-----============= acceptance-small: replay-dual ============----- Thu Sep 17 04:53:31 EDT 2026 MGS_OS_ID_LIKE=rhel centos fedora rocky MGS_OS_VERSION_ID=8.10 MGS_OS_ID=rocky MGS_OS_VERSION_CODE=134873088 MDS1_OS_VERSION_ID=8.10 MDS1_OS_VERSION_CODE=134873088 MDS1_OS_ID_LIKE=rhel centos fedora rocky MDS1_OS_ID=rocky OST1_OS_VERSION_CODE=134873088 OST1_OS_ID_LIKE=rhel centos fedora rocky OST1_OS_VERSION_ID=8.10 OST1_OS_ID=rocky CLIENT_OS_ID=rocky CLIENT_OS_VERSION_CODE=134873088 CLIENT_OS_VERSION_ID=8.10 CLIENT_OS_ID_LIKE=rhel centos fedora rocky oleg450-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 04:53:52 (1789635232) === Starting client oleg450-client.virtnet: -o user_xattr,flock 192.168.204.150@tcp:/lustre /mnt/lustre2 Mount client oleg450-client.virtnet: mount -t lustre -o user_xattr,flock 192.168.204.150@tcp:/lustre /mnt/lustre2 Started clients oleg450-client.virtnet: 192.168.204.150@tcp:/lustre on /mnt/lustre2 type lustre (rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose) oleg450-client.virtnet: executing check_config_client /mnt/lustre oleg450-client.virtnet: Checking config lustre mounted on /mnt/lustre Checking servers environments Checking clients oleg450-client.virtnet environments Using TIMEOUT=20 osc.lustre-OST0000-osc-ffff8f49593f2800.idle_timeout=debug osc.lustre-OST0000-osc-ffff8f496007d000.idle_timeout=debug osc.lustre-OST0001-osc-ffff8f49593f2800.idle_timeout=debug osc.lustre-OST0001-osc-ffff8f496007d000.idle_timeout=debug disable quota as required oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all osd-ldiskfs.track_declares_assert=1 === replay-dual: finish setup 04:54:39 (1789635279) === == replay-dual test 0a: expired recovery with lost client ========================================================== 04:54:40 (1789635280) Check file is LU482_FAILED=/tmp/replay-dual.lu482.pVbzMV UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1708 1269596 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1532 1269772 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre total: 50 open/close in 2.18 seconds: 22.93 ops/second fail_loc=0x80000514 Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 04:54:56 (1789635296) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 04:55:32 (1789635332) targets are mounted 04:55:32 (1789635332) facet_failover done Starting client: oleg450-client.virtnet: -o user_xattr,flock 192.168.204.150@tcp:/lustre /mnt/lustre2 - unlinked 0 (time 1789635447 ; total 0 ; last 0) total: 50 unlinks in 2 seconds: 25.000000 unlinks/second PASS 0a (175s) == replay-dual test 0b: lost client during waiting for next transno ========================================================== 04:57:36 (1789635456) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1676 1269628 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1532 1269772 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 04:57:54 (1789635474) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 04:58:29 (1789635509) targets are mounted 04:58:29 (1789635509) facet_failover done Starting client: oleg450-client.virtnet: -o user_xattr,flock 192.168.204.150@tcp:/lustre /mnt/lustre Starting client: oleg450-client.virtnet: -o user_xattr,flock 192.168.204.150@tcp:/lustre /mnt/lustre2 PASS 0b (226s) == replay-dual test 1: |X| simple create ================= 05:01:22 (1789635682) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1676 1269628 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1532 1269772 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 05:01:39 (1789635699) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:02:16 (1789635736) targets are mounted 05:02:16 (1789635736) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 1 (73s) == replay-dual test 2: |X| mkdir adir ==================== 05:02:35 (1789635755) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1676 1269628 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1532 1269772 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 05:02:49 (1789635769) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:03:23 (1789635803) targets are mounted 05:03:23 (1789635803) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 2 (66s) == replay-dual test 3: |X| mkdir adir, mkdir adir/bdir === 05:03:41 (1789635821) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1676 1269628 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1532 1269772 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 05:03:56 (1789635836) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:04:31 (1789635871) targets are mounted 05:04:31 (1789635871) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 3 (67s) == replay-dual test 4: |X| mkdir adir (-EEXIST), mkdir adir/bdir ========================================================== 05:04:48 (1789635888) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1852 1269452 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre mkdir: cannot create directory '/mnt/lustre/adir': File exists Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 05:05:02 (1789635902) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:05:38 (1789635938) targets are mounted 05:05:38 (1789635938) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 4 (64s) == replay-dual test 5: open, unlink |X| close ============ 05:05:52 (1789635952) multiop /mnt/lustre2/a vo_tSc TMPPIPE=/tmp/multiop_open_wait_pipe.8254 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1788 1269516 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 05:06:03 (1789635963) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:06:35 (1789635995) targets are mounted 05:06:35 (1789635995) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 5 (56s) == replay-dual test 6: open1, open2, unlink |X| close1 [fail mds1] close2 ========================================================== 05:06:48 (1789636008) multiop /mnt/lustre2/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8254 multiop /mnt/lustre/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8254 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1788 1269516 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 05:07:00 (1789636020) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:07:32 (1789636052) targets are mounted 05:07:32 (1789636052) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 6 (57s) == replay-dual test 8: replay of resent request ========== 05:07:45 (1789636065) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1788 1269516 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre fail_loc=0x119 fail_loc=0 Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 05:08:14 (1789636094) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:08:45 (1789636125) targets are mounted 05:08:45 (1789636125) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 8 (73s) == replay-dual test 9: resending a replayed create ======= 05:08:58 (1789636138) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1788 1269516 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre fail_loc=0x80000119 Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 05:09:09 (1789636149) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:09:43 (1789636183) targets are mounted 05:09:43 (1789636183) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec fail_loc=0 PASS 9 (70s) == replay-dual test 10: resending a replayed unlink ====== 05:10:08 (1789636208) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1788 1269516 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre fail_loc=0x80000119 Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 05:10:21 (1789636221) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:10:56 (1789636256) targets are mounted 05:10:56 (1789636256) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec fail_loc=0 PASS 10 (71s) == replay-dual test 11: both clients timeout during replay ========================================================== 05:11:20 (1789636280) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1788 1269516 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre fail_loc=0x0119 Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 05:11:32 (1789636292) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:12:03 (1789636323) targets are mounted 05:12:03 (1789636323) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount FULL mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 7 sec fail_loc=0 PASS 11 (63s) == replay-dual test 12: open resend timeout ============== 05:12:22 (1789636342) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1788 1269516 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre multiop /mnt/lustre/f12.replay-dual vmo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8254 fail_loc=0x80000302 Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 05:12:34 (1789636354) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:13:07 (1789636387) targets are mounted 05:13:07 (1789636387) facet_failover done fail_loc=0 /mnt/lustre/f12.replay-dual /mnt/lustre/f12.replay-dual has type file OK PASS 12 (65s) == replay-dual test 13: close resend timeout ============= 05:13:28 (1789636408) multiop /mnt/lustre/f13.replay-dual vmo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8254 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1788 1269516 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre fail_loc=0x80000115 Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 05:13:37 (1789636417) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:14:10 (1789636450) targets are mounted 05:14:10 (1789636450) facet_failover done fail_loc=0 /mnt/lustre/f13.replay-dual /mnt/lustre/f13.replay-dual has type file OK PASS 13 (64s) SKIP: replay-dual test_14b skipping ALWAYS excluded test 14b == replay-dual test 15a: timeout waiting for lost client during replay, 1 client completes ========================================================== 05:14:33 (1789636473) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1788 1269516 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre total: 25 open/close in 0.81 seconds: 30.80 ops/second total: 1 open/close in 0.04 seconds: 23.93 ops/second Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 05:14:45 (1789636485) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:15:19 (1789636519) targets are mounted 05:15:19 (1789636519) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec - unlinked 0 (time 1789636593 ; total 1 ; last 1) total: 25 unlinks in 1 seconds: 25.000000 unlinks/second Starting client: oleg450-client.virtnet: -o user_xattr,flock 192.168.204.150@tcp:/lustre /mnt/lustre2 PASS 15a (125s) == replay-dual test 15c: remove multiple OST orphans ===== 05:16:38 (1789636598) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1788 1269516 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 05:18:26 (1789636706) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:18:57 (1789636737) targets are mounted 05:18:57 (1789636737) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec Starting client: oleg450-client.virtnet: -o user_xattr,flock 192.168.204.150@tcp:/lustre /mnt/lustre2 PASS 15c (217s) == replay-dual test 16: fail MDS during recovery (3571) == 05:20:16 (1789636816) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1788 1269516 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre total: 25 open/close in 0.94 seconds: 26.48 ops/second total: 1 open/close in 0.03 seconds: 36.45 ops/second Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 05:20:28 (1789636828) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:20:50 (1789636850) targets are mounted 05:20:50 (1789636850) facet_failover done Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 05:21:14 (1789636874) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:21:33 (1789636893) targets are mounted 05:21:33 (1789636893) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec - unlinked 0 (time 1789636968 ; total 0 ; last 0) total: 25 unlinks in 1 seconds: 25.000000 unlinks/second Starting client: oleg450-client.virtnet: -o user_xattr,flock 192.168.204.150@tcp:/lustre /mnt/lustre2 PASS 16 (157s) == replay-dual test 17: fail OST during recovery (3571) == 05:22:53 (1789636973) total: 25 open/close in 0.72 seconds: 34.92 ops/second total: 1 open/close in 0.04 seconds: 25.11 ops/second UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1788 1269516 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing