-----============= acceptance-small: replay-dual ============----- Mon Aug 24 08:29:41 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 oleg343-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 08:30:02 (1787574602) === Starting client oleg343-client.virtnet: -o user_xattr,flock 192.168.203.143@tcp:/lustre /mnt/lustre2 Mount client oleg343-client.virtnet: mount -t lustre -o user_xattr,flock 192.168.203.143@tcp:/lustre /mnt/lustre2 Started clients oleg343-client.virtnet: 192.168.203.143@tcp:/lustre on /mnt/lustre2 type lustre (rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose) oleg343-client.virtnet: executing check_config_client /mnt/lustre oleg343-client.virtnet: Checking config lustre mounted on /mnt/lustre Checking servers environments Checking clients oleg343-client.virtnet environments Using TIMEOUT=20 osc.lustre-OST0000-osc-ffff93308718c000.idle_timeout=debug osc.lustre-OST0000-osc-ffff933090e5c800.idle_timeout=debug osc.lustre-OST0001-osc-ffff93308718c000.idle_timeout=debug osc.lustre-OST0001-osc-ffff933090e5c800.idle_timeout=debug disable quota as required oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all osd-ldiskfs.track_declares_assert=1 === replay-dual: finish setup 08:30:47 (1787574647) === == replay-dual test 0a: expired recovery with lost client ========================================================== 08:30:49 (1787574649) Check file is LU482_FAILED=/tmp/replay-dual.lu482.ciViJB 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 2.14 seconds: 23.33 ops/second fail_loc=0x80000514 Failing mds1 on oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 08:31:05 (1787574665) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 08:31:40 (1787574700) targets are mounted 08:31:40 (1787574700) facet_failover done Starting client: oleg343-client.virtnet: -o user_xattr,flock 192.168.203.143@tcp:/lustre /mnt/lustre2 - unlinked 0 (time 1787574816 ; total 0 ; last 0) total: 50 unlinks in 2 seconds: 25.000000 unlinks/second PASS 0a (176s) == replay-dual test 0b: lost client during waiting for next transno ========================================================== 08:33:45 (1787574825) 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 oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 08:34:03 (1787574843) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 08:34:38 (1787574878) targets are mounted 08:34:38 (1787574878) facet_failover done Starting client: oleg343-client.virtnet: -o user_xattr,flock 192.168.203.143@tcp:/lustre /mnt/lustre Starting client: oleg343-client.virtnet: -o user_xattr,flock 192.168.203.143@tcp:/lustre /mnt/lustre2 PASS 0b (225s) == replay-dual test 1: |X| simple create ================= 08:37:30 (1787575050) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1676 1269628 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1532 1269772 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre mcreate: cannot create `/mnt/lustre/fsa-oleg343-client.virtnet' with mode 0100644: File exists Failing mds1 on oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 08:37:44 (1787575064) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 08:38:19 (1787575099) targets are mounted 08:38:19 (1787575099) facet_failover done oleg343-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 (65s) == replay-dual test 2: |X| mkdir adir ==================== 08:38:36 (1787575116) 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 oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 08:38:49 (1787575129) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 08:39:26 (1787575166) targets are mounted 08:39:26 (1787575166) facet_failover done oleg343-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 (69s) == replay-dual test 3: |X| mkdir adir, mkdir adir/bdir === 08:39:45 (1787575185) 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 oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 08:40:01 (1787575201) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 08:40:35 (1787575235) targets are mounted 08:40:35 (1787575235) facet_failover done oleg343-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 (68s) == replay-dual test 4: |X| mkdir adir (-EEXIST), mkdir adir/bdir ========================================================== 08:40:53 (1787575253) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1852 1269452 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1704 1269600 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 oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 08:41:07 (1787575267) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 08:41:44 (1787575304) targets are mounted 08:41:44 (1787575304) facet_failover done oleg343-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 (68s) == replay-dual test 5: open, unlink |X| close ============ 08:42:01 (1787575321) multiop /mnt/lustre2/a vo_tSc TMPPIPE=/tmp/multiop_open_wait_pipe.8212 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1824 1269480 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1704 1269600 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 oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 08:42:16 (1787575336) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 08:42:50 (1787575370) targets are mounted 08:42:50 (1787575370) facet_failover done oleg343-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 (70s) == replay-dual test 6: open1, open2, unlink |X| close1 [fail mds1] close2 ========================================================== 08:43:11 (1787575391) multiop /mnt/lustre2/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8212 multiop /mnt/lustre/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8212 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1824 1269480 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1704 1269600 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 oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 08:43:25 (1787575405) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 08:44:02 (1787575442) targets are mounted 08:44:02 (1787575442) facet_failover done oleg343-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 (70s) == replay-dual test 8: replay of resent request ========== 08:44:22 (1787575462) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1824 1269480 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1704 1269600 