-----============= acceptance-small: replay-dual ============----- Wed May 21 13:12:48 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 oleg405-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 13:12:56 (1747847576) === Starting client oleg405-client.virtnet: -o user_xattr,flock 192.168.204.105@tcp:/lustre /mnt/lustre2 Started clients oleg405-client.virtnet: 192.168.204.105@tcp:/lustre on /mnt/lustre2 type lustre (rw,checksum,noencrypt,flock,lazystatfs,lruresize,nolock,statfs_project,nouser_fid2path,user_xattr,verbose) oleg405-client.virtnet: executing check_config_client /mnt/lustre oleg405-client.virtnet: Checking config lustre mounted on /mnt/lustre Checking servers environments Checking clients oleg405-client.virtnet environments Using TIMEOUT=20 osc.lustre-OST0000-osc-ffff8800a9d4c800.idle_timeout=debug osc.lustre-OST0000-osc-ffff8800b62e4000.idle_timeout=debug osc.lustre-OST0001-osc-ffff8800a9d4c800.idle_timeout=debug osc.lustre-OST0001-osc-ffff8800b62e4000.idle_timeout=debug disable quota as required oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all osd-ldiskfs.track_declares_assert=1 === replay-dual: finish setup 13:13:07 (1747847587) === == replay-dual test 0a: expired recovery with lost client ========================================================== 13:13:08 (1747847588) Check file is LU482_FAILED=/tmp/replay-dual.lu482.2pnsoT 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 0.51 seconds: 98.52 ops/second fail_loc=0x80000514 Failing mds1 on oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:13:12 (1747847592) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:13:27 (1747847607) targets are mounted 13:13:27 (1747847607) facet_failover done Starting client: oleg405-client.virtnet: -o user_xattr,flock 192.168.204.105@tcp:/lustre /mnt/lustre2 - unlinked 0 (time 1747847723 ; total 0 ; last 0) total: 50 unlinks in 1 seconds: 50.000000 unlinks/second PASS 0a (138s) == replay-dual test 0b: lost client during waiting for next transno ========================================================== 13:15:26 (1747847726) 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 oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:15:31 (1747847731) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:15:46 (1747847746) targets are mounted 13:15:46 (1747847746) facet_failover done Starting client: oleg405-client.virtnet: -o user_xattr,flock 192.168.204.105@tcp:/lustre /mnt/lustre Starting client: oleg405-client.virtnet: -o user_xattr,flock 192.168.204.105@tcp:/lustre /mnt/lustre2 PASS 0b (97s) == replay-dual test 1: |X| simple create ================= 13:17:03 (1747847823) 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 oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:17:09 (1747847829) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:17:25 (1747847845) targets are mounted 13:17:25 (1747847845) facet_failover done oleg405-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 (30s) == replay-dual test 2: |X| mkdir adir ==================== 13:17:34 (1747847854) 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 oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:17:40 (1747847860) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:17:57 (1747847877) targets are mounted 13:17:57 (1747847877) facet_failover done oleg405-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 (33s) == replay-dual test 3: |X| mkdir adir, mkdir adir/bdir === 13:18:06 (1747847886) 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 oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:18:12 (1747847892) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:18:29 (1747847909) targets are mounted 13:18:29 (1747847909) facet_failover done oleg405-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 (31s) == replay-dual test 4: |X| mkdir adir (-EEXIST), mkdir adir/bdir ========================================================== 13:18:37 (1747847917) 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 oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:18:45 (1747847925) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:19:00 (1747847940) targets are mounted 13:19:00 (1747847940) facet_failover done oleg405-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 (32s) == replay-dual test 5: open, unlink |X| close ============ 13:19:09 (1747847949) multiop /mnt/lustre2/a vo_tSc TMPPIPE=/tmp/multiop_open_wait_pipe.7927 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 oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:19:15 (1747847955) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:19:32 (1747847972) targets are mounted 13:19:32 (1747847972) facet_failover done oleg405-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 (31s) == replay-dual test 6: open1, open2, unlink |X| close1 [fail mds1] close2 ========================================================== 13:19:40 (1747847980) multiop /mnt/lustre2/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.7927 multiop /mnt/lustre/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.7927 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 oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:19:46 (1747847986) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:20:03 (1747848003) targets are mounted 13:20:03 (1747848003) facet_failover done oleg405-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 (31s) == replay-dual test 8: replay of resent request ========== 13:20:11 (1747848011) 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 oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:20:33 (1747848033) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:20:48 (1747848048) targets are mounted 13:20:48 (1747848048) facet_failover done oleg405-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 (44s) == replay-dual test 9: resending a replayed create ======= 13:20:55 (1747848055) 