ost1 on oleg450-server Stopping /mnt/lustre-ost1 (opts:) on oleg450-server 05:23:04 (1789636984) shut down facet: ost1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover ost1 to oleg450-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 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-OST0000 05:23:27 (1789637007) targets are mounted 05:23:27 (1789637007) facet_failover done Failing ost1 on oleg450-server Stopping /mnt/lustre-ost1 (opts:) on oleg450-server 05:23:50 (1789637030) shut down facet: ost1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover ost1 to oleg450-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 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-OST0000 05:24:10 (1789637050) targets are mounted 05:24:10 (1789637050) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid 1475 0 osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in FULL state after 0 sec - unlinked 0 (time 1789637123 ; total 0 ; last 0) total: 25 unlinks in 1 seconds: 25.000000 unlinks/second Starting client: oleg450-client.virtnet: -o user_xattr,flock 192.168.204.150@tcp:/lustre /mnt/lustre2 PASS 17 (154s) == replay-dual test 18: ldlm_handle_enqueue succeeds on evicted export (3822) ========================================================== 05:25:27 (1789637127) debug=+dlmtrace fail_loc=0x8000030b using seed 2117216637 running for 500 iterations total: 500 stats in 1 seconds: 500.000000 stats/second ldlm.namespaces.MGC192.168.204.150@tcp.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffff8f4944dad000.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffff8f4950f32000.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0001-mdc-ffff8f4944dad000.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0001-mdc-ffff8f4950f32000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffff8f4944dad000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffff8f4950f32000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffff8f4944dad000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffff8f4950f32000.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.MGC192.168.204.150@tcp.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffff8f4944dad000.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffff8f4950f32000.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0001-mdc-ffff8f4944dad000.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0001-mdc-ffff8f4950f32000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffff8f4944dad000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffff8f4950f32000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffff8f4944dad000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffff8f4950f32000.early_lock_cancel=1 fail_loc=0 fail_loc=0 PASS 18 (53s) == replay-dual test 19: resend of open request =========== 05:26:20 (1789637180) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1792 1269512 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre fail_loc=0x157 - open/close 0 (time 1789637276.85 total 87.39 last 0.00) total: 1 open/close in 87.39 seconds: 0.01 ops/second fail_loc=0 Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 05:28:00 (1789637280) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:28:31 (1789637311) targets are mounted 05:28:31 (1789637311) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 19 (142s) == replay-dual test 20: recovery time is not increasing == 05:28:42 (1789637322) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1792 1269512 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 05:28:51 (1789637331) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:29:12 (1789637352) targets are mounted 05:29:12 (1789637352) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec Starting client: oleg450-client.virtnet: -o user_xattr,flock 192.168.204.150@tcp:/lustre /mnt/lustre2 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1792 1269512 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 05:31:46 (1789637506) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:32:17 (1789637537) targets are mounted 05:32:17 (1789637537) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec Starting client: oleg450-client.virtnet: -o user_xattr,flock 192.168.204.150@tcp:/lustre /mnt/lustre2 PASS 20 (382s) == replay-dual test 21a: commit on sharing =============== 05:35:05 (1789637705) mdt.lustre-MDT0000.commit_on_sharing=1 mdt.lustre-MDT0001.commit_on_sharing=1 Replay barrier on lustre-MDT0000 Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 05:35:34 (1789637734) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:36:10 (1789637770) targets are mounted 05:36:10 (1789637770) facet_failover done Starting client: oleg450-client.virtnet: -o user_xattr,flock 192.168.204.150@tcp:/lustre /mnt/lustre2 mdt.lustre-MDT0000.commit_on_sharing=0 mdt.lustre-MDT0001.commit_on_sharing=0 PASS 21a (206s) 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 ========================================================== 05:38:33 (1789637913) fail_loc=0x119 Failing mds2 on oleg450-server Stopping /mnt/lustre-mds2 (opts:) on oleg450-server 05:38:41 (1789637921) shut down facet: mds2 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds2 to oleg450-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0001 05:39:06 (1789637946) targets are mounted 05:39:06 (1789637946) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1800 1269504 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1672 1269632 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.11 seconds: 17.92 ops/second total: 2 open/close in 0.04 seconds: 47.97 ops/second Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 05:39:29 (1789637969) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:40:03 (1789638003) targets are mounted 05:40:03 (1789638003) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 22a (108s) == replay-dual test 22b: c1 lfs mkdir -i 1 d1, M1 drop reply & fail M0/M1, c2 mkdir d1/dir ========================================================== 05:40:21 (1789638021) fail_loc=0x119 Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server Failing mds2 on oleg450-server Stopping /mnt/lustre-mds2 (opts:) on oleg450-server 05:40:35 (1789638035) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server facet: mds2 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Failover mds2 to oleg450-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 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 Started lustre-MDT0001 05:41:06 (1789638066) targets are mounted 05:41:06 (1789638066) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1800 1269504 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1672 1269632 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.18 seconds: 11.22 ops/second total: 2 open/close in 0.08 seconds: 26.47 ops/second Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 05:41:43 (1789638103) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:42:33 (1789638153) targets are mounted 05:42:33 (1789638153) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 22b (151s) == replay-dual test 22c: c1 lfs mkdir -i 1 d1, M1 drop update & fail M1, c2 mkdir d1/dir ========================================================== 05:42:52 (1789638172) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 05:43:02 (1789638182) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:43:34 (1789638214) targets are mounted 05:43:34 (1789638214) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1800 1269504 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1684 1269620 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.13 seconds: 14.96 ops/second total: 2 open/close in 0.04 seconds: 44.83 ops/second Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 05:44:02 (1789638242) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:44:51 (1789638291) targets are mounted 05:44:51 (1789638291) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 22c (137s) == replay-dual test 22d: c1 lfs mkdir -i 1 d1, M1 drop update & fail M0/M1,c2 mkdir d1/dir ========================================================== 05:45:09 (1789638309) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server Failing mds2 on oleg450-server Stopping /mnt/lustre-mds2 (opts:) on oleg450-server 05:45:34 (1789638334) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server facet: mds2 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Failover mds2 to oleg450-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 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0001 pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:46:19 (1789638379) targets are mounted 05:46:19 (1789638379) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1764 1269540 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1636 1269668 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.09 seconds: 22.36 ops/second total: 2 open/close in 0.03 seconds: 57.83 ops/second Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 05:46:46 (1789638406) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:47:21 (1789638441) targets are mounted 05:47:21 (1789638441) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 22d (149s) == replay-dual test 23a: c1 rmdir d1, M1 drop reply and fail, client2 mkdir d1 ========================================================== 05:47:38 (1789638458) fail_loc=0x119 fail_loc=0 Failing mds2 on oleg450-server Stopping /mnt/lustre-mds2 (opts:) on oleg450-server 05:47:53 (1789638473) shut down facet: mds2 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds2 to oleg450-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0001 05:48:17 (1789638497) targets are mounted 05:48:17 (1789638497) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1796 1269508 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.06 seconds: 31.42 ops/second Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 05:48:44 (1789638524) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:49:18 (1789638558) targets are mounted 05:49:18 (1789638558) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 23a (118s) == replay-dual test 23b: c1 rmdir d1, M1 drop reply and fail M0/M1, c2 mkdir d1 ========================================================== 05:49:36 (1789638576) fail_loc=0x119 fail_loc=0 Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server Failing mds2 on oleg450-server Stopping /mnt/lustre-mds2 (opts:) on oleg450-server 05:49:54 (1789638594) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server facet: mds2 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Failover mds2 to oleg450-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 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 05:50:24 (1789638624) targets are mounted 05:50:24 (1789638624) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1796 1269508 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1668 1269636 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.11 seconds: 18.86 ops/second Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 05:50:53 (1789638653) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:51:26 (1789638686) targets are mounted 05:51:26 (1789638686) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 23b (128s) == replay-dual test 23c: c1 rmdir d1, M0 drop update reply and fail M0, c2 mkdir d1 ========================================================== 05:51:44 (1789638704) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 05:51:53 (1789638713) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:52:17 (1789638737) targets are mounted 05:52:17 (1789638737) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1796 1269508 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1680 1269624 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.09 seconds: 23.52 ops/second Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 05:52:42 (1789638762) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:53:18 (1789638798) targets are mounted 05:53:18 (1789638798) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 23c (113s) == replay-dual test 23d: c1 rmdir d1, M0 drop update reply and fail M0/M1, c2 mkdir d1 ========================================================== 05:53:37 (1789638817) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server Failing mds2 on oleg450-server Stopping /mnt/lustre-mds2 (opts:) on oleg450-server 05:54:00 (1789638840) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server