-----============= acceptance-small: replay-dual ============----- Wed May 21 02:34:30 EDT 2025 mgs: CentOS Linux release 7.9.2009 (Core) MGS_OS_VERSION_ID=7 MGS_OS_ID=centos MGS_OS_VERSION_CODE=117440512 MGS_OS_ID_LIKE=rhel fedora centos mds1: CentOS Linux release 7.9.2009 (Core) MDS1_OS_ID_LIKE=rhel fedora centos MDS1_OS_ID=centos MDS1_OS_VERSION_ID=7 MDS1_OS_VERSION_CODE=117440512 ost1: CentOS Linux release 7.9.2009 (Core) OST1_OS_VERSION_CODE=117440512 OST1_OS_VERSION_ID=7 OST1_OS_ID_LIKE=rhel fedora centos OST1_OS_ID=centos client: CentOS Linux release 7.9.2009 (Core) CLIENT_OS_ID=centos CLIENT_OS_ID_LIKE=rhel fedora centos CLIENT_OS_VERSION_ID=7 CLIENT_OS_VERSION_CODE=117440512 oleg439-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 02:34:35 (1747809275) === Starting client oleg439-client.virtnet: -o user_xattr,flock 192.168.204.139@tcp:/lustre /mnt/lustre2 Started clients oleg439-client.virtnet: 192.168.204.139@tcp:/lustre on /mnt/lustre2 type lustre (rw,checksum,noencrypt,flock,lazystatfs,lruresize,nolock,statfs_project,nouser_fid2path,user_xattr,verbose) oleg439-client.virtnet: executing check_config_client /mnt/lustre oleg439-client.virtnet: Checking config lustre mounted on /mnt/lustre Checking servers environments Checking clients oleg439-client.virtnet environments Using TIMEOUT=20 osc.lustre-OST0000-osc-ffff8800b393e000.idle_timeout=debug osc.lustre-OST0000-osc-ffff8800b5d5d000.idle_timeout=debug osc.lustre-OST0001-osc-ffff8800b393e000.idle_timeout=debug osc.lustre-OST0001-osc-ffff8800b5d5d000.idle_timeout=debug disable quota as required oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all osd-ldiskfs.track_declares_assert=1 === replay-dual: finish setup 02:34:43 (1747809283) === == replay-dual test 0a: expired recovery with lost client ========================================================== 02:34:44 (1747809284) Check file is LU482_FAILED=/tmp/replay-dual.lu482.BNfQyz UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1772 1285916 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1616 1286072 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre total: 50 open/close in 0.41 seconds: 123.17 ops/second fail_loc=0x80000514 Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 02:34:48 (1747809288) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 02:35:01 (1747809301) targets are mounted 02:35:01 (1747809301) facet_failover done Starting client: oleg439-client.virtnet: -o user_xattr,flock 192.168.204.139@tcp:/lustre /mnt/lustre2 - unlinked 0 (time 1747809418 ; total 0 ; last 0) total: 50 unlinks in 0 seconds: inf unlinks/second PASS 0a (135s) == replay-dual test 0b: lost client during waiting for next transno ========================================================== 02:36:59 (1747809419) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1772 1285916 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1616 1286072 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 02:37:02 (1747809422) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 02:37:16 (1747809436) targets are mounted 02:37:16 (1747809436) facet_failover done Starting client: oleg439-client.virtnet: -o user_xattr,flock 192.168.204.139@tcp:/lustre /mnt/lustre Starting client: oleg439-client.virtnet: -o user_xattr,flock 192.168.204.139@tcp:/lustre /mnt/lustre2 PASS 0b (94s) == replay-dual test 1: |X| simple create ================= 02:38:33 (1747809513) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1772 1285916 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1616 1286072 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 02:38:36 (1747809516) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 02:38:50 (1747809530) targets are mounted 02:38:50 (1747809530) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 1 (24s) == replay-dual test 2: |X| mkdir adir ==================== 02:38:57 (1747809537) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1772 1285916 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1616 1286072 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 02:39:01 (1747809541) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 02:39:14 (1747809554) targets are mounted 02:39:14 (1747809554) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 2 (24s) == replay-dual test 3: |X| mkdir adir, mkdir adir/bdir === 02:39:22 (1747809562) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1776 1285912 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1616 1286072 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 02:39:25 (1747809565) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 02:39:39 (1747809579) targets are mounted 02:39:39 (1747809579) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 3 (24s) == replay-dual test 4: |X| mkdir adir (-EEXIST), mkdir adir/bdir ========================================================== 02:39:46 (1747809586) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1920 1285768 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre mkdir: cannot create directory '/mnt/lustre/adir': File exists Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 02:39:50 (1747809590) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 02:40:03 (1747809603) targets are mounted 02:40:03 (1747809603) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 4 (25s) == replay-dual test 5: open, unlink |X| close ============ 02:40:11 (1747809611) multiop /mnt/lustre2/a vo_tSc TMPPIPE=/tmp/multiop_open_wait_pipe.7912 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1916 1285772 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 02:40:14 (1747809614) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 02:40:28 (1747809628) targets are mounted 02:40:28 (1747809628) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 5 (24s) == replay-dual test 6: open1, open2, unlink |X| close1 [fail mds1] close2 ========================================================== 02:40:35 (1747809635) multiop /mnt/lustre2/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.7912 multiop /mnt/lustre/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.7912 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1916 1285772 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 02:40:39 (1747809639) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 02:40:52 (1747809652) targets are mounted 02:40:52 (1747809652) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 6 (25s) == replay-dual test 8: replay of resent request ========== 02:41:00 (1747809660) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1916 1285772 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre fail_loc=0x119 fail_loc=0 Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 02:41:19 (1747809679) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 02:41:33 (1747809693) targets are mounted 02:41:33 (1747809693) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 8 (41s) == replay-dual test 9: resending a replayed create ======= 02:41:41 (1747809701) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1916 1285772 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre fail_loc=0x80000119 Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 02:41:44 (1747809704) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 02:41:58 (1747809718) targets are mounted 02:41:58 (1747809718) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec fail_loc=0 PASS 9 (37s) == replay-dual test 10: resending a replayed unlink ====== 02:42:18 (1747809738) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1916 1285772 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre fail_loc=0x80000119 Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 02:42:22 (1747809742) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 02:42:36 (1747809756) targets are mounted 02:42:36 (1747809756) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec fail_loc=0 PASS 10 (41s) == replay-dual test 11: both clients timeout during replay ========================================================== 02:42:59 (1747809779) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1916 1285772 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre fail_loc=0x0119 Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 02:43:04 (1747809784) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 02:43:18 (1747809798) targets are mounted 02:43:18 (1747809798) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount FULL mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 16 sec fail_loc=0 PASS 11 (38s) == replay-dual test 12: open resend timeout ============== 02:43:37 (1747809817) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1916 1285772 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre multiop /mnt/lustre/f12.replay-dual vmo_c TMPPIPE=/tmp/multiop_open_wait_pipe.7912 fail_loc=0x80000302 Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 02:43:42 (1747809822) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 02:43:57 (1747809837) targets are mounted 02:43:57 (1747809837) facet_failover done fail_loc=0 /mnt/lustre/f12.replay-dual /mnt/lustre/f12.replay-dual has type file OK PASS 12 (24s) == replay-dual test 13: close resend timeout ============= 02:44:01 (1747809841) multiop /mnt/lustre/f13.replay-dual vmo_c TMPPIPE=/tmp/multiop_open_wait_pipe.7912 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1916 1285772 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre fail_loc=0x80000115 Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 02:44:05 (1747809845) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 02:44:20 (1747809860) targets are mounted 02:44:20 (1747809860) facet_failover done fail_loc=0 /mnt/lustre/f13.replay-dual /mnt/lustre/f13.replay-dual has type file OK PASS 13 (24s) SKIP: replay-dual test_14b skipping ALWAYS excluded test 14b == replay-dual test 15a: timeout waiting for lost client during replay, 1 client completes ========================================================== 02:44:26 (1747809866) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1916 1285772 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre total: 25 open/close in 0.18 seconds: 135.24 ops/second total: 1 open/close in 0.01 seconds: 128.58 ops/second Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 02:44:30 (1747809870) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 02:44:44 (1747809884) targets are mounted 02:44:44 (1747809884) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec - unlinked 0 (time 1747809956 ; total 0 ; last 0) total: 25 unlinks in 0 seconds: inf unlinks/second Starting client: oleg439-client.virtnet: -o user_xattr,flock 192.168.204.139@tcp:/lustre /mnt/lustre2 PASS 15a (92s) == replay-dual test 15c: remove multiple OST orphans ===== 02:45:58 (1747809958) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1916 1285772 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 02:46:27 (1747809987) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 02:46:41 (1747810001) targets are mounted 02:46:41 (1747810001) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec Starting client: oleg439-client.virtnet: -o user_xattr,flock 192.168.204.139@tcp:/lustre /mnt/lustre2 PASS 15c (118s) == replay-dual test 16: fail MDS during recovery (3571) == 02:47:56 (1747810076) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1916 1285772 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre total: 25 open/close in 0.23 seconds: 107.49 ops/second total: 1 open/close in 0.01 seconds: 76.18 ops/second Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 02:48:01 (1747810081) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 02:48:15 (1747810095) targets are mounted 02:48:15 (1747810095) facet_failover done Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 02:48:36 (1747810116) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 02:48:49 (1747810129) targets are mounted 02:48:49 (1747810129) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec - unlinked 0 (time 1747810203 ; total 0 ; last 0) total: 25 unlinks in 0 seconds: inf unlinks/second Starting client: oleg439-client.virtnet: -o user_xattr,flock 192.168.204.139@tcp:/lustre /mnt/lustre2 PASS 16 (128s) == replay-dual test 17: fail OST during recovery (3571) == 02:50:04 (1747810204) total: 25 open/close in 0.17 seconds: 143.93 ops/second total: 1 open/close in 0.01 seconds: 103.60 ops/second UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1988 1285700 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3072 7210968 1% /mnt/lustre Failing ost1 on oleg439-server Stopping /mnt/lustre-ost1 (opts:) on oleg439-server 02:50:08 (1747810208) shut down facet: ost1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover ost1 to oleg439-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 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-OST0000 02:50:23 (1747810223) targets are mounted 02:50:23 (1747810223) facet_failover done Failing ost1 on oleg439-server Stopping /mnt/lustre-ost1 (opts:) on oleg439-server 02:50:44 (1747810244) shut down facet: ost1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover ost1 to oleg439-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 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-OST0000 02:50:57 (1747810257) targets are mounted 02:50:57 (1747810257) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in FULL state after 0 sec - unlinked 0 (time 1747810334 ; total 0 ; last 0) total: 25 unlinks in 0 seconds: inf unlinks/second Starting client: oleg439-client.virtnet: -o user_xattr,flock 192.168.204.139@tcp:/lustre /mnt/lustre2 PASS 17 (131s) == replay-dual test 18: ldlm_handle_enqueue succeeds on evicted export (3822) ========================================================== 02:52:15 (1747810335) debug=+dlmtrace fail_loc=0x8000030b using seed 2614491854 running for 500 iterations total: 500 stats in 0 seconds: inf stats/second ldlm.namespaces.MGC192.168.204.139@tcp.