-----============= acceptance-small: replay-dual ============----- Mon Sep 21 09:05:44 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 use REPLAY_DUAL_ONLY='' REPLAY_DUAL_EXCEPT='' oleg456-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 09:05:52 (1789995952) === Starting client oleg456-client.virtnet: -o user_xattr,flock 192.168.204.156@tcp:/lustre /mnt/lustre2 Mount client oleg456-client.virtnet: mount -t lustre -o user_xattr,flock 192.168.204.156@tcp:/lustre /mnt/lustre2 Started clients oleg456-client.virtnet: 192.168.204.156@tcp:/lustre on /mnt/lustre2 type lustre (rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose) oleg456-client.virtnet: executing check_config_client /mnt/lustre oleg456-client.virtnet: Checking config lustre mounted on /mnt/lustre Checking servers environments Checking clients oleg456-client.virtnet environments Using TIMEOUT=20 osc.lustre-OST0000-osc-ffff9f3dc500b000.idle_timeout=debug osc.lustre-OST0000-osc-ffff9f3de0ea9000.idle_timeout=debug osc.lustre-OST0001-osc-ffff9f3dc500b000.idle_timeout=debug osc.lustre-OST0001-osc-ffff9f3de0ea9000.idle_timeout=debug disable quota as required oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all osd-ldiskfs.track_declares_assert=1 === replay-dual: finish setup 09:06:58 (1789996018) === == replay-dual test 0a: expired recovery with lost client ========================================================== 09:07:00 (1789996020) Check file is LU482_FAILED=/tmp/replay-dual.lu482.GxBkNn 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 2.50 seconds: 20.04 ops/second fail_loc=0x80000514 Failing mds1 on oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 09:07:20 (1789996040) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 09:07:53 (1789996073) targets are mounted 09:07:53 (1789996073) facet_failover done Starting client: oleg456-client.virtnet: -o user_xattr,flock 192.168.204.156@tcp:/lustre /mnt/lustre2 - unlinked 0 (time 1789996186 ; total 0 ; last 0) total: 50 unlinks in 2 seconds: 25.000000 unlinks/second PASS 0a (174s) == replay-dual test 0b: lost client during waiting for next transno ========================================================== 09:09:54 (1789996194) 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 oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 09:10:07 (1789996207) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 09:10:42 (1789996242) targets are mounted 09:10:42 (1789996242) facet_failover done Starting client: oleg456-client.virtnet: -o user_xattr,flock 192.168.204.156@tcp:/lustre /mnt/lustre Starting client: oleg456-client.virtnet: -o user_xattr,flock 192.168.204.156@tcp:/lustre /mnt/lustre2 PASS 0b (224s) == replay-dual test 1: |X| simple create ================= 09:13:38 (1789996418) 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-oleg456-client.virtnet' with mode 0100644: File exists Failing mds1 on oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 09:13:51 (1789996431) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 09:14:25 (1789996465) targets are mounted 09:14:25 (1789996465) facet_failover done oleg456-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 (62s) == replay-dual test 2: |X| mkdir adir ==================== 09:14:40 (1789996480) 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 oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 09:14:51 (1789996491) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 09:15:16 (1789996516) targets are mounted 09:15:16 (1789996516) facet_failover done oleg456-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 (49s) == replay-dual test 3: |X| mkdir adir, mkdir adir/bdir === 09:15:29 (1789996529) 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 oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 09:15:39 (1789996539) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 09:16:13 (1789996573) targets are mounted 09:16:13 (1789996573) facet_failover done oleg456-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 (59s) == replay-dual test 4: |X| mkdir adir (-EEXIST), mkdir adir/bdir ========================================================== 09:16:29 (1789996589) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1752 1269552 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 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 oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 09:16:41 (1789996601) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 09:17:18 (1789996638) targets are mounted 09:17:18 (1789996638) facet_failover done oleg456-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 ============ 09:17:33 (1789996653) multiop /mnt/lustre2/a vo_tSc TMPPIPE=/tmp/multiop_open_wait_pipe.8214 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1748 1269556 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 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 oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 09:17:45 (1789996665) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 09:18:08 (1789996688) targets are mounted 09:18:08 (1789996688) facet_failover done oleg456-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 (50s) == replay-dual test 6: open1, open2, unlink |X| close1 [fail mds1] close2 ========================================================== 09:18:23 (1789996703) multiop /mnt/lustre2/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8214 multiop /mnt/lustre/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8214 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1748 1269556 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 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 oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 09:18:34 (1789996714) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 09:19:07 (1789996747) targets are mounted 09:19:07 (1789996747) facet_failover done oleg456-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 (58s) == replay-dual test 8: replay of resent request ========== 09:19:21 (1789996761) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1748 1269556 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 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 oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 09:19:51 (1789996791) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 09:20:24 (1789996824) targets are mounted 09:20:24 (1789996824) facet_failover done oleg456-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 (81s) == replay-dual test 9: resending a replayed create ======= 09:20:42 (1789996842) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1748 1269556 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 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 oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 09:21:00 (1789996860) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 09:21:32 (1789996892) targets are mounted 09:21:32 (1789996892) facet_failover done oleg456-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 (79s) == replay-dual test 10: resending a replayed unlink ====== 09:22:01 (1789996921) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1748 1269556 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 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 oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 09:22:15 (1789996935) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 09:22:51 (1789996971) targets are mounted 09:22:51 (1789996971) facet_failover done oleg456-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 (75s) == replay-dual test 11: both clients timeout during replay ========================================================== 09:23:16 (1789996996) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1748 1269556 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 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 oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 09:23:29 (1789997009) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 09:24:03 (1789997043) targets are mounted 09:24:03 (1789997043) facet_failover done oleg456-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 (65s) == replay-dual test 12: open resend timeout ============== 09:24:21 (1789997061) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1748 1269556 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 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.8214 fail_loc=0x80000302 Failing mds1 on oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 09:24:35 (1789997075) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 09:25:11 (1789997111) targets are mounted 09:25:11 (1789997111) 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 ============= 09:25:30 (1789997130) multiop /mnt/lustre/f13.replay-dual vmo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8214 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1748 1269556 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 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 oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 09:25:42 (1789997142) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 09:26:14 (1789997174) targets are mounted 09:26:14 (1789997174) facet_failover done fail_loc=0 /mnt/lustre/f13.replay-dual /mnt/lustre/f13.replay-dual has type file OK PASS 13 (63s) SKIP: replay-dual test_14b skipping ALWAYS excluded test 14b == replay-dual test 15a: timeout waiting for lost client during replay, 1 client completes ========================================================== 09:26:35 (1789997195) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1748 1269556 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 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 0.82 seconds: 30.44 ops/second total: 1 open/close in 0.04 seconds: 28.53 ops/second Failing mds1 on oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 09:26:46 (1789997206) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 09:27:20 (1789997240) targets are mounted 09:27:20 (1789997240) facet_failover done oleg456-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 1789997315 ; total 0 ; last 0) total: 25 unlinks in 1 seconds: 25.000000 unlinks/second Starting client: oleg456-client.virtnet: -o user_xattr,flock 192.168.204.156@tcp:/lustre /mnt/lustre2 PASS 15a (126s) == replay-dual test 15c: remove multiple OST orphans ===== 09:28:41 (1789997321) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1748 1269556 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 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 oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 09:30:19 (1789997419) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 09:30:40 (1789997440) targets are mounted 09:30:40 (1789997440) facet_failover done oleg456-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: oleg456-client.virtnet: -o user_xattr,flock 192.168.204.156@tcp:/lustre /mnt/lustre2 PASS 15c (200s) == replay-dual test 16: fail MDS during recovery (3571) == 09:32:01 (1789997521) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1748 1269556 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 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 0.83 seconds: 30.12 ops/second total: 1 open/close in 0.04 seconds: 26.03 ops/second Failing mds1 on oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 09:32:11 (1789997531) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 09:32:33 (1789997553) targets are mounted 09:32:33 (1789997553) facet_failover done Failing mds1 on oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 09:32:55 (1789997575) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 09:33:15 (1789997595) targets are mounted 09:33:15 (1789997595) facet_failover done oleg456-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 1789997671 ; total 0 ; last 0) total: 25 unlinks in 0 seconds: inf unlinks/second Starting client: oleg456-client.virtnet: -o user_xattr,flock 192.168.204.156@tcp:/lustre /mnt/lustre2 PASS 16 (156s) == replay-dual test 17: fail OST during recovery (3571) == 09:34:37 (1789997677) total: 25 open/close in 1.00 seconds: 25.03 ops/second total: 1 open/close in 0.11 seconds: 8.80 ops/second UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1780 1269524 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 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 oleg456-server Stopping /mnt/lustre-ost1 (opts:) on oleg456-server 09:34:57 (1789997697) shut down facet: ost1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover ost1 to oleg456-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 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-OST0000 09:35:22 (1789997722) targets are mounted 09:35:22 (1789997722) facet_failover done Failing ost1 on oleg456-server Stopping /mnt/lustre-ost1 (opts:) on oleg456-server 09:35:48 (1789997748) shut down facet: ost1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover ost1 to oleg456-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 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-OST0000 09:36:12 (1789997772) targets are mounted 09:36:12 (1789997772) facet_failover done oleg456-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 1789997844 ; total 0 ; last 0) total: 25 unlinks in 1 seconds: 25.000000 unlinks/second Starting client: oleg456-client.virtnet: -o user_xattr,flock 192.168.204.156@tcp:/lustre /mnt/lustre2 PASS 17 (173s) == replay-dual test 18: ldlm_handle_enqueue succeeds on evicted export (3822) ========================================================== 09:37:30 (1789997850) debug=+dlmtrace fail_loc=0x8000030b using seed 1605929132 running for 500 iterations total: 500 stats in 1 seconds: 500.000000 stats/second ldlm.namespaces.MGC192.168.204.156@tcp.