facet: mds2 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Failover mds2 to oleg450-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 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 Started lustre-MDT0001 05:54:47 (1789638887) targets are mounted 05:54:47 (1789638887) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1760 1269544 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.09 seconds: 21.29 ops/second Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 05:55:13 (1789638913) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 05:55:49 (1789638949) targets are mounted 05:55:49 (1789638949) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 23d (148s) == replay-dual test 24: reconstruct on non-existing object ========================================================== 05:56:05 (1789638965) fail_loc=0x119 fail_loc=0 truncate: cannot truncate '/mnt/lustre/f24.replay-dual' to length 100: No such file or directory PASS 24 (94s) == replay-dual test 25: replay|resend ==================== 05:57:39 (1789639059) 1+0 records in 1+0 records out 512 bytes copied, 0.0102357 s, 50.0 kB/s fail_loc=0x304 fail_loc=0x80000325 Failing ost1 on oleg450-server Stopping /mnt/lustre-ost1 (opts:) on oleg450-server 05:57:46 (1789639066) shut down facet: ost1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover ost1 to oleg450-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 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-OST0000 05:58:10 (1789639090) targets are mounted 05:58:10 (1789639090) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid 1475 0 osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in FULL state after 0 sec /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 7016: 64261 Terminated LUSTRE="/home/green/git/lustre-release/lustre" bash -c "multiop /mnt/lustre2/f25.replay-dual Ow512" fail_loc=0 PASS 25 (45s) == replay-dual test 26: dbench and tar with mds failover ========================================================== 05:58:24 (1789639104) Starting client oleg450-client.virtnet: -o user_xattr,flock 192.168.204.150@tcp:/lustre /mnt/lustre Started clients oleg450-client.virtnet: 192.168.204.150@tcp:/lustre on /mnt/lustre type lustre (rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose) Started tar loop with pid 65690 Started dbench loop with 65691 striped dir -i0 -c2 -H crush2 /mnt/lustre2/d26.replay-dual/run_dbench striped dir -i0 -c2 -H all_char /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 Thu Sep 17 05:58:28 EDT 2026 waiting for dbench pid 65741 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 1940 1269364 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1756 1269548 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1564 3579572 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3108 7185048 1% /mnt/lustre 1 31 1.05 MB/sec warmup 1 sec latency 55.997 ms 1 111 2.62 MB/sec warmup 2 sec latency 108.592 ms 1 148 2.09 MB/sec warmup 3 sec latency 153.460 ms 1 184 1.84 MB/sec warmup 4 sec latency 153.318 ms 1 223 1.72 MB/sec warmup 5 sec latency 273.937 ms 1 270 1.69 MB/sec warmup 6 sec latency 132.802 ms 1 310 1.62 MB/sec warmup 7 sec latency 103.168 ms 1 349 1.56 MB/sec warmup 8 sec latency 109.910 ms test_26 fail mds1 1 times 1 397 1.56 MB/sec warmup 9 sec latency 145.182 ms Failing mds1 on oleg450-server 1 438 1.53 MB/sec warmup 10 sec latency 126.122 ms Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 1 480 1.51 MB/sec warmup 11 sec latency 172.874 ms 1 513 1.47 MB/sec warmup 12 sec latency 121.381 ms 1 591 1.57 MB/sec warmup 13 sec latency 123.865 ms 05:58:42 (1789639122) shut down 1 606 1.49 MB/sec warmup 14 sec latency 843.682 ms facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server 1 606 1.39 MB/sec warmup 15 sec latency 1843.877 ms 1 606 1.31 MB/sec warmup 16 sec latency 2846.180 ms 1 606 1.23 MB/sec warmup 17 sec latency 3846.390 ms 1 606 1.16 MB/sec warmup 18 sec latency 4846.766 ms 1 606 1.10 MB/sec warmup 19 sec latency 5847.150 ms 1 606 0.00 MB/sec execute 1 sec latency 7847.763 ms 1 606 0.00 MB/sec execute 2 sec latency 8848.434 ms 1 606 0.00 MB/sec execute 3 sec latency 9849.473 ms 1 606 0.00 MB/sec execute 4 sec latency 10849.773 ms Failover mds1 to oleg450-server mount facets: mds1 1 606 0.00 MB/sec execute 5 sec latency 11852.993 ms 1 606 0.00 MB/sec execute 6 sec latency 12853.292 ms 1 606 0.00 MB/sec execute 7 sec latency 13853.604 ms 1 606 0.00 MB/sec execute 8 sec latency 14853.964 ms 1 606 0.00 MB/sec execute 9 sec latency 15855.397 ms 1 606 0.00 MB/sec execute 10 sec latency 16855.566 ms 1 606 0.00 MB/sec execute 11 sec latency 17857.026 ms 1 606 0.00 MB/sec execute 12 sec latency 18857.245 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 606 0.00 MB/sec execute 13 sec latency 19857.461 ms 1 606 0.00 MB/sec execute 14 sec latency 20857.913 ms 1 606 0.00 MB/sec execute 15 sec latency 21858.145 ms 1 606 0.00 MB/sec execute 16 sec latency 22858.400 ms 1 606 0.00 MB/sec execute 17 sec latency 23858.707 ms 1 606 0.00 MB/sec execute 18 sec latency 24858.919 ms 1 606 0.00 MB/sec execute 19 sec latency 25859.252 ms 1 606 0.00 MB/sec execute 20 sec latency 26859.549 ms 1 606 0.00 MB/sec execute 21 sec latency 27859.757 ms 1 606 0.00 MB/sec execute 22 sec latency 28862.665 ms 1 606 0.00 MB/sec execute 23 sec latency 29862.865 ms 1 606 0.00 MB/sec execute 24 sec latency 30865.385 ms 1 606 0.00 MB/sec execute 25 sec latency 31865.632 ms oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all 1 606 0.00 MB/sec execute 26 sec latency 32867.051 ms pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 1 606 0.00 MB/sec execute 27 sec latency 33869.902 ms Started lustre-MDT0000 05:59:16 (1789639156) targets are mounted 05:59:16 (1789639156) facet_failover done 1 606 0.00 MB/sec execute 28 sec latency 34870.028 ms 1 606 0.00 MB/sec execute 29 sec latency 35870.233 ms 1 607 0.00 MB/sec execute 30 sec latency 36856.353 ms 1 676 0.01 MB/sec execute 31 sec latency 64.355 ms 1 718 0.01 MB/sec execute 32 sec latency 94.918 ms 1 765 0.01 MB/sec execute 33 sec latency 102.459 ms oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 804 0.01 MB/sec execute 34 sec latency 