-----============= acceptance-small: replay-dual ============----- Wed Aug 26 19:03:47 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 oleg320-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 19:04:08 (1787785448) === Starting client oleg320-client.virtnet: -o user_xattr,flock 192.168.203.120@tcp:/lustre /mnt/lustre2 Mount client oleg320-client.virtnet: mount -t lustre -o user_xattr,flock 192.168.203.120@tcp:/lustre /mnt/lustre2 Started clients oleg320-client.virtnet: 192.168.203.120@tcp:/lustre on /mnt/lustre2 type lustre (rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose) oleg320-client.virtnet: executing check_config_client /mnt/lustre oleg320-client.virtnet: Checking config lustre mounted on /mnt/lustre Checking servers environments Checking clients oleg320-client.virtnet environments Using TIMEOUT=20 osc.lustre-OST0000-osc-ffff98e991634800.idle_timeout=debug osc.lustre-OST0000-osc-ffff98e99201b800.idle_timeout=debug osc.lustre-OST0001-osc-ffff98e991634800.idle_timeout=debug osc.lustre-OST0001-osc-ffff98e99201b800.idle_timeout=debug disable quota as required oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all osd-ldiskfs.track_declares_assert=1 === replay-dual: finish setup 19:04:48 (1787785488) === == replay-dual test 0a: expired recovery with lost client ========================================================== 19:04:50 (1787785490) Check file is LU482_FAILED=/tmp/replay-dual.lu482.vhfnk4 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 2.16 seconds: 23.20 ops/second fail_loc=0x80000514 Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 19:05:08 (1787785508) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 19:05:44 (1787785544) targets are mounted 19:05:44 (1787785544) facet_failover done Starting client: oleg320-client.virtnet: -o user_xattr,flock 192.168.203.120@tcp:/lustre /mnt/lustre2 - unlinked 0 (time 1787785657 ; total 0 ; last 0) total: 50 unlinks in 2 seconds: 25.000000 unlinks/second PASS 0a (175s) == replay-dual test 0b: lost client during waiting for next transno ========================================================== 19:07:46 (1787785666) 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 oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 19:08:00 (1787785680) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 19:08:35 (1787785715) targets are mounted 19:08:35 (1787785715) facet_failover done Starting client: oleg320-client.virtnet: -o user_xattr,flock 192.168.203.120@tcp:/lustre /mnt/lustre Starting client: oleg320-client.virtnet: -o user_xattr,flock 192.168.203.120@tcp:/lustre /mnt/lustre2 PASS 0b (225s) == replay-dual test 1: |X| simple create ================= 19:11:31 (1787785891) 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 mcreate: cannot create `/mnt/lustre/fsa-oleg320-client.virtnet' with mode 0100644: File exists Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 19:11:45 (1787785905) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 19:12:18 (1787785938) targets are mounted 19:12:18 (1787785938) facet_failover done oleg320-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 (64s) == replay-dual test 2: |X| mkdir adir ==================== 19:12:35 (1787785955) 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 oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 19:12:49 (1787785969) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 19:13:21 (1787786001) targets are mounted 19:13:21 (1787786001) facet_failover done oleg320-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 (63s) == replay-dual test 3: |X| mkdir adir, mkdir adir/bdir === 19:13:38 (1787786018) 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 oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 19:13:51 (1787786031) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 19:14:23 (1787786063) targets are mounted 19:14:23 (1787786063) facet_failover done oleg320-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 (62s) == replay-dual test 4: |X| mkdir adir (-EEXIST), mkdir adir/bdir ========================================================== 19:14:40 (1787786080) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1848 1269456 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre mkdir: cannot create directory '/mnt/lustre/adir': File exists Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 19:14:54 (1787786094) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 19:15:26 (1787786126) targets are mounted 19:15:26 (1787786126) facet_failover done oleg320-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 (61s) == replay-dual test 5: open, unlink |X| close ============ 19:15:41 (1787786141) multiop /mnt/lustre2/a vo_tSc TMPPIPE=/tmp/multiop_open_wait_pipe.8240 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 19:15:55 (1787786155) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 19:16:28 (1787786188) targets are mounted 19:16:28 (1787786188) facet_failover done oleg320-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 ========================================================== 19:16:45 (1787786205) multiop /mnt/lustre2/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8240 multiop /mnt/lustre/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8240 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 19:16:58 (1787786218) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 19:17:31 (1787786251) targets are mounted 19:17:31 (1787786251) facet_failover done oleg320-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 (63s) == replay-dual test 8: replay of resent request ========== 19:17:48 (1787786268) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre fail_loc=0x119 fail_loc=0 Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 19:18:19 (1787786299) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 19:18:55 (1787786335) targets are mounted 19:18:55 (1787786335) facet_failover done oleg320-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 ======= 19:19:10 (1787786350) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre fail_loc=0x80000119 Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 