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 oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 08:44:56 (1787575496) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 08:45:31 (1787575531) targets are mounted 08:45:31 (1787575531) facet_failover done oleg343-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 (87s) == replay-dual test 9: resending a replayed create ======= 08:45:49 (1787575549) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1824 1269480 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1704 1269600 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 oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 08:46:04 (1787575564) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 08:46:41 (1787575601) targets are mounted 08:46:41 (1787575601) facet_failover done oleg343-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 (78s) == replay-dual test 10: resending a replayed unlink ====== 08:47:07 (1787575627) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1824 1269480 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1704 1269600 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 oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 08:47:23 (1787575643) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 08:48:00 (1787575680) targets are mounted 08:48:00 (1787575680) facet_failover done oleg343-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 (81s) == replay-dual test 11: both clients timeout during replay ========================================================== 08:48:28 (1787575708) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1824 1269480 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1704 1269600 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 oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 08:48:45 (1787575725) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 08:49:21 (1787575761) targets are mounted 08:49:21 (1787575761) facet_failover done oleg343-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 3 sec fail_loc=0 PASS 11 (71s) == replay-dual test 12: open resend timeout ============== 08:49:39 (1787575779) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1824 1269480 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1704 1269600 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.8212 fail_loc=0x80000302 Failing mds1 on oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 08:49:54 (1787575794) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 08:50:30 (1787575830) targets are mounted 08:50:30 (1787575830) facet_failover done fail_loc=0 /mnt/lustre/f12.replay-dual /mnt/lustre/f12.replay-dual has type file OK PASS 12 (72s) == replay-dual test 13: close resend timeout ============= 08:50:51 (1787575851) multiop /mnt/lustre/f13.replay-dual vmo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8212 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1824 1269480 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1704 1269600 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 oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 08:51:09 (1787575869) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 08:51:43 (1787575903) targets are mounted 08:51:43 (1787575903) facet_failover done fail_loc=0 /mnt/lustre/f13.replay-dual /mnt/lustre/f13.replay-dual has type file OK PASS 13 (72s) SKIP: replay-dual test_14b skipping ALWAYS excluded test 14b == replay-dual test 15a: timeout waiting for lost client during replay, 1 client completes ========================================================== 08:52:05 (1787575925) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1824 1269480 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1704 1269600 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 1.11 seconds: 22.61 ops/second total: 1 open/close in 0.03 seconds: 31.15 ops/second Failing mds1 on oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 08:52:20 (1787575940) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 08:52:54 (1787575974) targets are mounted 08:52:54 (1787575974) facet_failover done oleg343-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 1787576050 ; total 0 ; last 0) total: 25 unlinks in 1 seconds: 25.000000 unlinks/second Starting client: oleg343-client.virtnet: -o user_xattr,flock 192.168.203.143@tcp:/lustre /mnt/lustre2 PASS 15a (132s) == replay-dual test 15c: remove multiple OST orphans ===== 08:54:17 (1787576057) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1824 1269480 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1704 1269600 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 oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 08:56:26 (1787576186) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 08:57:00 (1787576220) targets are mounted 08:57:00 (1787576220) facet_failover done oleg343-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: oleg343-client.virtnet: -o user_xattr,flock 192.168.203.143@tcp:/lustre /mnt/lustre2 PASS 15c (244s) == replay-dual test 16: fail MDS during recovery (3571) == 08:58:21 (1787576301) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1824 1269480 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1704 1269600 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 1.22 seconds: 20.45 ops/second total: 1 open/close in 0.08 seconds: 12.29 ops/second Failing mds1 on oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 08:58:37 (1787576317) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 08:59:10 (1787576350) targets are mounted 08:59:10 (1787576350) facet_failover done Failing mds1 on oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 08:59:36 (1787576376) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 09:00:11 (1787576411) targets are mounted 09:00:11 (1787576411) facet_failover done oleg343-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 1787576483 ; total 0 ; last 0) total: 25 unlinks in 1 seconds: 25.000000 unlinks/second Starting client: oleg343-client.virtnet: -o user_xattr,flock 192.168.203.143@tcp:/lustre /mnt/lustre2 PASS 16 (190s) == replay-dual test 17: fail OST during recovery (3571) == 09:01:31 (1787576491) total: 25 open/close in 0.93 seconds: 26.84 ops/second total: 1 open/close in 0.07 seconds: 14.27 ops/second UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1824 1269480 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1704 