-----============= acceptance-small: replay-dual ============----- Fri Aug 21 22:56:18 EDT 2026 MGS_OS_ID_LIKE=rhel centos fedora rocky MGS_OS_VERSION_ID=8.10 MGS_OS_ID=rocky MGS_OS_VERSION_CODE=134873088 MDS1_OS_VERSION_ID=8.10 MDS1_OS_VERSION_CODE=134873088 MDS1_OS_ID_LIKE=rhel centos fedora rocky MDS1_OS_ID=rocky OST1_OS_VERSION_CODE=134873088 OST1_OS_ID_LIKE=rhel centos fedora rocky OST1_OS_VERSION_ID=8.10 OST1_OS_ID=rocky CLIENT_OS_ID=rocky CLIENT_OS_VERSION_CODE=134873088 CLIENT_OS_VERSION_ID=8.10 CLIENT_OS_ID_LIKE=rhel centos fedora rocky oleg348-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 22:56:41 (1787367401) === Starting client oleg348-client.virtnet: -o user_xattr,flock 192.168.203.148@tcp:/lustre /mnt/lustre2 Mount client oleg348-client.virtnet: mount -t lustre -o user_xattr,flock 192.168.203.148@tcp:/lustre /mnt/lustre2 Started clients oleg348-client.virtnet: 192.168.203.148@tcp:/lustre on /mnt/lustre2 type lustre (rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose) oleg348-client.virtnet: executing check_config_client /mnt/lustre oleg348-client.virtnet: Checking config lustre mounted on /mnt/lustre Checking servers environments Checking clients oleg348-client.virtnet environments Using TIMEOUT=20 osc.lustre-OST0000-osc-ffff9045c8092800.idle_timeout=debug osc.lustre-OST0000-osc-ffff9045e5524000.idle_timeout=debug osc.lustre-OST0001-osc-ffff9045c8092800.idle_timeout=debug osc.lustre-OST0001-osc-ffff9045e5524000.idle_timeout=debug disable quota as required oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all osd-ldiskfs.track_declares_assert=1 === replay-dual: finish setup 22:57:29 (1787367449) === == replay-dual test 0a: expired recovery with lost client ========================================================== 22:57:31 (1787367451) Check file is LU482_FAILED=/tmp/replay-dual.lu482.rIKyxu UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1708 1269596 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1532 1269772 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre total: 50 open/close in 2.22 seconds: 22.51 ops/second fail_loc=0x80000514 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 22:57:50 (1787367470) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 22:58:27 (1787367507) targets are mounted 22:58:27 (1787367507) facet_failover done Starting client: oleg348-client.virtnet: -o user_xattr,flock 192.168.203.148@tcp:/lustre /mnt/lustre2 - unlinked 0 (time 1787367621 ; total 0 ; last 0) total: 50 unlinks in 2 seconds: 25.000000 unlinks/second PASS 0a (178s) == replay-dual test 0b: lost client during waiting for next transno ========================================================== 23:00:30 (1787367630) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1676 1269628 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1532 1269772 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:00:48 (1787367648) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 23:01:23 (1787367683) targets are mounted 23:01:23 (1787367683) facet_failover done Starting client: oleg348-client.virtnet: -o user_xattr,flock 192.168.203.148@tcp:/lustre /mnt/lustre Starting client: oleg348-client.virtnet: -o user_xattr,flock 192.168.203.148@tcp:/lustre /mnt/lustre2 PASS 0b (227s) == replay-dual test 1: |X| simple create ================= 23:04:16 (1787367856) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1676 1269628 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1532 1269772 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:04:31 (1787367871) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 23:05:04 (1787367904) targets are mounted 23:05:04 (1787367904) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 1 (68s) == replay-dual test 2: |X| mkdir adir ==================== 23:05:24 (1787367924) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1676 1269628 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1532 1269772 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:05:41 (1787367941) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 23:06:12 (1787367972) targets are mounted 23:06:12 (1787367972) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 2 (65s) == replay-dual test 3: |X| mkdir adir, mkdir adir/bdir === 23:06:29 (1787367989) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1676 1269628 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1532 1269772 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:06:43 (1787368003) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 23:07:21 (1787368041) targets are mounted 23:07:21 (1787368041) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 3 (69s) == replay-dual test 4: |X| mkdir adir (-EEXIST), mkdir adir/bdir ========================================================== 23:07:39 (1787368059) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1852 1269452 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre mkdir: cannot create directory '/mnt/lustre/adir': File exists Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:07:53 (1787368073) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 23:08:28 (1787368108) targets are mounted 23:08:28 (1787368108) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 4 (65s) == replay-dual test 5: open, unlink |X| close ============ 23:08:44 (1787368124) multiop /mnt/lustre2/a vo_tSc TMPPIPE=/tmp/multiop_open_wait_pipe.8204 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1788 1269516 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:08:58 (1787368138) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 23:09:31 (1787368171) targets are mounted 23:09:31 (1787368171) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 5 (63s) == replay-dual test 6: open1, open2, unlink |X| close1 [fail mds1] close2 ========================================================== 23:09:47 (1787368187) multiop /mnt/lustre2/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8204 multiop /mnt/lustre/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8204 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1788 1269516 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:10:02 (1787368202) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 23:10:35 (1787368235) targets are mounted 23:10:35 (1787368235) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 6 (61s) == replay-dual test 8: replay of resent request ========== 23:10:49 (1787368249) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1788 1269516 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre fail_loc=0x119 