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffff9f3dc500b000.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffff9f3de0cb2000.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0001-mdc-ffff9f3dc500b000.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0001-mdc-ffff9f3de0cb2000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffff9f3dc500b000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffff9f3de0cb2000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffff9f3dc500b000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffff9f3de0cb2000.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.MGC192.168.204.156@tcp.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffff9f3dc500b000.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffff9f3de0cb2000.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0001-mdc-ffff9f3dc500b000.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0001-mdc-ffff9f3de0cb2000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffff9f3dc500b000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffff9f3de0cb2000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffff9f3dc500b000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffff9f3de0cb2000.early_lock_cancel=1 fail_loc=0 fail_loc=0 PASS 18 (56s) == replay-dual test 19: resend of open request =========== 09:38:26 (1789997906) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1784 1269520 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 fail_loc=0x157 - open/close 0 (time 1789998002.66 total 86.78 last 0.00) total: 1 open/close in 86.78 seconds: 0.01 ops/second fail_loc=0 Failing mds1 on oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 09:40:07 (1789998007) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 09:40:38 (1789998038) targets are mounted 09:40:38 (1789998038) facet_failover done oleg456-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 (145s) == replay-dual test 20: recovery time is not increasing == 09:40:51 (1789998051) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1784 1269520 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 Failing mds1 on oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 09:41:02 (1789998062) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 09:41:24 (1789998084) targets are mounted 09:41:24 (1789998084) facet_failover done oleg456-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: oleg456-client.virtnet: -o user_xattr,flock 192.168.204.156@tcp:/lustre /mnt/lustre2 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1784 1269520 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 Failing mds1 on oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 09:44:14 (1789998254) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 09:45:02 (1789998302) targets are mounted 09:45:02 (1789998302) facet_failover done oleg456-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: oleg456-client.virtnet: -o user_xattr,flock 192.168.204.156@tcp:/lustre /mnt/lustre2 PASS 20 (399s) == replay-dual test 21a: commit on sharing =============== 09:47:31 (1789998451) mdt.lustre-MDT0000.commit_on_sharing=1 mdt.lustre-MDT0001.commit_on_sharing=1 Replay barrier on lustre-MDT0000 Failing mds1 on oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 09:47:44 (1789998464) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 09:48:16 (1789998496) targets are mounted 09:48:16 (1789998496) facet_failover done Starting client: oleg456-client.virtnet: -o user_xattr,flock 192.168.204.156@tcp:/lustre /mnt/lustre2 mdt.lustre-MDT0000.commit_on_sharing=0 mdt.lustre-MDT0001.commit_on_sharing=0 PASS 21a (189s) 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 ========================================================== 09:50:41 (1789998641) fail_loc=0x119 Failing mds2 on oleg456-server Stopping /mnt/lustre-mds2 (opts:) on oleg456-server 09:50:48 (1789998648) shut down facet: mds2 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds2 to oleg456-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0001 09:51:13 (1789998673) targets are mounted 09:51:13 (1789998673) facet_failover done oleg456-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 1792 1269512 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 0.11 seconds: 18.99 ops/second total: 2 open/close in 0.05 seconds: 42.50 ops/second Failing mds1 on oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 09:51:37 (1789998697) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 09:52:09 (1789998729) targets are mounted 09:52:09 (1789998729) facet_failover done oleg456-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 (101s) == replay-dual test 22b: c1 lfs mkdir -i 1 d1, M1 drop reply & fail M0/M1, c2 mkdir d1/dir ========================================================== 09:52:22 (1789998742) fail_loc=0x119 Failing mds1 on oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server Failing mds2 on oleg456-server Stopping /mnt/lustre-mds2 (opts:) on oleg456-server 09:52:34 (1789998754) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server facet: mds2 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Failover mds2 to oleg456-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 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 Started lustre-MDT0001 09:53:05 (1789998785) targets are mounted 09:53:05 (1789998785) facet_failover done oleg456-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 1792 1269512 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 0.10 seconds: 19.11 ops/second total: 2 open/close in 0.03 seconds: 58.70 ops/second Failing mds1 on oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 09:53:31 (1789998811) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 09:54:03 (1789998843) targets are mounted 09:54:03 (1789998843) facet_failover done oleg456-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 (115s) == replay-dual test 22c: c1 lfs mkdir -i 1 d1, M1 drop update & fail M1, c2 mkdir d1/dir ========================================================== 09:54:17 (1789998857) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 09:54:24 (1789998864) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 09:54:54 (1789998894) targets are mounted 09:54:54 (1789998894) facet_failover done oleg456-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 1792 1269512 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1648 1269656 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: 17.67 ops/second total: 2 open/close in 0.09 seconds: 22.90 ops/second Failing mds1 on oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 09:55:13 (1789998913) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 09:55:47 (1789998947) targets are mounted 09:55:47 (1789998947) facet_failover done oleg456-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 (104s) == replay-dual test 22d: c1 lfs mkdir -i 1 d1, M1 drop update & fail M0/M1,c2 mkdir d1/dir ========================================================== 09:56:01 (1789998961) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server Failing mds2 on oleg456-server Stopping /mnt/lustre-mds2 (opts:) on oleg456-server 09:56:19 (1789998979) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server facet: mds2 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Failover mds2 to oleg456-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 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 Started lustre-MDT0001 09:56:43 (1789999003) targets are mounted 09:56:43 (1789999003) facet_failover done oleg456-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 1756 1269548 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1600 1269704 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: 25.58 ops/second total: 2 open/close in 0.04 seconds: 45.64 ops/second Failing mds1 on oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 09:57:02 (1789999022) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 09:57:41 (1789999061) targets are mounted 09:57:41 (1789999061) facet_failover done oleg456-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 (128s) == replay-dual test 23a: c1 rmdir d1, M1 drop reply and fail, client2 mkdir d1 ========================================================== 09:58:09 (1789999089) fail_loc=0x119 fail_loc=0 Failing mds2 on oleg456-server Stopping /mnt/lustre-mds2 (opts:) on oleg456-server 09:58:20 (1789999100) shut down facet: mds2 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds2 to oleg456-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0001 09:58:47 (1789999127) targets are mounted 09:58:48 (1789999128) facet_failover done oleg456-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 1788 1269516 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: 21.22 ops/second Failing mds1 on oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 09:59:14 (1789999154) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 09:59:48 (1789999188) targets are mounted 09:59:48 (1789999188) facet_failover done oleg456-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 (117s) == replay-dual test 23b: c1 rmdir d1, M1 drop reply and fail M0/M1, c2 mkdir d1 ========================================================== 10:00:06 (1789999206) fail_loc=0x119 fail_loc=0 Failing mds1 on oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server Failing mds2 on oleg456-server Stopping /mnt/lustre-mds2 (opts:) on oleg456-server 10:00:20 (1789999220) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server facet: mds2 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Failover mds2 to oleg456-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 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 10:00:51 (1789999251) targets are mounted 10:00:51 (1789999251) facet_failover done oleg456-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 1788 1269516 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 0.10 seconds: 20.34 ops/second Failing mds1 on oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 10:01:17 (1789999277) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 10:01:53 (1789999313) targets are mounted 10:01:53 (1789999313) facet_failover done oleg456-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 (126s) == replay-dual test 23c: c1 rmdir d1, M0 drop update reply and fail M0, c2 mkdir d1 ========================================================== 10:02:12 (1789999332) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 10:02:21 (1789999341) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 10:02:56 (1789999376) targets are mounted 10:02:56 (1789999376) facet_failover done oleg456-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 1788 1269516 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1644 1269660 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: 16.17 ops/second Failing mds1 on oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 10:03:24 (1789999404) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 10:03:59 (1789999439) targets are mounted 10:03:59 (1789999439) facet_failover done oleg456-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 (128s) == replay-dual test 23d: c1 rmdir d1, M0 drop update reply and fail M0/M1, c2 mkdir d1 ========================================================== 10:04:20 (1789999460) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server Failing mds2 on oleg456-server Stopping /mnt/lustre-mds2 (opts:) on oleg456-server 10:04:44 (1789999484) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server facet: mds2 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Failover mds2 to oleg456-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 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 Started lustre-MDT0001 10:05:29 (1789999529) targets are mounted 10:05:29 (1789999529) facet_failover done oleg456-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 1752 1269552 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1596 1269708 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: 23.07 ops/second