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffff8800a8a09800.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffff8800a946a000.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0001-mdc-ffff8800a8a09800.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0001-mdc-ffff8800a946a000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffff8800a8a09800.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffff8800a946a000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffff8800a8a09800.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffff8800a946a000.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.MGC192.168.204.139@tcp.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffff8800a8a09800.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffff8800a946a000.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0001-mdc-ffff8800a8a09800.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0001-mdc-ffff8800a946a000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffff8800a8a09800.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffff8800a946a000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffff8800a8a09800.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffff8800a946a000.early_lock_cancel=1 fail_loc=0 fail_loc=0 PASS 18 (45s) == replay-dual test 19: resend of open request =========== 02:53:00 (1747810380) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1992 1285696 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1540 3605480 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3076 7210964 1% /mnt/lustre fail_loc=0x157 - open/close 0 (time 1747810469.44 total 86.03 last 0.00) total: 1 open/close in 86.03 seconds: 0.01 ops/second fail_loc=0 Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 02:54:30 (1747810470) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 02:54:46 (1747810486) targets are mounted 02:54:46 (1747810486) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 19 (114s) == replay-dual test 20: recovery time is not increasing == 02:54:54 (1747810494) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1992 1285696 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1540 3605480 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3076 7210964 1% /mnt/lustre Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 02:54:58 (1747810498) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 02:55:13 (1747810513) targets are mounted 02:55:13 (1747810513) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec Starting client: oleg439-client.virtnet: -o user_xattr,flock 192.168.204.139@tcp:/lustre /mnt/lustre2 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1992 1285696 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1800 1285888 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1540 3605480 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3076 7210964 1% /mnt/lustre Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 02:57:39 (1747810659) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 02:57:53 (1747810673) targets are mounted 02:57:53 (1747810673) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec Starting client: oleg439-client.virtnet: -o user_xattr,flock 192.168.204.139@tcp:/lustre /mnt/lustre2 PASS 20 (325s) == replay-dual test 21a: commit on sharing =============== 03:00:19 (1747810819) mdt.lustre-MDT0000.commit_on_sharing=1 mdt.lustre-MDT0001.commit_on_sharing=1 Replay barrier on lustre-MDT0000 Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 03:00:22 (1747810822) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 03:00:36 (1747810836) targets are mounted 03:00:36 (1747810836) facet_failover done Starting client: oleg439-client.virtnet: -o user_xattr,flock 192.168.204.139@tcp:/lustre /mnt/lustre2 mdt.lustre-MDT0000.commit_on_sharing=0 mdt.lustre-MDT0001.commit_on_sharing=0 PASS 21a (160s) 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 ========================================================== 03:02:59 (1747810979) fail_loc=0x119 Failing mds2 on oleg439-server Stopping /mnt/lustre-mds2 (opts:) on oleg439-server 03:03:02 (1747810982) shut down facet: mds2 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds2 to oleg439-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0001 03:03:16 (1747810996) targets are mounted 03:03:16 (1747810996) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2000 1285688 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1824 1285864 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1540 3605480 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3076 7210964 1% /mnt/lustre total: 2 open/close in 0.03 seconds: 62.26 ops/second total: 2 open/close in 0.02 seconds: 118.79 ops/second Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 03:03:26 (1747811006) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 03:03:41 (1747811021) targets are mounted 03:03:41 (1747811021) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 22a (50s) == replay-dual test 22b: c1 lfs mkdir -i 1 d1, M1 drop reply & fail M0/M1, c2 mkdir d1/dir ========================================================== 03:03:49 (1747811029) fail_loc=0x119 Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server Failing mds2 on oleg439-server Stopping /mnt/lustre-mds2 (opts:) on oleg439-server 03:03:54 (1747811034) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server facet: mds2 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Failover mds2 to oleg439-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 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 03:04:20 (1747811060) targets are mounted 03:04:20 (1747811060) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2000 1285688 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1824 1285864 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1540 3605480 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3076 7210964 1% /mnt/lustre total: 2 open/close in 0.04 seconds: 52.54 ops/second total: 2 open/close in 0.02 seconds: 109.34 ops/second Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 03:04:31 (1747811071) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 03:04:45 (1747811085) targets are mounted 03:04:45 (1747811085) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 22b (65s) == replay-dual test 22c: c1 lfs mkdir -i 1 d1, M1 drop update & fail M1, c2 mkdir d1/dir ========================================================== 03:04:54 (1747811094) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 03:04:57 (1747811097) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 03:05:11 (1747811111) targets are mounted 03:05:11 (1747811111) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2000 1285688 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1824 1285864 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1540 3605480 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3076 7210964 1% /mnt/lustre total: 2 open/close in 0.02 seconds: 95.36 ops/second total: 2 open/close in 0.01 seconds: 193.37 ops/second Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 03:05:21 (1747811121) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 03:05:36 (1747811136) targets are mounted 03:05:36 (1747811136) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 22c (50s) == replay-dual test 22d: c1 lfs mkdir -i 1 d1, M1 drop update & fail M0/M1,c2 mkdir d1/dir ========================================================== 03:05:44 (1747811144) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server Failing mds2 on oleg439-server Stopping /mnt/lustre-mds2 (opts:) on oleg439-server 03:05:56 (1747811156) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server facet: mds2 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Failover mds2 to oleg439-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 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 03:06:17 (1747811177) targets are mounted 03:06:17 (1747811177) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1964 1285724 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1788 1285900 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1540 3605480 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3076 7210964 1% /mnt/lustre total: 2 open/close in 0.03 seconds: 79.33 ops/second total: 2 open/close in 0.01 seconds: 154.38 ops/second Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 03:06:28 (1747811188) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 03:06:42 (1747811202) targets are mounted 03:06:42 (1747811202) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 22d (66s) == replay-dual test 23a: c1 rmdir d1, M1 drop reply and fail, client2 mkdir d1 ========================================================== 03:06:50 (1747811210) fail_loc=0x119 fail_loc=0 Failing mds2 on oleg439-server Stopping /mnt/lustre-mds2 (opts:) on oleg439-server 03:06:59 (1747811219) shut down facet: mds2 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds2 to oleg439-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0001 03:07:13 (1747811233) targets are mounted 03:07:13 (1747811233) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1996 1285692 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1820 1285868 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1540 3605480 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3076 7210964 1% /mnt/lustre total: 2 open/close in 0.02 seconds: 126.96 ops/second Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 03:07:22 (1747811242) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 03:07:35 (1747811255) targets are mounted 03:07:36 (1747811256) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 23a (53s) == replay-dual test 23b: c1 rmdir d1, M1 drop reply and fail M0/M1, c2 mkdir d1 ========================================================== 03:07:43 (1747811263) fail_loc=0x119 fail_loc=0 Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server Failing mds2 on oleg439-server Stopping /mnt/lustre-mds2 (opts:) on oleg439-server 03:07:53 (1747811273) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server facet: mds2 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Failover mds2 to oleg439-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 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 03:08:14 (1747811294) targets are mounted 03:08:14 (1747811294) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1996 1285692 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1820 1285868 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1540 3605480 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3076 7210964 1% /mnt/lustre total: 2 open/close in 0.02 seconds: 124.53 ops/second Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 03:08:23 (1747811303) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 03:08:37 (1747811317) targets are mounted 03:08:37 (1747811317) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 23b (61s) == replay-dual test 23c: c1 rmdir d1, M0 drop update reply and fail M0, c2 mkdir d1 ========================================================== 03:08:44 (1747811324) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 03:08:47 (1747811327) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 03:09:00 (1747811340) targets are mounted 03:09:00 (1747811340) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1996 1285692 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1820 1285868 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1540 3605480 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3076 7210964 1% /mnt/lustre total: 2 open/close in 0.02 seconds: 123.46 ops/second Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 03:09:09 (1747811349) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 03:09:24 (1747811364) targets are mounted 03:09:24 (1747811364) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 23c (47s) == replay-dual test 23d: c1 rmdir d1, M0 drop update reply and fail M0/M1, c2 mkdir d1 ========================================================== 03:09:31 (1747811371) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server Failing mds2 on oleg439-server Stopping /mnt/lustre-mds2 (opts:) on oleg439-server 03:09:44 (1747811384) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server facet: mds2 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Failover mds2 to oleg439-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 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 03:10:04 (1747811404) targets are mounted 03:10:04 (1747811404) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1960 1285728 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1784 1285904 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1540 3605480 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3076 7210964 1% /mnt/lustre total: 2 open/close in 0.02 seconds: 114.39 ops/second Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 03:10:14 (1747811414) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 03:10:29 (1747811429) targets are mounted 03:10:29 (1747811429) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 23d (67s) == replay-dual test 24: reconstruct on non-existing object ========================================================== 03:10:38 (1747811438) fail_loc=0x119 fail_loc=0 truncate: cannot truncate '/mnt/lustre/f24.replay-dual' to length 100: No such file or directory PASS 24 (88s) == replay-dual test 25: replay|resend ==================== 03:12:06 (1747811526) 1+0 records in 1+0 records out 512 bytes (512 B) copied, 0.0053116 s, 96.4 kB/s fail_loc=0x304 fail_loc=0x80000325 Failing ost1 on oleg439-server Stopping /mnt/lustre-ost1 (opts:) on oleg439-server 03:12:09 (1747811529) shut down facet: ost1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover ost1 to oleg439-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 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-OST0000 03:12:25 (1747811545) targets are mounted 03:12:25 (1747811545) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in FULL state after 0 sec /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 6829: 3445 Terminated LUSTRE="/home/green/git/lustre-release/lustre" bash -c "multiop /mnt/lustre2/f25.replay-dual Ow512" fail_loc=0 PASS 25 (26s) == replay-dual test 26: dbench and tar with mds failover ========================================================== 03:12:32 (1747811552) Starting client oleg439-client.virtnet: -o user_xattr,flock 192.168.204.139@tcp:/lustre /mnt/lustre Started clients oleg439-client.virtnet: 192.168.204.139@tcp:/lustre on /mnt/lustre type lustre (rw,checksum,noencrypt,flock,lazystatfs,lruresize,nolock,statfs_project,nouser_fid2path,user_xattr,verbose) Started tar loop with pid 4988 Started dbench loop with 4989 striped dir -i0 -c2 -H fnv_1a_64 /mnt/lustre2/d26.replay-dual/run_dbench striped dir -i0 -c2 -H crush /mnt/lustre/d26.replay-dual/run_tar looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt '/usr/share/dbench/client.txt' -> 'client.txt' running 'dbench 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100' on /mnt/lustre at Wed May 21 03:12:34 EDT 2025 waiting for dbench pid 5031 dbench version 4.00 - Copyright Andrew Tridgell 1999-2004 Running for 100 seconds with load 'client.txt' and minimum warmup 20 secs failed to create barrier semaphore 0 of 1 processes prepared for launch 0 sec 1 of 1 processes prepared for launch 0 sec releasing clients UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2184 1285504 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1952 1285736 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 26112 3556016 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 27656 7161492 1% /mnt/lustre 1 135 5.96 MB/sec warmup 1 sec latency 57.703 ms 1 247 4.70 MB/sec warmup 2 sec latency 42.761 ms 1 341 4.09 MB/sec warmup 3 sec latency 53.734 ms 1 461 4.04 MB/sec warmup 4 sec latency 41.843 ms 1 614 4.19 MB/sec warmup 5 sec latency 49.511 ms test_26 fail mds1 1 times Failing mds1 on oleg439-server 1 711 3.53 MB/sec warmup 6 sec latency 48.419 ms Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 1 779 3.05 MB/sec warmup 7 sec latency 274.093 ms 03:12:42 (1747811562) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server 1 779 2.67 MB/sec warmup 8 sec latency 1275.881 ms 1 779 2.37 MB/sec warmup 9 sec latency 2276.661 ms 1 779 2.14 MB/sec warmup 10 sec latency 3276.971 ms 1 779 1.94 MB/sec warmup 11 sec latency 4277.725 ms 1 779 1.78 MB/sec warmup 12 sec latency 5277.899 ms 1 779 1.64 MB/sec warmup 13 sec latency 6278.106 ms 1 779 1.53 MB/sec warmup 14 sec latency 7278.444 ms 1 779 1.42 MB/sec warmup 15 sec latency 8278.757 ms 1 779 1.33 MB/sec warmup 16 sec latency 9279.077 ms 1 779 1.26 MB/sec warmup 17 sec latency 10279.345 ms Failover mds1 to oleg439-server mount facets: mds1 1 779 1.19 MB/sec warmup 18 sec latency 11279.739 ms 1 779 1.12 MB/sec warmup 19 sec latency 12279.949 ms 1 779 0.00 MB/sec execute 1 sec latency 14281.987 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 779 0.00 MB/sec execute 2 sec latency 15282.223 ms 1 779 0.00 MB/sec execute 3 sec latency 16282.633 ms oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 1 779 0.00 MB/sec execute 4 sec latency 17283.087 ms Started lustre-MDT0000 03:12:58 (1747811578) targets are mounted 03:12:58 (1747811578) facet_failover done 1 779 0.00 MB/sec execute 5 sec latency 18284.724 ms 1 779 0.00 MB/sec execute 6 sec latency 19285.441 ms 1 779 0.00 MB/sec execute 7 sec latency 20285.744 ms 1 779 0.00 MB/sec execute 8 sec latency 21286.313 ms oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 878 0.03 MB/sec execute 9 sec latency 21350.727 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 977 0.05 MB/sec execute 10 sec latency 42.570 ms 1 1126 0.15 MB/sec execute 11 sec latency 41.993 ms 1 1233 0.14 MB/sec execute 12 sec latency 31.462 ms 1 1421 0.36 MB/sec execute 13 sec latency 45.718 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2672 1285016 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2440 1285248 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 5164 3596108 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 32200 3561548 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 37364 7157656 1% /mnt/lustre 1 1516 0.34 MB/sec execute 14 sec latency 44.716 ms 1 1597 0.32 MB/sec execute 15 sec latency 45.510 ms 1 1689 0.30 MB/sec execute 16 sec latency 62.275 ms 1 1820 0.29 MB/sec execute 17 sec latency 44.391 ms 1 1950 0.28 MB/sec execute 18 sec latency 38.743 ms test_26 fail mds2 2 times 1 2061 0.28 MB/sec execute 19 sec latency 32.092 ms Failing mds2 on oleg439-server 1 2168 0.27 MB/sec execute 20 sec latency 60.304 ms