97.175 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 863 0.02 MB/sec execute 35 sec latency 79.399 ms 1 884 0.02 MB/sec execute 36 sec latency 371.233 ms 1 888 0.02 MB/sec execute 37 sec latency 1173.134 ms 1 919 0.02 MB/sec execute 38 sec latency 133.889 ms 1 969 0.02 MB/sec execute 39 sec latency 101.486 ms 1 1028 0.05 MB/sec execute 40 sec latency 111.234 ms 1 1092 0.05 MB/sec execute 41 sec latency 81.810 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2108 1269196 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1928 1269376 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 44844 3560520 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 14128 3592556 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 58972 7153076 1% /mnt/lustre 1 1147 0.05 MB/sec execute 42 sec latency 99.077 ms 1 1193 0.05 MB/sec execute 43 sec latency 121.450 ms 1 1242 0.05 MB/sec execute 44 sec latency 75.532 ms 1 1377 0.11 MB/sec execute 45 sec latency 103.135 ms 1 1421 0.11 MB/sec execute 46 sec latency 83.338 ms 1 1467 0.11 MB/sec execute 47 sec latency 122.586 ms 1 1504 0.11 MB/sec execute 48 sec latency 338.915 ms 1 1560 0.10 MB/sec execute 49 sec latency 95.158 ms test_26 fail mds2 2 times 1 1605 0.10 MB/sec execute 50 sec latency 61.277 ms 1 1651 0.10 MB/sec execute 51 sec latency 81.910 ms Failing mds2 on oleg450-server Stopping /mnt/lustre-mds2 (opts:) on oleg450-server 1 1689 0.10 MB/sec execute 52 sec latency 104.036 ms 1 1762 0.10 MB/sec execute 53 sec latency 103.502 ms 1 1845 0.10 MB/sec execute 54 sec latency 81.074 ms 1 1924 0.10 MB/sec execute 55 sec latency 68.350 ms 1 2010 0.10 MB/sec execute 56 sec latency 58.694 ms 1 2083 0.10 MB/sec execute 57 sec latency 85.013 ms 1 2156 0.10 MB/sec execute 58 sec latency 97.896 ms 1 2202 0.10 MB/sec execute 59 sec latency 95.544 ms 1 2259 0.10 MB/sec execute 60 sec latency 404.553 ms 05:59:49 (1789639189) shut down facet: mds2 facet_host: oleg450-server facet_failover_host: oleg450-server 1 2259 0.10 MB/sec execute 61 sec latency 1404.798 ms 1 2259 0.09 MB/sec execute 62 sec latency 2405.033 ms 1 2259 0.09 MB/sec execute 63 sec latency 3405.701 ms 1 2259 0.09 MB/sec execute 64 sec latency 4405.916 ms 1 2259 0.09 MB/sec execute 65 sec latency 5406.116 ms 1 2259 0.09 MB/sec execute 66 sec latency 6406.455 ms 1 2259 0.09 MB/sec execute 67 sec latency 7406.693 ms 1 2259 0.09 MB/sec execute 68 sec latency 8406.933 ms 1 2259 0.08 MB/sec execute 69 sec latency 9407.116 ms 1 2259 0.08 MB/sec execute 70 sec latency 10407.316 ms Failover mds2 to oleg450-server mount facets: mds2 1 2259 0.08 MB/sec execute 71 sec latency 11407.510 ms 1 2259 0.08 MB/sec execute 72 sec latency 12407.713 ms 1 2259 0.08 MB/sec execute 73 sec latency 13408.005 ms 1 2259 0.08 MB/sec execute 74 sec latency 14411.373 ms 1 2259 0.08 MB/sec execute 75 sec latency 15411.633 ms 1 2259 0.08 MB/sec execute 76 sec latency 16411.859 ms 1 2259 0.08 MB/sec execute 77 sec latency 17415.447 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 2259 0.07 MB/sec execute 78 sec latency 18415.800 ms 1 2259 0.07 MB/sec execute 79 sec latency 19420.122 ms 1 2259 0.07 MB/sec execute 80 sec latency 20420.345 ms 1 2259 0.07 MB/sec execute 81 sec latency 21426.978 ms 1 2259 0.07 MB/sec execute 82 sec latency 22427.296 ms oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all 1 2259 0.07 MB/sec execute 83 sec latency 23427.509 ms pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0001 06:00:12 (1789639212) targets are mounted 06:00:12 (1789639212) facet_failover done 1 2259 0.07 MB/sec execute 84 sec latency 24427.784 ms 1 2259 0.07 MB/sec execute 85 sec latency 25428.274 ms 1 2336 0.08 MB/sec execute 86 sec latency 25803.212 ms 1 2381 0.08 MB/sec execute 87 sec latency 105.619 ms 1 2428 0.08 MB/sec execute 88 sec latency 90.379 ms 1 2485 0.09 MB/sec execute 89 sec latency 83.918 ms oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 1 2582 0.09 MB/sec execute 90 sec latency 95.301 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 2747 0.12 MB/sec execute 91 sec latency 81.650 ms 1 2884 0.12 MB/sec execute 92 sec latency 87.615 ms 1 2976 0.13 MB/sec execute 93 sec latency 77.360 ms 1 3025 0.13 MB/sec execute 94 sec latency 92.257 ms 1 3246 0.15 MB/sec execute 95 sec latency 68.732 ms 1 3353 0.15 MB/sec execute 96 sec latency 54.416 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2288 1269016 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2196 1269108 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 46688 3558844 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 22528 3581916 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 69216 7140760 1% /mnt/lustre 1 3497 0.18 MB/sec execute 97 sec latency 83.805 ms 1 3572 0.18 MB/sec execute 98 sec latency 65.436 ms 1 3641 0.18 MB/sec execute 99 sec latency 78.678 ms 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec 1 cleanup 103 sec 0 cleanup 104 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 471 94.787 25803.197 Close 392 9.944 103.402 Rename 25 72.872 121.419 Unlink 59 20.864 40.393 Qpathinfo 468 92.420 36856.331 Qfileinfo 96 1.559 16.805 Qfsinfo 86 2.314 25.891 Sfileinfo 50 51.395 118.434 Find 191 8.804 45.570 WriteX 277 10.367 146.593 ReadX 938 1.060 68.978 LockX 2 8.086 8.821 UnlockX 2 8.983 11.357 Flush 43 46.913 133.872 Throughput 0.178171 MB/sec 1 clients 1 procs max_latency=36856.353 ms stopping dbench on /mnt/lustre at Thu Sep 17 06:00:32 EDT 2026 with return code 0 test_26 fail mds1 3 times clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished Failing mds1 on oleg450-server striped dir -i0 -c2 -H crush /mnt/lustre2/d26.replay-dual/run_dbench Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 06:00:37 (1789639237) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 06:01:10 (1789639270) targets are mounted 06:01:10 (1789639270) facet_failover done 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 Thu Sep 17 06:01:14 EDT 2026 waiting for dbench pid 68555 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 oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 31 1.04 MB/sec warmup 1 sec latency 98.162 ms 1 109 2.58 MB/sec warmup 2 sec latency 122.432 