-----============= acceptance-small: replay-dual ============----- Wed Jul 8 09:22:09 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 oleg322-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 09:22:15 (1783516935) === Starting client oleg322-client.virtnet: -o user_xattr,flock 192.168.203.122@tcp:/lustre /mnt/lustre2 Mount client oleg322-client.virtnet: mount -t lustre -o user_xattr,flock 192.168.203.122@tcp:/lustre /mnt/lustre2 Started clients oleg322-client.virtnet: 192.168.203.122@tcp:/lustre on /mnt/lustre2 type lustre (rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nouser_fid2path,user_xattr,verbose) oleg322-client.virtnet: executing check_config_client /mnt/lustre oleg322-client.virtnet: Checking config lustre mounted on /mnt/lustre Checking servers environments Checking clients oleg322-client.virtnet environments Using TIMEOUT=20 osc.lustre-OST0000-osc-ffff9cae097c8800.idle_timeout=debug osc.lustre-OST0000-osc-ffff9cae1112f000.idle_timeout=debug osc.lustre-OST0001-osc-ffff9cae097c8800.idle_timeout=debug osc.lustre-OST0001-osc-ffff9cae1112f000.idle_timeout=debug disable quota as required oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all osd-ldiskfs.track_declares_assert=1 === replay-dual: finish setup 09:22:28 (1783516948) === == replay-dual test 0a: expired recovery with lost client ========================================================== 09:22:28 (1783516948) Check file is LU482_FAILED=/tmp/replay-dual.lu482.lTkhpy 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 0.50 seconds: 100.99 ops/second fail_loc=0x80000514 Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:22:33 (1783516953) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:22:49 (1783516969) targets are mounted 09:22:49 (1783516969) facet_failover done Starting client: oleg322-client.virtnet: -o user_xattr,flock 192.168.203.122@tcp:/lustre /mnt/lustre2 - unlinked 0 (time 1783517084 ; total 0 ; last 0) total: 50 unlinks in 1 seconds: 50.000000 unlinks/second PASS 0a (139s) == replay-dual test 0b: lost client during waiting for next transno ========================================================== 09:24:47 (1783517087) 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 oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:24:52 (1783517092) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:25:08 (1783517108) targets are mounted 09:25:08 (1783517108) facet_failover done Starting client: oleg322-client.virtnet: -o user_xattr,flock 192.168.203.122@tcp:/lustre /mnt/lustre Starting client: oleg322-client.virtnet: -o user_xattr,flock 192.168.203.122@tcp:/lustre /mnt/lustre2 PASS 0b (100s) == replay-dual test 1: |X| simple create ================= 09:26:27 (1783517187) 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 oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:26:32 (1783517192) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:26:49 (1783517209) targets are mounted 09:26:49 (1783517209) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 1 (31s) == replay-dual test 2: |X| mkdir adir ==================== 09:26:58 (1783517218) 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 oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:27:04 (1783517224) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:27:22 (1783517242) targets are mounted 09:27:22 (1783517242) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 2 (33s) == replay-dual test 3: |X| mkdir adir, mkdir adir/bdir === 09:27:31 (1783517251) 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 oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:27:37 (1783517257) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:27:53 (1783517273) targets are mounted 09:27:54 (1783517274) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 3 (32s) == replay-dual test 4: |X| mkdir adir (-EEXIST), mkdir adir/bdir ========================================================== 09:28:03 (1783517283) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1848 1269456 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre mkdir: cannot create directory '/mnt/lustre/adir': File exists Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:28:08 (1783517288) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:28:24 (1783517304) targets are mounted 09:28:24 (1783517304) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 4 (30s) == replay-dual test 5: open, unlink |X| close ============ 09:28:33 (1783517313) multiop /mnt/lustre2/a vo_tSc TMPPIPE=/tmp/multiop_open_wait_pipe.8211 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:28:38 (1783517318) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:28:53 (1783517333) targets are mounted 09:28:53 (1783517333) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 5 (29s) == replay-dual test 6: open1, open2, unlink |X| close1 [fail mds1] close2 ========================================================== 09:29:02 (1783517342) multiop /mnt/lustre2/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8211 multiop /mnt/lustre/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8211 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:29:06 (1783517346) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:29:22 (1783517362) targets are mounted 09:29:22 (1783517362) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 6 (28s) == replay-dual test 8: replay of resent request ========== 09:29:30 (1783517370) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre fail_loc=0x119 fail_loc=0 Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:29:52 (1783517392) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:30:08 (1783517408) targets are mounted 09:30:08 (1783517408) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 8 (47s) == replay-dual test 9: resending a replayed create ======= 09:30:17 (1783517417) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre fail_loc=0x80000119 Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:30:21 (1783517421) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:30:37 (1783517437) targets are mounted 09:30:37 (1783517437) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec fail_loc=0 PASS 9 (40s) == replay-dual test 10: resending a replayed unlink ====== 09:30:57 (1783517457) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre fail_loc=0x80000119 Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:31:02 (1783517462) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:31:17 (1783517477) targets are mounted 09:31:17 (1783517477) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec fail_loc=0 PASS 10 (41s) == replay-dual test 11: both clients timeout during replay ========================================================== 09:31:38 (1783517498) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre fail_loc=0x0119 Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:31:43 (1783517503) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:31:58 (1783517518) targets are mounted 09:31:58 (1783517518) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount FULL mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 14 sec fail_loc=0 PASS 11 (39s) == replay-dual test 12: open resend timeout ============== 09:32:17 (1783517537) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre multiop /mnt/lustre/f12.replay-dual vmo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8211 fail_loc=0x80000302 Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:32:21 (1783517541) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:32:36 (1783517556) targets are mounted 09:32:36 (1783517556) facet_failover done fail_loc=0 /mnt/lustre/f12.replay-dual /mnt/lustre/f12.replay-dual has type file OK PASS 12 (24s) == replay-dual test 13: close resend timeout ============= 09:32:41 (1783517561) multiop /mnt/lustre/f13.replay-dual vmo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8211 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre fail_loc=0x80000115 Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:32:46 (1783517566) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:33:01 (1783517581) targets are mounted 09:33:01 (1783517581) facet_failover done fail_loc=0 /mnt/lustre/f13.replay-dual /mnt/lustre/f13.replay-dual has type file OK PASS 13 (25s) SKIP: replay-dual test_14b skipping ALWAYS excluded test 14b == replay-dual test 15a: timeout waiting for lost client during replay, 1 client completes ========================================================== 09:33:06 (1783517586) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre total: 25 open/close in 0.20 seconds: 122.94 ops/second total: 1 open/close in 0.01 seconds: 102.82 ops/second Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:33:11 (1783517591) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:33:26 (1783517606) targets are mounted 09:33:26 (1783517606) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec - unlinked 0 (time 1783517680 ; total 0 ; last 0) total: 25 unlinks in 0 seconds: inf unlinks/second Starting client: oleg322-client.virtnet: -o user_xattr,flock 192.168.203.122@tcp:/lustre /mnt/lustre2 PASS 15a (96s) == replay-dual test 15c: remove multiple OST orphans ===== 09:34:42 (1783517682) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:35:14 (1783517714) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:35:29 (1783517729) targets are mounted 09:35:29 (1783517729) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec Starting client: oleg322-client.virtnet: -o user_xattr,flock 192.168.203.122@tcp:/lustre /mnt/lustre2 PASS 15c (125s) == replay-dual test 16: fail MDS during recovery (3571) == 09:36:47 (1783517807) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1820 1269484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre total: 25 open/close in 0.24 seconds: 104.19 ops/second total: 1 open/close in 0.01 seconds: 95.74 ops/second Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:36:52 (1783517812) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:37:07 (1783517827) targets are mounted 09:37:07 (1783517827) facet_failover done Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:37:29 (1783517849) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:37:43 (1783517863) targets are mounted 09:37:43 (1783517863) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec - unlinked 0 (time 1783517938 ; total 0 ; last 0) total: 25 unlinks in 0 seconds: inf unlinks/second Starting client: oleg322-client.virtnet: -o user_xattr,flock 192.168.203.122@tcp:/lustre /mnt/lustre2 PASS 16 (133s) == replay-dual test 17: fail