fail_loc=0 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:11:18 (1787368278) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 23:11:55 (1787368315) targets are mounted 23:11:55 (1787368315) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 8 (82s) == replay-dual test 9: resending a replayed create ======= 23:12:12 (1787368332) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1788 1269516 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre fail_loc=0x80000119 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:12:26 (1787368346) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 23:12:59 (1787368379) targets are mounted 23:12:59 (1787368379) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec fail_loc=0 PASS 9 (73s) == replay-dual test 10: resending a replayed unlink ====== 23:13:25 (1787368405) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1788 1269516 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre fail_loc=0x80000119 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:13:40 (1787368420) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 23:14:13 (1787368453) targets are mounted 23:14:13 (1787368453) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec fail_loc=0 PASS 10 (73s) == replay-dual test 11: both clients timeout during replay ========================================================== 23:14:38 (1787368478) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1788 1269516 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre fail_loc=0x0119 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:14:55 (1787368495) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 23:15:29 (1787368529) targets are mounted 23:15:29 (1787368529) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount FULL mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 6 sec fail_loc=0 PASS 11 (71s) == replay-dual test 12: open resend timeout ============== 23:15:49 (1787368549) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1788 1269516 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre multiop /mnt/lustre/f12.replay-dual vmo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8204 fail_loc=0x80000302 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:16:01 (1787368561) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 23:16:37 (1787368597) targets are mounted 23:16:37 (1787368597) facet_failover done fail_loc=0 /mnt/lustre/f12.replay-dual /mnt/lustre/f12.replay-dual has type file OK PASS 12 (69s) == replay-dual test 13: close resend timeout ============= 23:16:58 (1787368618) multiop /mnt/lustre/f13.replay-dual vmo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8204 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1788 1269516 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre fail_loc=0x80000115 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:17:12 (1787368632) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 23:17:48 (1787368668) targets are mounted 23:17:48 (1787368668) facet_failover done fail_loc=0 /mnt/lustre/f13.replay-dual /mnt/lustre/f13.replay-dual has type file OK PASS 13 (68s) SKIP: replay-dual test_14b skipping ALWAYS excluded test 14b == replay-dual test 15a: timeout waiting for lost client during replay, 1 client completes ========================================================== 23:18:08 (1787368688) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1788 1269516 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre total: 25 open/close in 1.11 seconds: 22.43 ops/second total: 1 open/close in 0.02 seconds: 41.93 ops/second Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:18:24 (1787368704) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 23:18:58 (1787368738) targets are mounted 23:18:59 (1787368739) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec - unlinked 0 (time 1787368814 ; total 0 ; last 0) total: 25 unlinks in 1 seconds: 25.000000 unlinks/second Starting client: oleg348-client.virtnet: -o user_xattr,flock 192.168.203.148@tcp:/lustre /mnt/lustre2 PASS 15a (134s) == replay-dual test 15c: remove multiple OST orphans ===== 23:20:22 (1787368822) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1788 1269516 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:22:32 (1787368952) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 23:23:05 (1787368985) targets are mounted 23:23:05 (1787368985) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec Starting client: oleg348-client.virtnet: -o user_xattr,flock 192.168.203.148@tcp:/lustre /mnt/lustre2 PASS 15c (246s) == replay-dual test 16: fail MDS during recovery (3571) == 23:24:29 (1787369069) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1788 1269516 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre total: 25 open/close in 1.03 seconds: 24.23 ops/second total: 1 open/close in 0.04 seconds: 25.61 ops/second Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:24:46 (1787369086) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 23:25:20 (1787369120) targets are mounted 23:25:20 (1787369120) facet_failover done Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:25:45 (1787369145) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 23:26:09 (1787369169) targets are mounted 23:26:09 (1787369169) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec - unlinked 0 (time 1787369244 ; total 0 ; last 0) total: 25 unlinks in 1 seconds: 25.000000 unlinks/second Starting client: oleg348-client.virtnet: -o user_xattr,flock 192.168.203.148@tcp:/lustre /mnt/lustre2 PASS 16 (182s) == replay-dual test 17: fail OST during recovery (3571) == 23:27:31 (1787369251) total: 25 open/close in 0.81 seconds: 30.83 ops/second total: 1 open/close in 0.04 seconds: 22.81 ops/second UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1788 1269516 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing ost1 on oleg348-server Stopping /mnt/lustre-ost1 (opts:) on oleg348-server 23:27:44 (1787369264) shut down facet: ost1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover ost1 to oleg348-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 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-OST0000 23:28:13 (1787369293) targets are mounted 23:28:13 (1787369293) facet_failover done Failing ost1 on oleg348-server Stopping /mnt/lustre-ost1 (opts:) on oleg348-server 23:28:38 (1787369318) shut down facet: ost1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover ost1 to oleg348-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 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-OST0000 23:29:03 (1787369343) targets are mounted 23:29:03 (1787369343) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid 1475 0 osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in FULL state after 0 sec - unlinked 0 (time 1787369415 ; total 0 ; last 0) total: 25 unlinks in 1 seconds: 25.000000 unlinks/second Starting client: oleg348-client.virtnet: -o user_xattr,flock 192.168.203.148@tcp:/lustre /mnt/lustre2 PASS 17 (170s) == replay-dual test 18: ldlm_handle_enqueue succeeds on evicted export (3822) ========================================================== 23:30:21 (1787369421) debug=+dlmtrace fail_loc=0x8000030b using seed 2540566691 running for 500 iterations total: 500 stats in 1 seconds: 500.000000 stats/second ldlm.namespaces.MGC192.168.203.148@tcp.