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 oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:21:01 (1747848061) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:21:15 (1747848075) targets are mounted 13:21:15 (1747848075) facet_failover done oleg405-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 (42s) == replay-dual test 10: resending a replayed unlink ====== 13:21:37 (1747848097) 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 oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:21:41 (1747848101) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:21:57 (1747848117) targets are mounted 13:21:57 (1747848117) facet_failover done oleg405-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec fail_loc=0 PASS 10 (40s) == replay-dual test 11: both clients timeout during replay ========================================================== 13:22:17 (1747848137) 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 oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:22:23 (1747848143) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:22:38 (1747848158) targets are mounted 13:22:38 (1747848158) facet_failover done oleg405-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 14 sec fail_loc=0 PASS 11 (39s) == replay-dual test 12: open resend timeout ============== 13:22:56 (1747848176) 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.7927 fail_loc=0x80000302 Failing mds1 on oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:23:01 (1747848181) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:23:15 (1747848195) targets are mounted 13:23:15 (1747848195) 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 ============= 13:23:20 (1747848200) multiop /mnt/lustre/f13.replay-dual vmo_c TMPPIPE=/tmp/multiop_open_wait_pipe.7927 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 oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:23:25 (1747848205) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:23:40 (1747848220) targets are mounted 13:23:40 (1747848220) facet_failover done fail_loc=0 /mnt/lustre/f13.replay-dual /mnt/lustre/f13.replay-dual has type file OK PASS 13 (25s) SKIP: replay-dual test_14b skipping ALWAYS excluded test 14b == replay-dual test 15a: timeout waiting for lost client during replay, 1 client completes ========================================================== 13:23:45 (1747848225) 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 0.32 seconds: 77.33 ops/second total: 1 open/close in 0.01 seconds: 71.81 ops/second Failing mds1 on oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:23:50 (1747848230) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:24:05 (1747848245) targets are mounted 13:24:05 (1747848245) facet_failover done oleg405-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 1747848320 ; total 0 ; last 0) total: 25 unlinks in 0 seconds: inf unlinks/second Starting client: oleg405-client.virtnet: -o user_xattr,flock 192.168.204.105@tcp:/lustre /mnt/lustre2 PASS 15a (97s) == replay-dual test 15c: remove multiple OST orphans ===== 13:25:22 (1747848322) 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 oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:26:14 (1747848374) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:26:28 (1747848388) targets are mounted 13:26:28 (1747848388) facet_failover done oleg405-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: oleg405-client.virtnet: -o user_xattr,flock 192.168.204.105@tcp:/lustre /mnt/lustre2 PASS 15c (142s) == replay-dual test 16: fail MDS during recovery (3571) == 13:27:44 (1747848464) 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 0.29 seconds: 85.55 ops/second total: 1 open/close in 0.01 seconds: 78.35 ops/second Failing mds1 on oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:27:49 (1747848469) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:28:03 (1747848483) targets are mounted 13:28:03 (1747848483) facet_failover done Failing mds1 on oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:28:25 (1747848505) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:28:38 (1747848518) targets are mounted 13:28:38 (1747848518) facet_failover done oleg405-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 1747848591 ; total 0 ; last 0) total: 25 unlinks in 1 seconds: 25.000000 unlinks/second Starting client: oleg405-client.virtnet: -o user_xattr,flock 192.168.204.105@tcp:/lustre /mnt/lustre2 PASS 16 (129s) == replay-dual test 17: fail OST during recovery (3571) == 13:29:53 (1747848593) total: 25 open/close in 0.24 seconds: 103.40 ops/second total: 1 open/close in 0.01 seconds: 76.52 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 oleg405-server Stopping /mnt/lustre-ost1 (opts:) on oleg405-server 13:29:57 (1747848597) shut down facet: ost1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover ost1 to oleg405-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 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-OST0000 13:30:12 (1747848612) targets are mounted 13:30:12 (1747848612) facet_failover done Failing ost1 on oleg405-server Stopping /mnt/lustre-ost1 (opts:) on oleg405-server 13:30:33 (1747848633) shut down facet: ost1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover ost1 to oleg405-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 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-OST0000 13:30:47 (1747848647) targets are mounted 13:30:47 (1747848647) facet_failover done oleg405-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 1747848723 ; total 0 ; last 0) total: 25 unlinks in 1 seconds: 25.000000 unlinks/second Starting client: oleg405-client.virtnet: -o user_xattr,flock 192.168.204.105@tcp:/lustre /mnt/lustre2 PASS 17 (132s) == replay-dual test 18: ldlm_handle_enqueue succeeds on evicted export (3822) ========================================================== 13:32:05 (1747848725) debug=+dlmtrace fail_loc=0x8000030b using seed 2470456794 running for 500 iterations total: 500 stats in 0 seconds: inf stats/second ldlm.namespaces.MGC192.168.204.105@tcp.