Stopping /mnt/lustre-mds2 (opts:) on oleg439-server 1 2259 0.26 MB/sec execute 21 sec latency 331.276 ms 03:13:16 (1747811596) shut down facet: mds2 facet_host: oleg439-server facet_failover_host: oleg439-server 1 2259 0.25 MB/sec execute 22 sec latency 1331.634 ms 1 2259 0.24 MB/sec execute 23 sec latency 2331.856 ms 1 2259 0.23 MB/sec execute 24 sec latency 3332.153 ms 1 2259 0.22 MB/sec execute 25 sec latency 4332.694 ms 1 2259 0.21 MB/sec execute 26 sec latency 5333.009 ms 1 2259 0.20 MB/sec execute 27 sec latency 6333.247 ms 1 2259 0.19 MB/sec execute 28 sec latency 7333.541 ms 1 2259 0.19 MB/sec execute 29 sec latency 8333.916 ms 1 2259 0.18 MB/sec execute 30 sec latency 9334.438 ms 1 2259 0.17 MB/sec execute 31 sec latency 10334.704 ms Failover mds2 to oleg439-server mount facets: mds2 1 2259 0.17 MB/sec execute 32 sec latency 11334.988 ms 1 2259 0.16 MB/sec execute 33 sec latency 12335.422 ms 1 2259 0.16 MB/sec execute 34 sec latency 13335.850 ms 1 2259 0.15 MB/sec execute 35 sec latency 14337.378 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 2259 0.15 MB/sec execute 36 sec latency 15337.848 ms 1 2259 0.15 MB/sec execute 37 sec latency 16338.913 ms oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0001 03:13:32 (1747811612) targets are mounted 03:13:32 (1747811612) facet_failover done 1 2259 0.14 MB/sec execute 38 sec latency 17339.207 ms 1 2259 0.14 MB/sec execute 39 sec latency 18340.062 ms 1 2259 0.14 MB/sec execute 40 sec latency 19340.633 ms 1 2259 0.13 MB/sec execute 41 sec latency 20341.361 ms 1 2292 0.15 MB/sec execute 42 sec latency 21196.796 ms oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1 2389 0.15 MB/sec execute 43 sec latency 50.713 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 2489 0.17 MB/sec execute 44 sec latency 40.022 ms 1 2752 0.24 MB/sec execute 45 sec latency 49.534 ms 1 2979 0.26 MB/sec execute 46 sec latency 42.520 ms 1 3278 0.30 MB/sec execute 47 sec latency 34.925 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2820 1284868 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2548 1285140 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 9056 3595260 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 41316 3561576 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 50372 7156836 1% /mnt/lustre 1 3501 0.35 MB/sec execute 48 sec latency 36.493 ms 1 3653 0.35 MB/sec execute 49 sec latency 37.018 ms 1 3785 0.37 MB/sec execute 50 sec latency 41.400 ms 1 3879 0.36 MB/sec execute 51 sec latency 46.345 ms 1 3988 0.36 MB/sec execute 52 sec latency 35.726 ms test_26 fail mds1 3 times 1 4073 0.35 MB/sec execute 53 sec latency 47.204 ms Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 1 4213 0.35 MB/sec execute 54 sec latency 43.190 ms 1 4213 0.34 MB/sec execute 55 sec latency 1043.370 ms 1 4213 0.34 MB/sec execute 56 sec latency 2043.849 ms 03:13:51 (1747811631) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server 1 4213 0.33 MB/sec execute 57 sec latency 3044.031 ms 1 4213 0.32 MB/sec execute 58 sec latency 4044.226 ms 1 4213 0.32 MB/sec execute 59 sec latency 5044.956 ms 1 4213 0.31 MB/sec execute 60 sec latency 6045.406 ms 1 4213 0.31 MB/sec execute 61 sec latency 7047.165 ms 1 4213 0.30 MB/sec execute 62 sec latency 8047.338 ms 1 4213 0.30 MB/sec execute 63 sec latency 9047.800 ms 1 4213 0.29 MB/sec execute 64 sec latency 10048.039 ms 1 4213 0.29 MB/sec execute 65 sec latency 11048.987 ms 1 4213 0.28 MB/sec execute 66 sec latency 12050.748 ms 1 4213 0.28 MB/sec execute 67 sec latency 13052.441 ms Failover mds1 to oleg439-server mount facets: mds1 1 4213 0.28 MB/sec execute 68 sec latency 14052.598 ms 1 4213 0.27 MB/sec execute 69 sec latency 15052.768 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 4213 0.27 MB/sec execute 70 sec latency 16052.992 ms 1 4213 0.26 MB/sec execute 71 sec latency 17053.096 ms oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all 1 4213 0.26 MB/sec execute 72 sec latency 18055.326 ms pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 03:14:07 (1747811647) targets are mounted 03:14:07 (1747811647) facet_failover done 1 4213 0.26 MB/sec execute 73 sec latency 19055.508 ms 1 4213 0.25 MB/sec execute 74 sec latency 20055.798 ms 1 4213 0.25 MB/sec execute 75 sec latency 21056.234 ms 1 4213 0.25 MB/sec execute 76 sec latency 22056.686 ms 1 4213 0.24 MB/sec execute 77 sec latency 23056.944 ms 1 4214 0.24 MB/sec execute 78 sec latency 24025.967 ms oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 4309 0.24 MB/sec execute 79 sec latency 68.293 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 4434 0.24 MB/sec execute 80 sec latency 40.881 ms 1 4541 0.24 MB/sec execute 81 sec latency 45.110 ms 1 4710 0.25 MB/sec execute 82 sec latency 34.519 ms 1 4842 0.25 MB/sec execute 83 sec latency 32.314 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 3016 1284672 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2436 1285252 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 12092 3593232 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 45804 3551304 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 57896 7144536 1% /mnt/lustre 1 5052 0.28 MB/sec execute 84 sec latency 40.767 ms 1 5211 0.28 MB/sec execute 85 sec latency 38.629 ms 1 5373 0.28 MB/sec execute 86 sec latency 41.055 ms 1 5538 0.28 MB/sec execute 87 sec latency 36.909 ms 1 5716 0.28 MB/sec execute 88 sec latency 31.878 ms test_26 fail mds2 4 times Failing mds2 on oleg439-server 1 5897 0.29 MB/sec execute 89 sec latency 39.346 ms Stopping /mnt/lustre-mds2 (opts:) on oleg439-server 1 5949 0.29 MB/sec execute 90 sec latency 426.965 ms 1 5949 0.28 MB/sec execute 91 sec latency 1427.222 ms 1 5949 0.28 MB/sec execute 92 sec latency 2428.203 ms 1 5949 0.28 MB/sec execute 93 sec latency 3428.978 ms 1 5949 0.27 MB/sec execute 94 sec latency 4429.093 ms 1 5949 0.27 MB/sec execute 95 sec latency 5429.437 ms 1 5949 0.27 MB/sec execute 96 sec latency 6429.600 ms 03:14:31 (1747811671) shut down facet: mds2 facet_host: oleg439-server facet_failover_host: oleg439-server 1 5949 0.27 MB/sec execute 97 sec latency 7429.784 ms 1 5949 0.26 MB/sec execute 98 sec latency 8430.176 ms 1 5949 0.26 MB/sec execute 99 sec latency 9430.419 ms 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec 1 cleanup 103 sec 1 cleanup 104 sec 1 cleanup 105 sec 1 cleanup 106 sec Failover mds2 to oleg439-server mount facets: mds2 1 cleanup 107 sec 1 cleanup 108 sec 1 cleanup 109 sec Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 cleanup 110 sec 