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffff9045c49f2800.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffff9045d1455000.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0001-mdc-ffff9045c49f2800.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0001-mdc-ffff9045d1455000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffff9045c49f2800.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffff9045d1455000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffff9045c49f2800.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffff9045d1455000.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.MGC192.168.203.148@tcp.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffff9045c49f2800.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffff9045d1455000.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0001-mdc-ffff9045c49f2800.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0001-mdc-ffff9045d1455000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffff9045c49f2800.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffff9045d1455000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffff9045c49f2800.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffff9045d1455000.early_lock_cancel=1 fail_loc=0 fail_loc=0 PASS 18 (59s) == replay-dual test 19: resend of open request =========== 23:31:21 (1787369481) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1792 1269512 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre fail_loc=0x157 - open/close 0 (time 1787369579.57 total 88.34 last 0.00) total: 1 open/close in 88.34 seconds: 0.01 ops/second fail_loc=0 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:33:05 (1787369585) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 23:33:35 (1787369615) targets are mounted 23:33:35 (1787369615) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 19 (149s) == replay-dual test 20: recovery time is not increasing == 23:33:50 (1787369630) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1792 1269512 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:34:03 (1787369643) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 23:34:39 (1787369679) targets are mounted 23:34:39 (1787369679) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec Starting client: oleg348-client.virtnet: -o user_xattr,flock 192.168.203.148@tcp:/lustre /mnt/lustre2 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1792 1269512 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:37:18 (1787369838) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 23:37:48 (1787369868) targets are mounted 23:37:48 (1787369868) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec Starting client: oleg348-client.virtnet: -o user_xattr,flock 192.168.203.148@tcp:/lustre /mnt/lustre2 PASS 20 (396s) == replay-dual test 21a: commit on sharing =============== 23:40:26 (1787370026) mdt.lustre-MDT0000.commit_on_sharing=1 mdt.lustre-MDT0001.commit_on_sharing=1 Replay barrier on lustre-MDT0000 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:40:41 (1787370041) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 23:41:17 (1787370077) targets are mounted 23:41:17 (1787370077) facet_failover done Starting client: oleg348-client.virtnet: -o user_xattr,flock 192.168.203.148@tcp:/lustre /mnt/lustre2 mdt.lustre-MDT0000.commit_on_sharing=0 mdt.lustre-MDT0001.commit_on_sharing=0 PASS 21a (196s) 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 ========================================================== 23:43:44 (1787370224) fail_loc=0x119 Failing mds2 on oleg348-server Stopping /mnt/lustre-mds2 (opts:) on oleg348-server 23:43:52 (1787370232) shut down facet: mds2 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds2 to oleg348-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0001 23:44:16 (1787370256) targets are mounted 23:44:16 (1787370256) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1800 1269504 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1672 1269632 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.14 seconds: 14.42 ops/second total: 2 open/close in 0.06 seconds: 31.87 ops/second Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:44:38 (1787370278) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 23:45:14 (1787370314) targets are mounted 23:45:15 (1787370315) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 22a (108s) == replay-dual test 22b: c1 lfs mkdir -i 1 d1, M1 drop reply & fail M0/M1, c2 mkdir d1/dir ========================================================== 23:45:33 (1787370333) fail_loc=0x119 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server Failing mds2 on oleg348-server Stopping /mnt/lustre-mds2 (opts:) on oleg348-server 23:45:45 (1787370345) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server facet: mds2 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Failover mds2 to oleg348-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 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 Started lustre-MDT0001 23:46:15 (1787370375) targets are mounted 23:46:15 (1787370375) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1800 1269504 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1672 1269632 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.14 seconds: 14.00 ops/second total: 2 open/close in 0.05 seconds: 38.42 ops/second Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:46:43 (1787370403) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 23:47:16 (1787370436) targets are mounted 23:47:17 (1787370437) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 22b (124s) == replay-dual test 22c: c1 lfs mkdir -i 1 d1, M1 drop update & fail M1, c2 mkdir d1/dir ========================================================== 23:47:36 (1787370456) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:47:45 (1787370465) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 23:48:21 (1787370501) targets are mounted 23:48:21 (1787370501) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1800 1269504 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1684 1269620 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.12 seconds: 17.03 ops/second total: 2 open/close in 0.06 seconds: 32.03 ops/second Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:48:45 (1787370525) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 23:49:20 (1787370560) targets are mounted 23:49:20 (1787370560) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 22c (124s) == replay-dual test 22d: c1 lfs mkdir -i 1 d1, M1 drop update & fail M0/M1,c2 mkdir d1/dir ========================================================== 23:49:40 (1787370580) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server Failing mds2 on oleg348-server Stopping /mnt/lustre-mds2 (opts:) on oleg348-server 23:50:03 (1787370603) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server facet: mds2 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Failover mds2 to oleg348-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 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 23:50:48 (1787370648) targets are mounted 23:50:48 (1787370648) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1764 1269540 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1636 1269668 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.12 seconds: 17.27 ops/second total: 2 open/close in 0.04 seconds: 46.16 ops/second Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:51:20 (1787370680) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 23:51:53 (1787370713) targets are mounted 23:51:53 (1787370713) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 22d (150s) == replay-dual test 23a: c1 rmdir d1, M1 drop reply and fail, client2 mkdir d1 ========================================================== 23:52:11 (1787370731) fail_loc=0x119 fail_loc=0 Failing mds2 on oleg348-server Stopping /mnt/lustre-mds2 (opts:) on oleg348-server 23:52:20 (1787370740) shut down facet: mds2 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds2 to oleg348-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0001 23:52:45 (1787370765) targets are mounted 23:52:45 (1787370765) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1796 1269508 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.07 seconds: 27.07 ops/second Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:53:10 (1787370790) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 23:53:42 (1787370822) targets are mounted 23:53:42 (1787370822) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 23a (107s) == replay-dual test 23b: c1 rmdir d1, M1 drop reply and fail M0/M1, c2 mkdir d1 ========================================================== 23:53:58 (1787370838) fail_loc=0x119 fail_loc=0 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server Failing mds2 on oleg348-server Stopping /mnt/lustre-mds2 (opts:) on oleg348-server 23:54:11 (1787370851) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server facet: mds2 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Failover mds2 to oleg348-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 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 Started lustre-MDT0001 23:54:42 (1787370882) targets are mounted 23:54:42 (1787370882) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1796 1269508 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.06 seconds: 31.81 ops/second Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:55:11 (1787370911) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 23:55:46 (1787370946) targets are mounted 23:55:46 (1787370946) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 23b (125s) == replay-dual test 23c: c1 rmdir d1, M0 drop update reply and fail M0, c2 mkdir d1 ========================================================== 23:56:04 (1787370964) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:56:13 (1787370973) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 23:56:48 (1787371008) targets are mounted 23:56:48 (1787371008) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1796 1269508 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1680 1269624 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.11 seconds: 18.89 ops/second Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:57:12 (1787371032) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 23:57:44 (1787371064) targets are mounted 23:57:44 (1787371064) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 23c (116s) == replay-dual test 23d: c1 rmdir d1, M0 drop update reply and fail M0/M1, c2 mkdir d1 ========================================================== 23:58:00 (1787371080) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server Failing mds2 on oleg348-server Stopping /mnt/lustre-mds2 (opts:) on oleg348-server 23:58:22 (1787371102) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server facet: mds2 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Failover mds2 to oleg348-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 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 23:59:06 (1787371146) targets are mounted 23:59:06 (1787371146) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1760 1269544 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.09 seconds: 22.06 ops/second Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 23:59:42 (1787371182) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 00:00:18 (1787371218) targets are mounted 00:00:18 (1787371218) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 23d (158s) == replay-dual test 24: reconstruct on non-existing object ========================================================== 00:00:38 (1787371238) fail_loc=0x119 fail_loc=0 truncate: cannot truncate '/mnt/lustre/f24.replay-dual' to length 100: No such file or directory PASS 24 (93s) == replay-dual test 25: replay|resend ==================== 00:02:12 (1787371332) 1+0 records in 1+0 records out 512 bytes copied, 0.0160646 s, 31.9 kB/s fail_loc=0x304 fail_loc=0x80000325 Failing ost1 on oleg348-server Stopping /mnt/lustre-ost1 (opts:) on oleg348-server 00:02:20 (1787371340) shut down facet: ost1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover ost1 to oleg348-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 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-OST0000 00:02:47 (1787371367) targets are mounted 00:02:47 (1787371367) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid 1475 0 osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in FULL state after 0 sec /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 6982: 64236 Terminated LUSTRE="/home/green/git/lustre-release/lustre" bash -c "multiop /mnt/lustre2/f25.replay-dual Ow512" fail_loc=0 PASS 25 (51s) == replay-dual test 26: dbench and tar with mds failover ========================================================== 00:03:04 (1787371384) Starting client oleg348-client.virtnet: -o user_xattr,flock 192.168.203.148@tcp:/lustre /mnt/lustre Started clients oleg348-client.virtnet: 192.168.203.148@tcp:/lustre on /mnt/lustre type lustre (rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose) Started tar loop with pid 65666 Started dbench loop with 65667 striped dir -i0 -c2 -H crush /mnt/lustre/d26.replay-dual/run_tar striped dir -i0 -c2 -H crush2 /mnt/lustre2/d26.replay-dual/run_dbench looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1944 1269360 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1756 1269548 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 13852 3588964 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 15396 7194440 1% /mnt/lustre '/usr/share/dbench/client.txt' -> 'client.txt' running 'dbench 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100' on /mnt/lustre at Sat Aug 22 00:03:10 EDT 2026 waiting for dbench pid 65743 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 0 10 0.00 MB/sec warmup 1 sec latency 115.414 ms 1 57 1.15 MB/sec warmup 2 sec latency 163.135 ms 1 111 1.75 MB/sec warmup 3 sec latency 141.861 ms 1 139 1.50 MB/sec warmup 4 sec latency 147.868 ms 1 173 1.41 MB/sec warmup 5 sec latency 210.011 ms 1 184 1.23 MB/sec warmup 6 sec latency 620.210 ms 1 215 1.19 MB/sec warmup 7 sec latency 686.089 ms 1 255 1.21 MB/sec warmup 8 sec latency 127.274 ms test_26 fail mds1 1 times 1 289 1.19 MB/sec warmup 9 sec latency 141.903 ms 1 322 1.17 MB/sec warmup 10 sec latency 143.511 ms Failing mds1 on oleg348-server 1 350 1.14 MB/sec warmup 11 sec latency 155.645 ms Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 1 386 1.14 MB/sec warmup 12 sec latency 173.541 ms 1 426 1.15 MB/sec warmup 13 sec latency 125.530 ms 1 436 1.10 MB/sec warmup 14 sec latency 795.854 ms 1 436 1.02 MB/sec warmup 15 sec latency 1796.069 ms 00:03:26 (1787371406) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server 1 436 0.96 MB/sec warmup 16 sec latency 2796.378 ms 1 436 0.90 MB/sec warmup 17 sec latency 3796.635 ms 1 436 0.85 MB/sec warmup 18 sec latency 4796.870 ms 1 436 0.81 MB/sec warmup 19 sec latency 5797.547 ms 1 436 0.00 MB/sec execute 1 sec latency 7798.755 ms 1 436 0.00 MB/sec execute 2 sec latency 8798.936 ms 1 436 0.00 MB/sec execute 3 sec latency 9801.286 ms 1 436 0.00 MB/sec execute 4 sec latency 10801.473 ms 1 436 0.00 MB/sec execute 5 sec latency 11802.208 ms Failover mds1 to oleg348-server 1 436 0.00 MB/sec execute 6 sec latency 12802.757 ms mount facets: mds1 1 436 0.00 MB/sec execute 7 sec latency 13802.924 ms 1 436 0.00 MB/sec execute 8 sec latency 14803.063 ms 1 436 0.00 MB/sec execute 9 sec latency 15803.351 ms 1 436 0.00 MB/sec execute 10 sec latency 16803.668 ms 1 436 0.00 MB/sec execute 11 sec latency 17805.731 ms 1 436 0.00 MB/sec execute 12 sec latency 18807.027 ms 1 436 0.00 MB/sec execute 13 sec latency 19807.208 ms 1 436 0.00 MB/sec execute 14 sec latency 20807.548 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 436 0.00 MB/sec execute 15 sec latency 21807.788 ms 1 436 0.00 MB/sec execute 16 sec latency 22808.121 ms 1 436 0.00 MB/sec execute 17 sec latency 23808.448 ms 1 436 0.00 MB/sec execute 18 sec latency 24812.351 ms 1 436 0.00 MB/sec execute 19 sec latency 25813.856 ms 1 436 0.00 MB/sec execute 20 sec latency 26814.141 ms 1 436 0.00 MB/sec execute 21 sec latency 27814.458 ms 1 436 0.00 MB/sec execute 22 sec latency 28815.372 ms 1 436 0.00 MB/sec execute 23 sec latency 29815.769 ms 1 436 0.00 MB/sec execute 24 sec latency 30816.201 ms 1 436 0.00 MB/sec execute 25 sec latency 31816.353 ms oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all 1 436 0.00 MB/sec execute 26 sec latency 32816.527 ms pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 1 436 0.00 MB/sec execute 27 sec latency 33820.408 ms Started lustre-MDT0000 00:03:58 (1787371438) targets are mounted 00:03:58 (1787371438) facet_failover done 1 436 0.00 MB/sec execute 28 sec latency 34821.087 ms 1 474 0.04 MB/sec execute 29 sec latency 34936.984 ms 1 511 0.08 MB/sec execute 30 sec latency 151.106 ms 1 552 0.12 MB/sec execute 31 sec latency 207.959 ms 1 612 0.17 MB/sec execute 32 sec latency 439.613 ms 1 664 0.17 MB/sec execute 33 sec latency 107.438 ms 1 695 0.17 MB/sec execute 34 sec latency 125.674 ms oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 730 0.17 MB/sec execute 35 sec latency 101.829 ms 1 762 0.17 MB/sec execute 36 sec latency 147.350 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 789 0.16 MB/sec execute 37 sec latency 97.814 ms 1 824 0.16 MB/sec execute 38 sec latency 116.256 ms 1 874 0.16 MB/sec execute 39 sec latency 132.208 ms 1 903 0.16 MB/sec execute 40 sec latency 139.283 ms 1 949 0.16 MB/sec execute 41 sec latency 124.518 ms 1 981 0.15 MB/sec execute 42 sec latency 110.374 ms 1 1037 0.17 MB/sec execute 43 sec latency 103.324 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2144 1269160 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1940 1269364 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 43104 3560744 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 10176 3593224 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 53280 7153968 1% /mnt/lustre 1 1072 0.17 MB/sec execute 44 sec latency 120.442 ms 1 1126 0.17 MB/sec execute 45 sec latency 113.124 ms 1 1156 0.17 MB/sec execute 46 sec latency 154.875 ms 1 1172 0.16 MB/sec execute 47 sec latency 673.895 ms 1 1192 0.16 MB/sec execute 48 sec latency 922.866 ms 1 1229 0.16 MB/sec execute 49 sec latency 110.903 ms 1 1267 0.15 MB/sec execute 50 sec latency 108.109 ms 1 1391 0.21 MB/sec execute 51 sec latency 118.943 ms 1 1422 0.20 MB/sec execute 52 sec latency 117.279 ms 1 1480 0.20 MB/sec execute 53 sec latency 95.712 ms test_26 fail mds2 2 times 1 1513 0.20 MB/sec execute 54 sec latency 144.141 ms 1 1560 0.19 MB/sec execute 55 sec latency 105.865 ms Failing mds2 on oleg348-server 1 1597 0.19 MB/sec execute 56 sec latency 96.889 ms Stopping /mnt/lustre-mds2 (opts:) on oleg348-server 1 1637 0.19 MB/sec execute 