OST during recovery (3571) == 09:39:00 (1783517940) total: 25 open/close in 0.20 seconds: 124.83 ops/second total: 1 open/close in 0.01 seconds: 96.58 ops/second UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1916 1269388 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Failing ost1 on oleg322-server Stopping /mnt/lustre-ost1 (opts:) on oleg322-server 09:39:04 (1783517944) shut down facet: ost1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover ost1 to oleg322-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 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-OST0000 09:39:20 (1783517960) targets are mounted 09:39:20 (1783517960) facet_failover done Failing ost1 on oleg322-server Stopping /mnt/lustre-ost1 (opts:) on oleg322-server 09:39:42 (1783517982) shut down facet: ost1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover ost1 to oleg322-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 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-OST0000 09:40:05 (1783518005) targets are mounted 09:40:05 (1783518005) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in FULL state after 0 sec - unlinked 0 (time 1783518073 ; total 0 ; last 0) total: 25 unlinks in 0 seconds: inf unlinks/second Starting client: oleg322-client.virtnet: -o user_xattr,flock 192.168.203.122@tcp:/lustre /mnt/lustre2 PASS 17 (135s) == replay-dual test 18: ldlm_handle_enqueue succeeds on evicted export (3822) ========================================================== 09:41:15 (1783518075) debug=+dlmtrace fail_loc=0x8000030b using seed 1725843457 running for 500 iterations total: 500 stats in 1 seconds: 500.000000 stats/second ldlm.namespaces.MGC192.168.203.122@tcp.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffff9cae0418c000.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffff9cae097ce000.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0001-mdc-ffff9cae0418c000.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0001-mdc-ffff9cae097ce000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffff9cae0418c000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffff9cae097ce000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffff9cae0418c000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffff9cae097ce000.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.MGC192.168.203.122@tcp.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffff9cae0418c000.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffff9cae097ce000.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0001-mdc-ffff9cae0418c000.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0001-mdc-ffff9cae097ce000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffff9cae0418c000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffff9cae097ce000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffff9cae0418c000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffff9cae097ce000.early_lock_cancel=1 fail_loc=0 fail_loc=0 PASS 18 (47s) == replay-dual test 19: resend of open request =========== 09:42:02 (1783518122) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1920 1269384 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 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 1783518213.00 total 87.31 last 0.00) total: 1 open/close in 87.31 seconds: 0.01 ops/second fail_loc=0 Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:43:35 (1783518215) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:43:50 (1783518230) targets are mounted 09:43:50 (1783518230) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 19 (116s) == replay-dual test 20: recovery time is not increasing == 09:43:58 (1783518238) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1896 1269408 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 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 oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:44:03 (1783518243) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:44:18 (1783518258) targets are mounted 09:44:18 (1783518258) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec Starting client: oleg322-client.virtnet: -o user_xattr,flock 192.168.203.122@tcp:/lustre /mnt/lustre2 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1896 1269408 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 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 oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:46:48 (1783518408) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:47:03 (1783518423) targets are mounted 09:47:03 (1783518423) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec Starting client: oleg322-client.virtnet: -o user_xattr,flock 192.168.203.122@tcp:/lustre /mnt/lustre2 PASS 20 (333s) == replay-dual test 21a: commit on sharing =============== 09:49:31 (1783518571) mdt.lustre-MDT0000.commit_on_sharing=1 mdt.lustre-MDT0001.commit_on_sharing=1 Replay barrier on lustre-MDT0000 Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:49:36 (1783518576) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:49:51 (1783518591) targets are mounted 09:49:51 (1783518591) facet_failover done Starting client: oleg322-client.virtnet: -o user_xattr,flock 192.168.203.122@tcp:/lustre /mnt/lustre2 mdt.lustre-MDT0000.commit_on_sharing=0 mdt.lustre-MDT0001.commit_on_sharing=0 