcvd after abort_recovery ========================================================== 16:10:54 (1744143054) at_min=60 Stopping /mnt/lustre-mds2 (opts:) on oleg337-server last_rcvd in /dev/mapper/mds2_flakey: incompat = 0x61c Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0001 oleg337-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 oleg337-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 oleg337-server: oleg337-server.virtnet: executing _wait_recovery_complete *.lustre-MDT0001.recovery_status 1475 oleg337-server: *.lustre-MDT0001.recovery_status status: COMPLETE Stopping /mnt/lustre-mds2 (opts:) on oleg337-server last_rcvd in /dev/mapper/mds2_flakey: incompat = 0x61c Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg337-server: oleg337-server.virtnet: executing set_default_debug -1 all pdsh@oleg337-client: oleg337-server: ssh exited with exit code 1 Started lustre-MDT0001 Starting client: oleg337-client.virtnet: -o user_xattr,flock 192.168.203.137@tcp:/lustre /mnt/lustre2 oleg337-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 oleg337-server: oleg337-server.virtnet: executing _wait_recovery_complete *.lustre-MDT0001.recovery_status 1475 oleg337-server: *.lustre-MDT0001.recovery_status status: COMPLETE at_min=5 PASS 33 (37s) == replay-dual test complete, duration 2577 sec ========== 16:11:31 (1744143091) === replay-dual: start cleanup 16:11:31 (1744143091) === Stopping clients: oleg337-client.virtnet /mnt/lustre2 (opts:) Stopping client oleg337-client.virtnet /mnt/lustre2 opts: === replay-dual: finish cleanup 16:11:33 (1744143093) ===