Failing mds1 on oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 10:06:07 (1789999567) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 10:06:38 (1789999598) targets are mounted 10:06:38 (1789999598) facet_failover done oleg456-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 (153s) == replay-dual test 24: reconstruct on non-existing object ========================================================== 10:06:53 (1789999613) fail_loc=0x119 fail_loc=0 truncate: cannot truncate '/mnt/lustre/f24.replay-dual' to length 100: No such file or directory PASS 24 (94s) == replay-dual test 25: replay|resend ==================== 10:08:27 (1789999707) 1+0 records in 1+0 records out 512 bytes copied, 0.0153349 s, 33.4 kB/s fail_loc=0x304 fail_loc=0x80000325 Failing ost1 on oleg456-server Stopping /mnt/lustre-ost1 (opts:) on oleg456-server 10:08:35 (1789999715) shut down facet: ost1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover ost1 to oleg456-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 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-OST0000 10:09:02 (1789999742) targets are mounted 10:09:02 (1789999742) facet_failover done oleg456-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 7030: 64198 Terminated LUSTRE="/home/green/git/lustre-release/lustre" bash -c "multiop /mnt/lustre2/f25.replay-dual Ow512" fail_loc=0 PASS 25 (50s) == replay-dual test 26: dbench and tar with mds failover ========================================================== 10:09:17 (1789999757) Starting client oleg456-client.virtnet: -o user_xattr,flock 192.168.204.156@tcp:/lustre /mnt/lustre Started clients oleg456-client.virtnet: 192.168.204.156@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 65627 Started dbench loop with 65628 striped dir -i0 -c2 -H crush /mnt/lustre2/d26.replay-dual/run_dbench striped dir -i0 -c2 -H crush /mnt/lustre/d26.replay-dual/run_tar looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1940 1269364 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1756 1269548 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 22044 3580772 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 23588 7186248 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 Mon Sep 21 10:09:23 EDT 2026 waiting for dbench pid 65694 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 27 0.85 MB/sec warmup 1 sec latency 16.325 ms 1 91 2.10 MB/sec warmup 2 sec latency 115.858 ms 1 137 2.00 MB/sec warmup 3 sec latency 177.904 ms 1 181 1.83 MB/sec warmup 4 sec latency 117.358 ms 1 211 1.63 MB/sec warmup 5 sec latency 344.621 ms 1 242 1.52 MB/sec warmup 6 sec latency 213.349 ms 1 287 1.53 MB/sec warmup 7 sec latency 129.525 ms 1 331 1.50 MB/sec warmup 8 sec latency 123.489 ms test_26 fail mds1 1 times 1 361 1.43 MB/sec warmup 9 sec latency 189.266 ms 1 391 1.38 MB/sec warmup 10 sec latency 151.718 ms Failing mds1 on oleg456-server 1 429 1.37 MB/sec warmup 11 sec latency 146.818 ms Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 1 469 1.37 MB/sec warmup 12 sec latency 151.947 ms 1 492 1.32 MB/sec warmup 13 sec latency 372.298 ms 1 492 1.23 MB/sec warmup 14 sec latency 1373.938 ms 10:09:38 (1789999778) shut down 1 492 1.15 MB/sec warmup 15 sec latency 2375.454 ms facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server 1 492 1.07 MB/sec warmup 16 sec latency 3375.670 ms 1 492 1.01 MB/sec warmup 17 sec latency 4376.758 ms 1 492 0.96 MB/sec warmup 18 sec latency 5377.060 ms 1 492 0.90 MB/sec warmup 19 sec latency 6377.431 ms 1 492 0.00 MB/sec execute 1 sec latency 8388.573 ms 1 492 0.00 MB/sec execute 2 sec latency 9388.956 ms 1 492 0.00 MB/sec execute 3 sec latency 10389.409 ms 1 492 0.00 MB/sec execute 4 sec latency 11390.425 ms 1 492 0.00 MB/sec execute 5 sec latency 12392.538 ms Failover mds1 to oleg456-server mount facets: mds1 1 492 0.00 MB/sec execute 6 sec latency 13392.701 ms 1 492 0.00 MB/sec execute 7 sec latency 14392.939 ms 1 492 0.00 MB/sec execute 8 sec latency 15393.681 ms 1 492 0.00 MB/sec execute 9 sec latency 16393.927 ms 1 492 0.00 MB/sec execute 10 sec latency 17400.084 ms 1 492 0.00 MB/sec execute 11 sec latency 18400.295 ms 1 492 0.00 MB/sec execute 12 sec latency 19400.469 ms 1 492 0.00 MB/sec execute 13 sec latency 20402.207 ms 1 492 0.00 MB/sec execute 14 sec latency 21403.106 ms 1 492 0.00 MB/sec execute 15 sec latency 22403.313 ms 1 492 0.00 MB/sec execute 16 sec latency 23403.628 ms 1 492 0.00 MB/sec execute 17 sec latency 24406.200 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 492 0.00 MB/sec execute 18 sec latency 25406.395 ms 1 492 0.00 MB/sec execute 19 sec latency 26406.609 ms 1 492 0.00 MB/sec execute 20 sec latency 27406.805 ms 1 492 0.00 MB/sec execute 21 sec latency 28407.201 ms 1 492 0.00 MB/sec execute 22 sec latency 29407.521 ms 1 492 0.00 MB/sec execute 23 sec latency 30417.692 ms 1 492 0.00 MB/sec execute 24 sec latency 31417.901 ms 1 492 0.00 MB/sec execute 25 sec latency 32418.095 ms 1 492 0.00 MB/sec execute 26 sec latency 33418.291 ms oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all 1 492 0.00 MB/sec execute 27 sec latency 34422.435 ms pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 1 492 0.00 MB/sec execute 28 sec latency 35422.639 ms Started lustre-MDT0000 10:10:12 (1789999812) targets are mounted 10:10:12 (1789999812) facet_failover done 1 492 0.00 MB/sec execute 29 sec latency 36424.833 ms 1 511 0.02 MB/sec execute 30 sec latency 36860.303 ms 1 552 0.06 MB/sec execute 31 sec latency 154.306 ms 1 585 0.09 MB/sec execute 32 sec latency 913.526 ms 1 618 0.11 MB/sec execute 33 sec latency 144.157 ms 1 672 0.12 MB/sec execute 34 sec latency 118.604 ms 1 710 0.11 MB/sec execute 35 sec latency 115.699 ms oleg456-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 738 0.11 MB/sec execute 36 sec latency 199.638 ms 1 778 0.11 MB/sec execute 37 sec latency 114.876 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 808 0.11 MB/sec execute 38 sec latency 150.746 ms 1 857 0.11 MB/sec execute 39 sec latency 115.849 ms 1 900 0.11 MB/sec execute 40 sec latency 105.182 ms 1 927 0.11 MB/sec execute 41 sec latency 136.036 ms 1 979 0.11 MB/sec execute 42 sec latency 85.709 ms 1 1039 0.13 MB/sec execute 43 sec latency 82.196 ms UUID 1K-blocks Used Available Use% Mounted on 1 1079 0.13 MB/sec execute 44 sec latency 87.418 ms lustre-MDT0000_UUID 1414116 2140 1269164 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1948 1269356 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 