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffff8800a840d000.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffff8800a9e03000.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0001-mdc-ffff8800a840d000.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0001-mdc-ffff8800a9e03000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffff8800a840d000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffff8800a9e03000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffff8800a840d000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffff8800a9e03000.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.MGC192.168.204.105@tcp.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffff8800a840d000.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffff8800a9e03000.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0001-mdc-ffff8800a840d000.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0001-mdc-ffff8800a9e03000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffff8800a840d000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffff8800a9e03000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffff8800a840d000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffff8800a9e03000.early_lock_cancel=1 fail_loc=0 fail_loc=0 PASS 18 (45s) == replay-dual test 19: resend of open request =========== 13:32:50 (1747848770) 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 1747848859.57 total 86.02 last 0.00) total: 1 open/close in 86.02 seconds: 0.01 ops/second fail_loc=0 Failing mds1 on oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:34:20 (1747848860) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:34:34 (1747848874) targets are mounted 13:34:34 (1747848874) facet_failover done oleg405-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 19 (112s) == replay-dual test 20: recovery time is not increasing == 13:34:42 (1747848882) 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 oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:34:45 (1747848885) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:35:00 (1747848900) targets are mounted 13:35:00 (1747848900) facet_failover done oleg405-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: oleg405-client.virtnet: -o user_xattr,flock 192.168.204.105@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 oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:37:25 (1747849045) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:37:39 (1747849059) targets are mounted 13:37:39 (1747849059) facet_failover done oleg405-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: oleg405-client.virtnet: -o user_xattr,flock 192.168.204.105@tcp:/lustre /mnt/lustre2 PASS 20 (322s) == replay-dual test 21a: commit on sharing =============== 13:40:04 (1747849204) mdt.lustre-MDT0000.commit_on_sharing=1 mdt.lustre-MDT0001.commit_on_sharing=1 Replay barrier on lustre-MDT0000 Failing mds1 on oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:40:08 (1747849208) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:40:21 (1747849221) targets are mounted 13:40:21 (1747849221) facet_failover done Starting client: oleg405-client.virtnet: -o user_xattr,flock 192.168.204.105@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 ========================================================== 13:42:44 (1747849364) fail_loc=0x119 Failing mds2 on oleg405-server Stopping /mnt/lustre-mds2 (opts:) on oleg405-server 13:42:47 (1747849367) shut down facet: mds2 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds2 to oleg405-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0001 13:43:00 (1747849380) targets are mounted 13:43:00 (1747849380) facet_failover done oleg405-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2000 1285688 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1824 1285864 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1540 3605480 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3076 7210964 1% /mnt/lustre total: 2 open/close in 0.02 seconds: 82.88 ops/second total: 2 open/close in 0.01 seconds: 164.65 ops/second Failing mds1 on oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:43:09 (1747849389) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:43:23 (1747849403) targets are mounted 13:43:23 (1747849403) facet_failover done oleg405-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 (46s) == replay-dual test 22b: c1 lfs mkdir -i 1 d1, M1 drop reply & fail M0/M1, c2 mkdir d1/dir ========================================================== 13:43:30 (1747849410) fail_loc=0x119 Failing mds1 on oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server Failing mds2 on oleg405-server Stopping /mnt/lustre-mds2 (opts:) on oleg405-server 13:43:39 (1747849419) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server facet: mds2 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Failover mds2 to oleg405-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 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 13:44:00 (1747849440) targets are mounted 13:44:00 (1747849440) facet_failover done oleg405-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 0.03 seconds: 70.43 ops/second total: 2 open/close in 0.01 seconds: 161.11 ops/second Failing mds1 on oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:44:09 (1747849449) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:44:23 (1747849463) targets are mounted 13:44:23 (1747849463) facet_failover done oleg405-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 22b (61s) == replay-dual test 22c: c1 lfs mkdir -i 1 d1, M1 drop update & fail M1, c2 mkdir d1/dir ========================================================== 13:44:31 (1747849471) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:44:34 (1747849474) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:44:47 (1747849487) targets are mounted 13:44:47 (1747849487) facet_failover done oleg405-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: 85.15 ops/second total: 2 open/close in 0.01 seconds: 169.58 ops/second Failing mds1 on oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:44:56 (1747849496) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:45:09 (1747849509) targets are mounted 13:45:09 (1747849509) facet_failover done oleg405-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 22c (46s) == replay-dual test 22d: c1 lfs mkdir -i 1 d1, M1 drop update & fail M0/M1,c2 mkdir d1/dir ========================================================== 13:45:17 (1747849517) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server Failing mds2 on oleg405-server Stopping /mnt/lustre-mds2 (opts:) on oleg405-server 13:45:29 (1747849529) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server facet: mds2 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Failover mds2 to oleg405-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 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 13:45:49 (1747849549) targets are mounted 13:45:49 (1747849549) facet_failover done oleg405-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 0.04 seconds: 53.73 ops/second total: 2 open/close in 0.02 seconds: 103.61 ops/second Failing mds1 on oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:45:59 (1747849559) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:46:13 (1747849573) targets are mounted 13:46:13 (1747849573) facet_failover done oleg405-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 (63s) == replay-dual test 23a: c1 rmdir d1, M1 drop reply and fail, client2 mkdir d1 ========================================================== 13:46:20 (1747849580) fail_loc=0x119 fail_loc=0 Failing mds2 on oleg405-server Stopping /mnt/lustre-mds2 (opts:) on oleg405-server 13:46:28 (1747849588) shut down facet: mds2 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds2 to oleg405-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0001 13:46:41 (1747849601) targets are mounted 13:46:41 (1747849601) facet_failover done oleg405-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: 99.29 ops/second Failing mds1 on oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:46:50 (1747849610) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:47:04 (1747849624) targets are mounted 13:47:04 (1747849624) facet_failover done oleg405-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 (51s) == replay-dual test 23b: c1 rmdir d1, M1 drop reply and fail M0/M1, c2 mkdir d1 ========================================================== 13:47:11 (1747849631) fail_loc=0x119 fail_loc=0 Failing mds1 on oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server Failing mds2 on oleg405-server Stopping /mnt/lustre-mds2 (opts:) on oleg405-server 13:47:21 (1747849641) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server facet: mds2 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Failover mds2 to oleg405-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 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 Started lustre-MDT0001 13:47:41 (1747849661) targets are mounted 13:47:41 (1747849661) facet_failover done oleg405-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: 101.54 ops/second Failing mds1 on oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:48:03 (1747849683) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:48:17 (1747849697) targets are mounted 13:48:17 (1747849697) facet_failover done oleg405-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 (73s) == replay-dual test 23c: c1 rmdir d1, M0 drop update reply and fail M0, c2 mkdir d1 ========================================================== 13:48:24 (1747849704) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:48:27 (1747849707) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:48:40 (1747849720) targets are mounted 13:48:40 (1747849720) facet_failover done oleg405-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1996 1285692 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1820 1285868 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1540 3605480 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3076 7210964 1% /mnt/lustre total: 2 open/close in 0.01 seconds: 138.15 ops/second Failing mds1 on oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:48:50 (1747849730) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:49:03 (1747849743) targets are mounted 13:49:03 (1747849743) facet_failover done oleg405-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 ========================================================== 13:49:11 (1747849751) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server Failing mds2 on oleg405-server Stopping /mnt/lustre-mds2 (opts:) on oleg405-server 13:49:23 (1747849763) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server facet: mds2 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Failover mds2 to oleg405-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 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 13:49:43 (1747849783) targets are mounted 13:49:43 (1747849783) facet_failover done oleg405-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: 112.84 ops/second Failing mds1 on oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:49:53 (1747849793) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:50:07 (1747849807) targets are mounted 13:50:07 (1747849807) facet_failover done oleg405-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 23d (63s) == replay-dual test 24: reconstruct on non-existing object ========================================================== 13:50:14 (1747849814) fail_loc=0x119 fail_loc=0 