1269600 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 oleg343-server Stopping /mnt/lustre-ost1 (opts:) on oleg343-server 09:01:48 (1787576508) shut down facet: ost1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover ost1 to oleg343-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 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-OST0000 09:02:19 (1787576539) targets are mounted 09:02:19 (1787576539) facet_failover done Failing ost1 on oleg343-server Stopping /mnt/lustre-ost1 (opts:) on oleg343-server 09:02:43 (1787576563) shut down facet: ost1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover ost1 to oleg343-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 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-OST0000 09:03:09 (1787576589) targets are mounted 09:03:09 (1787576589) facet_failover done oleg343-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 1787576662 ; total 0 ; last 0) total: 25 unlinks in 0 seconds: inf unlinks/second Starting client: oleg343-client.virtnet: -o user_xattr,flock 192.168.203.143@tcp:/lustre /mnt/lustre2 PASS 17 (176s) == replay-dual test 18: ldlm_handle_enqueue succeeds on evicted export (3822) ========================================================== 09:04:28 (1787576668) debug=+dlmtrace fail_loc=0x8000030b using seed 3615753490 running for 500 iterations total: 500 stats in 1 seconds: 500.000000 stats/second ldlm.namespaces.MGC192.168.203.143@tcp.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffff933083072000.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffff93309267e000.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0001-mdc-ffff933083072000.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0001-mdc-ffff93309267e000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffff933083072000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffff93309267e000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffff933083072000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffff93309267e000.early_lock_cancel=0 fail_loc=0x80000305 Error in opening file "/mnt/lustre2/d18.replay-dual/f18.replay-dual"(flags=O_RDONLY) 2: No such file or directory ldlm.namespaces.MGC192.168.203.143@tcp.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffff933083072000.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffff93309267e000.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0001-mdc-ffff933083072000.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0001-mdc-ffff93309267e000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffff933083072000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffff93309267e000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffff933083072000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffff93309267e000.early_lock_cancel=1 fail_loc=0 fail_loc=0 PASS 18 (58s) == replay-dual test 19: resend of open request =========== 09:05:26 (1787576726) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1828 1269476 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1704 1269600 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre fail_loc=0x157 - open/close 0 (time 1787576826.07 total 88.51 last 0.00) total: 1 open/close in 88.51 seconds: 0.01 ops/second fail_loc=0 Failing mds1 on oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 09:07:12 (1787576832) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 09:07:43 (1787576863) targets are mounted 09:07:43 (1787576863) facet_failover done oleg343-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 (159s) == replay-dual test 20: recovery time is not increasing == 09:08:05 (1787576885) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1828 1269476 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1704 1269600 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre Failing mds1 on oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 09:08:20 (1787576900) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 09:08:55 (1787576935) targets are mounted 09:08:55 (1787576935) facet_failover done oleg343-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: oleg343-client.virtnet: -o user_xattr,flock 192.168.203.143@tcp:/lustre /mnt/lustre2 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1828 1269476 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1704 1269600 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre Failing mds1 on oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 09:11:36 (1787577096) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 09:12:11 (1787577131) targets are mounted 09:12:11 (1787577131) facet_failover done oleg343-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: oleg343-client.virtnet: -o user_xattr,flock 192.168.203.143@tcp:/lustre /mnt/lustre2 PASS 20 (399s) == replay-dual test 21a: commit on sharing =============== 09:14:44 (1787577284) mdt.lustre-MDT0000.commit_on_sharing=1 mdt.lustre-MDT0001.commit_on_sharing=1 Replay barrier on lustre-MDT0000 Failing mds1 on oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 09:14:58 (1787577298) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 09:15:31 (1787577331) targets are mounted 09:15:31 (1787577331) facet_failover done Starting client: oleg343-client.virtnet: -o user_xattr,flock 192.168.203.143@tcp:/lustre /mnt/lustre2 mdt.lustre-MDT0000.commit_on_sharing=0 mdt.lustre-MDT0001.commit_on_sharing=0 PASS 21a (190s) SKIP: replay-dual test_21b skipping SLOW test 21b == replay-dual test 22a: c1 lfs mkdir -i 1 dir1, M1 drop reply & fail, c2 mkdir dir1/dir ========================================================== 09:17:56 (1787577476) fail_loc=0x119 Failing mds2 on oleg343-server Stopping /mnt/lustre-mds2 (opts:) on oleg343-server 09:18:04 (1787577484) shut down facet: mds2 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds2 to oleg343-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0001 09:18:26 (1787577506) targets are mounted 09:18:26 (1787577506) facet_failover done oleg343-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 1836 1269468 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1708 1269596 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.17 seconds: 11.63 ops/second total: 2 open/close in 0.04 seconds: 46.90 ops/second Failing mds1 on oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 09:18:53 (1787577533) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 