PASS 21a (163s) 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 ========================================================== 09:52:14 (1783518734) fail_loc=0x119 Failing mds2 on oleg322-server Stopping /mnt/lustre-mds2 (opts:) on oleg322-server 09:52:17 (1783518737) shut down facet: mds2 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds2 to oleg322-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0001 09:52:31 (1783518751) targets are mounted 09:52:31 (1783518751) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1904 1269400 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1744 1269560 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 0.03 seconds: 69.89 ops/second total: 2 open/close in 0.01 seconds: 143.91 ops/second Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:52:42 (1783518762) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:52:57 (1783518777) targets are mounted 09:52:57 (1783518777) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 22a (52s) == replay-dual test 22b: c1 lfs mkdir -i 1 d1, M1 drop reply & fail M0/M1, c2 mkdir d1/dir ========================================================== 09:53:06 (1783518786) fail_loc=0x119 Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server Failing mds2 on oleg322-server Stopping /mnt/lustre-mds2 (opts:) on oleg322-server 09:53:17 (1783518797) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server facet: mds2 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Failover mds2 to oleg322-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 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 09:53:38 (1783518818) targets are mounted 09:53:38 (1783518818) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1904 1269400 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1744 1269560 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 0.03 seconds: 75.94 ops/second total: 2 open/close in 0.01 seconds: 155.53 ops/second Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:53:49 (1783518829) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:54:04 (1783518844) targets are mounted 09:54:04 (1783518844) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 22b (67s) == replay-dual test 22c: c1 lfs mkdir -i 1 d1, M1 drop update & fail M1, c2 mkdir d1/dir ========================================================== 09:54:13 (1783518853) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:54:17 (1783518857) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:54:31 (1783518871) targets are mounted 09:54:31 (1783518871) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1904 1269400 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1756 1269548 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 0.02 seconds: 84.98 ops/second total: 2 open/close in 0.01 seconds: 155.05 ops/second Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:54:42 (1783518882) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:54:57 (1783518897) targets are mounted 09:54:57 (1783518897) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 22c (52s) == replay-dual test 22d: c1 lfs mkdir -i 1 d1, M1 drop update & fail M0/M1,c2 mkdir d1/dir ========================================================== 09:55:05 (1783518905) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server Failing mds2 on oleg322-server Stopping /mnt/lustre-mds2 (opts:) on oleg322-server 09:55:18 (1783518918) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server facet: mds2 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Failover mds2 to oleg322-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 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 09:55:40 (1783518940) targets are mounted 09:55:40 (1783518940) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1868 1269436 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 0.04 seconds: 55.40 ops/second total: 2 open/close in 0.01 seconds: 136.11 ops/second Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:55:50 (1783518950) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:56:05 (1783518965) targets are mounted 09:56:05 (1783518965) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 22d (69s) == replay-dual test 23a: c1 rmdir d1, M1 drop reply and fail, client2 mkdir d1 ========================================================== 09:56:14 (1783518974) fail_loc=0x119 fail_loc=0 Failing mds2 on oleg322-server Stopping /mnt/lustre-mds2 (opts:) on oleg322-server 09:56:24 (1783518984) shut down facet: mds2 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds2 to oleg322-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0001 09:56:38 (1783518998) targets are mounted 09:56:38 (1783518998) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1900 1269404 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 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 0.02 seconds: 82.63 ops/second Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:56:49 (1783519009) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:57:05 (1783519025) targets are mounted 09:57:05 (1783519025) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 23a (60s) == replay-dual test 23b: c1 rmdir d1, M1 drop reply and fail M0/M1, c2 mkdir d1 ========================================================== 