19:19:22 (1787786362) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 19:19:58 (1787786398) targets are mounted 19:19:58 (1787786398) facet_failover done oleg320-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 (71s) == replay-dual test 10: resending a replayed unlink ====== 19:20:22 (1787786422) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre fail_loc=0x80000119 Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 19:20:36 (1787786436) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 19:21:09 (1787786469) targets are mounted 19:21:09 (1787786469) facet_failover done oleg320-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 ========================================================== 19:21:35 (1787786495) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre fail_loc=0x0119 Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 19:21:48 (1787786508) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 19:22:13 (1787786533) targets are mounted 19:22:13 (1787786533) facet_failover done oleg320-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 (56s) == replay-dual test 12: open resend timeout ============== 19:22:31 (1787786551) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre multiop /mnt/lustre/f12.replay-dual vmo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8240 fail_loc=0x80000302 Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 19:22:44 (1787786564) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 19:23:16 (1787786596) targets are mounted 19:23:16 (1787786596) facet_failover done fail_loc=0 /mnt/lustre/f12.replay-dual /mnt/lustre/f12.replay-dual has type file OK PASS 12 (66s) == replay-dual test 13: close resend timeout ============= 19:23:38 (1787786618) multiop /mnt/lustre/f13.replay-dual vmo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8240 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre fail_loc=0x80000115 Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 19:23:55 (1787786635) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 19:24:30 (1787786670) targets are mounted 19:24:30 (1787786670) facet_failover done fail_loc=0 /mnt/lustre/f13.replay-dual /mnt/lustre/f13.replay-dual has type file OK PASS 13 (72s) SKIP: replay-dual test_14b skipping ALWAYS excluded test 14b == replay-dual test 15a: timeout waiting for lost client during replay, 1 client completes ========================================================== 19:24:50 (1787786690) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre total: 25 open/close in 0.95 seconds: 26.18 ops/second total: 1 open/close in 0.02 seconds: 41.33 ops/second Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 19:25:05 (1787786705) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 19:25:41 (1787786741) targets are mounted 19:25:41 (1787786741) facet_failover done oleg320-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 1787786817 ; total 0 ; last 0) total: 25 unlinks in 1 seconds: 25.000000 unlinks/second Starting client: oleg320-client.virtnet: -o user_xattr,flock 192.168.203.120@tcp:/lustre /mnt/lustre2 PASS 15a (133s) == replay-dual test 15c: remove multiple OST orphans ===== 19:27:03 (1787786823) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 19:29:11 (1787786951) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 19:29:45 (1787786985) targets are mounted 19:29:45 (1787786985) facet_failover done oleg320-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: oleg320-client.virtnet: -o user_xattr,flock 192.168.203.120@tcp:/lustre /mnt/lustre2 PASS 15c (243s) == replay-dual test 16: fail MDS during recovery (3571) == 19:31:06 (1787787066) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre total: 25 open/close in 0.84 seconds: 29.73 ops/second total: 1 open/close in 0.02 seconds: 44.38 ops/second Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 19:31:22 (1787787082) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 19:31:53 (1787787113) targets are mounted 19:31:53 (1787787113) facet_failover done Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 19:32:18 (1787787138) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 19:32:51 (1787787171) targets are mounted 19:32:51 (1787787171) facet_failover done oleg320-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 1787787249 ; total 0 ; last 0) total: 25 unlinks in 1 seconds: 25.000000 unlinks/second Starting client: oleg320-client.virtnet: -o user_xattr,flock 192.168.203.120@tcp:/lustre /mnt/lustre2 PASS 16 (189s) == replay-dual test 17: fail OST during recovery (3571) == 19:34:16 (1787787256) total: 25 open/close in 0.97 seconds: 25.88 ops/second total: 1 open/close in 0.04 seconds: 27.89 ops/second UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1916 1269388 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing ost1 on oleg320-server Stopping /mnt/lustre-ost1 (opts:) on oleg320-server 19:34:31 (1787787271) shut down facet: ost1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover ost1 to oleg320-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 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-OST0000 19:35:01 (1787787301) targets are mounted 19:35:01 (1787787301) facet_failover done Failing ost1 on oleg320-server Stopping /mnt/lustre-ost1 (opts:) on oleg320-server 19:35:26 (1787787326) shut down facet: ost1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover ost1 to oleg320-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 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-OST0000 19:35:49 (1787787349) targets are mounted 19:35:49 (1787787349) facet_failover done oleg320-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 1787787425 ; total 0 ; last 0) total: 25 unlinks in 0 seconds: inf unlinks/second Starting client: oleg320-client.virtnet: -o user_xattr,flock 192.168.203.120@tcp:/lustre /mnt/lustre2 PASS 17 (175s) == replay-dual test 18: ldlm_handle_enqueue succeeds on evicted export (3822) ========================================================== 19:37:11 (1787787431) debug=+dlmtrace using seed 333537824 running for 500 iterations total: 500 stats in 1 seconds: 500.000000 stats/second fail_loc=0x8000030b ldlm.namespaces.MGC192.168.203.120@tcp.