1 cleanup 111 sec oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 1 cleanup 112 sec Started lustre-MDT0001 03:14:46 (1747811686) targets are mounted 03:14:46 (1747811686) facet_failover done 1 cleanup 113 sec 1 cleanup 114 sec 1 cleanup 115 sec 1 cleanup 116 sec oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 0 cleanup 116 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 910 94.841 25898.799 Close 706 38.408 24025.940 Rename 37 31.565 62.240 Unlink 152 9.154 27.552 Qpathinfo 873 5.573 33.802 Qfileinfo 149 0.703 5.461 Qfsinfo 127 1.660 10.992 Sfileinfo 84 20.205 43.285 Find 310 7.429 30.036 WriteX 455 4.133 49.708 ReadX 1301 0.294 25.599 LockX 2 5.892 7.103 UnlockX 2 3.667 4.207 Flush 63 19.777 39.871 Throughput 0.259668 MB/sec 1 clients 1 procs max_latency=24025.967 ms stopping dbench on /mnt/lustre at Wed May 21 03:14:51 EDT 2025 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec removed 'client.txt' /mnt/lustre dbench successfully finished striped dir -i0 -c2 -H crush /mnt/lustre2/d26.replay-dual/run_dbench looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt '/usr/share/dbench/client.txt' -> 'client.txt' running 'dbench 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100' on /mnt/lustre at Wed May 21 03:14:53 EDT 2025 waiting for dbench pid 9569 dbench version 4.00 - Copyright Andrew Tridgell 1999-2004 Running for 100 seconds with load 'client.txt' and minimum warmup 20 secs 0 of 1 processes prepared for launch 0 sec 1 of 1 processes prepared for launch 0 sec releasing clients 1 147 6.28 MB/sec warmup 1 sec latency 41.326 ms 1 297 5.48 MB/sec warmup 2 sec latency 35.747 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 4228 1283460 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2436 1285252 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 8956 3586296 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 39060 3526740 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 48016 7113036 1% /mnt/lustre 1 451 5.28 MB/sec warmup 3 sec latency 40.950 ms 1 650 5.26 MB/sec warmup 4 sec latency 38.626 ms 1 804 4.29 MB/sec warmup 5 sec latency 44.694 ms 1 971 3.64 MB/sec warmup 6 sec latency 27.244 ms test_26 fail mds1 5 times Failing mds1 on oleg439-server 1 1164 3.29 MB/sec warmup 7 sec latency 29.051 ms Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 1 1252 2.89 MB/sec warmup 8 sec latency 468.920 ms 03:15:01 (1747811701) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server 1 1252 2.56 MB/sec warmup 9 sec latency 1469.768 ms 1 1252 2.31 MB/sec warmup 10 sec latency 2469.943 ms 1 1252 2.10 MB/sec warmup 11 sec latency 3470.116 ms 1 1252 1.92 MB/sec warmup 12 sec latency 4470.329 ms 1 1252 1.78 MB/sec warmup 13 sec latency 5471.534 ms 1 1252 1.65 MB/sec warmup 14 sec latency 6471.730 ms 1 1252 1.54 MB/sec warmup 15 sec latency 7472.998 ms 1 1252 1.44 MB/sec warmup 16 sec latency 8473.497 ms 1 1252 1.36 MB/sec warmup 17 sec latency 9473.705 ms 1 1252 1.28 MB/sec warmup 18 sec latency 10477.837 ms Failover mds1 to oleg439-server mount facets: mds1 1 1252 1.21 MB/sec warmup 19 sec latency 11478.708 ms 1 1252 0.00 MB/sec execute 1 sec latency 13479.233 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 1252 0.00 MB/sec execute 2 sec latency 14479.798 ms oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all 1 1252 0.00 MB/sec execute 3 sec latency 15479.971 ms pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 03:15:16 (1747811716) targets are mounted 03:15:16 (1747811716) facet_failover done 1 1252 0.00 MB/sec execute 4 sec latency 16480.140 ms 1 1252 0.00 MB/sec execute 5 sec latency 17480.323 ms 1 1252 0.00 MB/sec execute 6 sec latency 18480.589 ms 1 1252 0.00 MB/sec execute 7 sec latency 19480.868 ms 1 1252 0.00 MB/sec execute 8 sec latency 20481.009 ms 1 1252 0.00 MB/sec execute 9 sec latency 21481.688 ms oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 1422 0.29 MB/sec execute 10 sec latency 21802.090 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 1559 0.27 MB/sec execute 11 sec latency 37.852 ms 1 1686 0.26 MB/sec execute 12 sec latency 38.968 ms 1 1924 0.26 MB/sec execute 13 sec latency 42.401 ms 1 2182 0.26 MB/sec execute 14 sec latency 19.247 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 4664 1283024 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2676 1285012 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 14904 3585412 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 44440 3554396 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 59344 7139808 1% /mnt/lustre 1 2424 0.33 MB/sec execute 15 sec latency 24.638 ms 1 2768 0.55 MB/sec execute 16 sec latency 99.682 ms 1 3045 0.62 MB/sec execute 17 sec latency 344.204 ms 1 3550 0.85 MB/sec execute 18 sec latency 30.850 ms test_26 fail mds2 6 times 1 3792 0.88 MB/sec execute 19 sec latency 19.019 ms Failing mds2 on oleg439-server Stopping /mnt/lustre-mds2 (opts:) on oleg439-server 1 3884 0.83 MB/sec execute 20 sec latency 448.389 ms 03:15:33 (1747811733) shut down facet: mds2 facet_host: oleg439-server facet_failover_host: oleg439-server 1 3884 0.79 MB/sec execute 21 sec latency 1448.593 ms 1 3884 0.76 MB/sec execute 22 sec latency 2448.760 ms 1 3884 0.72 MB/sec execute 23 sec latency 3448.951 ms 1 3884 0.69 MB/sec execute 24 sec latency 4449.163 ms 1 3884 0.67 MB/sec execute 25 sec latency 5449.419 ms 1 3884 0.64 MB/sec execute 26 sec latency 6450.183 ms 1 3884 0.62 MB/sec execute 27 sec latency 7450.379 ms 1 3884 0.60 MB/sec execute 28 sec latency 8450.566 ms 1 3884 0.57 MB/sec execute 29 sec latency 9450.719 ms 1 3884 0.56 MB/sec execute 30 sec latency 10450.997 ms Failover mds2 to oleg439-server mount facets: mds2 1 3884 0.54 MB/sec execute 31 sec latency 11451.149 ms 1 3884 0.52 MB/sec execute 32 sec latency 12451.433 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 3884 0.51 MB/sec execute 33 sec latency 13451.613 ms 1 3884 0.49 MB/sec execute 34 sec latency 14451.823 ms oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0001 03:15:48 (1747811748) targets are mounted 03:15:48 (1747811748) facet_failover done 1 3884 0.48 MB/sec execute 35 sec latency 15452.576 ms 1 3884 0.46 MB/sec execute 36 sec latency 16452.746 ms 1 3884 0.45 MB/sec execute 37 sec latency 17452.930 ms 1 3884 0.44 MB/sec execute 38 sec latency 18453.167 ms 1 3884 0.43 MB/sec execute 39 sec latency 19453.405 ms oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1 4039 0.42 MB/sec execute 40 sec latency 19542.225 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 