truncate: cannot truncate '/mnt/lustre/f24.replay-dual' to length 100: No such file or directory PASS 24 (87s) == replay-dual test 25: replay|resend ==================== 13:51:41 (1747849901) 1+0 records in 1+0 records out 512 bytes (512 B) copied, 0.00310603 s, 165 kB/s fail_loc=0x304 fail_loc=0x80000325 Failing ost1 on oleg405-server Stopping /mnt/lustre-ost1 (opts:) on oleg405-server 13:51:44 (1747849904) shut down facet: ost1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover ost1 to oleg405-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 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-OST0000 13:51:57 (1747849917) targets are mounted 13:51:57 (1747849917) facet_failover done oleg405-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 6823: 3511 Terminated LUSTRE="/home/green/git/lustre-release/lustre" bash -c "multiop /mnt/lustre2/f25.replay-dual Ow512" fail_loc=0 PASS 25 (21s) == replay-dual test 26: dbench and tar with mds failover ========================================================== 13:52:02 (1747849922) Starting client oleg405-client.virtnet: -o user_xattr,flock 192.168.204.105@tcp:/lustre /mnt/lustre Started clients oleg405-client.virtnet: 192.168.204.105@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 5051 Started dbench loop with 5052 striped dir -i0 -c2 -H crush2 /mnt/lustre2/d26.replay-dual/run_dbench striped dir -i0 -c2 -H fnv_1a_64 /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 13:52:04 EDT 2025 waiting for dbench pid 5093 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 2268 1285420 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2044 1285644 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] 1 231 8.88 MB/sec warmup 1 sec latency 24.597 ms lustre-OST0001_UUID 3833116 26112 3555936 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 27656 7161412 1% /mnt/lustre 1 468 8.21 MB/sec warmup 2 sec latency 19.652 ms 1 737 7.10 MB/sec warmup 3 sec latency 126.169 ms 1 990 5.48 MB/sec warmup 4 sec latency 17.730 ms test_26 fail mds1 1 times 1 1383 5.20 MB/sec warmup 5 sec latency 16.173 ms Failing mds1 on oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 1 1580 4.36 MB/sec warmup 6 sec latency 319.150 ms 13:52:10 (1747849930) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server 1 1580 3.73 MB/sec warmup 7 sec latency 1319.303 ms 1 1580 3.27 MB/sec warmup 8 sec latency 2319.462 ms 1 1580 2.90 MB/sec warmup 9 sec latency 3319.629 ms 1 1580 2.61 MB/sec warmup 10 sec latency 4319.826 ms 1 1580 2.38 MB/sec warmup 11 sec latency 5319.971 ms 1 1580 2.18 MB/sec warmup 12 sec latency 6320.100 ms 1 1580 2.01 MB/sec warmup 13 sec latency 7320.353 ms 1 1580 1.87 MB/sec warmup 14 sec latency 8320.552 ms 1 1580 1.74 MB/sec warmup 15 sec latency 9320.722 ms 1 1580 1.63 MB/sec warmup 16 sec latency 10320.886 ms Failover mds1 to oleg405-server mount facets: mds1 1 1580 1.54 MB/sec warmup 17 sec latency 11321.055 ms 1 1580 1.45 MB/sec warmup 18 sec latency 12321.251 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 1580 1.38 MB/sec warmup 19 sec latency 13321.409 ms oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:52:24 (1747849944) targets are mounted 13:52:24 (1747849944) facet_failover done 1 1580 0.00 MB/sec execute 1 sec latency 15321.674 ms 1 1580 0.00 MB/sec execute 2 sec latency 16321.840 ms 1 1580 0.00 MB/sec execute 3 sec latency 17322.036 ms 1 1580 0.00 MB/sec execute 4 sec latency 18322.172 ms 1 1642 0.01 MB/sec execute 5 sec latency 19050.725 ms oleg405-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 1908 0.05 MB/sec execute 6 sec latency 20.730 ms 1 2191 0.09 MB/sec execute 7 sec latency 14.670 ms 1 2502 0.32 MB/sec execute 8 sec latency 16.886 ms 1 3030 0.83 MB/sec execute 9 sec latency 16.544 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2984 1284704 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2600 1285088 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 5924 3593764 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 31252 3567840 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 37176 7161604 1% /mnt/lustre 1 3624 1.25 MB/sec execute 10 sec latency 20.767 ms 1 3874 1.24 MB/sec execute 11 sec latency 15.625 ms 1 4096 1.16 MB/sec execute 12 sec latency 18.979 ms 1 4372 1.11 MB/sec execute 13 sec latency 40.103 ms test_26 fail mds2 2 times Failing mds2 on oleg405-server 1 4629 1.13 MB/sec execute 14 sec latency 19.951 ms Stopping /mnt/lustre-mds2 (opts:) on oleg405-server 1 4851 1.07 MB/sec execute 15 sec latency 163.716 ms 13:52:39 (1747849959) shut down facet: mds2 facet_host: oleg405-server facet_failover_host: oleg405-server 1 4851 1.01 MB/sec execute 16 sec latency 1163.813 ms 1 4851 0.95 MB/sec execute 17 sec latency 2163.918 ms 1 4851 0.90 MB/sec execute 18 sec latency 3164.047 ms 1 4851 0.85 MB/sec execute 19 sec latency 4164.166 ms 1 4851 0.81 MB/sec execute 20 sec latency 5164.283 ms 1 4851 0.77 MB/sec execute 21 sec latency 6164.374 ms 1 4851 0.73 MB/sec execute 22 sec latency 7164.485 ms 1 4851 0.70 MB/sec execute 23 sec latency 8164.606 ms 1 4851 0.67 MB/sec execute 24 sec latency 9164.714 ms 1 4851 0.64 MB/sec execute 25 sec latency 10164.818 ms Failover mds2 to oleg405-server mount facets: mds2 1 4851 0.62 MB/sec execute 26 sec latency 11164.963 ms 1 4851 0.60 MB/sec execute 27 sec latency 12165.098 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 4851 0.58 MB/sec execute 28 sec latency 13165.178 ms oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 1 4851 0.56 MB/sec execute 29 sec latency 14165.356 ms Started lustre-MDT0001 13:52:53 (1747849973) targets are mounted 13:52:53 (1747849973) facet_failover done 1 4851 0.54 MB/sec execute 30 sec latency 15165.531 ms 1 4851 0.52 MB/sec execute 31 sec latency 16165.765 ms 1 4851 0.50 MB/sec execute 32 sec latency 17165.937 ms 1 4851 0.49 MB/sec execute 33 sec latency 18166.083 ms