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffff98e98952c000.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffff98e991634800.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0001-mdc-ffff98e98952c000.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0001-mdc-ffff98e991634800.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffff98e98952c000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffff98e991634800.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffff98e98952c000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffff98e991634800.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.MGC192.168.203.120@tcp.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffff98e98952c000.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffff98e991634800.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0001-mdc-ffff98e98952c000.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0001-mdc-ffff98e991634800.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffff98e98952c000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffff98e991634800.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffff98e98952c000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffff98e991634800.early_lock_cancel=1 fail_loc=0 fail_loc=0 PASS 18 (57s) == replay-dual test 19: resend of open request =========== 19:38:08 (1787787488) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1920 1269384 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre fail_loc=0x157 - open/close 0 (time 1787787583.86 total 86.06 last 0.00) total: 1 open/close in 86.06 seconds: 0.01 ops/second fail_loc=0 Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 19:39:49 (1787787589) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 19:40:26 (1787787626) targets are mounted 19:40:26 (1787787626) facet_failover done oleg320-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 (154s) == replay-dual test 20: recovery time is not increasing == 19:40:42 (1787787642) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1896 1269408 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 19:40:54 (1787787654) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 19:41:26 (1787787686) targets are mounted 19:41:26 (1787787686) facet_failover done oleg320-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: oleg320-client.virtnet: -o user_xattr,flock 192.168.203.120@tcp:/lustre /mnt/lustre2 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1896 1269408 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 19:44:05 (1787787845) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 19:44:37 (1787787877) targets are mounted 19:44:37 (1787787877) facet_failover done oleg320-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: oleg320-client.virtnet: -o user_xattr,flock 192.168.203.120@tcp:/lustre /mnt/lustre2 PASS 20 (386s) == replay-dual test 21a: commit on sharing =============== 19:47:08 (1787788028) mdt.lustre-MDT0000.commit_on_sharing=1 mdt.lustre-MDT0001.commit_on_sharing=1 Replay barrier on lustre-MDT0000 Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 19:47:24 (1787788044) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 19:47:58 (1787788078) targets are mounted 19:47:58 (1787788078) facet_failover done Starting client: oleg320-client.virtnet: -o user_xattr,flock 192.168.203.120@tcp:/lustre /mnt/lustre2 mdt.lustre-MDT0000.commit_on_sharing=0 mdt.lustre-MDT0001.commit_on_sharing=0 PASS 21a (192s) 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 ========================================================== 19:50:22 (1787788222) fail_loc=0x119 Failing mds2 on oleg320-server Stopping /mnt/lustre-mds2 (opts:) on oleg320-server 19:50:28 (1787788228) shut down facet: mds2 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds2 to oleg320-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0001 19:50:48 (1787788248) targets are mounted 19:50:48 (1787788248) facet_failover done oleg320-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1904 1269400 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1744 1269560 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.10 seconds: 21.03 ops/second total: 2 open/close in 0.04 seconds: 47.61 ops/second Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 19:51:09 (1787788269) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 19:51:42 (1787788302) targets are mounted 19:51:42 (1787788302) facet_failover done oleg320-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 (96s) == replay-dual test 22b: c1 lfs mkdir -i 1 d1, M1 drop reply & fail M0/M1, c2 mkdir d1/dir ========================================================== 19:51:59 (1787788319) fail_loc=0x119 Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server Failing mds2 on oleg320-server Stopping /mnt/lustre-mds2 (opts:) on oleg320-server 19:52:09 (1787788329) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server facet: mds2 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Failover mds2 to oleg320-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 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 19:52:37 (1787788357) targets are mounted 19:52:37 (1787788357) facet_failover done oleg320-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1904 1269400 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1744 1269560 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.13 seconds: 14.90 ops/second total: 2 open/close in 0.05 seconds: 40.39 ops/second Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 19:52:59 (1787788379) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 19:53:31 (1787788411) targets are mounted 19:53:31 (1787788411) facet_failover done oleg320-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 (112s) == replay-dual test 22c: c1 lfs mkdir -i 1 d1, M1 drop update & fail M1, c2 mkdir d1/dir ========================================================== 19:53:50 (1787788430) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 19:53:58 (1787788438) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 