45296 3559384 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 10012 3593864 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 55308 7153248 1% /mnt/lustre 1 1126 0.13 MB/sec execute 45 sec latency 104.500 ms 1 1163 0.13 MB/sec execute 46 sec latency 114.600 ms 1 1173 0.12 MB/sec execute 47 sec latency 815.037 ms 1 1215 0.12 MB/sec execute 48 sec latency 208.831 ms 1 1257 0.12 MB/sec execute 49 sec latency 104.806 ms 1 1394 0.18 MB/sec execute 50 sec latency 72.923 ms 1 1433 0.17 MB/sec execute 51 sec latency 107.750 ms 1 1492 0.17 MB/sec execute 52 sec latency 82.179 ms test_26 fail mds2 2 times 1 1559 0.17 MB/sec execute 53 sec latency 73.340 ms 1 1593 0.17 MB/sec execute 54 sec latency 85.102 ms Failing mds2 on oleg456-server 1 1646 0.16 MB/sec execute 55 sec latency 83.295 ms Stopping /mnt/lustre-mds2 (opts:) on oleg456-server 1 1689 0.16 MB/sec execute 56 sec latency 120.246 ms 1 1756 0.16 MB/sec execute 57 sec latency 92.849 ms 1 1810 0.16 MB/sec execute 58 sec latency 74.799 ms 10:10:41 (1789999841) shut down facet: mds2 facet_host: oleg456-server facet_failover_host: oleg456-server 1 1843 0.15 MB/sec execute 59 sec latency 126.493 ms 1 1886 0.15 MB/sec execute 60 sec latency 127.237 ms 1 1965 0.15 MB/sec execute 61 sec latency 79.488 ms 1 2030 0.15 MB/sec execute 62 sec latency 117.356 ms 1 2123 0.15 MB/sec execute 63 sec latency 71.741 ms 1 2202 0.15 MB/sec execute 64 sec latency 66.571 ms 1 2259 0.15 MB/sec execute 65 sec latency 598.585 ms 1 2259 0.14 MB/sec execute 66 sec latency 1598.746 ms 1 2259 0.14 MB/sec execute 67 sec latency 2599.347 ms 1 2259 0.14 MB/sec execute 68 sec latency 3601.825 ms Failover mds2 to oleg456-server mount facets: mds2 1 2259 0.14 MB/sec execute 69 sec latency 4601.961 ms 1 2259 0.14 MB/sec execute 70 sec latency 5602.186 ms 1 2259 0.13 MB/sec execute 71 sec latency 6602.397 ms 1 2259 0.13 MB/sec execute 72 sec latency 7614.361 ms 1 2259 0.13 MB/sec execute 73 sec latency 8614.723 ms 1 2259 0.13 MB/sec execute 74 sec latency 9614.922 ms 1 2259 0.13 MB/sec execute 75 sec latency 10616.133 ms 1 2259 0.13 MB/sec execute 76 sec latency 11616.834 ms 1 2259 0.12 MB/sec execute 77 sec latency 12617.050 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 2259 0.12 MB/sec execute 78 sec latency 13617.262 ms 1 2259 0.12 MB/sec execute 79 sec latency 14619.026 ms 1 2259 0.12 MB/sec execute 80 sec latency 15619.241 ms 1 2259 0.12 MB/sec execute 81 sec latency 16623.419 ms 1 2259 0.12 MB/sec execute 82 sec latency 17624.343 ms 1 2259 0.12 MB/sec execute 83 sec latency 18624.727 ms 1 2259 0.11 MB/sec execute 84 sec latency 19625.009 ms 1 2259 0.11 MB/sec execute 85 sec latency 20626.183 ms oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all 1 2259 0.11 MB/sec execute 86 sec latency 21628.241 ms pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 1 2259 0.11 MB/sec execute 87 sec latency 22628.527 ms Started lustre-MDT0001 10:11:10 (1789999870) targets are mounted 10:11:11 (1789999871) facet_failover done 1 2345 0.12 MB/sec execute 88 sec latency 22654.688 ms 1 2386 0.12 MB/sec execute 89 sec latency 115.665 ms 1 2417 0.12 MB/sec execute 90 sec latency 128.550 ms 1 2454 0.12 MB/sec execute 91 sec latency 135.489 ms 1 2494 0.13 MB/sec execute 92 sec latency 94.818 ms 1 2576 0.13 MB/sec execute 93 sec latency 89.604 ms 1 2610 0.13 MB/sec execute 94 sec latency 107.618 ms oleg456-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 1 2773 0.16 MB/sec execute 95 sec latency 105.548 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 2898 0.16 MB/sec execute 96 sec latency 97.558 ms 1 2967 0.17 MB/sec execute 97 sec latency 103.266 ms 1 3012 0.17 MB/sec execute 98 sec latency 81.818 ms 1 3181 0.17 MB/sec execute 99 sec latency 155.364 ms 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2520 1268784 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2304 1269000 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 47984 3555948 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 21392 3582364 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 69376 7138312 1% /mnt/lustre 1 cleanup 103 sec 0 cleanup 104 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 417 102.898 22654.675 Close 347 117.031 36860.280 Rename 22 85.834 199.618 Unlink 49 25.133 72.222 Qpathinfo 407 15.714 98.259 Qfileinfo 106 2.216 32.898 Qfsinfo 59 4.169 28.951 Sfileinfo 50 55.887 135.476 Find 135 12.708 134.856 WriteX 332 12.753 74.858 ReadX 804 1.491 95.852 LockX 2 13.833 15.170 UnlockX 2 15.664 21.948 Flush 39 56.909 127.220 Throughput 0.1706 MB/sec 1 clients 1 procs max_latency=36860.303 ms stopping dbench on /mnt/lustre at Mon Sep 21 10:11:27 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 all_char /mnt/lustre2/d26.replay-dual/run_dbench looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt '/usr/share/dbench/client.txt' -> 'client.txt' running 'dbench 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100' on /mnt/lustre at Mon Sep 21 10:11:34 EDT 2026 waiting for dbench pid 67927 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 18 0.26 MB/sec warmup 1 sec latency 18.714 ms Failing mds1 on oleg456-server 1 71 1.57 MB/sec warmup 2 sec latency 129.409 ms Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 1 117 1.76 MB/sec warmup 3 sec latency 251.517 ms 1 155 1.63 MB/sec warmup 4 sec latency 170.873 ms 1 155 1.31 MB/sec warmup 5 sec latency 1171.096 ms 1 155 1.09 MB/sec warmup 6 sec latency 2171.735 ms 10:11:41 (1789999901) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server 1 155 0.93 MB/sec warmup 7 sec latency 3172.000 ms 1 155 0.82 MB/sec warmup 8 sec latency 4172.402 ms 1 155 0.73 MB/sec warmup 9 sec latency 5172.771 ms 1 155 0.65 MB/sec warmup 10 sec latency 6174.112 ms 1 155 0.59 MB/sec warmup 11 sec latency 7174.421 ms 1 155 0.54 MB/sec warmup 12 sec latency 8174.641 ms 1 155 0.50 MB/sec warmup 13 sec latency 9174.842 ms 1 155 0.47 MB/sec warmup 14 sec latency 10175.097 ms 1 155 0.44 MB/sec warmup 15 sec latency 11175.312 ms 1 155 0.41 MB/sec warmup 16 sec latency 12175.585 ms 1 155 0.38 MB/sec warmup 17 sec latency 13185.030 ms Failover mds1 to oleg456-server mount facets: mds1 1 155 0.36 MB/sec warmup 18 sec latency 14185.834 ms 1 155 0.34 MB/sec warmup 19 sec latency 15185.991 ms 1 155 0.00 MB/sec execute 1 sec latency 17188.258 ms 1 155 0.00 MB/sec execute 2 sec latency 18188.428 ms 1 155 0.00 MB/sec execute 3 sec latency 19188.669 