09:19:27 (1787577567) targets are mounted 09:19:27 (1787577567) facet_failover done oleg343-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 (111s) == replay-dual test 22b: c1 lfs mkdir -i 1 d1, M1 drop reply & fail M0/M1, c2 mkdir d1/dir ========================================================== 09:19:48 (1787577588) fail_loc=0x119 Failing mds1 on oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server Failing mds2 on oleg343-server Stopping /mnt/lustre-mds2 (opts:) on oleg343-server 09:20:02 (1787577602) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server facet: mds2 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Failover mds2 to oleg343-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 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 09:20:33 (1787577633) targets are mounted 09:20:33 (1787577633) facet_failover done oleg343-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 1836 1269468 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1708 1269596 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.15 seconds: 13.63 ops/second total: 2 open/close in 0.07 seconds: 29.61 ops/second Failing mds1 on oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 09:21:04 (1787577664) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 09:21:41 (1787577701) targets are mounted 09:21:41 (1787577701) facet_failover done oleg343-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 (133s) == replay-dual test 22c: c1 lfs mkdir -i 1 d1, M1 drop update & fail M1, c2 mkdir d1/dir ========================================================== 09:22:00 (1787577720) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 09:22:11 (1787577731) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 09:22:34 (1787577754) targets are mounted 09:22:34 (1787577754) facet_failover done oleg343-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 1836 1269468 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1720 1269584 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.10 seconds: 19.71 ops/second total: 2 open/close in 0.08 seconds: 25.62 ops/second Failing mds1 on oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 09:22:58 (1787577778) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 09:23:31 (1787577811) targets are mounted 09:23:31 (1787577811) facet_failover done oleg343-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 (109s) == replay-dual test 22d: c1 lfs mkdir -i 1 d1, M1 drop update & fail M0/M1,c2 mkdir d1/dir ========================================================== 09:23:49 (1787577829) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server Failing mds2 on oleg343-server Stopping /mnt/lustre-mds2 (opts:) on oleg343-server 09:24:14 (1787577854) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server facet: mds2 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Failover mds2 to oleg343-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 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 09:25:01 (1787577901) targets are mounted 09:25:01 (1787577901) facet_failover done oleg343-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 0.13 seconds: 15.18 ops/second total: 2 open/close in 0.09 seconds: 22.34 ops/second Failing mds1 on oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 09:25:27 (1787577927) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 09:26:03 (1787577963) targets are mounted 09:26:03 (1787577963) facet_failover done oleg343-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 (151s) == replay-dual test 23a: c1 rmdir d1, M1 drop reply and fail, client2 mkdir d1 ========================================================== 09:26:21 (1787577981) fail_loc=0x119 fail_loc=0 Failing mds2 on oleg343-server Stopping /mnt/lustre-mds2 (opts:) on oleg343-server 09:26:29 (1787577989) shut down facet: mds2 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds2 to oleg343-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0001 09:26:59 (1787578019) targets are mounted 09:27:00 (1787578020) facet_failover done oleg343-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 1832 1269472 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1704 1269600 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.10 seconds: 19.58 ops/second Failing mds1 on oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 09:27:24 (1787578044) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 09:27:58 (1787578078) targets are mounted 09:27:58 (1787578078) facet_failover done oleg343-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 (115s) == replay-dual test 23b: c1 rmdir d1, M1 drop reply and fail M0/M1, c2 mkdir d1 ========================================================== 09:28:15 (1787578095) fail_loc=0x119 fail_loc=0 Failing mds1 on oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server Failing mds2 on oleg343-server Stopping /mnt/lustre-mds2 (opts:) on oleg343-server 09:28:31 (1787578111) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server facet: mds2 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Failover mds2 to oleg343-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 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 Started lustre-MDT0001 09:29:11 (1787578151) targets are mounted 09:29:11 (1787578151) facet_failover done oleg343-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 1832 1269472 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1704 1269600 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.08 seconds: 24.78 ops/second Failing mds1 on oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 09:29:38 (1787578178) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 09:30:12 (1787578212) targets are mounted 09:30:12 (1787578212) facet_failover done oleg343-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 (138s) == replay-dual test 23c: c1 rmdir d1, M0 drop update reply and fail M0, c2 mkdir d1 ========================================================== 09:30:33 (1787578233) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 09:30:44 (1787578244) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 09:31:08 (1787578268) targets are mounted 09:31:08 (1787578268) facet_failover done oleg343-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 1832 1269472 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1716 1269588 