19:54:21 (1787788461) targets are mounted 19:54:21 (1787788461) facet_failover done oleg320-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1904 1269400 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1756 1269548 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.08 seconds: 23.58 ops/second total: 2 open/close in 0.04 seconds: 51.05 ops/second Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 19:54:42 (1787788482) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 19:55:10 (1787788510) targets are mounted 19:55:10 (1787788510) facet_failover done oleg320-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 (98s) == replay-dual test 22d: c1 lfs mkdir -i 1 d1, M1 drop update & fail M0/M1,c2 mkdir d1/dir ========================================================== 19:55:28 (1787788528) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server Failing mds2 on oleg320-server Stopping /mnt/lustre-mds2 (opts:) on oleg320-server 19:55:51 (1787788551) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server facet: mds2 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Failover mds2 to oleg320-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 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 19:56:17 (1787788577) targets are mounted 19:56:17 (1787788577) facet_failover done oleg320-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1868 1269436 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1708 1269596 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.13 seconds: 14.88 ops/second total: 2 open/close in 0.06 seconds: 35.49 ops/second Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 19:56:41 (1787788601) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 19:57:06 (1787788626) targets are mounted 19:57:06 (1787788626) facet_failover done oleg320-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 (113s) == replay-dual test 23a: c1 rmdir d1, M1 drop reply and fail, client2 mkdir d1 ========================================================== 19:57:22 (1787788642) fail_loc=0x119 fail_loc=0 Failing mds2 on oleg320-server Stopping /mnt/lustre-mds2 (opts:) on oleg320-server 19:57:31 (1787788651) shut down facet: mds2 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds2 to oleg320-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0001 19:57:53 (1787788673) targets are mounted 19:57:53 (1787788673) facet_failover done oleg320-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1900 1269404 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.08 seconds: 24.72 ops/second Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 19:58:16 (1787788696) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 19:58:50 (1787788730) targets are mounted 19:58:50 (1787788730) facet_failover done oleg320-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 (102s) == replay-dual test 23b: c1 rmdir d1, M1 drop reply and fail M0/M1, c2 mkdir d1 ========================================================== 19:59:05 (1787788745) fail_loc=0x119 fail_loc=0 Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server Failing mds2 on oleg320-server Stopping /mnt/lustre-mds2 (opts:) on oleg320-server 19:59:17 (1787788757) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server facet: mds2 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Failover mds2 to oleg320-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 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 19:59:47 (1787788787) targets are mounted 19:59:47 (1787788787) facet_failover done oleg320-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1900 1269404 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.08 seconds: 25.03 ops/second Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 20:00:11 (1787788811) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 20:00:35 (1787788835) targets are mounted 20:00:35 (1787788835) facet_failover done oleg320-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 (105s) == replay-dual test 23c: c1 rmdir d1, M0 drop update reply and fail M0, c2 mkdir d1 ========================================================== 20:00:50 (1787788850) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 20:00:57 (1787788857) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 20:01:28 (1787788888) targets are mounted 20:01:29 (1787788889) facet_failover done oleg320-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1900 1269404 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1752 1269552 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.07 seconds: 29.24 ops/second Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 20:01:48 (1787788908) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 20:02:20 (1787788940) targets are mounted 20:02:20 (1787788940) facet_failover done oleg320-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 (109s) == replay-dual test 23d: c1 rmdir d1, M0 drop update reply and fail M0/M1, c2 mkdir d1 ========================================================== 20:02:38 (1787788958) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server Failing mds2 on oleg320-server Stopping /mnt/lustre-mds2 (opts:) on oleg320-server 20:03:00 (1787788980) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server facet: mds2 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Failover mds2 to oleg320-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 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 20:03:23 (1787789003) targets are mounted 20:03:23 (1787789003) facet_failover done oleg320-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1864 1269440 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1704 1269600 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.08 seconds: 25.60 ops/second Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 20:03:47 (1787789027) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 20:04:20 (1787789060) targets are mounted 20:04:20 (1787789060) facet_failover done oleg320-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 (118s) == replay-dual test 24: reconstruct on non-existing object ========================================================== 