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 143 2.02 MB/sec warmup 3 sec latency 146.808 ms 1 184 1.84 MB/sec warmup 4 sec latency 112.443 ms 1 222 1.72 MB/sec warmup 5 sec latency 341.479 ms 1 260 1.63 MB/sec warmup 6 sec latency 141.343 ms 1 304 1.60 MB/sec warmup 7 sec latency 107.894 ms 1 349 1.56 MB/sec warmup 8 sec latency 97.488 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2804 1268500 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2628 1268676 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 12940 3593628 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 42216 3552464 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 55156 7146092 1% /mnt/lustre 1 397 1.56 MB/sec warmup 9 sec latency 144.880 ms 1 444 1.56 MB/sec warmup 10 sec latency 121.303 ms 1 488 1.54 MB/sec warmup 11 sec latency 124.809 ms 1 530 1.53 MB/sec warmup 12 sec latency 129.324 ms 1 600 1.61 MB/sec warmup 13 sec latency 432.628 ms 1 600 1.50 MB/sec warmup 14 sec latency 1432.861 ms 1 609 1.40 MB/sec warmup 15 sec latency 2195.033 ms 1 656 1.31 MB/sec warmup 16 sec latency 148.937 ms 1 708 1.25 MB/sec warmup 17 sec latency 76.052 ms test_26 fail mds2 4 times 1 740 1.18 MB/sec warmup 18 sec latency 139.617 ms 1 776 1.12 MB/sec warmup 19 sec latency 219.543 ms Failing mds2 on oleg450-server 1 815 0.01 MB/sec execute 1 sec latency 188.600 ms Stopping /mnt/lustre-mds2 (opts:) on oleg450-server 1 857 0.05 MB/sec execute 2 sec latency 155.846 ms 1 878 0.06 MB/sec execute 3 sec latency 184.902 ms 1 884 0.05 MB/sec execute 4 sec latency 665.514 ms 1 884 0.04 MB/sec execute 5 sec latency 1665.764 ms 1 885 0.03 MB/sec execute 6 sec latency 2435.693 ms 1 892 0.03 MB/sec execute 7 sec latency 732.869 ms 1 914 0.04 MB/sec execute 8 sec latency 215.284 ms 06:01:42 (1789639302) shut down facet: mds2 facet_host: oleg450-server facet_failover_host: oleg450-server 1 933 0.03 MB/sec execute 9 sec latency 193.424 ms 1 970 0.03 MB/sec execute 10 sec latency 131.543 ms 1 994 0.04 MB/sec execute 11 sec latency 140.131 ms 1 995 0.04 MB/sec execute 12 sec latency 985.980 ms 1 995 0.03 MB/sec execute 13 sec latency 1992.031 ms 1 995 0.03 MB/sec execute 14 sec latency 2993.950 ms 1 995 0.03 MB/sec execute 15 sec latency 4000.677 ms 1 995 0.03 MB/sec execute 16 sec latency 5001.621 ms 1 995 0.03 MB/sec execute 17 sec latency 6003.216 ms 1 995 0.02 MB/sec execute 18 sec latency 7011.876 ms Failover mds2 to oleg450-server mount facets: mds2 1 995 0.02 MB/sec execute 19 sec latency 8018.301 ms 1 995 0.02 MB/sec execute 20 sec latency 9018.825 ms 1 995 0.02 MB/sec execute 21 sec latency 10019.342 ms 1 995 0.02 MB/sec execute 22 sec latency 11023.597 ms 1 995 0.02 MB/sec execute 23 sec latency 12024.174 ms 1 995 0.02 MB/sec execute 24 sec latency 13024.516 ms 1 995 0.02 MB/sec execute 25 sec latency 14026.230 ms 1 995 0.02 MB/sec execute 26 sec latency 15027.343 ms 1 995 0.02 MB/sec execute 27 sec latency 16027.951 ms 1 995 0.02 MB/sec execute 28 sec latency 17029.793 ms 1 995 0.01 MB/sec execute 29 sec latency 18030.165 ms 1 995 0.01 MB/sec execute 30 sec latency 19031.168 ms 1 995 0.01 MB/sec execute 31 sec latency 20031.373 ms 1 995 0.01 MB/sec execute 32 sec latency 21032.639 ms 1 995 0.01 MB/sec execute 33 sec latency 22033.101 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 995 0.01 MB/sec execute 34 sec latency 23033.474 ms 1 995 0.01 MB/sec execute 35 sec latency 24034.643 ms 1 995 0.01 MB/sec execute 36 sec latency 25035.056 ms 1 995 0.01 MB/sec execute 37 sec latency 26035.464 ms 1 995 0.01 MB/sec execute 38 sec latency 27036.001 ms 1 995 0.01 MB/sec execute 39 sec latency 28036.203 ms 1 995 0.01 MB/sec execute 40 sec latency 29038.471 ms oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all 1 995 0.01 MB/sec execute 41 sec latency 30038.817 ms 1 995 0.01 MB/sec execute 42 sec latency 31039.012 ms pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 1 995 0.01 MB/sec execute 43 sec latency 32039.582 ms Started lustre-MDT0001 06:02:18 (1789639338) targets are mounted 06:02:18 (1789639338) facet_failover done 1 995 0.01 MB/sec execute 44 sec latency 33040.598 ms 1 1057 0.03 MB/sec execute 45 sec latency 33048.662 ms 1 1103 0.03 MB/sec execute 46 sec latency 88.766 ms 1 1147 0.03 MB/sec execute 47 sec latency 118.218 ms 1 1190 0.03 MB/sec execute 48 sec latency 100.856 ms 1 1231 0.03 MB/sec execute 49 sec latency 85.078 ms 1 1268 0.03 MB/sec execute 50 sec latency 141.989 ms oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 1 1403 0.09 MB/sec execute 51 sec latency 120.857 ms 1 1428 0.09 MB/sec execute 52 sec latency 155.914 ms 1 1465 0.09 MB/sec execute 53 sec latency 141.998 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 1497 0.08 MB/sec execute 54 sec latency 372.572 ms 1 1554 0.08 MB/sec execute 55 sec latency 99.521 ms 1 1618 0.08 MB/sec execute 56 sec latency 86.359 ms 1 1653 0.08 MB/sec execute 57 sec latency 155.998 ms 1 1692 0.08 MB/sec execute 58 sec latency 164.241 ms 1 1762 0.08 MB/sec execute 59 sec latency 66.402 ms 1 1821 0.08 MB/sec execute 60 sec latency 102.631 ms 1 1862 0.08 MB/sec execute 61 sec latency 101.183 ms 1 1936 0.08 MB/sec execute 62 sec latency 80.670 ms 1 1996 0.08 MB/sec execute 63 sec latency 101.060 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 2087 0.08 MB/sec execute 64 sec latency 86.390 ms 1 2145 0.08 MB/sec execute 65 sec latency 84.833 ms 1 2184 0.08 MB/sec execute 66 sec latency 122.446 ms 1 2248 0.08 MB/sec execute 67 sec latency 94.628 ms 1 2334 0.09 MB/sec execute 68 sec latency 83.807 ms 1 2359 0.09 MB/sec execute 69 sec latency 139.244 ms 1 2394 0.09 MB/sec execute 70 sec latency 118.913 ms 1 2424 0.09 MB/sec execute 71 sec latency 92.516 ms 1 2465 0.10 MB/sec execute 72 sec latency 118.876 ms 1 2555 0.10 MB/sec execute 73 sec latency 71.990 ms 1 2596 0.10 MB/sec execute 74 sec latency 114.340 ms 1 2765 0.14 MB/sec execute 75 sec latency 96.921 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Thu Sep 17 06:02:49 EDT 2026 with return code 0 68555 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 68555 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished PASS 26 (310s) == replay-dual test 28: lock replay should be ordered: waiting after