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.12 seconds: 16.12 ops/second Failing mds1 on oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 09:31:38 (1787578298) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 09:32:12 (1787578332) targets are mounted 09:32:12 (1787578332) facet_failover done oleg343-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 (116s) == replay-dual test 23d: c1 rmdir d1, M0 drop update reply and fail M0/M1, c2 mkdir d1 ========================================================== 09:32:29 (1787578349) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server Failing mds2 on oleg343-server Stopping /mnt/lustre-mds2 (opts:) on oleg343-server 09:32:51 (1787578371) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server facet: mds2 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Failover mds2 to oleg343-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 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 09:33:37 (1787578417) targets are mounted 09:33:37 (1787578417) facet_failover done oleg343-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 0.13 seconds: 15.10 ops/second Failing mds1 on oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 09:34:07 (1787578447) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 09:34:39 (1787578479) targets are mounted 09:34:39 (1787578479) facet_failover done oleg343-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 (145s) == replay-dual test 24: reconstruct on non-existing object ========================================================== 09:34:55 (1787578495) fail_loc=0x119 fail_loc=0 truncate: cannot truncate '/mnt/lustre/f24.replay-dual' to length 100: No such file or directory PASS 24 (96s) == replay-dual test 25: replay|resend ==================== 09:36:31 (1787578591) 1+0 records in 1+0 records out 512 bytes copied, 0.0190732 s, 26.8 kB/s fail_loc=0x304 fail_loc=0x80000325 Failing ost1 on oleg343-server Stopping /mnt/lustre-ost1 (opts:) on oleg343-server 09:36:42 (1787578602) shut down facet: ost1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover ost1 to oleg343-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 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-OST0000 09:37:10 (1787578630) targets are mounted 09:37:10 (1787578630) facet_failover done oleg343-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid 1475 0 osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in FULL state after 0 sec /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 6982: 64219 Terminated LUSTRE="/home/green/git/lustre-release/lustre" bash -c "multiop /mnt/lustre2/f25.replay-dual Ow512" fail_loc=0 PASS 25 (56s) == replay-dual test 26: dbench and tar with mds failover ========================================================== 09:37:28 (1787578648) Starting client oleg343-client.virtnet: -o user_xattr,flock 192.168.203.143@tcp:/lustre /mnt/lustre Started clients oleg343-client.virtnet: 192.168.203.143@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 65649 Started dbench loop with 65651 striped dir -i0 -c2 -H crush2 /mnt/lustre/d26.replay-dual/run_tar striped dir -i0 -c2 -H crush /mnt/lustre2/d26.replay-dual/run_dbench looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1980 1269324 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1792 1269512 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1564 3605456 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 17928 3589016 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 19492 7194472 1% /mnt/lustre '/usr/share/dbench/client.txt' -> 'client.txt' running 'dbench 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100' on /mnt/lustre at Mon Aug 24 09:37:34 EDT 2026 waiting for dbench pid 65727 dbench version 4.00 - Copyright Andrew Tridgell 1999-2004 Running for 100 seconds with load 'client.txt' and minimum warmup 20 secs failed to create barrier semaphore 0 of 1 processes prepared for launch 0 sec 1 of 1 processes prepared for launch 0 sec releasing clients 1 29 0.98 MB/sec warmup 1 sec latency 13.324 ms 1 74 1.57 MB/sec warmup 2 sec latency 167.200 ms 1 116 1.74 MB/sec warmup 3 sec latency 234.850 ms 1 144 1.54 MB/sec warmup 4 sec latency 178.121 ms 1 166 1.36 MB/sec warmup 5 sec latency 178.505 ms 1 184 1.23 MB/sec warmup 6 sec latency 387.728 ms 1 197 1.12 MB/sec warmup 7 sec latency 585.079 ms 1 220 1.06 MB/sec warmup 8 sec latency 250.545 ms 1 263 1.10 MB/sec warmup 9 sec latency 149.003 ms test_26 fail mds1 1 times 1 290 1.07 MB/sec warmup 10 sec latency 184.229 ms 1 315 1.04 MB/sec warmup 11 sec latency 195.862 ms Failing mds1 on oleg343-server 1 332 1.00 MB/sec warmup 12 sec latency 407.045 ms 1 361 0.99 MB/sec warmup 13 sec latency 184.351 ms Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 1 396 1.00 MB/sec warmup 14 sec latency 135.358 ms 1 397 0.94 MB/sec warmup 15 sec latency 997.941 ms 1 397 0.88 MB/sec warmup 16 sec latency 1998.222 ms 09:37:51 (1787578671) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server 1 397 0.83 MB/sec warmup 17 sec latency 2998.461 ms 1 397 0.78 MB/sec warmup 18 sec latency 3999.465 ms 1 397 0.74 MB/sec warmup 19 sec latency 4999.706 ms 1 397 0.00 MB/sec execute 1 sec latency 7001.617 ms 1 397 0.00 MB/sec execute 2 sec latency 8001.837 ms 1 397 0.00 MB/sec execute 3 sec latency 9002.120 ms 1 397 0.00 MB/sec execute 4 sec latency 10002.328 ms 1 397 0.00 MB/sec execute 5 sec latency 11003.518 ms 1 397 0.00 MB/sec execute 6 sec latency 12005.319 ms 1 397 0.00 MB/sec execute 7 sec latency 13006.861 ms Failover mds1 to oleg343-server mount facets: mds1 1 397 0.00 MB/sec execute 8 sec latency 14007.740 ms 1 397 0.00 MB/sec execute 9 sec latency 15008.254 ms 1 397 0.00 MB/sec execute 10 sec latency 16009.633 ms 1 397 0.00 MB/sec execute 11 sec latency 17011.335 ms 1 397 0.00 MB/sec execute 12 sec latency 18012.724 ms 1 397 0.00 MB/sec execute 13 sec latency 19012.958 ms 1 397 0.00 MB/sec execute 14 sec latency 20013.675 ms 1 397 0.00 MB/sec execute 15 sec latency 21014.047 ms 1 397 0.00 MB/sec execute 16 sec latency 22014.278 ms 1 397 0.00 MB/sec execute 17 sec latency 23015.131 ms 1 397 0.00 MB/sec execute 18 sec latency 24017.342 ms 1 397 0.00 MB/sec execute 19 sec latency 25018.982 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 397 0.00 MB/sec execute 20 sec latency 26019.260 ms 1 397 0.00 MB/sec execute 21 sec latency 27019.447 ms 1 397 