09:57:14 (1783519034) fail_loc=0x119 fail_loc=0 Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server Failing mds2 on oleg322-server Stopping /mnt/lustre-mds2 (opts:) on oleg322-server 09:57:25 (1783519045) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server facet: mds2 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Failover mds2 to oleg322-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 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 09:57:45 (1783519065) targets are mounted 09:57:45 (1783519065) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1900 1269404 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1740 1269564 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 0.02 seconds: 103.02 ops/second Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:57:55 (1783519075) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:58:11 (1783519091) targets are mounted 09:58:11 (1783519091) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 23b (65s) == replay-dual test 23c: c1 rmdir d1, M0 drop update reply and fail M0, c2 mkdir d1 ========================================================== 09:58:19 (1783519099) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:58:23 (1783519103) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:58:37 (1783519117) targets are mounted 09:58:37 (1783519117) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1900 1269404 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1752 1269552 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 0.02 seconds: 85.58 ops/second Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:58:48 (1783519128) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 09:59:03 (1783519143) targets are mounted 09:59:03 (1783519143) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 23c (53s) == replay-dual test 23d: c1 rmdir d1, M0 drop update reply and fail M0/M1, c2 mkdir d1 ========================================================== 09:59:12 (1783519152) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server Failing mds2 on oleg322-server Stopping /mnt/lustre-mds2 (opts:) on oleg322-server 09:59:26 (1783519166) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server facet: mds2 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Failover mds2 to oleg322-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 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 09:59:46 (1783519186) targets are mounted 09:59:46 (1783519186) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1864 1269440 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 0.02 seconds: 114.51 ops/second Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 09:59:57 (1783519197) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 10:00:13 (1783519213) targets are mounted 10:00:13 (1783519213) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 23d (69s) == replay-dual test 24: reconstruct on non-existing object ========================================================== 10:00:22 (1783519222) fail_loc=0x119 fail_loc=0 truncate: cannot truncate '/mnt/lustre/f24.replay-dual' to length 100: No such file or directory PASS 24 (88s) == replay-dual test 25: replay|resend ==================== 10:01:49 (1783519309) 1+0 records in 1+0 records out 512 bytes copied, 0.00379204 s, 135 kB/s fail_loc=0x304 fail_loc=0x80000325 Failing ost1 on oleg322-server Stopping /mnt/lustre-ost1 (opts:) on oleg322-server 10:01:52 (1783519312) shut down facet: ost1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover ost1 to oleg322-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 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-OST0000 10:02:07 (1783519327) targets are mounted 10:02:07 (1783519327) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in FULL state after 0 sec /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 6933: 64001 Terminated LUSTRE="/home/green/git/lustre-release/lustre" bash -c "multiop /mnt/lustre2/f25.replay-dual Ow512" fail_loc=0 PASS 25 (25s) == replay-dual test 26: dbench and tar with mds failover ========================================================== 10:02:14 (1783519334) Starting client oleg322-client.virtnet: -o user_xattr,flock 192.168.203.122@tcp:/lustre /mnt/lustre Started clients oleg322-client.virtnet: 192.168.203.122@tcp:/lustre on /mnt/lustre type lustre (rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nouser_fid2path,user_xattr,verbose) Started tar loop with pid 65436 Started dbench loop with 65437 striped dir -i0 -c2 -H fnv_1a_64 /mnt/lustre2/d26.replay-dual/run_dbench striped dir -i0 -c2 -H crush2 /mnt/lustre/d26.replay-dual/run_tar looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt '/usr/share/dbench/client.txt' -> 'client.txt' running 'dbench 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100' on /mnt/lustre at Wed Jul 8 10:02:16 EDT 2026 waiting for dbench pid 65478 dbench version 4.00 - Copyright Andrew Tridgell 1999-2004 Running for 100 seconds with load 'client.txt' and minimum warmup 20 secs failed to create barrier semaphore 0 of 1 processes prepared for launch 0 sec 1 of 1 processes prepared for launch 0 sec releasing clients UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2004 1269300 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1780 