oleg405-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1 5123 0.56 MB/sec execute 34 sec latency 18387.285 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 5344 0.55 MB/sec execute 35 sec latency 22.052 ms 1 5598 0.54 MB/sec execute 36 sec latency 15.380 ms 1 5933 0.56 MB/sec execute 37 sec latency 12.965 ms 1 6316 0.66 MB/sec execute 38 sec latency 18.089 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 4616 1283072 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2592 1285096 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 12668 3577384 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 38024 3552252 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 50692 7129636 1% /mnt/lustre 1 6798 0.71 MB/sec execute 39 sec latency 42.825 ms 1 7190 0.79 MB/sec execute 40 sec latency 15.385 ms 1 7424 0.80 MB/sec execute 41 sec latency 25.449 ms test_26 fail mds1 3 times 1 7638 0.79 MB/sec execute 42 sec latency 16.990 ms Failing mds1 on oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 1 7860 0.78 MB/sec execute 43 sec latency 116.035 ms 13:53:08 (1747849988) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server 1 7860 0.76 MB/sec execute 44 sec latency 1116.210 ms 1 7860 0.74 MB/sec execute 45 sec latency 2116.380 ms 1 7860 0.73 MB/sec execute 46 sec latency 3116.593 ms 1 7860 0.71 MB/sec execute 47 sec latency 4116.765 ms 1 7860 0.70 MB/sec execute 48 sec latency 5116.951 ms 1 7860 0.68 MB/sec execute 49 sec latency 6117.114 ms 1 7860 0.67 MB/sec execute 50 sec latency 7117.266 ms 1 7860 0.66 MB/sec execute 51 sec latency 8117.502 ms 1 7860 0.64 MB/sec execute 52 sec latency 9117.674 ms 1 7860 0.63 MB/sec execute 53 sec latency 10117.835 ms Failover mds1 to oleg405-server mount facets: mds1 1 7860 0.62 MB/sec execute 54 sec latency 11117.937 ms 1 7860 0.61 MB/sec execute 55 sec latency 12118.101 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 7860 0.60 MB/sec execute 56 sec latency 13118.248 ms 1 7860 0.59 MB/sec execute 57 sec latency 14118.433 ms oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:53:22 (1747850002) targets are mounted 13:53:22 (1747850002) facet_failover done 1 7860 0.58 MB/sec execute 58 sec latency 15118.668 ms 1 7860 0.57 MB/sec execute 59 sec latency 16118.926 ms 1 7860 0.56 MB/sec execute 60 sec latency 17119.097 ms 1 7860 0.55 MB/sec execute 61 sec latency 18119.313 ms 1 7860 0.54 MB/sec execute 62 sec latency 19119.466 ms 1 7988 0.54 MB/sec execute 63 sec latency 19617.426 ms oleg405-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 8255 0.55 MB/sec execute 64 sec latency 21.228 ms 1 8576 0.59 MB/sec execute 65 sec latency 19.200 ms 1 8819 0.58 MB/sec execute 66 sec latency 18.341 ms 1 9103 0.58 MB/sec execute 67 sec latency 17.240 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 5024 1282664 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 3056 1284632 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 12508 3573488 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 46788 3535408 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 59296 7108896 1% /mnt/lustre 1 9378 0.58 MB/sec execute 68 sec latency 22.159 ms 1 9532 0.58 MB/sec execute 69 sec latency 460.842 ms 1 9991 0.64 MB/sec execute 70 sec latency 19.569 ms 1 10464 0.67 MB/sec execute 71 sec latency 17.790 ms test_26 fail mds2 4 times Failing mds2 on oleg405-server Stopping /mnt/lustre-mds2 (opts:) on oleg405-server 1 10811 0.71 MB/sec execute 72 sec latency 15.499 ms 13:53:37 (1747850017) shut down facet: mds2 facet_host: oleg405-server facet_failover_host: oleg405-server 1 10870 0.71 MB/sec execute 73 sec latency 813.219 ms 1 10870 0.70 MB/sec execute 74 sec latency 1813.433 ms 1 10870 0.69 MB/sec execute 75 sec latency 2813.649 ms 1 10870 0.68 MB/sec execute 76 sec latency 3813.856 ms 1 10870 0.67 MB/sec execute 77 sec latency 4814.087 ms 1 10870 0.66 MB/sec execute 78 sec latency 5814.269 ms 1 10870 0.66 MB/sec execute 79 sec latency 6814.439 ms 1 10870 0.65 MB/sec execute 80 sec latency 7814.613 ms 1 10870 0.64 MB/sec execute 81 sec latency 8814.759 ms 1 10870 0.63 MB/sec execute 82 sec latency 9814.936 ms Failover mds2 to oleg405-server mount facets: mds2 1 10870 0.62 MB/sec execute 83 sec latency 10815.059 ms 1 10870 0.62 MB/sec execute 84 sec latency 11815.191 ms 1 10870 0.61 MB/sec execute 85 sec latency 12815.332 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 10870 0.60 MB/sec execute 86 sec latency 13815.470 ms oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0001 13:53:51 (1747850031) targets are mounted 13:53:51 (1747850031) facet_failover done 1 10870 0.60 MB/sec execute 87 sec latency 14815.624 ms 1 10870 0.59 MB/sec execute 88 sec latency 15815.735 ms 1 10870 0.58 MB/sec execute 89 sec latency 16815.881 ms 1 10870 0.58 MB/sec execute 90 sec latency 17816.076 ms 1 10870 0.57 MB/sec execute 91 sec latency 18816.209 ms oleg405-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1 10981 0.57 MB/sec execute 92 sec latency 19260.352 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 11175 0.56 MB/sec execute 93 sec latency 17.747 ms 1 11407 0.56 MB/sec execute 94 sec latency 23.118 ms 1 11643 0.56 MB/sec execute 95 sec latency 23.634 ms 1 11908 0.57 MB/sec execute 96 sec latency 30.913 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 5404 1282284 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 3468 1284220 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 20176 3581652 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 57596 3542928 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 77772 7124580 2% /mnt/lustre 1 12231 0.59 MB/sec execute 97 sec latency 24.402 ms 1 12461 0.59 MB/sec execute 98 sec latency 21.713 ms 1 12792 0.58 MB/sec execute 99 sec latency 17.401 ms 1 cleanup 100 sec test_26 fail mds1 5 times Failing mds1 on oleg405-server 0 cleanup 101 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 