-----============= acceptance-small: replay-dual ============----- Mon Aug 24 07:11:20 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 oleg348-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 07:11:43 (1787569903) === Starting client oleg348-client.virtnet: -o user_xattr,flock 192.168.203.148@tcp:/lustre /mnt/lustre2 Mount client oleg348-client.virtnet: mount -t lustre -o user_xattr,flock 192.168.203.148@tcp:/lustre /mnt/lustre2 Started clients oleg348-client.virtnet: 192.168.203.148@tcp:/lustre on /mnt/lustre2 type lustre (rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose) oleg348-client.virtnet: executing check_config_client /mnt/lustre oleg348-client.virtnet: Checking config lustre mounted on /mnt/lustre Checking servers environments Checking clients oleg348-client.virtnet environments Using TIMEOUT=20 osc.lustre-OST0000-osc-ffff989647878000.idle_timeout=debug osc.lustre-OST0000-osc-ffff989648f97800.idle_timeout=debug osc.lustre-OST0001-osc-ffff989647878000.idle_timeout=debug osc.lustre-OST0001-osc-ffff989648f97800.idle_timeout=debug disable quota as required oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all osd-ldiskfs.track_declares_assert=1 === replay-dual: finish setup 07:12:30 (1787569950) === == replay-dual test 0a: expired recovery with lost client ========================================================== 07:12:32 (1787569952) Check file is LU482_FAILED=/tmp/replay-dual.lu482.tzfRSG 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 2.42 seconds: 20.69 ops/second fail_loc=0x80000514 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 07:12:50 (1787569970) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 07:13:24 (1787570004) targets are mounted 07:13:24 (1787570004) facet_failover done Starting client: oleg348-client.virtnet: -o user_xattr,flock 192.168.203.148@tcp:/lustre /mnt/lustre2 - unlinked 0 (time 1787570118 ; total 0 ; last 0) total: 50 unlinks in 2 seconds: 25.000000 unlinks/second PASS 0a (174s) == replay-dual test 0b: lost client during waiting for next transno ========================================================== 07:15:27 (1787570127) 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 oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 07:15:42 (1787570142) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 07:16:15 (1787570175) targets are mounted 07:16:15 (1787570175) facet_failover done Starting client: oleg348-client.virtnet: -o user_xattr,flock 192.168.203.148@tcp:/lustre /mnt/lustre Starting client: oleg348-client.virtnet: -o user_xattr,flock 192.168.203.148@tcp:/lustre /mnt/lustre2 PASS 0b (225s) == replay-dual test 1: |X| simple create ================= 07:19:11 (1787570351) 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-oleg348-client.virtnet' with mode 0100644: File exists Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 07:19:25 (1787570365) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 07:19:59 (1787570399) targets are mounted 07:19:59 (1787570399) facet_failover done oleg348-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 ==================== 07:20:16 (1787570416) 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 oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 07:20:30 (1787570430) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 07:21:04 (1787570464) targets are mounted 07:21:04 (1787570464) facet_failover done oleg348-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 (63s) == replay-dual test 3: |X| mkdir adir, mkdir adir/bdir === 07:21:20 (1787570480) 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 oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 07:21:33 (1787570493) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 07:22:07 (1787570527) targets are mounted 07:22:07 (1787570527) facet_failover done oleg348-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 ========================================================== 07:22:27 (1787570547) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1752 1269552 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre mkdir: cannot create directory '/mnt/lustre/adir': File exists Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 07:22:43 (1787570563) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 07:23:20 (1787570600) targets are mounted 07:23:20 (1787570600) facet_failover done oleg348-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 (70s) == replay-dual test 5: open, unlink |X| close ============ 07:23:37 (1787570617) multiop /mnt/lustre2/a vo_tSc TMPPIPE=/tmp/multiop_open_wait_pipe.8229 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1748 1269556 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 07:23:54 (1787570634) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 07:24:27 (1787570667) targets are mounted 07:24:27 (1787570667) facet_failover done oleg348-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 (68s) == replay-dual test 6: open1, open2, unlink |X| close1 [fail mds1] close2 ========================================================== 07:24:45 (1787570685) multiop /mnt/lustre2/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8229 multiop /mnt/lustre/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8229 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1748 1269556 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 07:25:01 (1787570701) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 07:25:33 (1787570733) targets are mounted 07:25:33 (1787570733) facet_failover done oleg348-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 (66s) == replay-dual test 8: replay of resent request ========== 07:25:51 (1787570751) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1748 1269556 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre fail_loc=0x119 fail_loc=0 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 07:26:26 (1787570786) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 07:27:02 (1787570822) targets are mounted 07:27:02 (1787570822) facet_failover done oleg348-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 (88s) == replay-dual test 9: resending a replayed create ======= 07:27:19 (1787570839) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1748 1269556 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre fail_loc=0x80000119 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 07:27:35 (1787570855) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 07:28:12 (1787570892) targets are mounted 07:28:12 (1787570892) facet_failover done oleg348-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 (80s) == replay-dual test 10: resending a replayed unlink ====== 07:28:39 (1787570919) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1748 1269556 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre fail_loc=0x80000119 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 07:28:54 (1787570934) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 07:29:27 (1787570967) targets are mounted 07:29:27 (1787570967) facet_failover done oleg348-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 (77s) == replay-dual test 11: both clients timeout during replay ========================================================== 07:29:57 (1787570997) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1748 1269556 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre fail_loc=0x0119 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 07:30:12 (1787571012) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 07:30:45 (1787571045) targets are mounted 07:30:45 (1787571045) facet_failover done oleg348-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 4 sec fail_loc=0 PASS 11 (68s) == replay-dual test 12: open resend timeout ============== 07:31:05 (1787571065) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1748 1269556 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre multiop /mnt/lustre/f12.replay-dual vmo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8229 fail_loc=0x80000302 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 07:31:21 (1787571081) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 07:31:58 (1787571118) targets are mounted 07:31:58 (1787571118) facet_failover done fail_loc=0 /mnt/lustre/f12.replay-dual /mnt/lustre/f12.replay-dual has type file OK PASS 12 (74s) == replay-dual test 13: close resend timeout ============= 07:32:19 (1787571139) multiop /mnt/lustre/f13.replay-dual vmo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8229 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1748 1269556 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre fail_loc=0x80000115 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 07:32:37 (1787571157) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 07:33:12 (1787571192) targets are mounted 07:33:12 (1787571192) 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 ========================================================== 07:33:32 (1787571212) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1748 1269556 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre total: 25 open/close in 0.97 seconds: 25.73 ops/second total: 1 open/close in 0.06 seconds: 17.40 ops/second Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 07:33:46 (1787571226) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 07:34:23 (1787571263) targets are mounted 07:34:23 (1787571263) facet_failover done oleg348-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 1787571340 ; total 0 ; last 0) total: 25 unlinks in 1 seconds: 25.000000 unlinks/second Starting client: oleg348-client.virtnet: -o user_xattr,flock 192.168.203.148@tcp:/lustre /mnt/lustre2 PASS 15a (135s) == replay-dual test 15c: remove multiple OST orphans ===== 07:35:46 (1787571346) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1748 1269556 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 07:37:58 (1787571478) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 07:38:30 (1787571510) targets are mounted 07:38:30 (1787571510) facet_failover done oleg348-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: oleg348-client.virtnet: -o user_xattr,flock 192.168.203.148@tcp:/lustre /mnt/lustre2 PASS 15c (245s) == replay-dual test 16: fail MDS during recovery (3571) == 07:39:51 (1787571591) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1748 1269556 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre total: 25 open/close in 1.14 seconds: 21.94 ops/second total: 1 open/close in 0.04 seconds: 28.32 ops/second Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 07:40:06 (1787571606) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 07:40:38 (1787571638) targets are mounted 07:40:38 (1787571638) facet_failover done Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 07:41:03 (1787571663) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 07:41:36 (1787571696) targets are mounted 07:41:36 (1787571696) facet_failover done oleg348-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 1787571771 ; total 0 ; last 0) total: 25 unlinks in 1 seconds: 25.000000 unlinks/second Starting client: oleg348-client.virtnet: -o user_xattr,flock 192.168.203.148@tcp:/lustre /mnt/lustre2 PASS 16 (187s) == replay-dual test 17: fail OST during recovery (3571) == 07:42:58 (1787571778) total: 25 open/close in 0.81 seconds: 30.76 ops/second total: 1 open/close in 0.06 seconds: 18.04 ops/second UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1780 1269524 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing ost1 on oleg348-server Stopping /mnt/lustre-ost1 (opts:) on oleg348-server 07:43:13 (1787571793) shut down facet: ost1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover ost1 to oleg348-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 