20:04:36 (1787789076) 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 ==================== 20:06:09 (1787789169) 1+0 records in 1+0 records out 512 bytes copied, 0.0181314 s, 28.2 kB/s fail_loc=0x304 fail_loc=0x80000325 Failing ost1 on oleg320-server Stopping /mnt/lustre-ost1 (opts:) on oleg320-server 20:06:17 (1787789177) shut down facet: ost1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover ost1 to oleg320-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 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-OST0000 20:06:40 (1787789200) targets are mounted 20:06:40 (1787789200) facet_failover done oleg320-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: 64223 Terminated LUSTRE="/home/green/git/lustre-release/lustre" bash -c "multiop /mnt/lustre2/f25.replay-dual Ow512" fail_loc=0 PASS 25 (45s) == replay-dual test 26: dbench and tar with mds failover ========================================================== 20:06:54 (1787789214) Starting client oleg320-client.virtnet: -o user_xattr,flock 192.168.203.120@tcp:/lustre /mnt/lustre Started clients oleg320-client.virtnet: 192.168.203.120@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 65653 Started dbench loop with 65655 striped dir -i0 -c2 -H all_char /mnt/lustre/d26.replay-dual/run_tar 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 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1964 1269340 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1756 1269548 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1564 3580624 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3108 7186100 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 Wed Aug 26 20:06:59 EDT 2026 waiting for dbench pid 65718 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 31 1.05 MB/sec warmup 1 sec latency 109.264 ms 1 92 2.10 MB/sec warmup 2 sec latency 120.349 ms 1 136 2.01 MB/sec warmup 3 sec latency 192.472 ms 1 168 1.70 MB/sec warmup 4 sec latency 128.875 ms 1 199 1.57 MB/sec warmup 5 sec latency 353.764 ms 1 247 1.56 MB/sec warmup 6 sec latency 122.400 ms 1 301 1.57 MB/sec warmup 7 sec latency 100.128 ms 1 349 1.56 MB/sec warmup 8 sec latency 102.638 ms test_26 fail mds1 1 times 1 389 1.53 MB/sec warmup 9 sec latency 162.979 ms Failing mds1 on oleg320-server 1 440 1.53 MB/sec warmup 10 sec latency 97.390 ms Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 1 486 1.54 MB/sec warmup 11 sec latency 126.699 ms 1 522 1.50 MB/sec warmup 12 sec latency 165.829 ms 1 606 1.61 MB/sec warmup 13 sec latency 292.015 ms 20:07:13 (1787789233) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server 1 606 1.49 MB/sec warmup 14 sec latency 1293.028 ms 1 606 1.40 MB/sec warmup 15 sec latency 2293.282 ms 1 606 1.31 MB/sec warmup 16 sec latency 3293.499 ms 1 606 1.23 MB/sec warmup 17 sec latency 4293.706 ms 1 606 1.16 MB/sec warmup 18 sec latency 5295.463 ms 1 606 1.10 MB/sec warmup 19 sec latency 6296.823 ms 1 606 0.00 MB/sec execute 1 sec latency 8300.450 ms 1 606 0.00 MB/sec execute 2 sec latency 9300.598 ms 1 606 0.00 MB/sec execute 3 sec latency 10300.827 ms Failover mds1 to oleg320-server mount facets: mds1 1 606 0.00 MB/sec execute 4 sec latency 11307.160 ms 1 606 0.00 MB/sec execute 5 sec latency 12307.405 ms 1 606 0.00 MB/sec execute 6 sec latency 13307.672 ms 1 606 0.00 MB/sec execute 7 sec latency 14308.076 ms 1 606 0.00 MB/sec execute 8 sec latency 15308.348 ms 1 606 0.00 MB/sec execute 9 sec latency 16308.683 ms 1 606 0.00 MB/sec execute 10 sec latency 17310.593 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 606 0.00 MB/sec execute 11 sec latency 18310.861 ms 1 606 0.00 MB/sec execute 12 sec latency 19311.163 ms 1 606 0.00 MB/sec execute 13 sec latency 20311.763 ms 1 606 0.00 MB/sec execute 14 sec latency 21312.077 ms 1 606 0.00 MB/sec execute 15 sec latency 22312.918 ms 1 606 0.00 MB/sec execute 16 sec latency 23313.189 ms 1 606 0.00 MB/sec execute 17 sec latency 24314.363 ms 1 606 0.00 MB/sec execute 18 sec latency 25314.590 ms 1 606 0.00 MB/sec execute 19 sec latency 26315.425 ms 1 606 0.00 MB/sec execute 20 sec latency 27315.837 ms 1 606 0.00 MB/sec execute 21 sec latency 28316.661 ms 1 606 0.00 MB/sec execute 22 sec latency 29316.858 ms 1 606 0.00 MB/sec execute 23 sec latency 30317.287 ms oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all 1 606 0.00 MB/sec execute 24 sec latency 31317.538 ms pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 20:07:44 (1787789264) targets are mounted 20:07:44 (1787789264) facet_failover done 1 606 0.00 MB/sec execute 25 sec latency 32317.992 ms 1 606 0.00 MB/sec execute 26 sec latency 33318.860 ms 1 606 0.00 MB/sec execute 27 sec latency 34319.151 ms 1 607 0.00 MB/sec execute 28 sec latency 35311.088 ms 1 674 0.01 MB/sec execute 29 sec latency 68.998 ms 1 720 0.01 MB/sec execute 30 sec latency 91.664 ms 1 723 0.01 MB/sec execute 31 sec latency 853.345 ms oleg320-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 767 0.01 MB/sec execute 32 sec latency 122.636 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 803 0.02 MB/sec execute 33 sec latency 100.267 ms 1 863 0.02 MB/sec execute 34 sec latency 88.913 ms 1 892 0.02 MB/sec execute 35 sec latency 101.779 ms 1 934 0.02 MB/sec execute 36 sec latency 79.701 ms 1 988 0.03 MB/sec execute 37 sec latency 75.575 ms 1 1073 0.05 MB/sec execute 38 sec latency 74.989 ms 1 1124 0.05 MB/sec execute 39 sec latency 105.326 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2192 1269112 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2000 1269304 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 39552 3566936 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 19428 3586708 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 58980 7153644 1% /mnt/lustre 1 1163 0.05 MB/sec execute 40 sec latency 144.226 ms 1 1215 0.05 MB/sec execute 41 sec latency 71.462 ms 1 1257 0.05 MB/sec execute 42 sec latency 112.899 ms 1 1319 0.07 MB/sec execute 43 sec latency 396.923 ms 1 1403 0.11 MB/sec execute 44 sec latency 514.513 ms 1 1447 0.11 MB/sec execute 45 sec latency 123.375 ms 1 1497 0.11 MB/sec execute 46 sec