2012 47.622 19617.415 Close 1504 1.718 9.899 Rename 82 14.938 21.212 Unlink 386 4.786 17.931 Qpathinfo 1874 2.727 42.784 Qfileinfo 325 0.486 2.673 Qfsinfo 313 0.942 15.720 Sfileinfo 160 9.177 30.901 Find 699 2.327 11.367 WriteX 990 2.135 8.098 ReadX 3021 0.103 9.968 LockX 6 1.631 1.725 UnlockX 6 1.748 1.879 Flush 137 12.013 460.824 Throughput 0.584665 MB/sec 1 clients 1 procs max_latency=19617.426 ms stopping dbench on /mnt/lustre at Wed May 21 13:54:05 EDT 2025 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre Stopping /mnt/lustre-mds1 (opts:) on oleg405-server removed 'client.txt' /mnt/lustre dbench successfully finished 13:54:06 (1747850046) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:54:20 (1747850060) targets are mounted 13:54:20 (1747850060) facet_failover done striped dir -i0 -c2 -H fnv_1a_64 /mnt/lustre2/d26.replay-dual/run_dbench looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt oleg405-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 '/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 13:54:26 EDT 2025 waiting for dbench pid 10650 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 1 223 8.62 MB/sec warmup 1 sec latency 27.745 ms 1 474 8.28 MB/sec warmup 2 sec latency 18.573 ms 1 778 7.12 MB/sec warmup 3 sec latency 36.024 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 4288 1283400 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 3208 1284480 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 30652 3538440 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 17460 3588632 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 48112 7127072 1% /mnt/lustre 1 1029 5.72 MB/sec warmup 4 sec latency 31.582 ms 1 1406 5.20 MB/sec warmup 5 sec latency 17.322 ms 1 1684 4.37 MB/sec warmup 6 sec latency 32.328 ms 1 2018 3.79 MB/sec warmup 7 sec latency 17.391 ms test_26 fail mds2 6 times Failing mds2 on oleg405-server 1 2367 3.49 MB/sec warmup 8 sec latency 16.774 ms Stopping /mnt/lustre-mds2 (opts:) on oleg405-server 13:54:35 (1747850075) shut down facet: mds2 facet_host: oleg405-server facet_failover_host: oleg405-server 1 2436 3.12 MB/sec warmup 9 sec latency 691.219 ms 1 2436 2.81 MB/sec warmup 10 sec latency 1691.346 ms 1 2436 2.55 MB/sec warmup 11 sec latency 2691.472 ms 1 2436 2.34 MB/sec warmup 12 sec latency 3691.631 ms 1 2436 2.16 MB/sec warmup 13 sec latency 4691.774 ms 1 2436 2.01 MB/sec warmup 14 sec latency 5691.947 ms 1 2436 1.87 MB/sec warmup 15 sec latency 6692.098 ms 1 2436 1.76 MB/sec warmup 16 sec latency 7692.276 ms 1 2436 1.65 MB/sec warmup 17 sec latency 8692.472 ms 1 2436 1.56 MB/sec warmup 18 sec latency 9692.671 ms Failover mds2 to oleg405-server mount facets: mds2 1 2436 1.48 MB/sec warmup 19 sec latency 10692.784 ms 1 2436 0.00 MB/sec execute 1 sec latency 12693.009 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 2436 0.00 MB/sec execute 2 sec latency 13693.211 ms oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0001 13:54:49 (1747850089) targets are mounted 13:54:49 (1747850089) facet_failover done 1 2436 0.00 MB/sec execute 3 sec latency 14693.393 ms 1 2436 0.00 MB/sec execute 4 sec latency 15693.568 ms 1 2436 0.00 MB/sec execute 5 sec latency 16693.747 ms 1 2436 0.00 MB/sec execute 6 sec latency 17693.926 ms 1 2559 0.11 MB/sec execute 7 sec latency 18342.635 ms oleg405-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 2997 0.68 MB/sec execute 8 sec latency 19.818 ms 1 3527 1.14 MB/sec execute 9 sec latency 16.617 ms 1 3821 1.17 MB/sec execute 10 sec latency 14.501 ms 1 4041 1.09 MB/sec execute 11 sec latency 14.571 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2968 1284720 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2556 1285132 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 29488 3562784 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 14464 3580812 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 43952 7143596 1% /mnt/lustre 1 4289 1.02 MB/sec execute 12 sec latency 18.006 ms 1 4483 0.98 MB/sec execute 13 sec latency 252.106 ms 1 4743 1.00 MB/sec execute 14 sec latency 323.795 ms 1 5070 1.14 MB/sec execute 15 sec latency 25.527 ms test_26 fail mds1 7 times Failing mds1 on oleg405-server 1 5288 1.08 MB/sec execute 16 sec latency 26.047 ms Stopping /mnt/lustre-mds1 (opts:) on oleg405-server striped dir -i0 -c2 -H crush2 /mnt/lustre/d26.replay-dual/run_tar 1 5372 1.02 MB/sec execute 17 sec latency 636.400 ms 13:55:03 (1747850103) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server 1 5372 0.96 MB/sec execute 18 sec latency 1636.578 ms 1 5372 0.91 MB/sec execute 19 sec latency 2636.746 ms 1 5372 0.87 MB/sec execute 20 sec latency 3636.904 ms 1 5372 0.83 MB/sec execute 21 sec latency 4637.092 ms 1 5372 0.79 MB/sec execute 22 sec latency 5637.246 ms 1 5372 0.75 MB/sec execute 23 sec latency 6637.412 ms 1 5372 0.72 MB/sec execute 24 sec latency 7637.584 ms 1 5372 0.69 MB/sec execute 25 sec latency 8637.740 ms 1 5372 0.67 MB/sec execute 26 sec latency 9637.893 ms 1 5372 0.64 MB/sec execute 27 sec latency 10638.073 ms Failover mds1 to oleg405-server mount facets: mds1 1 5372 0.62 MB/sec execute 28 sec latency 11638.220 ms 1 5372 0.60 MB/sec execute 29 sec latency 12638.365 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 5372 0.58 MB/sec execute 30 sec latency 13638.534 ms oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:55:17 (1747850117) targets are mounted 13:55:17 (1747850117) facet_failover done 1 5372 0.56 MB/sec execute 31 sec latency 14638.705 ms 1 5372 0.54 MB/sec execute 32 sec latency 15638.862 ms 1 5372 0.53 MB/sec execute 33 sec latency 16639.036 ms 1 5372 0.51 MB/sec execute 34 sec latency 17639.228 ms 1 5372 0.50 MB/sec execute 35 sec latency 18639.364 ms oleg405-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 5583 0.49 MB/sec execute 36 sec latency 18855.860 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 