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-OST0000 07:43:41 (1787571821) targets are mounted 07:43:41 (1787571821) facet_failover done Failing ost1 on oleg348-server Stopping /mnt/lustre-ost1 (opts:) on oleg348-server 07:44:06 (1787571846) shut down facet: ost1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover ost1 to oleg348-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 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-OST0000 07:44:30 (1787571870) targets are mounted 07:44:30 (1787571870) facet_failover done oleg348-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 1787571944 ; total 0 ; last 0) total: 25 unlinks in 1 seconds: 25.000000 unlinks/second Starting client: oleg348-client.virtnet: -o user_xattr,flock 192.168.203.148@tcp:/lustre /mnt/lustre2 PASS 17 (173s) == replay-dual test 18: ldlm_handle_enqueue succeeds on evicted export (3822) ========================================================== 07:45:51 (1787571951) debug=+dlmtrace fail_loc=0x8000030b using seed 359494656 running for 500 iterations total: 500 stats in 2 seconds: 250.000000 stats/second ldlm.namespaces.MGC192.168.203.148@tcp.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffff98964787b800.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffff989648b2b000.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0001-mdc-ffff98964787b800.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0001-mdc-ffff989648b2b000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffff98964787b800.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffff989648b2b000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffff98964787b800.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffff989648b2b000.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.MGC192.168.203.148@tcp.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffff98964787b800.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffff989648b2b000.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0001-mdc-ffff98964787b800.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0001-mdc-ffff989648b2b000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffff98964787b800.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffff989648b2b000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffff98964787b800.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffff989648b2b000.early_lock_cancel=1 fail_loc=0 fail_loc=0 PASS 18 (60s) == replay-dual test 19: resend of open request =========== 07:46:52 (1787572012) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1784 1269520 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre fail_loc=0x157 - open/close 0 (time 1787572112.87 total 88.23 last 0.00) total: 1 open/close in 88.23 seconds: 0.01 ops/second fail_loc=0 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 07:48:39 (1787572119) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 07:49:15 (1787572155) targets are mounted 07:49:15 (1787572155) facet_failover done oleg348-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 (163s) == replay-dual test 20: recovery time is not increasing == 07:49:35 (1787572175) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1784 1269520 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 07:49:50 (1787572190) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 07:50:28 (1787572228) targets are mounted 07:50:28 (1787572228) facet_failover done oleg348-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: oleg348-client.virtnet: -o user_xattr,flock 192.168.203.148@tcp:/lustre /mnt/lustre2 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1784 1269520 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 07:53:08 (1787572388) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 07:53:42 (1787572422) targets are mounted 07:53:42 (1787572422) facet_failover done oleg348-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: oleg348-client.virtnet: -o user_xattr,flock 192.168.203.148@tcp:/lustre /mnt/lustre2 PASS 20 (401s) == replay-dual test 21a: commit on sharing =============== 07:56:17 (1787572577) mdt.lustre-MDT0000.commit_on_sharing=1 mdt.lustre-MDT0001.commit_on_sharing=1 Replay barrier on lustre-MDT0000 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 07:56:31 (1787572591) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 07:57:03 (1787572623) targets are mounted 07:57:03 (1787572623) facet_failover done Starting client: oleg348-client.virtnet: -o user_xattr,flock 192.168.203.148@tcp:/lustre /mnt/lustre2 mdt.lustre-MDT0000.commit_on_sharing=0 mdt.lustre-MDT0001.commit_on_sharing=0 PASS 21a (191s) 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 ========================================================== 07:59:29 (1787572769) fail_loc=0x119 Failing mds2 on oleg348-server Stopping /mnt/lustre-mds2 (opts:) on oleg348-server 07:59:36 (1787572776) shut down facet: mds2 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds2 to oleg348-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0001 08:00:00 (1787572800) targets are mounted 08:00:00 (1787572800) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1792 1269512 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1636 1269668 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.11 seconds: 17.51 ops/second total: 2 open/close in 0.07 seconds: 28.21 ops/second Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 08:00:23 (1787572823) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 08:00:58 (1787572858) targets are mounted 08:00:58 (1787572858) facet_failover done oleg348-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 ========================================================== 08:01:17 (1787572877) fail_loc=0x119 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server Failing mds2 on oleg348-server Stopping /mnt/lustre-mds2 (opts:) on oleg348-server 08:01:29 (1787572889) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server facet: mds2 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Failover mds2 to oleg348-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 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 Started lustre-MDT0001 08:02:00 (1787572920) targets are mounted 08:02:00 (1787572920) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1792 1269512 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1636 1269668 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.13 seconds: 15.22 ops/second total: 2 open/close in 0.07 seconds: 28.86 ops/second Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 08:02:35 (1787572955) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 08:03:13 (1787572993) targets are mounted 08:03:13 (1787572993) facet_failover done oleg348-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 (131s) == replay-dual test 22c: c1 lfs mkdir -i 1 d1, M1 drop update & fail M1, c2 mkdir d1/dir ========================================================== 08:03:28 (1787573008) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 08:03:38 (1787573018) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 08:04:10 (1787573050) targets are mounted 08:04:11 (1787573051) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1792 1269512 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1648 1269656 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.12 seconds: 16.88 ops/second total: 2 open/close in 0.06 seconds: 35.76 ops/second Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 08:04:34 (1787573074) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 08:05:10 (1787573110) targets are mounted 08:05:10 (1787573110) facet_failover done oleg348-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 (119s) == replay-dual test 22d: c1 lfs mkdir -i 1 d1, M1 drop update & fail M0/M1,c2 mkdir d1/dir ========================================================== 08:05:28 (1787573128) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server Failing mds2 on oleg348-server Stopping /mnt/lustre-mds2 (opts:) on oleg348-server 08:05:51 (1787573151) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server facet: mds2 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Failover mds2 to oleg348-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 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 08:06:17 (1787573177) targets are mounted 08:06:17 (1787573177) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1756 1269548 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1600 1269704 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.11 seconds: 18.91 ops/second total: 2 open/close in 0.06 seconds: 32.18 ops/second Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 08:06:50 (1787573210) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 08:07:24 (1787573244) targets are mounted 08:07:24 (1787573244) facet_failover done oleg348-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 (134s) == replay-dual test 23a: c1 rmdir d1, M1 drop reply and fail, client2 mkdir d1 ========================================================== 08:07:41 (1787573261) fail_loc=0x119 fail_loc=0 Failing mds2 on oleg348-server Stopping /mnt/lustre-mds2 (opts:) on oleg348-server 08:07:50 (1787573270) shut down facet: mds2 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds2 to oleg348-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0001 08:08:14 (1787573294) targets are mounted 08:08:14 (1787573294) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1788 1269516 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.13 seconds: 15.53 ops/second Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 08:08:38 (1787573318) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 08:09:11 (1787573351) targets are mounted 08:09:11 (1787573351) facet_failover done oleg348-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 (105s) == replay-dual test 23b: c1 rmdir d1, M1 drop reply and fail M0/M1, c2 mkdir d1 ========================================================== 08:09:26 (1787573366) fail_loc=0x119 fail_loc=0 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server Failing mds2 on oleg348-server Stopping /mnt/lustre-mds2 (opts:) on oleg348-server 08:09:40 (1787573380) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server facet: mds2 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Failover mds2 to oleg348-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 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 08:10:11 (1787573411) targets are mounted 08:10:11 (1787573411) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1788 1269516 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1632 1269672 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.07 seconds: 29.90 ops/second Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 08:10:42 (1787573442) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 08:11:15 (1787573475) targets are mounted 08:11:15 (1787573475) facet_failover done oleg348-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 (132s) == replay-dual test 23c: c1 rmdir d1, M0 drop update reply and fail M0, c2 mkdir d1 ========================================================== 08:11:38 (1787573498) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 08:11:49 (1787573509) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 08:12:22 (1787573542) targets are mounted 08:12:22 (1787573542) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1788 1269516 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1644 1269660 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.11 seconds: 17.73 ops/second Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 08:12:48 (1787573568) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 08:13:25 (1787573605) targets are mounted 08:13:25 (1787573605) facet_failover done oleg348-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 (124s) == replay-dual test 23d: c1 rmdir d1, M0 drop update reply and fail M0/M1, c2 mkdir d1 ========================================================== 08:13:42 (1787573622) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server Failing mds2 on oleg348-server Stopping /mnt/lustre-mds2 (opts:) on oleg348-server 08:14:04 (1787573644) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server facet: mds2 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Failover mds2 to oleg348-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 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 08:14:49 (1787573689) targets are mounted 08:14:49 (1787573689) facet_failover done oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1752 1269552 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1596 1269708 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1560 3605460 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3104 7210936 1% /mnt/lustre total: 2 open/close in 0.08 seconds: 25.19 ops/second Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 08:15:17 (1787573717) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 08:15:53 (1787573753) targets are mounted 08:15:53 (1787573753) facet_failover done oleg348-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 (154s) == replay-dual test 24: reconstruct on non-existing object ========================================================== 08:16:16 (1787573776) fail_loc=0x119 fail_loc=0 truncate: cannot truncate '/mnt/lustre/f24.replay-dual' to length 100: No such file or directory PASS 24 (95s) == replay-dual test 25: replay|resend ==================== 08:17:51 (1787573871) 1+0 records in 1+0 records out 512 bytes copied, 0.0184475 s, 27.8 kB/s fail_loc=0x304 fail_loc=0x80000325 Failing ost1 on oleg348-server Stopping /mnt/lustre-ost1 (opts:) on oleg348-server 08:17:59 (1787573879) shut down facet: ost1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover ost1 to oleg348-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 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-OST0000 08:18:26 (1787573906) targets are mounted 08:18:26 (1787573906) facet_failover done oleg348-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: 64229 Terminated LUSTRE="/home/green/git/lustre-release/lustre" bash -c "multiop /mnt/lustre2/f25.replay-dual Ow512" fail_loc=0 PASS 25 (52s) == replay-dual test 26: dbench and tar with mds failover ========================================================== 08:18:43 (1787573923) Starting client oleg348-client.virtnet: -o user_xattr,flock 192.168.203.148@tcp:/lustre /mnt/lustre Started clients oleg348-client.virtnet: 192.168.203.148@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 65660 Started dbench loop with 65661 striped dir -i0 -c2 -H all_char /mnt/lustre/d26.replay-dual/run_tar striped dir -i0 -c2 -H fnv_1a_64 /mnt/lustre2/d26.replay-dual/run_dbench looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1936 1269368 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1756 1269548 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1564 3605456 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 17928 3580768 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 19492 7186224 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 08:18:49 EDT 2026 waiting for dbench pid 65728 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 24 0.65 MB/sec warmup 1 sec latency 13.332 ms 1 75 1.60 MB/sec warmup 2 sec latency 140.314 ms 1 114 1.74 MB/sec warmup 3 sec latency 207.702 ms 1 151 1.59 MB/sec warmup 4 sec latency 131.848 ms 1 184 1.48 MB/sec warmup 5 sec latency 127.388 ms 1 204 1.33 MB/sec warmup 6 sec latency 466.340 ms 1 247 1.34 MB/sec warmup 7 sec latency 133.511 ms 1 288 1.34 MB/sec warmup 8 sec latency 102.916 ms test_26 fail mds1 1 times 1 334 1.33 MB/sec warmup 9 sec latency 106.615 ms 1 374 1.33 MB/sec warmup 10 sec latency 111.033 ms Failing mds1 on oleg348-server 1 421 1.35 MB/sec warmup 11 sec latency 91.307 ms Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 1 453 1.32 MB/sec warmup 12 sec latency 173.612 ms 1 469 1.26 MB/sec warmup 13 sec latency 578.019 ms 1 469 1.17 MB/sec warmup 14 sec latency 1578.652 ms 08:19:04 (1787573944) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server 1 469 1.09 MB/sec warmup 15 sec latency 2578.887 ms 1 469 1.03 MB/sec warmup 16 sec latency 3579.090 ms 1 469 0.97 MB/sec warmup 17 sec latency 4579.890 ms 1 469 0.91 MB/sec warmup 18 sec latency 5580.112 ms 1 469 0.86 MB/sec warmup 19 sec latency 6580.349 ms 1 469 0.00 MB/sec execute 1 sec latency 8580.957 ms 1 469 0.00 MB/sec execute 2 sec latency 9581.190 ms 1 469 0.00 MB/sec execute 3 sec latency 10581.429 ms 1 469 0.00 MB/sec execute 4 sec latency 11583.254 ms 1 469 0.00 MB/sec execute 5 sec latency 12583.473 ms Failover mds1 to oleg348-server mount facets: mds1 1 469 0.00 MB/sec execute 6 sec latency 13583.881 ms 1 469 0.00 MB/sec execute 7 sec latency 14584.200 ms 1 469 0.00 MB/sec execute 8 sec latency 15585.025 ms 1 469 0.00 MB/sec execute 9 sec latency 16585.311 ms 1 469 0.00 MB/sec execute 10 sec latency 17585.543 ms 1 469 0.00 MB/sec execute 11 sec latency 18586.051 ms 1 469 0.00 MB/sec execute 12 sec latency 19586.408 ms 1 469 0.00 MB/sec execute 13 sec latency 20589.678 ms 1 469 0.00 MB/sec execute 14 sec latency 21591.224 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 469 0.00 MB/sec execute 15 sec latency 22591.504 ms 1 469 0.00 MB/sec execute 16 sec latency 23591.722 ms 1 469 0.00 MB/sec execute 17 sec latency 24591.941 ms 1 469 0.00 MB/sec execute 18 sec latency 25592.139 ms 1 469 0.00 MB/sec execute 19 sec latency 26593.653 ms 1 469 0.00 MB/sec execute 20 sec latency 27593.868 ms 1 469 0.00 MB/sec execute 21 sec latency 28594.240 ms 1 469 0.00 MB/sec execute 