granted ========================================================== 06:03:34 (1789639414) Waiting for MDT destroys to complete 1+0 records in 1+0 records out 4096 bytes (4.1 kB, 4.0 KiB) copied, 0.0119801 s, 342 kB/s fail_loc=0x80000324 fail_loc=0x32a Failing ost1 on oleg450-server Stopping /mnt/lustre-ost1 (opts:) on oleg450-server 06:03:51 (1789639431) shut down facet: ost1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover ost1 to oleg450-server mount facets: ost1 Start ost1: mount -t lustre -o localrecov /dev/mapper/ost1_flakey /mnt/lustre-ost1 seq.cli-lustre-OST0000-super.width=65536 1+0 records in 1+0 records out 4096 bytes (4.1 kB, 4.0 KiB) copied, 0.0106274 s, 385 kB/s oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-OST0000 06:04:20 (1789639460) targets are mounted 06:04:20 (1789639460) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid 1475 0 osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in FULL state after 0 sec PASS 28 (67s) == replay-dual test 29: replay vs update with the same xid ========================================================== 06:04:42 (1789639482) SKIP: replay-dual test_29 needs >= 2 clients SKIP 29 (3s) == replay-dual test 30: layout lock replay is not blocked on IO ========================================================== 06:04:45 (1789639485) 10+0 records in 10+0 records out 40960 bytes (41 kB, 40 KiB) copied, 0.0486649 s, 842 kB/s 10+0 records in 10+0 records out 40960 bytes (41 kB, 40 KiB) copied, 0.0245749 s, 1.7 MB/s fail_loc=0x32e fail_val=4 Failing mds1 on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 06:04:54 (1789639494) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server Failover mds1 to oleg450-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all 160+0 records in 160+0 records out 81920 bytes (82 kB, 80 KiB) copied, 39.3891 s, 2.1 kB/s pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 06:05:28 (1789639528) targets are mounted 06:05:28 (1789639528) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 30 (60s) == replay-dual test 31: deadlock on file_remove_privs and occupied mod rpc slots ========================================================== 06:05:45 (1789639545) Failing ost1 on oleg450-server Stopping /mnt/lustre-ost1 (opts:) on oleg450-server Creating to objid 2433 on ost lustre-OST0000... 06:05:53 (1789639553) shut down facet: ost1 facet_host: oleg450-server facet_failover_host: oleg450-server total: 32 open/close in 0.93 seconds: 34.30 ops/second at_max=0 fail_loc=0x80001420 file /mnt/lustre2/d31.replay-dual/mdtdir/f31.replay-dual is ready Failover ost1 to oleg450-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 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-OST0000 06:06:21 (1789639581) targets are mounted 06:06:21 (1789639581) facet_failover done oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid 1475 0 osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in FULL IDLE state after 0 sec pids: 74185 74186 74191 74192 74193 74194 74195 74196 74197 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2120 1269156 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1836 1269468 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1568 3605452 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3112 7210928 1% /mnt/lustre UUID Inodes IUsed IFree IUse% Mounted on lustre-MDT0000_UUID 1024000 340 1023660 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1024000 258 1023742 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 262144 476 261668 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 262144 411 261733 1% /mnt/lustre[OST:1] filesystem_summary: 523999 598 523401 1% /mnt/lustre at_max=600 PASS 31 (55s) == replay-dual test 32: gap in update llog shouldn't break recovery ========================================================== 06:06:40 (1789639600) fail_loc=0x0000131d fail_val=10 fail_loc=0x726 Stopping /mnt/lustre-mds2 (opts:) on oleg450-server Stopping /mnt/lustre-mds1 (opts:) on oleg450-server fail_loc=0 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0000 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0001 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2224 1269080 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1904 1269400 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1568 3605452 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3112 7210928 1% /mnt/lustre PASS 32 (49s) == replay-dual test 33: Check for OBD_INCOMPAT_MULTI_RPCS in last_rcvd after abort_recovery ========================================================== 06:07:29 (1789639649) at_min=60 Stopping /mnt/lustre-mds2 (opts:) on oleg450-server last_rcvd in /dev/mapper/mds2_flakey: incompat = 0x61c Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0001 oleg450-client.virtnet: executing wait_import_state_mount REPLAY_WAIT mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0001-mdc-*.mds_server_uuid in REPLAY_WAIT state after 0 sec oleg450-client.virtnet: executing wait_import_state_mount FULL mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec affected facets: mds2 oleg450-server: oleg450-server.virtnet: executing _wait_recovery_complete *.lustre-MDT0001.recovery_status 1475 oleg450-server: *.lustre-MDT0001.recovery_status status: COMPLETE Stopping /mnt/lustre-mds2 (opts:) on oleg450-server last_rcvd in /dev/mapper/mds2_flakey: incompat = 0x61c Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 Started lustre-MDT0001 Starting client: oleg450-client.virtnet: -o user_xattr,flock 192.168.204.150@tcp:/lustre /mnt/lustre2 oleg450-client.virtnet: executing wait_import_state_mount FULL mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec affected facets: mds2 oleg450-server: oleg450-server.virtnet: executing _wait_recovery_complete *.lustre-MDT0001.recovery_status 1475 oleg450-server: *.lustre-MDT0001.recovery_status status: COMPLETE at_min=5 PASS 33 (106s) == replay-dual test complete, duration 4542 sec ========== 06:09:15 (1789639755) === replay-dual: start cleanup 06:09:17 (1789639757) === Stopping clients: oleg450-client.virtnet /mnt/lustre2 (opts:) Stopping client oleg450-client.virtnet /mnt/lustre2 opts: === replay-dual: finish cleanup 06:09:28 (1789639768) ===