latency 95.206 ms 1 1552 0.11 MB/sec execute 47 sec latency 89.100 ms 1 1591 0.11 MB/sec execute 48 sec latency 71.091 ms test_26 fail mds2 2 times 1 1625 0.11 MB/sec execute 49 sec latency 124.274 ms 1 1660 0.10 MB/sec execute 50 sec latency 121.123 ms Failing mds2 on oleg320-server 1 1692 0.10 MB/sec execute 51 sec latency 135.154 ms Stopping /mnt/lustre-mds2 (opts:) on oleg320-server 1 1770 0.10 MB/sec execute 52 sec latency 74.648 ms 1 1825 0.10 MB/sec execute 53 sec latency 74.949 ms 1 1873 0.10 MB/sec execute 54 sec latency 110.284 ms 1 1956 0.10 MB/sec execute 55 sec latency 84.385 ms 1 2002 0.10 MB/sec execute 56 sec latency 89.375 ms 1 2051 0.10 MB/sec execute 57 sec latency 99.221 ms 1 2111 0.10 MB/sec execute 58 sec latency 93.209 ms 1 2158 0.10 MB/sec execute 59 sec latency 121.694 ms 20:08:19 (1787789299) shut down 1 2210 0.10 MB/sec execute 60 sec latency 84.577 ms facet: mds2 facet_host: oleg320-server facet_failover_host: oleg320-server 1 2259 0.10 MB/sec execute 61 sec latency 503.392 ms 1 2259 0.09 MB/sec execute 62 sec latency 1505.372 ms 1 2259 0.09 MB/sec execute 63 sec latency 2505.650 ms 1 2259 0.09 MB/sec execute 64 sec latency 3506.483 ms 1 2259 0.09 MB/sec execute 65 sec latency 4507.066 ms 1 2259 0.09 MB/sec execute 66 sec latency 5507.315 ms 1 2259 0.09 MB/sec execute 67 sec latency 6509.416 ms 1 2259 0.09 MB/sec execute 68 sec latency 7509.663 ms 1 2259 0.08 MB/sec execute 69 sec latency 8509.914 ms 1 2259 0.08 MB/sec execute 70 sec latency 9510.206 ms Failover mds2 to oleg320-server mount facets: mds2 1 2259 0.08 MB/sec execute 71 sec latency 10510.567 ms 1 2259 0.08 MB/sec execute 72 sec latency 11511.474 ms 1 2259 0.08 MB/sec execute 73 sec latency 12511.831 ms 1 2259 0.08 MB/sec execute 74 sec latency 13512.011 ms 1 2259 0.08 MB/sec execute 75 sec latency 14512.846 ms 1 2259 0.08 MB/sec execute 76 sec latency 15513.201 ms 1 2259 0.08 MB/sec execute 77 sec latency 16514.073 ms 1 2259 0.07 MB/sec execute 78 sec latency 17515.238 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 2259 0.07 MB/sec execute 79 sec latency 18515.690 ms 1 2259 0.07 MB/sec execute 80 sec latency 19516.950 ms 1 2259 0.07 MB/sec execute 81 sec latency 20517.237 ms 1 2259 0.07 MB/sec execute 82 sec latency 21518.045 ms oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all 1 2259 0.07 MB/sec execute 83 sec latency 22522.301 ms 1 2259 0.07 MB/sec execute 84 sec latency 23522.816 ms pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 1 2259 0.07 MB/sec execute 85 sec latency 24523.131 ms Started lustre-MDT0001 20:08:45 (1787789325) targets are mounted 20:08:45 (1787789325) facet_failover done 1 2259 0.07 MB/sec execute 86 sec latency 25531.762 ms 1 2335 0.08 MB/sec execute 87 sec latency 25543.175 ms 1 2368 0.08 MB/sec execute 88 sec latency 92.486 ms 1 2404 0.08 MB/sec execute 89 sec latency 141.581 ms 1 2432 0.08 MB/sec execute 90 sec latency 128.581 ms 1 2468 0.08 MB/sec execute 91 sec latency 79.823 ms 1 2508 0.08 MB/sec execute 92 sec latency 127.357 ms oleg320-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 1 2586 0.09 MB/sec execute 93 sec latency 122.610 ms 1 2633 0.09 MB/sec execute 94 sec latency 119.987 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 2779 0.12 MB/sec execute 95 sec latency 89.150 ms 1 2917 0.13 MB/sec execute 96 sec latency 74.323 ms 1 2989 0.13 MB/sec execute 97 sec latency 98.913 ms 1 3180 0.13 MB/sec execute 98 sec latency 78.146 ms 1 3283 0.14 MB/sec execute 99 sec latency 72.213 ms 1 cleanup 100 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2432 1268872 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2312 1268992 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 39808 3565964 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 29772 3575760 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 69580 7141724 1% /mnt/lustre 1 cleanup 101 sec 1 cleanup 102 sec 0 cleanup 103 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 421 107.985 25543.153 Close 349 11.106 40.954 Rename 22 83.045 144.203 Unlink 51 22.988 47.118 Qpathinfo 415 101.314 35311.064 Qfileinfo 91 2.331 16.017 Qfsinfo 70 2.725 24.739 Sfileinfo 50 55.994 112.015 Find 180 9.925 37.705 WriteX 265 12.389 76.458 ReadX 806 1.254 71.447 LockX 2 15.519 15.689 UnlockX 2 16.725 21.523 Flush 43 53.085 128.566 Throughput 0.144963 MB/sec 1 clients 1 procs max_latency=35311.088 ms stopping dbench on /mnt/lustre at Wed Aug 26 20:09:02 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished striped dir -i0 -c2 -H crush2 /mnt/lustre2/d26.replay-dual/run_dbench looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt test_26 fail mds1 3 times '/usr/share/dbench/client.txt' -> 'client.txt' running 'dbench 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100' on /mnt/lustre at Wed Aug 26 20:09:08 EDT 2026 waiting for dbench pid 68040 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 Failing mds1 on oleg320-server 1 29 0.98 MB/sec warmup 1 sec latency 10.999 ms Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 1 91 2.10 MB/sec warmup 2 sec latency 100.349 ms 1 110 1.75 MB/sec warmup 3 sec latency 802.934 ms 20:09:13 (1787789353) shut down 1 110 1.31 MB/sec warmup 4 sec latency 1803.150 ms facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server 1 110 1.05 MB/sec warmup 5 sec latency 2803.387 ms 1 110 0.87 MB/sec warmup 6 sec latency 3803.710 ms 1 110 0.75 MB/sec warmup 7 sec latency 4804.056 ms 1 110 0.66 MB/sec warmup 8 sec latency 5804.337 ms 1 110 0.58 MB/sec warmup 9 sec latency 6804.525 ms 1 110 0.52 MB/sec warmup 10 sec latency 7804.659 ms 1 110 0.48 MB/sec warmup 11 sec latency 8804.944 ms 1 110 0.44 MB/sec warmup 12 sec latency 9805.166 ms 1 110 0.40 MB/sec warmup 13 sec latency 10805.427 ms 1 110 0.37 MB/sec warmup 14 sec latency 11805.679 ms Failover mds1 to oleg320-server mount facets: mds1 1 110 0.35 MB/sec warmup 15 sec latency 12805.925 ms 1 110 0.33 MB/sec warmup 16 sec latency 13806.287 ms 1 110 0.31 MB/sec warmup 17 sec latency 14808.814 ms 1 110 0.29 MB/sec warmup 18 sec latency 15811.183 ms 1 110 0.28 MB/sec warmup 19 sec latency 16813.016 ms 1 110 