22 sec latency 29594.420 ms 1 469 0.00 MB/sec execute 23 sec latency 30594.664 ms 1 469 0.00 MB/sec execute 24 sec latency 31598.529 ms oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all 1 469 0.00 MB/sec execute 25 sec latency 32598.763 ms pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 1 469 0.00 MB/sec execute 26 sec latency 33600.637 ms 1 469 0.00 MB/sec execute 27 sec latency 34613.874 ms Started lustre-MDT0000 08:19:36 (1787573976) targets are mounted 08:19:37 (1787573977) facet_failover done 1 469 0.00 MB/sec execute 28 sec latency 35614.034 ms 1 469 0.00 MB/sec execute 29 sec latency 36615.322 ms 1 472 0.00 MB/sec execute 30 sec latency 37459.963 ms 1 493 0.03 MB/sec execute 31 sec latency 239.477 ms 1 514 0.04 MB/sec execute 32 sec latency 171.863 ms 1 552 0.08 MB/sec execute 33 sec latency 189.534 ms 1 593 0.12 MB/sec execute 34 sec latency 511.106 ms 1 636 0.13 MB/sec execute 35 sec latency 135.472 ms 1 664 0.13 MB/sec execute 36 sec latency 131.738 ms oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 688 0.13 MB/sec execute 37 sec latency 205.897 ms 1 708 0.13 MB/sec execute 38 sec latency 184.939 ms 1 731 0.13 MB/sec execute 39 sec latency 191.688 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 749 0.12 MB/sec execute 40 sec latency 142.189 ms 1 776 0.12 MB/sec execute 41 sec latency 158.969 ms 1 794 0.12 MB/sec execute 42 sec latency 177.772 ms 1 814 0.12 MB/sec execute 43 sec latency 226.103 ms 1 864 0.12 MB/sec execute 44 sec latency 113.060 ms 1 892 0.12 MB/sec execute 45 sec latency 131.963 ms 1 933 0.12 MB/sec execute 46 sec latency 95.059 ms 1 969 0.11 MB/sec execute 47 sec latency 159.448 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2068 1269236 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1908 1269396 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 19620 3579048 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 34752 3570712 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 54372 7149760 1% /mnt/lustre 1 991 0.11 MB/sec execute 48 sec latency 136.969 ms 1 1058 0.13 MB/sec execute 49 sec latency 80.394 ms 1 1091 0.13 MB/sec execute 50 sec latency 103.279 ms 1 1136 0.13 MB/sec execute 51 sec latency 75.770 ms 1 1172 0.13 MB/sec execute 52 sec latency 153.269 ms 1 1181 0.12 MB/sec execute 53 sec latency 813.310 ms 1 1223 0.12 MB/sec execute 54 sec latency 99.238 ms 1 1251 0.12 MB/sec execute 55 sec latency 171.929 ms 1 1378 0.17 MB/sec execute 56 sec latency 95.823 ms 1 1418 0.17 MB/sec execute 57 sec latency 87.816 ms 1 1468 0.17 MB/sec execute 58 sec latency 82.121 ms test_26 fail mds2 2 times 1 1502 0.16 MB/sec execute 59 sec latency 115.745 ms 1 1528 0.16 MB/sec execute 60 sec latency 137.255 ms Failing mds2 on oleg348-server 1 1569 0.16 MB/sec execute 61 sec latency 134.391 ms Stopping /mnt/lustre-mds2 (opts:) on oleg348-server 1 1597 0.16 MB/sec execute 62 sec latency 80.994 ms 1 1628 0.15 MB/sec execute 63 sec latency 125.112 ms 1 1671 0.15 MB/sec execute 64 sec latency 149.218 ms 1 1707 0.15 MB/sec execute 65 sec latency 135.157 ms 1 1783 0.15 MB/sec execute 66 sec latency 69.828 ms 1 1855 0.15 MB/sec execute 67 sec latency 93.088 ms 1 1909 0.15 MB/sec execute 68 sec latency 127.357 ms 1 1978 0.15 MB/sec execute 69 sec latency 111.142 ms 1 2022 0.14 MB/sec execute 70 sec latency 117.555 ms 1 2080 0.14 MB/sec execute 71 sec latency 110.630 ms 08:20:21 (1787574021) shut down facet: mds2 facet_host: oleg348-server facet_failover_host: oleg348-server 1 2129 0.14 MB/sec execute 72 sec latency 138.022 ms 1 2164 0.14 MB/sec execute 73 sec latency 129.601 ms 1 2210 0.14 MB/sec execute 74 sec latency 116.474 ms 1 2259 0.14 MB/sec execute 75 sec latency 267.451 ms 1 2259 0.14 MB/sec execute 76 sec latency 1269.762 ms 1 2259 0.13 MB/sec execute 77 sec latency 2270.382 ms 1 2259 0.13 MB/sec execute 78 sec latency 3271.166 ms 1 2259 0.13 MB/sec execute 79 sec latency 4271.993 ms 1 2259 0.13 MB/sec execute 80 sec latency 5272.260 ms 1 2259 0.13 MB/sec execute 81 sec latency 6272.847 ms Failover mds2 to oleg348-server mount facets: mds2 1 2259 0.13 MB/sec execute 82 sec latency 7273.066 ms 1 2259 0.12 MB/sec execute 83 sec latency 8273.508 ms 1 2259 0.12 MB/sec execute 84 sec latency 9275.249 ms 1 2259 0.12 MB/sec execute 85 sec latency 10275.490 ms 1 2259 0.12 MB/sec execute 86 sec latency 11275.773 ms 1 2259 0.12 MB/sec execute 87 sec latency 12276.409 ms 1 2259 0.12 MB/sec execute 88 sec latency 13276.710 ms 1 2259 0.12 MB/sec execute 89 sec latency 14277.747 ms 1 2259 0.11 MB/sec execute 90 sec latency 15277.915 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 2259 0.11 MB/sec execute 91 sec latency 16278.099 ms 1 2259 0.11 MB/sec execute 92 sec latency 17278.414 ms 1 2259 0.11 MB/sec execute 93 sec latency 18279.402 ms 1 2259 0.11 MB/sec execute 94 sec latency 19281.939 ms 1 2259 0.11 MB/sec execute 95 sec latency 20282.269 ms 1 2259 0.11 MB/sec execute 96 sec latency 21282.625 ms oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all 1 2259 0.11 MB/sec execute 97 sec latency 22282.845 ms pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 1 2259 0.11 MB/sec execute 98 sec latency 23282.995 ms Started lustre-MDT0001 08:20:48 (1787574048) targets are mounted 08:20:48 (1787574048) facet_failover done 1 2259 0.10 MB/sec execute 99 sec latency 24283.780 ms 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec 1 cleanup 103 sec 0 cleanup 104 sec 0 cleanup 104 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 327 251.998 37459.946 Close 280 13.213 181.775 Rename 11 116.052 191.666 Unlink 30 32.951 96.487 Qpathinfo 303 17.578 138.984 Qfileinfo 73 2.704 20.321 Qfsinfo 35 4.804 38.111 Sfileinfo 35 75.579 226.087 Find 96 15.591 121.954 WriteX 255 17.735 153.935 ReadX 364 3.431 114.105 Flush 30 80.541 205.881 Throughput 0.104485 MB/sec 1 clients 1 procs max_latency=37459.963 ms stopping