4221 0.42 MB/sec execute 41 sec latency 23.178 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 4383 0.42 MB/sec execute 42 sec latency 32.631 ms 1 4534 0.41 MB/sec execute 43 sec latency 29.981 ms 1 4706 0.43 MB/sec execute 44 sec latency 28.894 ms 1 4862 0.43 MB/sec execute 45 sec latency 31.567 ms 1 5070 0.48 MB/sec execute 46 sec latency 53.473 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Wed May 21 03:16:00 EDT 2025 with return code 0 9569 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 9569 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished PASS 26 (253s) == replay-dual test 28: lock replay should be ordered: waiting after granted ========================================================== 03:16:45 (1747811805) Waiting for MDT destroys to complete 1+0 records in 1+0 records out 4096 bytes (4.1 kB) copied, 0.00352329 s, 1.2 MB/s fail_loc=0x80000324 fail_loc=0x32a Failing ost1 on oleg439-server Stopping /mnt/lustre-ost1 (opts:) on oleg439-server 03:16:57 (1747811817) shut down facet: ost1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover ost1 to oleg439-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 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all 1+0 records in 1+0 records out 4096 bytes (4.1 kB) copied, 0.00365877 s, 1.1 MB/s pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-OST0000 03:17:11 (1747811831) targets are mounted 03:17:11 (1747811831) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in FULL state after 0 sec PASS 28 (33s) == replay-dual test 29: replay vs update with the same xid ========================================================== 03:17:18 (1747811838) SKIP: replay-dual test_29 needs >= 2 clients SKIP 29 (1s) == replay-dual test 30: layout lock replay is not blocked on IO ========================================================== 03:17:19 (1747811839) 10+0 records in 10+0 records out 40960 bytes (41 kB) copied, 0.0100116 s, 4.1 MB/s 10+0 records in 10+0 records out 40960 bytes (41 kB) copied, 0.00788571 s, 5.2 MB/s fail_loc=0x32e fail_val=4 Failing mds1 on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 03:17:22 (1747811842) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server Failover mds1 to oleg439-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 03:17:36 (1747811856) targets are mounted 03:17:36 (1747811856) facet_failover done 160+0 records in 160+0 records out 81920 bytes (82 kB) copied, 22.2844 s, 3.7 kB/s oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 30 (27s) == replay-dual test 31: deadlock on file_remove_privs and occupied mod rpc slots ========================================================== 03:17:46 (1747811866) Failing ost1 on oleg439-server Stopping /mnt/lustre-ost1 (opts:) on oleg439-server 03:17:48 (1747811868) shut down facet: ost1 facet_host: oleg439-server facet_failover_host: oleg439-server Creating to objid 2977 on ost lustre-OST0000... total: 32 open/close in 0.30 seconds: 106.65 ops/second at_max=0 fail_loc=0x80001420 file /mnt/lustre2/d31.replay-dual/mdtdir/f31.replay-dual is ready Failover ost1 to oleg439-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 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-OST0000 03:18:03 (1747811883) targets are mounted 03:18:03 (1747811883) facet_failover done oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in FULL IDLE state after 0 sec pids: 16454 16455 16461 16462 16463 16464 16465 16466 16467 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2320 1285368 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1952 1285736 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3084 7210956 1% /mnt/lustre UUID Inodes IUsed IFree IUse% Mounted on lustre-MDT0000_UUID 1024000 341 1023659 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1024000 258 1023742 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 262144 508 261636 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 262144 410 261734 1% /mnt/lustre[OST:1] filesystem_summary: 523969 599 523370 1% /mnt/lustre at_max=600 PASS 31 (23s) == replay-dual test 32: gap in update llog shouldn't break recovery ========================================================== 03:18:09 (1747811889) fail_loc=0x0000131d fail_val=10 fail_loc=0x726 Stopping /mnt/lustre-mds2 (opts:) on oleg439-server Stopping /mnt/lustre-mds1 (opts:) on oleg439-server fail_loc=0 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0000 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0001 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2424 1285236 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2032 1285656 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3084 7210956 1% /mnt/lustre PASS 32 (17s) == replay-dual test 33: Check for OBD_INCOMPAT_MULTI_RPCS in last_rcvd after abort_recovery ========================================================== 03:18:26 (1747811906) at_min=60 Stopping /mnt/lustre-mds2 (opts:) on oleg439-server last_rcvd in /dev/mapper/mds2_flakey: incompat = 0x61c Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0001 oleg439-client.virtnet: executing wait_import_state_mount REPLAY_WAIT mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0001-mdc-*.mds_server_uuid in REPLAY_WAIT state after 0 sec oleg439-client.virtnet: executing wait_import_state_mount FULL mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec affected facets: mds2 oleg439-server: oleg439-server.virtnet: executing _wait_recovery_complete *.lustre-MDT0001.recovery_status 1475 oleg439-server: *.lustre-MDT0001.recovery_status status: COMPLETE Stopping /mnt/lustre-mds2 (opts:) on oleg439-server last_rcvd in /dev/mapper/mds2_flakey: incompat = 0x61c Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 Started lustre-MDT0001 Starting client: oleg439-client.virtnet: -o user_xattr,flock 192.168.204.139@tcp:/lustre /mnt/lustre2 oleg439-client.virtnet: executing wait_import_state_mount FULL mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL DISCONN state after 3 sec affected facets: mds2 oleg439-server: oleg439-server.virtnet: executing _wait_recovery_complete *.lustre-MDT0001.recovery_status 1475 oleg439-server: *.lustre-MDT0001.recovery_status status: COMPLETE at_min=5 PASS 33 (39s) == replay-dual test complete, duration 2675 sec ========== 03:19:05 (1747811945) === replay-dual: start cleanup 03:19:05 (1747811945) === Stopping clients: oleg439-client.virtnet /mnt/lustre2 (opts:) Stopping client oleg439-client.virtnet /mnt/lustre2 opts: === replay-dual: finish cleanup 03:19:08 (1747811948) ===