0.00 MB/sec execute 1 sec latency 18814.402 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 110 0.00 MB/sec execute 2 sec latency 19817.317 ms 1 110 0.00 MB/sec execute 3 sec latency 20817.590 ms 1 110 0.00 MB/sec execute 4 sec latency 21817.789 ms 1 110 0.00 MB/sec execute 5 sec latency 22817.985 ms 1 110 0.00 MB/sec execute 6 sec latency 23818.242 ms 1 110 0.00 MB/sec execute 7 sec latency 24818.554 ms 1 110 0.00 MB/sec execute 8 sec latency 25818.814 ms 1 110 0.00 MB/sec execute 9 sec latency 26828.617 ms 1 110 0.00 MB/sec execute 10 sec latency 27829.502 ms 1 110 0.00 MB/sec execute 11 sec latency 28829.725 ms 1 110 0.00 MB/sec execute 12 sec latency 29830.183 ms 1 110 0.00 MB/sec execute 13 sec latency 30830.402 ms 1 110 0.00 MB/sec execute 14 sec latency 31830.594 ms 1 110 0.00 MB/sec execute 15 sec latency 32830.837 ms 1 110 0.00 MB/sec execute 16 sec latency 33831.338 ms oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all 1 110 0.00 MB/sec execute 17 sec latency 34831.678 ms pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 1 110 0.00 MB/sec execute 18 sec latency 35831.875 ms Started lustre-MDT0000 20:09:47 (1787789387) targets are mounted 20:09:47 (1787789387) facet_failover done 1 110 0.00 MB/sec execute 19 sec latency 36832.168 ms 1 111 0.00 MB/sec execute 20 sec latency 37627.151 ms 1 155 0.06 MB/sec execute 21 sec latency 283.295 ms 1 190 0.11 MB/sec execute 22 sec latency 308.633 ms 1 255 0.19 MB/sec execute 23 sec latency 96.563 ms oleg320-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 304 0.25 MB/sec execute 24 sec latency 145.443 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 339 0.28 MB/sec execute 25 sec latency 133.279 ms 1 373 0.31 MB/sec execute 26 sec latency 117.961 ms 1 421 0.36 MB/sec execute 27 sec latency 100.520 ms 1 469 0.40 MB/sec execute 28 sec latency 116.413 ms 1 513 0.43 MB/sec execute 29 sec latency 110.498 ms 1 612 0.52 MB/sec execute 30 sec latency 107.488 ms 1 678 0.51 MB/sec execute 31 sec latency 76.891 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2912 1268392 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2724 1268580 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 6320 3590760 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 48904 3556956 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 55224 7147716 1% /mnt/lustre 1 711 0.50 MB/sec execute 32 sec latency 158.196 ms 1 762 0.49 MB/sec execute 33 sec latency 100.098 ms 1 803 0.48 MB/sec execute 34 sec latency 107.653 ms 1 869 0.47 MB/sec execute 35 sec latency 72.343 ms 1 884 0.46 MB/sec execute 36 sec latency 544.859 ms 1 913 0.45 MB/sec execute 37 sec latency 819.929 ms 1 967 0.44 MB/sec execute 38 sec latency 81.963 ms 1 1038 0.45 MB/sec execute 39 sec latency 80.696 ms test_26 fail mds2 4 times 1 1127 0.44 MB/sec execute 40 sec latency 52.416 ms 1 1174 0.43 MB/sec execute 41 sec latency 99.818 ms Failing mds2 on oleg320-server Stopping /mnt/lustre-mds2 (opts:) on oleg320-server 1 1229 0.42 MB/sec execute 42 sec latency 61.765 ms 1 1278 0.42 MB/sec execute 43 sec latency 101.791 ms 1 1278 0.41 MB/sec execute 44 sec latency 1020.580 ms 20:10:13 (1787789413) shut down facet: mds2 facet_host: oleg320-server facet_failover_host: oleg320-server 1 1278 0.40 MB/sec execute 45 sec latency 2021.324 ms 1 1278 0.39 MB/sec execute 46 sec latency 3021.543 ms 1 1278 0.38 MB/sec execute 47 sec latency 4021.755 ms 1 1278 0.37 MB/sec execute 48 sec latency 5022.014 ms 1 1278 0.36 MB/sec execute 49 sec latency 6022.585 ms 1 1278 0.36 MB/sec execute 50 sec latency 7023.292 ms 1 1278 0.35 MB/sec execute 51 sec latency 8023.540 ms 1 1278 0.34 MB/sec execute 52 sec latency 9023.789 ms 1 1278 0.34 MB/sec execute 53 sec latency 10024.065 ms 1 1278 0.33 MB/sec execute 54 sec latency 11024.986 ms Failover mds2 to oleg320-server mount facets: mds2 1 1278 0.33 MB/sec execute 55 sec latency 12025.275 ms 1 1278 0.32 MB/sec execute 56 sec latency 13033.227 ms 1 1278 0.31 MB/sec execute 57 sec latency 14033.373 ms 1 1278 0.31 MB/sec execute 58 sec latency 15036.918 ms 1 1278 0.30 MB/sec execute 59 sec latency 16037.143 ms 1 1278 0.30 MB/sec execute 60 sec latency 17037.520 ms 1 1278 0.29 MB/sec execute 61 sec latency 18039.133 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 1278 0.29 MB/sec execute 62 sec latency 19039.546 ms 1 1278 0.28 MB/sec execute 63 sec latency 20041.352 ms 1 1278 0.28 MB/sec execute 64 sec latency 21041.585 ms 1 1278 0.28 MB/sec execute 65 sec latency 22041.864 ms oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all 1 1278 0.27 MB/sec execute 66 sec latency 23042.522 ms pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 1 1278 0.27 MB/sec execute 67 sec latency 24045.019 ms Started lustre-MDT0001 20:10:36 (1787789436) targets are mounted 20:10:36 (1787789436) facet_failover done 1 1278 0.26 MB/sec execute 68 sec latency 25045.352 ms 1 1404 0.30 MB/sec execute 69 sec latency 25327.737 ms 1 1466 0.30 MB/sec execute 70 sec latency 75.522 ms 1 1518 0.29 MB/sec execute 71 sec latency 205.579 ms 1 1603 0.29 MB/sec execute 72 sec latency 56.663 ms oleg320-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 1 1660 0.29 MB/sec execute 73 sec latency 79.296 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 1719 0.28 MB/sec execute 74 sec latency 105.294 ms 1 1801 0.28 MB/sec execute 75 sec latency 85.431 ms 1 1857 0.28 MB/sec execute 76 sec latency 106.376 ms 1 1941 0.28 MB/sec execute 77 sec latency 87.678 ms 1 2000 0.27 MB/sec execute 78 sec latency 90.027 ms 1 2069 0.27 MB/sec execute 79 sec latency 62.520 ms 1 2142 0.27 MB/sec execute 80 sec latency 84.354 ms 1 2197 0.27 MB/sec execute 81 sec latency 70.075 ms 1 2326 0.28 MB/sec execute 82 sec latency 54.302 ms 1 2375 0.27 MB/sec execute 83 sec latency 137.904 ms 1 2424 0.27 MB/sec execute 84 sec latency 79.869 ms 1 2479 0.28 MB/sec execute 85 sec latency 77.958 ms 1 2571 0.28 MB/sec execute 86 sec latency 101.951 ms 1 2622 0.27 MB/sec execute 87 sec latency 83.077 ms 1 2876 0.31 MB/sec execute 88 sec latency 72.985 ms 1 2931 0.32 MB/sec execute 89 sec latency 70.864 ms dbench killed by signal 