0.00 MB/sec execute 22 sec latency 28021.209 ms 1 397 0.00 MB/sec execute 23 sec latency 29021.634 ms 1 397 0.00 MB/sec execute 24 sec latency 30021.881 ms 1 397 0.00 MB/sec execute 25 sec latency 31022.152 ms 1 397 0.00 MB/sec execute 26 sec latency 32022.384 ms 1 397 0.00 MB/sec execute 27 sec latency 33022.855 ms 1 397 0.00 MB/sec execute 28 sec latency 34029.432 ms 1 397 0.00 MB/sec execute 29 sec latency 35030.015 ms 1 397 0.00 MB/sec execute 30 sec latency 36034.889 ms 1 397 0.00 MB/sec execute 31 sec latency 37037.255 ms oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all 1 397 0.00 MB/sec execute 32 sec latency 38037.955 ms 1 401 0.00 MB/sec execute 33 sec latency 38945.466 ms pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 1 437 0.04 MB/sec execute 34 sec latency 142.949 ms Started lustre-MDT0000 09:38:28 (1787578708) targets are mounted 09:38:28 (1787578708) facet_failover done 1 475 0.07 MB/sec execute 35 sec latency 162.366 ms 1 511 0.10 MB/sec execute 36 sec latency 144.517 ms 1 552 0.14 MB/sec execute 37 sec latency 242.889 ms 1 611 0.18 MB/sec execute 38 sec latency 444.483 ms 1 652 0.18 MB/sec execute 39 sec latency 124.349 ms 1 676 0.18 MB/sec execute 40 sec latency 170.593 ms 1 706 0.17 MB/sec execute 41 sec latency 146.965 ms 1 731 0.17 MB/sec execute 42 sec latency 166.184 ms oleg343-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 759 0.17 MB/sec execute 43 sec latency 144.429 ms 1 778 0.17 MB/sec execute 44 sec latency 226.619 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 799 0.16 MB/sec execute 45 sec latency 222.576 ms 1 815 0.16 MB/sec execute 46 sec latency 156.185 ms 1 854 0.16 MB/sec execute 47 sec latency 149.326 ms 1 882 0.16 MB/sec execute 48 sec latency 105.508 ms 1 903 0.15 MB/sec execute 49 sec latency 141.907 ms 1 923 0.15 MB/sec execute 50 sec latency 182.253 ms 1 959 0.15 MB/sec execute 51 sec latency 109.043 ms 1 990 0.15 MB/sec execute 52 sec latency 144.534 ms 1 1041 0.17 MB/sec execute 53 sec latency 100.938 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2148 1269156 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1928 1269376 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 18300 3585940 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 33636 3567996 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 51936 7153936 1% /mnt/lustre 1 1076 0.16 MB/sec execute 54 sec latency 155.999 ms 1 1117 0.16 MB/sec execute 55 sec latency 145.517 ms 1 1147 0.16 MB/sec execute 56 sec latency 126.123 ms 1 1172 0.16 MB/sec execute 57 sec latency 526.084 ms 1 1188 0.15 MB/sec execute 58 sec latency 754.144 ms 1 1217 0.15 MB/sec execute 59 sec latency 174.957 ms 1 1244 0.15 MB/sec execute 60 sec latency 119.963 ms 1 1279 0.15 MB/sec execute 61 sec latency 160.372 ms 1 1390 0.19 MB/sec execute 62 sec latency 139.272 ms 1 1422 0.19 MB/sec execute 63 sec latency 121.323 ms 1 1463 0.19 MB/sec execute 64 sec latency 114.732 ms test_26 fail mds2 2 times 1 1499 0.18 MB/sec execute 65 sec latency 151.431 ms 1 1518 0.18 MB/sec execute 66 sec latency 213.548 ms 1 1552 0.18 MB/sec execute 67 sec latency 169.446 ms Failing mds2 on oleg343-server 1 1572 0.18 MB/sec execute 68 sec latency 179.046 ms Stopping /mnt/lustre-mds2 (opts:) on oleg343-server 1 1609 0.17 MB/sec execute 69 sec latency 119.328 ms 1 1645 0.17 MB/sec execute 70 sec latency 211.619 ms 1 1676 0.17 MB/sec execute 71 sec latency 191.577 ms 1 1698 0.17 MB/sec execute 72 sec latency 179.800 ms 1 1736 0.17 MB/sec execute 73 sec latency 128.732 ms 09:39:08 (1787578748) shut down 1 1770 0.16 MB/sec execute 74 sec latency 165.769 ms facet: mds2 facet_host: oleg343-server facet_failover_host: oleg343-server 1 1813 0.16 MB/sec execute 75 sec latency 223.438 ms 1 1843 0.16 MB/sec execute 76 sec latency 105.889 ms 1 1871 0.16 MB/sec execute 77 sec latency 207.616 ms 1 1908 0.16 MB/sec execute 78 sec latency 167.539 ms 1 1965 0.16 MB/sec execute 79 sec latency 144.893 ms 1 2010 0.16 MB/sec execute 80 sec latency 121.279 ms 1 2060 0.15 MB/sec execute 81 sec latency 111.712 ms 1 2111 0.15 MB/sec execute 82 sec latency 145.667 ms 1 2156 0.15 MB/sec execute 83 sec latency 138.620 ms 1 2191 0.15 MB/sec execute 84 sec latency 109.270 ms Failover mds2 to oleg343-server mount facets: mds2 1 2226 0.15 MB/sec execute 85 sec latency 154.894 ms 1 2259 0.15 MB/sec execute 86 sec latency 501.016 ms 1 2259 0.15 MB/sec execute 87 sec latency 1501.186 ms 1 2259 0.14 MB/sec execute 88 sec latency 2502.925 ms 1 2259 0.14 MB/sec execute 89 sec latency 3503.136 ms 1 2259 0.14 MB/sec execute 90 sec latency 4503.444 ms 1 2259 0.14 MB/sec execute 91 sec latency 5503.696 ms 1 2259 0.14 MB/sec execute 92 sec latency 6505.503 ms 1 2259 0.14 MB/sec execute 93 sec latency 7505.729 ms 1 2259 0.13 MB/sec execute 94 sec latency 8506.108 ms 1 2259 0.13 MB/sec execute 95 sec latency 9506.311 ms 1 2259 0.13 MB/sec execute 96 sec latency 10506.795 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 2259 0.13 MB/sec execute 97 sec latency 11509.093 ms 1 2259 0.13 MB/sec execute 98 sec latency 12509.294 ms 1 2259 0.13 MB/sec execute 99 sec latency 13509.609 ms 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec 1 cleanup 103 sec oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all 1 cleanup 104 sec pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 1 cleanup 105 sec Started lustre-MDT0001 09:39:40 (1787578780) targets are mounted 09:39:40 (1787578780) facet_failover done 1 cleanup 106 sec 1 cleanup 107 sec 1 cleanup 108 sec 1 cleanup 109 sec 1 cleanup 110 sec 0 cleanup 111 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 333 254.846 38945.443 Close 289 16.376 78.192 Rename 11 139.180 222.547 Unlink 30 37.793 91.634 Qpathinfo 295 22.331 195.753 Qfileinfo 82 2.747 21.619 Qfsinfo 33 4.892 29.610 Sfileinfo 34 81.050 182.234 Find 92 15.792 49.234 WriteX 286 15.603 100.034 ReadX 348 3.519 141.401 Flush 30 65.924 170.575 Throughput 0.128044 MB/sec 1 clients 1 procs max_latency=38945.466 ms stopping dbench on /mnt/lustre at Mon Aug 24 09:39:45 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished striped dir -i0 -c2 -H crush /mnt/lustre2/d26.replay-dual/run_dbench oleg343-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 looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt '/usr/share/dbench/client.txt' -> 'client.txt' running 'dbench 