57 sec latency 102.670 ms 1 1672 0.19 MB/sec execute 58 sec latency 116.502 ms 1 1709 0.18 MB/sec execute 59 sec latency 160.670 ms 1 1771 0.18 MB/sec execute 60 sec latency 131.395 ms 00:04:31 (1787371471) shut down facet: mds2 facet_host: oleg348-server facet_failover_host: oleg348-server 1 1830 0.18 MB/sec execute 61 sec latency 104.245 ms 1 1896 0.18 MB/sec execute 62 sec latency 93.817 ms 1 1978 0.18 MB/sec execute 63 sec latency 70.477 ms 1 2014 0.17 MB/sec execute 64 sec latency 98.604 ms 1 2095 0.17 MB/sec execute 65 sec latency 112.833 ms 1 2160 0.17 MB/sec execute 66 sec latency 106.971 ms 1 2216 0.17 MB/sec execute 67 sec latency 73.615 ms 1 2259 0.17 MB/sec execute 68 sec latency 568.163 ms 1 2259 0.16 MB/sec execute 69 sec latency 1568.380 ms 1 2259 0.16 MB/sec execute 70 sec latency 2574.194 ms Failover mds2 to oleg348-server mount facets: mds2 1 2259 0.16 MB/sec execute 71 sec latency 3574.781 ms 1 2259 0.16 MB/sec execute 72 sec latency 4576.003 ms 1 2259 0.16 MB/sec execute 73 sec latency 5576.156 ms 1 2259 0.15 MB/sec execute 74 sec latency 6576.300 ms 1 2259 0.15 MB/sec execute 75 sec latency 7576.512 ms 1 2259 0.15 MB/sec execute 76 sec latency 8576.795 ms 1 2259 0.15 MB/sec execute 77 sec latency 9577.173 ms 1 2259 0.15 MB/sec execute 78 sec latency 10577.381 ms 1 2259 0.14 MB/sec execute 79 sec latency 11579.062 ms 1 2259 0.14 MB/sec execute 80 sec latency 12579.313 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 2259 0.14 MB/sec execute 81 sec latency 13581.559 ms 1 2259 0.14 MB/sec execute 82 sec latency 14581.829 ms 1 2259 0.14 MB/sec execute 83 sec latency 15593.417 ms 1 2259 0.14 MB/sec execute 84 sec latency 16593.826 ms 1 2259 0.13 MB/sec execute 85 sec latency 17594.147 ms 1 2259 0.13 MB/sec execute 86 sec latency 18597.265 ms oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all 1 2259 0.13 MB/sec execute 87 sec latency 19597.694 ms pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 1 2259 0.13 MB/sec execute 88 sec latency 20598.667 ms Started lustre-MDT0001 00:04:59 (1787371499) targets are mounted 00:04:59 (1787371499) facet_failover done 1 2301 0.14 MB/sec execute 89 sec latency 21158.009 ms 1 2358 0.14 MB/sec execute 90 sec latency 99.038 ms 1 2396 0.14 MB/sec execute 91 sec latency 86.641 ms 1 2428 0.14 MB/sec execute 92 sec latency 99.803 ms 1 2466 0.14 MB/sec execute 93 sec latency 162.625 ms 1 2554 0.14 MB/sec execute 94 sec latency 96.474 ms 1 2587 0.14 MB/sec execute 95 sec latency 118.975 ms oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 1 2717 0.17 MB/sec execute 96 sec latency 97.033 ms 1 2783 0.17 MB/sec execute 97 sec latency 95.702 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 2918 0.18 MB/sec execute 98 sec latency 82.450 ms 1 2982 0.18 MB/sec execute 99 sec latency 126.483 ms 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec 1 cleanup 103 sec 0 cleanup 104 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 412 105.111 21157.905 Close 345 113.540 34936.952 Rename 21 90.399 162.299 Unlink 47 26.775 85.887 Qpathinfo 396 16.379 125.368 Qfileinfo 108 2.213 23.839 Qfsinfo 56 3.572 24.660 Sfileinfo 50 64.426 147.334 Find 132 12.718 71.158 WriteX 345 13.362 103.499 ReadX 635 1.763 86.034 LockX 2 18.136 25.530 UnlockX 2 8.451 8.915 Flush 38 61.947 113.124 Throughput 0.182764 MB/sec 1 clients 1 procs max_latency=34936.984 ms stopping dbench on /mnt/lustre at Sat Aug 22 00:05:14 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2344 1268960 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2152 1269152 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 51504 3553872 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 11392 3595600 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 62896 7149472 1% /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished striped dir -i0 -c2 -H crush2 /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 Sat Aug 22 00:05:24 EDT 2026 waiting for dbench pid 67960 dbench version 4.00 - Copyright Andrew Tridgell 1999-2004 Running for 100 seconds with load 'client.txt' and minimum warmup 20 secs 0 of 1 processes prepared for launch 0 sec 1 of 1 processes prepared for launch 0 sec releasing clients test_26 fail mds1 3 times 1 21 0.46 MB/sec warmup 1 sec latency 19.460 ms 1 77 1.67 MB/sec warmup 2 sec latency 118.199 ms Failing mds1 on oleg348-server 1 121 1.83 MB/sec warmup 3 sec latency 186.635 ms 1 157 1.63 MB/sec warmup 4 sec latency 121.945 ms Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 1 184 1.48 MB/sec warmup 5 sec latency 401.134 ms 1 188 1.26 MB/sec warmup 6 sec latency 933.442 ms 00:05:31 (1787371531) shut down 1 188 1.08 MB/sec warmup 7 sec latency 1934.356 ms facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server 1 188 0.95 MB/sec warmup 8 sec latency 2936.909 ms 1 188 0.84 MB/sec warmup 9 sec latency 3937.136 ms 1 188 0.76 MB/sec warmup 10 sec latency 4937.274 ms 1 188 0.69 MB/sec warmup 11 sec latency 5937.514 ms 1 188 0.63 MB/sec warmup 12 sec latency 6941.631 ms 1 188 0.58 MB/sec warmup 13 sec latency 7941.825 ms 1 188 0.54 MB/sec warmup 14 sec latency 8943.184 ms 1 188 0.50 MB/sec warmup 15 sec latency 9945.247 ms 1 188 0.47 MB/sec warmup 16 sec latency 10945.574 ms 1 188 0.45 MB/sec warmup 17 sec latency 11945.839 ms Failover mds1 to oleg348-server mount facets: mds1 1 188 0.42 MB/sec warmup 18 sec latency 12946.043 ms 1 188 0.40 MB/sec warmup 19 sec latency 13946.232 ms 1 188 0.00 MB/sec execute 1 sec latency 15948.504 ms 1 188 0.00 MB/sec execute 2 sec latency 16948.966 ms 1 188 0.00 MB/sec execute 3 sec latency 17949.372 ms 1 188 0.00 MB/sec execute 4 sec latency 18949.558 ms 1 188 0.00 MB/sec execute 5 sec latency 19949.754 ms 1 188 0.00 MB/sec execute 6 sec latency 20950.078 ms 1 188 0.00 MB/sec execute 7 sec latency 21950.457 ms 1 188 0.00 MB/sec execute 8 sec latency 22951.255 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 188 0.00 MB/sec execute 9 sec latency 23951.436 ms 1 188 0.00 MB/sec execute 10 sec latency 24951.636 ms 1 188 0.00 MB/sec execute 11 sec latency 25952.578 ms 1 188 0.00 MB/sec execute 12 sec latency 26953.061 ms 1 188 0.00 MB/sec execute 13 sec latency 27953.861 ms 1 188 0.00 MB/sec execute 14 sec latency 28954.097 ms 1 188 0.00 MB/sec execute 15 sec latency 29955.821 ms 1 188 0.00 MB/sec execute 16 sec latency 30958.515 ms 1 188 0.00 MB/sec execute 17 sec latency 31959.081 ms 1 188 0.00 MB/sec execute 18 sec latency 32959.270 ms 1 188 0.00 MB/sec execute 19 sec latency 33959.708 ms 1 188 0.00 MB/sec execute 20 sec latency 34959.881 ms 1 188 