ms 1 155 0.00 MB/sec execute 4 sec latency 20189.171 ms 1 155 0.00 MB/sec execute 5 sec latency 21189.421 ms 1 155 0.00 MB/sec execute 6 sec latency 22190.195 ms 1 155 0.00 MB/sec execute 7 sec latency 23190.569 ms 1 155 0.00 MB/sec execute 8 sec latency 24191.943 ms 1 155 0.00 MB/sec execute 9 sec latency 25192.124 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 155 0.00 MB/sec execute 10 sec latency 26193.125 ms 1 155 0.00 MB/sec execute 11 sec latency 27193.450 ms 1 155 0.00 MB/sec execute 12 sec latency 28194.297 ms 1 155 0.00 MB/sec execute 13 sec latency 29194.833 ms 1 155 0.00 MB/sec execute 14 sec latency 30195.291 ms 1 155 0.00 MB/sec execute 15 sec latency 31197.140 ms 1 155 0.00 MB/sec execute 16 sec latency 32197.635 ms 1 155 0.00 MB/sec execute 17 sec latency 33199.318 ms 1 155 0.00 MB/sec execute 18 sec latency 34199.838 ms 1 155 0.00 MB/sec execute 19 sec latency 35200.422 ms 1 155 0.00 MB/sec execute 20 sec latency 36201.202 ms oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all 1 155 0.00 MB/sec execute 21 sec latency 37201.465 ms pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 1 155 0.00 MB/sec execute 22 sec latency 38203.440 ms Started lustre-MDT0000 10:12:17 (1789999937) targets are mounted 10:12:17 (1789999937) facet_failover done 1 157 0.00 MB/sec execute 23 sec latency 39170.219 ms 1 197 0.05 MB/sec execute 24 sec latency 346.749 ms 1 239 0.10 MB/sec execute 25 sec latency 133.639 ms 1 286 0.16 MB/sec execute 26 sec latency 128.778 ms 1 312 0.18 MB/sec execute 27 sec latency 191.255 ms 1 339 0.20 MB/sec execute 28 sec latency 193.699 ms oleg456-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 381 0.24 MB/sec execute 29 sec latency 124.044 ms 1 421 0.28 MB/sec execute 30 sec latency 132.642 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 461 0.31 MB/sec execute 31 sec latency 133.443 ms 1 492 0.33 MB/sec execute 32 sec latency 143.902 ms 1 527 0.35 MB/sec execute 33 sec latency 142.036 ms 1 640 0.43 MB/sec execute 34 sec latency 104.300 ms 1 695 0.42 MB/sec execute 35 sec latency 98.090 ms 1 731 0.41 MB/sec execute 36 sec latency 104.177 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2892 1268412 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2672 1268632 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 15852 3588512 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 40652 3556940 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 56504 7145452 1% /mnt/lustre 1 773 0.40 MB/sec execute 37 sec latency 98.816 ms 1 806 0.39 MB/sec execute 38 sec latency 124.232 ms 1 865 0.38 MB/sec execute 39 sec latency 92.767 ms 1 884 0.38 MB/sec execute 40 sec latency 467.857 ms 1 888 0.37 MB/sec execute 41 sec latency 1162.609 ms 1 913 0.36 MB/sec execute 42 sec latency 365.022 ms 1 926 0.35 MB/sec execute 43 sec latency 894.078 ms 1 980 0.35 MB/sec execute 44 sec latency 89.477 ms 1 1057 0.36 MB/sec execute 45 sec latency 76.560 ms test_26 fail mds2 4 times 1 1127 0.36 MB/sec execute 46 sec latency 59.485 ms 1 1177 0.35 MB/sec execute 47 sec latency 85.828 ms Failing mds2 on oleg456-server Stopping /mnt/lustre-mds2 (opts:) on oleg456-server 1 1231 0.34 MB/sec execute 48 sec latency 71.785 ms 1 1261 0.34 MB/sec execute 49 sec latency 450.868 ms 1 1261 0.33 MB/sec execute 50 sec latency 1452.834 ms 1 1261 0.32 MB/sec execute 51 sec latency 2453.098 ms 1 1261 0.32 MB/sec execute 52 sec latency 3453.380 ms 1 1261 0.31 MB/sec execute 53 sec latency 4453.673 ms 1 1261 0.31 MB/sec execute 54 sec latency 5453.889 ms 1 1261 0.30 MB/sec execute 55 sec latency 6454.161 ms 1 1261 0.30 MB/sec execute 56 sec latency 7454.476 ms 10:12:51 (1789999971) shut down facet: mds2 facet_host: oleg456-server facet_failover_host: oleg456-server 1 1261 0.29 MB/sec execute 57 sec latency 8454.764 ms 1 1261 0.29 MB/sec execute 58 sec latency 9454.949 ms 1 1261 0.28 MB/sec execute 59 sec latency 10455.214 ms 1 1261 0.28 MB/sec execute 60 sec latency 11455.638 ms 1 1261 0.27 MB/sec execute 61 sec latency 12455.866 ms 1 1261 0.27 MB/sec execute 62 sec latency 13456.137 ms 1 1261 0.26 MB/sec execute 63 sec latency 14456.347 ms 1 1261 0.26 MB/sec execute 64 sec latency 15456.542 ms 1 1261 0.25 MB/sec execute 65 sec latency 16456.794 ms 1 1261 0.25 MB/sec execute 66 sec latency 17457.224 ms Failover mds2 to oleg456-server mount facets: mds2 1 1261 0.25 MB/sec execute 67 sec latency 18457.385 ms 1 1261 0.24 MB/sec execute 68 sec latency 19461.119 ms 1 1261 0.24 MB/sec execute 69 sec latency 20461.373 ms 1 1261 0.24 MB/sec execute 70 sec latency 21461.799 ms 1 1261 0.23 MB/sec execute 71 sec latency 22464.728 ms 1 1261 0.23 MB/sec execute 72 sec latency 23466.115 ms 1 1261 0.23 MB/sec execute 73 sec latency 24466.432 ms 1 1261 0.22 MB/sec execute 74 sec latency 25466.756 ms 1 1261 0.22 MB/sec execute 75 sec latency 26467.111 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 1261 0.22 MB/sec execute 76 sec latency 27467.536 ms 1 1261 0.21 MB/sec execute 77 sec latency 28468.805 ms 1 1261 0.21 MB/sec execute 78 sec latency 29469.060 ms 1 1261 0.21 MB/sec execute 79 sec latency 30470.804 ms 1 1261 0.21 MB/sec execute 80 sec latency 31471.506 ms 1 1261 0.20 MB/sec execute 81 sec latency 32473.837 ms oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all 1 1261 0.20 MB/sec execute 82 sec latency 33474.237 ms pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 1 1261 0.20 MB/sec execute 83 sec latency 34474.603 ms Started lustre-MDT0001 10:13:18 (1789999998) targets are mounted 10:13:18 (1789999998) facet_failover done 1 1261 0.20 MB/sec execute 84 sec latency 35475.823 ms 1 1273 0.20 MB/sec execute 85 sec latency 36176.838 ms 1 1406 0.23 MB/sec execute 86 sec latency 77.676 ms 1 1462 0.22 MB/sec execute 87 sec latency 106.775 ms 1 1496 0.22 MB/sec execute 88 sec latency 313.813 ms 1 1546 0.22 MB/sec execute 89 sec latency 96.105 ms oleg456-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 1 1597 0.22 MB/sec execute 90 sec latency 71.992 ms 1 1647 0.22 MB/sec execute 91 sec latency 100.033 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 1686 0.21 MB/sec execute 92 sec latency 137.388 ms 1 1723 0.21 MB/sec execute 93 sec latency 163.694 ms 1 1799 0.21 MB/sec execute 94 sec latency 87.668 ms 1 1848 0.21 MB/sec execute 95 sec latency 116.558 ms 1 1917 0.21 MB/sec execute 96 sec latency 66.750 ms 1 1980 0.21 MB/sec execute 97 sec latency 95.590 ms 1 2022 0.20 MB/sec execute 98 sec