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100' on /mnt/lustre at Mon Aug 24 09:39:59 EDT 2026 waiting for dbench pid 67814 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 0 5 0.00 MB/sec warmup 1 sec latency 75.602 ms 1 31 0.52 MB/sec warmup 2 sec latency 104.318 ms 1 57 0.76 MB/sec warmup 3 sec latency 225.809 ms 1 92 1.05 MB/sec warmup 4 sec latency 171.486 ms 1 113 1.05 MB/sec warmup 5 sec latency 291.322 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2388 1268916 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2120 1269184 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 44764 3559784 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1852 3604944 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 46616 7164728 1% /mnt/lustre 1 129 0.96 MB/sec warmup 6 sec latency 398.948 ms 1 143 0.87 MB/sec warmup 7 sec latency 275.228 ms 1 165 0.85 MB/sec warmup 8 sec latency 223.142 ms 1 181 0.81 MB/sec warmup 9 sec latency 233.321 ms 1 184 0.74 MB/sec warmup 10 sec latency 802.338 ms 1 199 0.71 MB/sec warmup 11 sec latency 1000.229 ms 1 215 0.69 MB/sec warmup 12 sec latency 308.798 ms 1 235 0.69 MB/sec warmup 13 sec latency 248.125 ms 1 255 0.69 MB/sec warmup 14 sec latency 244.073 ms 1 279 0.69 MB/sec warmup 15 sec latency 234.306 ms 1 295 0.68 MB/sec warmup 16 sec latency 288.963 ms 1 320 0.68 MB/sec warmup 17 sec latency 196.068 ms 1 339 0.68 MB/sec warmup 18 sec latency 212.748 ms 1 353 0.66 MB/sec warmup 19 sec latency 330.489 ms 1 406 0.78 MB/sec execute 1 sec latency 237.056 ms test_26 fail mds1 3 times 1 433 0.81 MB/sec execute 2 sec latency 153.712 ms 1 457 0.80 MB/sec execute 3 sec latency 197.283 ms 1 475 0.76 MB/sec execute 4 sec latency 249.189 ms Failing mds1 on oleg343-server 1 498 0.75 MB/sec execute 5 sec latency 204.463 ms 1 513 0.69 MB/sec execute 6 sec latency 257.099 ms Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 1 554 0.79 MB/sec execute 7 sec latency 169.023 ms 1 609 0.92 MB/sec execute 8 sec latency 143.996 ms 1 642 0.83 MB/sec execute 9 sec latency 253.282 ms 1 642 0.75 MB/sec execute 10 sec latency 1253.465 ms 1 642 0.68 MB/sec execute 11 sec latency 2253.723 ms 1 642 0.62 MB/sec execute 12 sec latency 3253.998 ms 1 642 0.58 MB/sec execute 13 sec latency 4254.271 ms 1 642 0.53 MB/sec execute 14 sec latency 5255.122 ms 1 642 0.50 MB/sec execute 15 sec latency 6255.320 ms 1 642 0.47 MB/sec execute 16 sec latency 7255.505 ms 09:40:36 (1787578836) shut down 1 642 0.44 MB/sec execute 17 sec latency 8263.589 ms facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server 1 642 0.42 MB/sec execute 18 sec latency 9264.025 ms 1 642 0.39 MB/sec execute 19 sec latency 10264.227 ms 1 642 0.37 MB/sec execute 20 sec latency 11264.445 ms 1 642 0.36 MB/sec execute 21 sec latency 12264.672 ms 1 642 0.34 MB/sec execute 22 sec latency 13265.187 ms 1 642 0.33 MB/sec execute 23 sec latency 14265.980 ms 1 642 0.31 MB/sec execute 24 sec latency 15272.418 ms 1 642 0.30 MB/sec execute 25 sec latency 16272.753 ms 1 642 0.29 MB/sec execute 26 sec latency 17273.052 ms 1 642 0.28 MB/sec execute 27 sec latency 18273.285 ms Failover mds1 to oleg343-server mount facets: mds1 1 642 0.27 MB/sec execute 28 sec latency 19274.322 ms 1 642 0.26 MB/sec execute 29 sec latency 20274.526 ms 1 642 0.25 MB/sec execute 30 sec latency 21274.718 ms 1 642 0.24 MB/sec execute 31 sec latency 22275.848 ms 1 642 0.23 MB/sec execute 32 sec latency 23277.413 ms 1 642 0.23 MB/sec execute 33 sec latency 24280.879 ms 1 642 0.22 MB/sec execute 34 sec latency 25281.022 ms 1 642 0.21 MB/sec execute 35 sec latency 26282.384 ms 1 642 0.21 MB/sec execute 36 sec latency 27282.887 ms 1 642 0.20 MB/sec execute 37 sec latency 28284.433 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 642 0.20 MB/sec execute 38 sec latency 29284.649 ms 1 642 0.19 MB/sec execute 39 sec latency 30285.009 ms 1 642 0.19 MB/sec execute 40 sec latency 31285.227 ms 1 642 0.18 MB/sec execute 41 sec latency 32285.534 ms 1 642 0.18 MB/sec execute 42 sec latency 33285.865 ms 1 642 0.17 MB/sec execute 43 sec latency 34286.077 ms 1 642 0.17 MB/sec execute 44 sec latency 35288.768 ms 1 642 0.17 MB/sec execute 45 sec latency 36293.651 ms 1 642 0.16 MB/sec execute 46 sec latency 37297.934 ms 1 642 0.16 MB/sec execute 47 sec latency 38298.775 ms oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all 1 642 0.16 MB/sec execute 48 sec latency 39299.238 ms pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 1 642 0.15 MB/sec execute 49 sec latency 40302.704 ms Started lustre-MDT0000 1 666 0.15 MB/sec execute 50 sec latency 40396.360 ms 09:41:09 (1787578869) targets are mounted 09:41:09 (1787578869) facet_failover done 1 695 0.15 MB/sec execute 51 sec latency 180.505 ms 1 717 0.15 MB/sec execute 52 sec latency 164.124 ms 1 736 0.15 MB/sec execute 53 sec latency 167.590 ms 1 769 0.14 MB/sec execute 54 sec latency 137.758 ms 1 786 0.14 MB/sec execute 55 sec latency 237.113 ms 1 806 0.14 MB/sec execute 56 sec latency 211.434 ms 1 825 0.14 MB/sec execute 57 sec latency 167.338 ms 1 863 0.14 MB/sec execute 58 sec latency 190.457 ms oleg343-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 882 0.14 MB/sec execute 59 sec latency 171.395 ms 1 884 0.13 MB/sec execute 60 sec latency 876.560 ms 1 884 0.13 MB/sec execute 61 sec latency 1877.027 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 900 0.13 MB/sec execute 62 sec latency 1888.032 ms 1 914 0.13 MB/sec execute 63 sec latency 228.890 ms 1 955 0.13 MB/sec execute 64 sec latency 120.977 ms 1 984 0.13 MB/sec execute 65 sec latency 118.967 ms 1 1028 0.14 MB/sec execute 66 sec latency 139.668 ms 1 1084 0.14 MB/sec execute 67 sec latency 126.100 ms 1 1136 0.14 MB/sec execute 68 sec latency 90.099 ms 1 1192 0.14 MB/sec execute 69 sec latency 151.910 ms 1 1227 0.14 MB/sec execute 70 sec latency 86.828 ms 1 1259 0.13 MB/sec execute 71 sec latency 97.277 ms 1 1387 0.17 MB/sec execute 72 sec latency 103.010 ms 1 1421 0.17 MB/sec execute 73 sec latency 93.529 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 1467 0.17 MB/sec execute 74 sec latency 124.736 ms 1 1493 0.17 MB/sec execute 75 sec latency 362.000 ms 1 1537 0.16 MB/sec execute 76 sec latency 122.115 ms 1 1570 0.16 MB/sec execute 77 sec latency 84.485 ms 1 1610 0.16 MB/sec execute 78 sec latency 83.226 ms 1 1647 0.16 MB/sec execute 79 sec latency 150.907 ms 1 1689 0.16 MB/sec execute 80 sec latency 