0.00 MB/sec execute 21 sec latency 35960.088 ms oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all 1 188 0.00 MB/sec execute 22 sec latency 36962.910 ms pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 1 188 0.00 MB/sec execute 23 sec latency 37965.482 ms Started lustre-MDT0000 00:06:07 (1787371567) targets are mounted 00:06:07 (1787371567) facet_failover done 1 207 0.02 MB/sec execute 24 sec latency 38220.417 ms 1 255 0.08 MB/sec execute 25 sec latency 120.109 ms 1 297 0.13 MB/sec execute 26 sec latency 133.818 ms 1 323 0.15 MB/sec execute 27 sec latency 204.861 ms 1 357 0.19 MB/sec execute 28 sec latency 159.550 ms 1 389 0.22 MB/sec execute 29 sec latency 213.114 ms 1 428 0.25 MB/sec execute 30 sec latency 148.408 ms oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 462 0.28 MB/sec execute 31 sec latency 138.711 ms 1 502 0.31 MB/sec execute 32 sec latency 121.054 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 542 0.35 MB/sec execute 33 sec latency 152.525 ms 1 614 0.39 MB/sec execute 34 sec latency 112.027 ms 1 664 0.39 MB/sec execute 35 sec latency 174.799 ms 1 708 0.38 MB/sec execute 36 sec latency 97.829 ms 1 723 0.37 MB/sec execute 37 sec latency 451.999 ms 1 765 0.36 MB/sec execute 38 sec latency 100.293 ms 1 799 0.36 MB/sec execute 39 sec latency 103.738 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2864 1268440 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2644 1268660 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 26576 3576124 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 36896 3565956 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 63472 7142080 1% /mnt/lustre 1 829 0.35 MB/sec execute 40 sec latency 121.823 ms 1 873 0.34 MB/sec execute 41 sec latency 154.323 ms 1 902 0.34 MB/sec execute 42 sec latency 152.591 ms 1 923 0.33 MB/sec execute 43 sec latency 124.835 ms 1 969 0.32 MB/sec execute 44 sec latency 123.256 ms 1 990 0.32 MB/sec execute 45 sec latency 135.040 ms 1 1009 0.32 MB/sec execute 46 sec latency 687.522 ms 1 1050 0.33 MB/sec execute 47 sec latency 1039.069 ms 1 1091 0.32 MB/sec execute 48 sec latency 94.919 ms 1 1139 0.31 MB/sec execute 49 sec latency 100.448 ms test_26 fail mds2 4 times 1 1177 0.31 MB/sec execute 50 sec latency 117.683 ms 1 1219 0.30 MB/sec execute 51 sec latency 86.555 ms Failing mds2 on oleg348-server 1 1251 0.30 MB/sec execute 52 sec latency 123.712 ms Stopping /mnt/lustre-mds2 (opts:) on oleg348-server 1 1319 0.31 MB/sec execute 53 sec latency 86.343 ms 1 1319 0.31 MB/sec execute 54 sec latency 1074.399 ms 1 1418 0.33 MB/sec execute 55 sec latency 1308.654 ms 1 1433 0.33 MB/sec execute 56 sec latency 709.848 ms 1 1433 0.32 MB/sec execute 57 sec latency 1711.461 ms 1 1433 0.32 MB/sec execute 58 sec latency 2711.756 ms 1 1433 0.31 MB/sec execute 59 sec latency 3724.825 ms 1 1433 0.31 MB/sec execute 60 sec latency 4724.982 ms 1 1433 0.30 MB/sec execute 61 sec latency 5725.169 ms 1 1433 0.30 MB/sec execute 62 sec latency 6725.404 ms 00:06:46 (1787371606) shut down facet: mds2 facet_host: oleg348-server facet_failover_host: oleg348-server 1 1433 0.29 MB/sec execute 63 sec latency 7726.705 ms 1 1433 0.29 MB/sec execute 64 sec latency 8727.045 ms 1 1433 0.28 MB/sec execute 65 sec latency 9727.744 ms 1 1433 0.28 MB/sec execute 66 sec latency 10727.949 ms 1 1433 0.27 MB/sec execute 67 sec latency 11728.130 ms 1 1433 0.27 MB/sec execute 68 sec latency 12728.354 ms 1 1433 0.27 MB/sec execute 69 sec latency 13729.341 ms 1 1433 0.26 MB/sec execute 70 sec latency 14729.643 ms 1 1433 0.26 MB/sec execute 71 sec latency 15729.830 ms 1 1433 0.26 MB/sec execute 72 sec latency 16731.874 ms Failover mds2 to oleg348-server 1 1433 0.25 MB/sec execute 73 sec latency 17736.570 ms mount facets: mds2 1 1433 0.25 MB/sec execute 74 sec latency 18737.563 ms 1 1433 0.25 MB/sec execute 75 sec latency 19739.292 ms 1 1433 0.24 MB/sec execute 76 sec latency 20740.532 ms 1 1433 0.24 MB/sec execute 77 sec latency 21741.988 ms 1 1433 0.24 MB/sec execute 78 sec latency 22742.523 ms 1 1433 0.23 MB/sec execute 79 sec latency 23743.692 ms 1 1433 0.23 MB/sec execute 80 sec latency 24744.077 ms 1 1433 0.23 MB/sec execute 81 sec latency 25744.336 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 1433 0.22 MB/sec execute 82 sec latency 26744.576 ms 1 1433 0.22 MB/sec execute 83 sec latency 27745.221 ms 1 1433 0.22 MB/sec execute 84 sec latency 28745.498 ms 1 1433 0.22 MB/sec execute 85 sec latency 29745.728 ms 1 1433 0.21 MB/sec execute 86 sec latency 30746.054 ms 1 1433 0.21 MB/sec execute 87 sec latency 31746.378 ms oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all 1 1433 0.21 MB/sec execute 88 sec latency 32746.648 ms pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 1 1433 0.21 MB/sec execute 89 sec latency 33751.063 ms Started lustre-MDT0001 00:07:14 (1787371634) targets are mounted 00:07:14 (1787371634) facet_failover done 1 1436 0.20 MB/sec execute 90 sec latency 34684.967 ms 1 1492 0.20 MB/sec execute 91 sec latency 69.337 ms 1 1549 0.20 MB/sec execute 92 sec latency 89.508 ms 1 1609 0.20 MB/sec execute 93 sec latency 68.841 ms 1 1655 0.20 MB/sec execute 94 sec latency 109.333 ms 1 1689 0.20 MB/sec execute 95 sec latency 159.195 ms 1 1744 0.19 MB/sec execute 96 sec latency 131.563 ms oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 1 1801 0.19 MB/sec execute 97 sec latency 84.574 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 1845 0.19 MB/sec execute 98 sec latency 110.608 ms 1 1873 0.19 MB/sec execute 99 sec latency 394.292 ms 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec 1 cleanup 103 sec 0 cleanup 104 sec 0 cleanup 104 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 297 65.262 1039.048 Close 244 312.445 38220.384 Rename 11 106.178 159.172 Unlink 24 27.799 46.744 Qpathinfo 215 17.022 121.199 Qfileinfo 96 2.315 31.742 Qfsinfo 33 4.749 34.176 Sfileinfo 34 66.273 113.728 Find 75 12.746 74.340 WriteX 388 14.862 80.488 ReadX 297 1.881 89.670 Flush 30 55.641 152.575 Throughput 0.18944 MB/sec 1 clients 1 procs max_latency=38220.417 ms stopping dbench on /mnt/lustre at Sat Aug 22 00:07:28 EDT 2026 with return code 0 tar: Unexpected EOF in archive tar: Unexpected EOF in archive clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished striped dir -i0 -c2 -H fnv_1a_64 /mnt/lustre2/d26.replay-dual/run_dbench looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt '/usr/share/dbench/client.txt' -> 'client.txt' running 'dbench 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100' on /mnt/lustre at Sat Aug 22 00:07:36 