dbench on /mnt/lustre at Mon Aug 24 08:20:54 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished oleg348-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 striped dir -i0 -c2 -H all_char /mnt/lustre2/d26.replay-dual/run_dbench 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 08:21:03 EDT 2026 waiting for dbench pid 67855 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 8 0.00 MB/sec warmup 1 sec latency 135.969 ms 1 55 1.08 MB/sec warmup 2 sec latency 133.431 ms 1 111 1.74 MB/sec warmup 3 sec latency 121.696 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2256 1269048 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2188 1269116 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 36584 3569020 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 10636 3596044 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 47220 7165064 1% /mnt/lustre 1 137 1.50 MB/sec warmup 4 sec latency 258.664 ms 1 165 1.36 MB/sec warmup 5 sec latency 229.666 ms 1 184 1.23 MB/sec warmup 6 sec latency 423.452 ms 1 215 1.19 MB/sec warmup 7 sec latency 461.263 ms 1 263 1.24 MB/sec warmup 8 sec latency 107.731 ms 1 270 1.13 MB/sec warmup 9 sec latency 879.369 ms 1 298 1.10 MB/sec warmup 10 sec latency 1078.392 ms 1 336 1.10 MB/sec warmup 11 sec latency 127.373 ms 1 381 1.13 MB/sec warmup 12 sec latency 105.581 ms test_26 fail mds1 3 times 1 422 1.14 MB/sec warmup 13 sec latency 119.430 ms 1 469 1.17 MB/sec warmup 14 sec latency 124.343 ms Failing mds1 on oleg348-server 1 511 1.18 MB/sec warmup 15 sec latency 110.802 ms Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 1 576 1.21 MB/sec warmup 16 sec latency 131.956 ms 1 600 1.23 MB/sec warmup 17 sec latency 802.626 ms 1 600 1.16 MB/sec warmup 18 sec latency 1802.880 ms 08:21:21 (1787574081) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server 1 600 1.10 MB/sec warmup 19 sec latency 2803.778 ms 1 600 0.00 MB/sec execute 1 sec latency 4806.404 ms 1 600 0.00 MB/sec execute 2 sec latency 5808.463 ms 1 600 0.00 MB/sec execute 3 sec latency 6808.709 ms 1 600 0.00 MB/sec execute 4 sec latency 7809.059 ms 1 600 0.00 MB/sec execute 5 sec latency 8809.291 ms 1 600 0.00 MB/sec execute 6 sec latency 9809.662 ms 1 600 0.00 MB/sec execute 7 sec latency 10811.073 ms 1 600 0.00 MB/sec execute 8 sec latency 11813.883 ms Failover mds1 to oleg348-server mount facets: mds1 1 600 0.00 MB/sec execute 9 sec latency 12815.664 ms 1 600 0.00 MB/sec execute 10 sec latency 13816.583 ms 1 600 0.00 MB/sec execute 11 sec latency 14816.860 ms 1 600 0.00 MB/sec execute 12 sec latency 15821.841 ms 1 600 0.00 MB/sec execute 13 sec latency 16822.077 ms 1 600 0.00 MB/sec execute 14 sec latency 17830.296 ms 1 600 0.00 MB/sec execute 15 sec latency 18830.474 ms 1 600 0.00 MB/sec execute 16 sec latency 19830.787 ms 1 600 0.00 MB/sec execute 17 sec latency 20833.213 ms 1 600 0.00 MB/sec execute 18 sec latency 21833.396 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 600 0.00 MB/sec execute 19 sec latency 22833.788 ms 1 600 0.00 MB/sec execute 20 sec latency 23834.053 ms 1 600 0.00 MB/sec execute 21 sec latency 24834.544 ms 1 600 0.00 MB/sec execute 22 sec latency 25837.249 ms 1 600 0.00 MB/sec execute 23 sec latency 26839.214 ms 1 600 0.00 MB/sec execute 24 sec latency 27839.376 ms 1 600 0.00 MB/sec execute 25 sec latency 28839.598 ms 1 600 0.00 MB/sec execute 26 sec latency 29841.287 ms 1 600 0.00 MB/sec execute 27 sec latency 30851.178 ms 1 600 0.00 MB/sec execute 28 sec latency 31852.611 ms 1 600 0.00 MB/sec execute 29 sec latency 32852.872 ms 1 600 0.00 MB/sec execute 30 sec latency 33853.315 ms 1 600 0.00 MB/sec execute 31 sec latency 34853.572 ms 1 600 0.00 MB/sec execute 32 sec latency 35853.821 ms oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all 1 600 0.00 MB/sec execute 33 sec latency 36854.043 ms pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 1 600 0.00 MB/sec execute 34 sec latency 37854.276 ms Started lustre-MDT0000 08:21:57 (1787574117) targets are mounted 08:21:57 (1787574117) facet_failover done 1 616 0.00 MB/sec execute 35 sec latency 38408.612 ms 1 671 0.01 MB/sec execute 36 sec latency 128.895 ms 1 699 0.01 MB/sec execute 37 sec latency 176.185 ms 1 720 0.01 MB/sec execute 38 sec latency 310.356 ms 1 721 0.01 MB/sec execute 39 sec latency 1266.926 ms 1 741 0.01 MB/sec execute 40 sec latency 187.797 ms 1 778 0.01 MB/sec execute 41 sec latency 118.365 ms oleg348-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 42 sec latency 159.006 ms 1 856 0.01 MB/sec execute 43 sec latency 122.428 ms 1 876 0.02 MB/sec execute 44 sec latency 166.120 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 897 0.02 MB/sec execute 45 sec latency 233.761 ms 1 916 0.02 MB/sec execute 46 sec latency 168.296 ms 1 949 0.02 MB/sec execute 47 sec latency 166.145 ms 1 971 0.02 MB/sec execute 48 sec latency 152.511 ms 1 990 0.02 MB/sec execute 49 sec latency 122.895 ms 1 1011 0.03 MB/sec execute 50 sec latency 158.369 ms 1 1060 0.04 MB/sec execute 51 sec latency 183.780 ms 1 1100 0.04 MB/sec execute 52 sec latency 85.090 ms 1 1139 0.04 MB/sec execute 53 sec latency 95.699 ms 1 1176 0.04 MB/sec execute 54 sec latency 139.581 ms 1 1221 0.04 MB/sec execute 55 sec latency 79.759 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 1251 0.04 MB/sec execute 56 sec latency 126.365 ms 1 1319 0.06 MB/sec execute 57 sec latency 91.389 ms 1 1378 0.09 MB/sec execute 58 sec latency 798.903 ms 1 1418 0.09 MB/sec execute 59 sec latency 220.532 ms 1 1461 0.08 MB/sec execute 60 sec latency 96.043 ms 1 1499 0.08 MB/sec execute 61 sec latency 119.526 ms 1 1532 0.08 MB/sec execute 62 sec latency 138.371 ms 1 1582 0.08 MB/sec execute 63 sec latency 91.434 ms 1 1619 0.08 MB/sec execute 64 sec latency 112.180 ms 1 1656 0.08 MB/sec execute 65 sec latency 113.375 ms 1 1690 0.08 MB/sec execute 66 sec latency 121.136 ms 1 1746 0.08 MB/sec execute 67 