139.571 ms 1 1766 0.16 MB/sec execute 81 sec latency 81.994 ms 1 1814 0.16 MB/sec execute 82 sec latency 145.679 ms 1 1861 0.15 MB/sec execute 83 sec latency 117.110 ms 1 1909 0.15 MB/sec execute 84 sec latency 89.148 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Mon Aug 24 09:41:44 EDT 2026 with return code 0 1 1977 0.15 MB/sec execute 85 sec latency 89.672 ms 67814 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 67814 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished PASS 26 (294s) == replay-dual test 28: lock replay should be ordered: waiting after granted ========================================================== 09:42:21 (1787578941) Waiting for MDT destroys to complete 1+0 records in 1+0 records out 4096 bytes (4.1 kB, 4.0 KiB) copied, 0.0166548 s, 246 kB/s fail_loc=0x80000324 fail_loc=0x32a Failing ost1 on oleg343-server Stopping /mnt/lustre-ost1 (opts:) on oleg343-server 09:42:42 (1787578962) shut down facet: ost1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover ost1 to oleg343-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, 0.0185453 s, 221 kB/s oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-OST0000 09:43:07 (1787578987) targets are mounted 09:43:07 (1787578987) facet_failover done oleg343-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid 1475 0 osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in FULL state after 0 sec PASS 28 (70s) == replay-dual test 29: replay vs update with the same xid ========================================================== 09:43:32 (1787579012) SKIP: replay-dual test_29 needs >= 2 clients SKIP 29 (5s) == replay-dual test 30: layout lock replay is not blocked on IO ========================================================== 09:43:36 (1787579016) 10+0 records in 10+0 records out 40960 bytes (41 kB, 40 KiB) copied, 0.0714773 s, 573 kB/s 10+0 records in 10+0 records out 40960 bytes (41 kB, 40 KiB) copied, 0.0568689 s, 720 kB/s fail_loc=0x32e fail_val=4 Failing mds1 on oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server 09:43:44 (1787579024) shut down facet: mds1 facet_host: oleg343-server facet_failover_host: oleg343-server Failover mds1 to oleg343-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all 160+0 records in 160+0 records out 81920 bytes (82 kB, 80 KiB) copied, 38.2128 s, 2.1 kB/s pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 09:44:19 (1787579059) targets are mounted 09:44:19 (1787579059) facet_failover done oleg343-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 (61s) == replay-dual test 31: deadlock on file_remove_privs and occupied mod rpc slots ========================================================== 09:44:38 (1787579078) Failing ost1 on oleg343-server Stopping /mnt/lustre-ost1 (opts:) on oleg343-server Creating to objid 2433 on ost lustre-OST0000... total: 32 open/close in 1.31 seconds: 24.45 ops/second 09:44:46 (1787579086) shut down facet: ost1 facet_host: oleg343-server facet_failover_host: oleg343-server at_max=0 fail_loc=0x80001420 file /mnt/lustre2/d31.replay-dual/mdtdir/f31.replay-dual is ready Failover ost1 to oleg343-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 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-OST0000 09:45:13 (1787579113) targets are mounted 09:45:13 (1787579113) facet_failover done oleg343-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: 73168 73169 73174 73175 73176 73177 73178 73179 73180 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2188 1269088 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1864 1269440 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1568 3605452 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3112 7210928 1% /mnt/lustre UUID Inodes IUsed IFree IUse% Mounted on lustre-MDT0000_UUID 1024000 341 1023659 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1024000 258 1023742 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 262144 494 261650 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 262144 428 261716 1% /mnt/lustre[OST:1] filesystem_summary: 523965 599 523366 1% /mnt/lustre at_max=600 PASS 31 (60s) == replay-dual test 32: gap in update llog shouldn't break recovery ========================================================== 09:45:37 (1787579137) fail_loc=0x0000131d fail_val=10 fail_loc=0x726 Stopping /mnt/lustre-mds2 (opts:) on oleg343-server Stopping /mnt/lustre-mds1 (opts:) on oleg343-server fail_loc=0 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0000 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0001 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2296 1269008 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1936 1269368 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 (59s) == replay-dual test 33: Check for OBD_INCOMPAT_MULTI_RPCS in last_rcvd after abort_recovery ========================================================== 09:46:36 (1787579196) at_min=60 Stopping /mnt/lustre-mds2 (opts:) on oleg343-server last_rcvd in /dev/mapper/mds2_flakey: incompat = 0x61c Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0001 oleg343-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 oleg343-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 oleg343-server: oleg343-server.virtnet: executing _wait_recovery_complete *.lustre-MDT0001.recovery_status 1475 oleg343-server: *.lustre-MDT0001.recovery_status status: COMPLETE Stopping /mnt/lustre-mds2 (opts:) on oleg343-server last_rcvd in /dev/mapper/mds2_flakey: incompat = 0x61c Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg343-server: oleg343-server.virtnet: executing set_default_debug -1 all pdsh@oleg343-client: oleg343-server: ssh exited with exit code 1 Started lustre-MDT0001 Starting client: oleg343-client.virtnet: -o user_xattr,flock 192.168.203.143@tcp:/lustre /mnt/lustre2 oleg343-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 oleg343-server: oleg343-server.virtnet: executing _wait_recovery_complete *.lustre-MDT0001.recovery_status 1475 oleg343-server: *.lustre-MDT0001.recovery_status status: COMPLETE at_min=5 PASS 33 (106s) == replay-dual test complete, duration 4719 sec ========== 09:48:22 (1787579302) === replay-dual: start cleanup 09:48:24 (1787579304) === Stopping clients: oleg343-client.virtnet /mnt/lustre2 (opts:) Stopping client oleg343-client.virtnet /mnt/lustre2 opts: === replay-dual: finish cleanup 09:48:36 (1787579316) ===