EDT 2026 waiting for dbench pid 70029 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 16 0.13 MB/sec warmup 1 sec latency 14.270 ms 1 72 1.57 MB/sec warmup 2 sec latency 106.503 ms 1 126 1.88 MB/sec warmup 3 sec latency 99.663 ms 1 157 1.63 MB/sec warmup 4 sec latency 150.168 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Sat Aug 22 00:07:40 EDT 2026 with return code 0 70029 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 70029 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished PASS 26 (321s) == replay-dual test 28: lock replay should be ordered: waiting after granted ========================================================== 00:08:24 (1787371704) Waiting for MDT destroys to complete 1+0 records in 1+0 records out 4096 bytes (4.1 kB, 4.0 KiB) copied, 0.029995 s, 137 kB/s fail_loc=0x80000324 fail_loc=0x32a Failing ost1 on oleg348-server Stopping /mnt/lustre-ost1 (opts:) on oleg348-server 00:08:45 (1787371725) shut down facet: ost1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover ost1 to oleg348-server mount facets: ost1 Start ost1: mount -t lustre -o localrecov /dev/mapper/ost1_flakey /mnt/lustre-ost1 1+0 records in 1+0 records out 4096 bytes (4.1 kB, 4.0 KiB) copied, 0.0127221 s, 322 kB/s seq.cli-lustre-OST0000-super.width=65536 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-OST0000 00:09:12 (1787371752) targets are mounted 00:09:12 (1787371752) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid 1475 0 osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in FULL state after 0 sec PASS 28 (68s) == replay-dual test 29: replay vs update with the same xid ========================================================== 00:09:32 (1787371772) SKIP: replay-dual test_29 needs >= 2 clients SKIP 29 (3s) == replay-dual test 30: layout lock replay is not blocked on IO ========================================================== 00:09:35 (1787371775) 10+0 records in 10+0 records out 40960 bytes (41 kB, 40 KiB) copied, 0.0511981 s, 800 kB/s 10+0 records in 10+0 records out 40960 bytes (41 kB, 40 KiB) copied, 0.0330816 s, 1.2 MB/s fail_loc=0x32e fail_val=4 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 00:09:44 (1787371784) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 00:10:17 (1787371817) targets are mounted 00:10:17 (1787371817) facet_failover done 160+0 records in 160+0 records out 81920 bytes (82 kB, 80 KiB) copied, 40.4401 s, 2.0 kB/s oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 30 (59s) == replay-dual test 31: deadlock on file_remove_privs and occupied mod rpc slots ========================================================== 00:10:35 (1787371835) Failing ost1 on oleg348-server Stopping /mnt/lustre-ost1 (opts:) on oleg348-server Creating to objid 2433 on ost lustre-OST0000... total: 32 open/close in 1.59 seconds: 20.13 ops/second 00:10:44 (1787371844) shut down facet: ost1 facet_host: oleg348-server facet_failover_host: oleg348-server at_max=0 fail_loc=0x80001420 file /mnt/lustre2/d31.replay-dual/mdtdir/f31.replay-dual is ready Failover ost1 to oleg348-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 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-OST0000 00:11:10 (1787371870) targets are mounted 00:11:10 (1787371870) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid 1475 0 osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in FULL IDLE state after 0 sec pids: 74234 74235 74240 74241 74242 74243 74244 74245 74246 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2152 1269124 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1884 1269420 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1568 3605452 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3112 7210928 1% /mnt/lustre UUID Inodes IUsed IFree IUse% Mounted on lustre-MDT0000_UUID 1024000 340 1023660 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1024000 258 1023742 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 262144 455 261689 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 262144 389 261755 1% /mnt/lustre[OST:1] filesystem_summary: 524042 598 523444 1% /mnt/lustre at_max=600 PASS 31 (54s) == replay-dual test 32: gap in update llog shouldn't break recovery ========================================================== 00:11:30 (1787371890) fail_loc=0x0000131d fail_val=10 fail_loc=0x726 Stopping /mnt/lustre-mds2 (opts:) on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server fail_loc=0 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0001 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2256 1269048 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1940 1269364 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1568 3605452 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3112 7210928 1% /mnt/lustre PASS 32 (51s) == replay-dual test 33: Check for OBD_INCOMPAT_MULTI_RPCS in last_rcvd after abort_recovery ========================================================== 00:12:22 (1787371942) at_min=60 Stopping /mnt/lustre-mds2 (opts:) on oleg348-server last_rcvd in /dev/mapper/mds2_flakey: incompat = 0x61c Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0001 oleg348-client.virtnet: executing wait_import_state_mount REPLAY_WAIT mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0001-mdc-*.mds_server_uuid in REPLAY_WAIT state after 0 sec oleg348-client.virtnet: executing wait_import_state_mount FULL mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec affected facets: mds2 oleg348-server: oleg348-server.virtnet: executing _wait_recovery_complete *.lustre-MDT0001.recovery_status 1475 oleg348-server: *.lustre-MDT0001.recovery_status status: COMPLETE Stopping /mnt/lustre-mds2 (opts:) on oleg348-server last_rcvd in /dev/mapper/mds2_flakey: incompat = 0x61c Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0001 Starting client: oleg348-client.virtnet: -o user_xattr,flock 192.168.203.148@tcp:/lustre /mnt/lustre2 oleg348-client.virtnet: executing wait_import_state_mount FULL mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec affected facets: mds2 oleg348-server: oleg348-server.virtnet: executing _wait_recovery_complete *.lustre-MDT0001.recovery_status 1475 oleg348-server: *.lustre-MDT0001.recovery_status status: COMPLETE at_min=5 PASS 33 (104s) == replay-dual test complete, duration 4665 sec ========== 00:14:05 (1787372045) === replay-dual: start cleanup 00:14:07 (1787372047) === Stopping clients: oleg348-client.virtnet /mnt/lustre2 (opts:) Stopping client oleg348-client.virtnet /mnt/lustre2 opts: === replay-dual: finish cleanup 00:14:19 (1787372059) ===