latency 91.440 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 2095 0.20 MB/sec execute 99 sec latency 86.066 ms 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec 0 cleanup 103 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 345 170.745 39170.204 Close 301 11.898 40.517 Rename 11 74.939 143.779 Unlink 28 21.355 42.665 Qpathinfo 266 12.964 63.344 Qfileinfo 105 346.069 36176.820 Qfsinfo 33 3.025 17.961 Sfileinfo 34 50.368 90.035 Find 88 10.990 50.374 WriteX 425 13.381 71.137 ReadX 336 0.112 3.299 Flush 30 74.994 894.054 Throughput 0.202935 MB/sec 1 clients 1 procs max_latency=39170.219 ms stopping dbench on /mnt/lustre at Mon Sep 21 10:13:38 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 crush /mnt/lustre2/d26.replay-dual/run_dbench looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt tar: Error is not recoverable: exiting now '/usr/share/dbench/client.txt' -> 'client.txt' stopping dbench on /mnt/lustre at Mon Sep 21 10:13:44 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished PASS 26 (307s) == replay-dual test 28: lock replay should be ordered: waiting after granted ========================================================== 10:14:25 (1790000065) Waiting for MDT destroys to complete 1+0 records in 1+0 records out 4096 bytes (4.1 kB, 4.0 KiB) copied, 0.0121905 s, 336 kB/s fail_loc=0x80000324 fail_loc=0x32a Failing ost1 on oleg456-server Stopping /mnt/lustre-ost1 (opts:) on oleg456-server 10:14:48 (1790000088) shut down facet: ost1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover ost1 to oleg456-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, 0.0103218 s, 397 kB/s seq.cli-lustre-OST0000-super.width=65536 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-OST0000 10:15:12 (1790000112) targets are mounted 10:15:12 (1790000112) facet_failover done oleg456-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 (70s) == replay-dual test 29: replay vs update with the same xid ========================================================== 10:15:34 (1790000134) SKIP: replay-dual test_29 needs >= 2 clients SKIP 29 (4s) == replay-dual test 30: layout lock replay is not blocked on IO ========================================================== 10:15:38 (1790000138) 10+0 records in 10+0 records out 40960 bytes (41 kB, 40 KiB) copied, 0.0359928 s, 1.1 MB/s 10+0 records in 10+0 records out 40960 bytes (41 kB, 40 KiB) copied, 0.0248302 s, 1.6 MB/s fail_loc=0x32e fail_val=4 Failing mds1 on oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server 10:15:46 (1790000146) shut down facet: mds1 facet_host: oleg456-server facet_failover_host: oleg456-server Failover mds1 to oleg456-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all 160+0 records in 160+0 records out 81920 bytes (82 kB, 80 KiB) copied, 36.7385 s, 2.2 kB/s pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 10:16:18 (1790000178) targets are mounted 10:16:18 (1790000178) facet_failover done oleg456-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 (55s) == replay-dual test 31: deadlock on file_remove_privs and occupied mod rpc slots ========================================================== 10:16:33 (1790000193) Failing ost1 on oleg456-server Stopping /mnt/lustre-ost1 (opts:) on oleg456-server Creating to objid 2433 on ost lustre-OST0000... 10:16:42 (1790000202) shut down total: 32 open/close in 1.26 seconds: 25.34 ops/second facet: ost1 facet_host: oleg456-server facet_failover_host: oleg456-server at_max=0 fail_loc=0x80001420 file /mnt/lustre2/d31.replay-dual/mdtdir/f31.replay-dual is ready Failover ost1 to oleg456-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 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-OST0000 10:17:08 (1790000228) targets are mounted 10:17:08 (1790000228) facet_failover done oleg456-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: 74279 74280 74285 74286 74287 74288 74289 74290 74291 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2136 1269140 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1888 1269416 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 512 261632 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 262144 413 261731 1% /mnt/lustre[OST:1] filesystem_summary: 523961 598 523363 1% /mnt/lustre at_max=600 PASS 31 (54s) == replay-dual test 32: gap in update llog shouldn't break recovery ========================================================== 10:17:28 (1790000248) fail_loc=0x0000131d fail_val=10 fail_loc=0x726 Stopping /mnt/lustre-mds2 (opts:) on oleg456-server Stopping /mnt/lustre-mds1 (opts:) on oleg456-server fail_loc=0 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0000 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0001 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2240 1269064 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1956 1269348 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 ========================================================== 10:18:19 (1790000299) at_min=60 Stopping /mnt/lustre-mds2 (opts:) on oleg456-server last_rcvd in /dev/mapper/mds2_flakey: incompat = 0x61c Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0001 oleg456-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 oleg456-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 oleg456-server: oleg456-server.virtnet: executing _wait_recovery_complete *.lustre-MDT0001.recovery_status 1475 oleg456-server: *.lustre-MDT0001.recovery_status status: COMPLETE Stopping /mnt/lustre-mds2 (opts:) on oleg456-server last_rcvd in /dev/mapper/mds2_flakey: incompat = 0x61c Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg456-server: oleg456-server.virtnet: executing set_default_debug -1 all pdsh@oleg456-client: oleg456-server: ssh exited with exit code 1 Started lustre-MDT0001 Starting client: oleg456-client.virtnet: -o user_xattr,flock 192.168.204.156@tcp:/lustre /mnt/lustre2 oleg456-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 oleg456-server: oleg456-server.virtnet: executing _wait_recovery_complete *.lustre-MDT0001.recovery_status 1475 oleg456-server: *.lustre-MDT0001.recovery_status status: COMPLETE at_min=5 PASS 33 (107s) == replay-dual test complete, duration 4462 sec ========== 10:20:06 (1790000406) === replay-dual: start cleanup 10:20:08 (1790000408) === Stopping clients: oleg456-client.virtnet /mnt/lustre2 (opts:) Stopping client oleg456-client.virtnet /mnt/lustre2 opts: === replay-dual: finish cleanup 10:20:19 (1790000419) ===