5916 0.51 MB/sec execute 37 sec latency 14.861 ms 1 6176 0.53 MB/sec execute 38 sec latency 18.872 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 6800 0.66 MB/sec execute 39 sec latency 18.108 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Wed May 21 13:55:26 EDT 2025 with return code 0 10650 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 10650 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished PASS 26 (207s) == replay-dual test 28: lock replay should be ordered: waiting after granted ========================================================== 13:55:29 (1747850129) Waiting for MDT destroys to complete 1+0 records in 1+0 records out 4096 bytes (4.1 kB) copied, 0.00280596 s, 1.5 MB/s fail_loc=0x80000324 fail_loc=0x32a Failing ost1 on oleg405-server Stopping /mnt/lustre-ost1 (opts:) on oleg405-server 13:55:47 (1747850147) shut down facet: ost1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover ost1 to oleg405-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 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-OST0000 13:56:00 (1747850160) targets are mounted 13:56:00 (1747850160) facet_failover done 1+0 records in 1+0 records out 4096 bytes (4.1 kB) copied, 0.00346003 s, 1.2 MB/s oleg405-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 (38s) == replay-dual test 29: replay vs update with the same xid ========================================================== 13:56:07 (1747850167) SKIP: replay-dual test_29 needs >= 2 clients SKIP 29 (0s) == replay-dual test 30: layout lock replay is not blocked on IO ========================================================== 13:56:07 (1747850167) 10+0 records in 10+0 records out 40960 bytes (41 kB) copied, 0.00906347 s, 4.5 MB/s 10+0 records in 10+0 records out 40960 bytes (41 kB) copied, 0.0077194 s, 5.3 MB/s fail_loc=0x32e fail_val=4 Failing mds1 on oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 13:56:10 (1747850170) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server Failover mds1 to oleg405-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 13:56:23 (1747850183) targets are mounted 13:56:23 (1747850183) facet_failover done 160+0 records in 160+0 records out 81920 bytes (82 kB) copied, 20.7995 s, 3.9 kB/s oleg405-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 30 (25s) == replay-dual test 31: deadlock on file_remove_privs and occupied mod rpc slots ========================================================== 13:56:32 (1747850192) Failing ost1 on oleg405-server Stopping /mnt/lustre-ost1 (opts:) on oleg405-server 13:56:34 (1747850194) shut down facet: ost1 facet_host: oleg405-server facet_failover_host: oleg405-server Creating to objid 3073 on ost lustre-OST0000... total: 32 open/close in 0.18 seconds: 176.07 ops/second at_max=0 fail_loc=0x80001420 file /mnt/lustre2/d31.replay-dual/mdtdir/f31.replay-dual is ready Failover ost1 to oleg405-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 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-OST0000 13:56:47 (1747850207) targets are mounted 13:56:47 (1747850207) facet_failover done oleg405-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: 17779 17780 17785 17786 17787 17788 17789 17790 17791 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2400 1285288 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1984 1285704 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 473 261671 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 262144 439 261705 1% /mnt/lustre[OST:1] filesystem_summary: 523975 599 523376 1% /mnt/lustre at_max=600 PASS 31 (20s) == replay-dual test 32: gap in update llog shouldn't break recovery ========================================================== 13:56:52 (1747850212) fail_loc=0x0000131d fail_val=10 fail_loc=0x726 Stopping /mnt/lustre-mds2 (opts:) on oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server fail_loc=0 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0000 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0001 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2504 1285156 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2052 1285636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3084 7210956 1% /mnt/lustre PASS 32 (21s) == replay-dual test 33: Check for OBD_INCOMPAT_MULTI_RPCS in last_rcvd after abort_recovery ========================================================== 13:57:13 (1747850233) at_min=60 Stopping /mnt/lustre-mds2 (opts:) on oleg405-server last_rcvd in /dev/mapper/mds2_flakey: incompat = 0x61c Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0001 oleg405-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 oleg405-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 oleg405-server: oleg405-server.virtnet: executing _wait_recovery_complete *.lustre-MDT0001.recovery_status 1475 oleg405-server: *.lustre-MDT0001.recovery_status status: COMPLETE Stopping /mnt/lustre-mds2 (opts:) on oleg405-server last_rcvd in /dev/mapper/mds2_flakey: incompat = 0x61c Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 Started lustre-MDT0001 Starting client: oleg405-client.virtnet: -o user_xattr,flock 192.168.204.105@tcp:/lustre /mnt/lustre2 oleg405-client.virtnet: executing wait_import_state_mount FULL mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0001-mdc-*.mds_server_uuid in DISCONN FULL state after 3 sec affected facets: mds2 oleg405-server: oleg405-server.virtnet: executing _wait_recovery_complete *.lustre-MDT0001.recovery_status 1475 oleg405-server: *.lustre-MDT0001.recovery_status status: COMPLETE at_min=5 PASS 33 (34s) == replay-dual test complete, duration 2698 sec ========== 13:57:47 (1747850267) === replay-dual: start cleanup 13:57:48 (1747850268) === Stopping clients: oleg405-client.virtnet /mnt/lustre2 (opts:) Stopping client oleg405-client.virtnet /mnt/lustre2 opts: === replay-dual: finish cleanup 13:57:50 (1747850270) ===