sec latency 101.774 ms 1 1808 0.08 MB/sec execute 68 sec latency 100.716 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Mon Aug 24 08:22:31 EDT 2026 with return code 0 67855 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 67855 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished PASS 26 (274s) == replay-dual test 28: lock replay should be ordered: waiting after granted ========================================================== 08:23:17 (1787574197) Waiting for MDT destroys to complete 1+0 records in 1+0 records out 4096 bytes (4.1 kB, 4.0 KiB) copied, 0.0116457 s, 352 kB/s fail_loc=0x80000324 fail_loc=0x32a Failing ost1 on oleg348-server Stopping /mnt/lustre-ost1 (opts:) on oleg348-server 08:23:35 (1787574215) shut down facet: ost1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover ost1 to oleg348-server mount facets: ost1 Start ost1: mount -t lustre -o localrecov /dev/mapper/ost1_flakey /mnt/lustre-ost1 1+0 records in 1+0 records out 4096 bytes (4.1 kB, 4.0 KiB) copied, 0.0124449 s, 329 kB/s seq.cli-lustre-OST0000-super.width=65536 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-OST0000 08:24:03 (1787574243) targets are mounted 08:24:03 (1787574243) facet_failover done oleg348-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 (66s) == replay-dual test 29: replay vs update with the same xid ========================================================== 08:24:24 (1787574264) SKIP: replay-dual test_29 needs >= 2 clients SKIP 29 (5s) == replay-dual test 30: layout lock replay is not blocked on IO ========================================================== 08:24:29 (1787574269) 10+0 records in 10+0 records out 40960 bytes (41 kB, 40 KiB) copied, 0.0379886 s, 1.1 MB/s 10+0 records in 10+0 records out 40960 bytes (41 kB, 40 KiB) copied, 0.0209077 s, 2.0 MB/s fail_loc=0x32e fail_val=4 Failing mds1 on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server 08:24:37 (1787574277) shut down facet: mds1 facet_host: oleg348-server facet_failover_host: oleg348-server Failover mds1 to oleg348-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 08:25:02 (1787574302) targets are mounted 08:25:02 (1787574302) facet_failover done 160+0 records in 160+0 records out 81920 bytes (82 kB, 80 KiB) copied, 30.8224 s, 2.7 kB/s oleg348-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 (51s) == replay-dual test 31: deadlock on file_remove_privs and occupied mod rpc slots ========================================================== 08:25:20 (1787574320) Failing ost1 on oleg348-server Stopping /mnt/lustre-ost1 (opts:) on oleg348-server Creating to objid 2401 on ost lustre-OST0000... 08:25:29 (1787574329) shut down facet: ost1 facet_host: oleg348-server facet_failover_host: oleg348-server total: 32 open/close in 1.23 seconds: 26.06 ops/second at_max=0 fail_loc=0x80001420 file /mnt/lustre2/d31.replay-dual/mdtdir/f31.replay-dual is ready Failover ost1 to oleg348-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 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-OST0000 08:25:54 (1787574354) targets are mounted 08:25:54 (1787574354) facet_failover done oleg348-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: 73060 73061 73066 73067 73068 73069 73070 73071 73072 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2144 1269160 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1880 1269424 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 469 261675 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 262144 391 261753 1% /mnt/lustre[OST:1] filesystem_summary: 524026 598 523428 1% /mnt/lustre at_max=600 PASS 31 (54s) == replay-dual test 32: gap in update llog shouldn't break recovery ========================================================== 08:26:13 (1787574373) fail_loc=0x0000131d fail_val=10 fail_loc=0x726 Stopping /mnt/lustre-mds2 (opts:) on oleg348-server Stopping /mnt/lustre-mds1 (opts:) on oleg348-server fail_loc=0 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0000 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0001 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2248 1269056 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1952 1269352 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 (53s) == replay-dual test 33: Check for OBD_INCOMPAT_MULTI_RPCS in last_rcvd after abort_recovery ========================================================== 08:27:06 (1787574426) at_min=60 Stopping /mnt/lustre-mds2 (opts:) on oleg348-server last_rcvd in /dev/mapper/mds2_flakey: incompat = 0x61c Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0001 oleg348-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 oleg348-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 oleg348-server: oleg348-server.virtnet: executing _wait_recovery_complete *.lustre-MDT0001.recovery_status 1475 oleg348-server: *.lustre-MDT0001.recovery_status status: COMPLETE Stopping /mnt/lustre-mds2 (opts:) on oleg348-server last_rcvd in /dev/mapper/mds2_flakey: incompat = 0x61c Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg348-server: oleg348-server.virtnet: executing set_default_debug -1 all pdsh@oleg348-client: oleg348-server: ssh exited with exit code 1 Started lustre-MDT0001 Starting client: oleg348-client.virtnet: -o user_xattr,flock 192.168.203.148@tcp:/lustre /mnt/lustre2 oleg348-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 oleg348-server: oleg348-server.virtnet: executing _wait_recovery_complete *.lustre-MDT0001.recovery_status 1475 oleg348-server: *.lustre-MDT0001.recovery_status status: COMPLETE at_min=5 PASS 33 (106s) == replay-dual test complete, duration 4650 sec ========== 08:28:52 (1787574532) === replay-dual: start cleanup 08:28:54 (1787574534) === Stopping clients: oleg348-client.virtnet /mnt/lustre2 (opts:) Stopping client oleg348-client.virtnet /mnt/lustre2 opts: === replay-dual: finish cleanup 08:29:07 (1787574547) ===