15 stopping dbench on /mnt/lustre at Wed Aug 26 20:10:58 EDT 2026 with return code 0 68040 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 68040 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished PASS 26 (285s) == replay-dual test 28: lock replay should be ordered: waiting after granted ========================================================== 20:11:39 (1787789499) Waiting for MDT destroys to complete 1+0 records in 1+0 records out 4096 bytes (4.1 kB, 4.0 KiB) copied, 0.0139036 s, 295 kB/s fail_loc=0x80000324 fail_loc=0x32a Failing ost1 on oleg320-server Stopping /mnt/lustre-ost1 (opts:) on oleg320-server 20:12:00 (1787789520) shut down facet: ost1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover ost1 to oleg320-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 1+0 records in 1+0 records out 4096 bytes (4.1 kB, 4.0 KiB) copied, 0.0145912 s, 281 kB/s oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-OST0000 20:12:22 (1787789542) targets are mounted 20:12:22 (1787789542) facet_failover done oleg320-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 (57s) == replay-dual test 29: replay vs update with the same xid ========================================================== 20:12:36 (1787789556) SKIP: replay-dual test_29 needs >= 2 clients SKIP 29 (2s) == replay-dual test 30: layout lock replay is not blocked on IO ========================================================== 20:12:38 (1787789558) 10+0 records in 10+0 records out 40960 bytes (41 kB, 40 KiB) copied, 0.0255762 s, 1.6 MB/s 10+0 records in 10+0 records out 40960 bytes (41 kB, 40 KiB) copied, 0.0270576 s, 1.5 MB/s fail_loc=0x32e fail_val=4 Failing mds1 on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server 20:12:43 (1787789563) shut down facet: mds1 facet_host: oleg320-server facet_failover_host: oleg320-server Failover mds1 to oleg320-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 20:13:04 (1787789584) targets are mounted 20:13:04 (1787789584) facet_failover done 160+0 records in 160+0 records out 81920 bytes (82 kB, 80 KiB) copied, 26.5079 s, 3.1 kB/s oleg320-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 (39s) == replay-dual test 31: deadlock on file_remove_privs and occupied mod rpc slots ========================================================== 20:13:17 (1787789597) Failing ost1 on oleg320-server Stopping /mnt/lustre-ost1 (opts:) on oleg320-server Creating to objid 2433 on ost lustre-OST0000... 20:13:23 (1787789603) shut down facet: ost1 facet_host: oleg320-server facet_failover_host: oleg320-server total: 32 open/close in 0.83 seconds: 38.62 ops/second at_max=0 fail_loc=0x80001420 file /mnt/lustre2/d31.replay-dual/mdtdir/f31.replay-dual is not ready, wait 0.5 second... file /mnt/lustre2/d31.replay-dual/mdtdir/f31.replay-dual is ready Failover ost1 to oleg320-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 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-OST0000 20:13:49 (1787789629) targets are mounted 20:13:49 (1787789629) facet_failover done oleg320-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 IDLE FULL state after 0 sec pids: 74232 74234 74240 74241 74242 74243 74244 74245 74246 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2156 1269148 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1852 1269452 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1568 3605452 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3112 7210928 1% /mnt/lustre UUID Inodes IUsed IFree IUse% Mounted on lustre-MDT0000_UUID 1024000 341 1023659 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1024000 258 1023742 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 262144 471 261673 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 262144 405 261739 1% /mnt/lustre[OST:1] filesystem_summary: 524011 599 523412 1% /mnt/lustre at_max=600 PASS 31 (46s) == replay-dual test 32: gap in update llog shouldn't break recovery ========================================================== 20:14:03 (1787789643) fail_loc=0x0000131d fail_val=10 fail_loc=0x726 Stopping /mnt/lustre-mds2 (opts:) on oleg320-server Stopping /mnt/lustre-mds1 (opts:) on oleg320-server fail_loc=0 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0000 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0001 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2260 1269044 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1924 1269380 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 (39s) == replay-dual test 33: Check for OBD_INCOMPAT_MULTI_RPCS in last_rcvd after abort_recovery ========================================================== 20:14:42 (1787789682) at_min=60 Stopping /mnt/lustre-mds2 (opts:) on oleg320-server last_rcvd in /dev/mapper/mds2_flakey: incompat = 0x61c Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0001 oleg320-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 oleg320-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 oleg320-server: oleg320-server.virtnet: executing _wait_recovery_complete *.lustre-MDT0001.recovery_status 1475 oleg320-server: *.lustre-MDT0001.recovery_status status: COMPLETE Stopping /mnt/lustre-mds2 (opts:) on oleg320-server last_rcvd in /dev/mapper/mds2_flakey: incompat = 0x61c Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg320-server: oleg320-server.virtnet: executing set_default_debug -1 all pdsh@oleg320-client: oleg320-server: ssh exited with exit code 1 Started lustre-MDT0001 Starting client: oleg320-client.virtnet: -o user_xattr,flock 192.168.203.120@tcp:/lustre /mnt/lustre2 oleg320-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 oleg320-server: oleg320-server.virtnet: executing _wait_recovery_complete *.lustre-MDT0001.recovery_status 1475 oleg320-server: *.lustre-MDT0001.recovery_status status: COMPLETE at_min=5 PASS 33 (85s) == replay-dual test complete, duration 4338 sec ========== 20:16:07 (1787789767) === replay-dual: start cleanup 20:16:09 (1787789769) === Stopping clients: oleg320-client.virtnet /mnt/lustre2 (opts:) Stopping client oleg320-client.virtnet /mnt/lustre2 opts: === replay-dual: finish cleanup 20:16:18 (1787789778) ===