1269524 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 26140 3579564 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] 1 113 5.24 MB/sec warmup 1 sec latency 55.056 ms filesystem_summary: 7666232 27684 7185040 1% /mnt/lustre 1 207 4.05 MB/sec warmup 2 sec latency 171.126 ms 1 336 4.05 MB/sec warmup 3 sec latency 33.677 ms 1 455 3.98 MB/sec warmup 4 sec latency 72.076 ms 1 639 4.21 MB/sec warmup 5 sec latency 60.793 ms test_26 fail mds1 1 times Failing mds1 on oleg322-server 1 769 3.56 MB/sec warmup 6 sec latency 31.530 ms Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 1 806 3.07 MB/sec warmup 7 sec latency 618.782 ms 10:02:23 (1783519343) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server 1 806 2.68 MB/sec warmup 8 sec latency 1618.919 ms 1 806 2.39 MB/sec warmup 9 sec latency 2619.106 ms 1 806 2.15 MB/sec warmup 10 sec latency 3619.240 ms 1 806 1.95 MB/sec warmup 11 sec latency 4619.406 ms 1 806 1.79 MB/sec warmup 12 sec latency 5619.619 ms 1 806 1.65 MB/sec warmup 13 sec latency 6619.787 ms 1 806 1.53 MB/sec warmup 14 sec latency 7619.938 ms 1 806 1.43 MB/sec warmup 15 sec latency 8620.067 ms 1 806 1.34 MB/sec warmup 16 sec latency 9620.238 ms 1 806 1.26 MB/sec warmup 17 sec latency 10620.415 ms Failover mds1 to oleg322-server mount facets: mds1 1 806 1.19 MB/sec warmup 18 sec latency 11620.674 ms 1 806 1.13 MB/sec warmup 19 sec latency 12620.927 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 806 0.00 MB/sec execute 1 sec latency 14621.225 ms 1 806 0.00 MB/sec execute 2 sec latency 15621.382 ms oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 10:02:38 (1783519358) targets are mounted 10:02:38 (1783519358) facet_failover done 1 806 0.00 MB/sec execute 3 sec latency 16621.533 ms 1 806 0.00 MB/sec execute 4 sec latency 17621.709 ms 1 806 0.00 MB/sec execute 5 sec latency 18621.861 ms 1 806 0.00 MB/sec execute 6 sec latency 19621.982 ms 1 808 0.00 MB/sec execute 7 sec latency 20578.850 ms 1 884 0.02 MB/sec execute 8 sec latency 522.073 ms oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 988 0.05 MB/sec execute 9 sec latency 545.259 ms 1 1160 0.15 MB/sec execute 10 sec latency 29.571 ms 1 1378 0.41 MB/sec execute 11 sec latency 27.599 ms 1 1490 0.38 MB/sec execute 12 sec latency 120.228 ms 1 1601 0.36 MB/sec execute 13 sec latency 28.896 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2408 1268896 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2132 1269172 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 47804 3557928 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 11856 3588916 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 59660 7146844 1% /mnt/lustre 1 1721 0.34 MB/sec execute 14 sec latency 40.848 ms 1 1849 0.33 MB/sec execute 15 sec latency 36.111 ms 1 2053 0.32 MB/sec execute 16 sec latency 23.397 ms 1 2294 0.37 MB/sec execute 17 sec latency 23.886 ms test_26 fail mds2 2 times Failing mds2 on oleg322-server 1 2467 0.40 MB/sec execute 18 sec latency 24.157 ms Stopping /mnt/lustre-mds2 (opts:) on oleg322-server 1 2602 0.40 MB/sec execute 19 sec latency 423.451 ms 10:02:55 (1783519375) shut down facet: mds2 facet_host: oleg322-server facet_failover_host: oleg322-server 1 2602 0.38 MB/sec execute 20 sec latency 1423.598 ms 1 2602 0.36 MB/sec execute 21 sec latency 2423.746 ms 1 2602 0.34 MB/sec execute 22 sec latency 3423.903 ms 1 2602 0.33 MB/sec execute 23 sec latency 4424.068 ms 1 2602 0.31 MB/sec execute 24 sec latency 5424.195 ms 1 2602 0.30 MB/sec execute 25 sec latency 6424.363 ms 1 2602 0.29 MB/sec execute 26 sec latency 7424.562 ms 1 2602 0.28 MB/sec execute 27 sec latency 8424.696 ms 1 2602 0.27 MB/sec execute 28 sec latency 9424.879 ms 1 2602 0.26 MB/sec execute 29 sec latency 10425.059 ms Failover mds2 to oleg322-server mount facets: mds2 1 2602 0.25 MB/sec execute 30 sec latency 11425.228 ms 1 2602 0.24 MB/sec execute 31 sec latency 12425.409 ms 1 2602 0.24 MB/sec execute 32 sec latency 13425.575 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 2602 0.23 MB/sec execute 33 sec latency 14425.686 ms 1 2602 0.22 MB/sec execute 34 sec latency 15425.842 ms oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0001 10:03:11 (1783519391) targets are mounted 10:03:11 (1783519391) facet_failover done 1 2602 0.22 MB/sec execute 35 sec latency 16425.998 ms 1 2602 0.21 MB/sec execute 36 sec latency 17426.168 ms 1 2602 0.20 MB/sec execute 37 sec latency 18426.314 ms 1 2602 0.20 MB/sec execute 38 sec latency 19426.468 ms 1 2768 0.27 MB/sec execute 39 sec latency 20059.281 ms 1 3013 0.30 MB/sec execute 40 sec latency 38.826 ms oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 3352 0.34 MB/sec execute 41 sec latency 31.128 ms 1 3636 0.41 MB/sec execute 42 sec latency 34.228 ms 1 3800 0.43 MB/sec execute 43 sec latency 30.372 ms 1 3948 0.42 MB/sec execute 44 sec latency 44.904 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2968 1268336 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2772 1268532 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 48572 3552468 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 20584 3580496 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 69156 7132964 1% /mnt/lustre 1 4055 0.41 MB/sec execute 45 sec latency 54.658 ms 1 4220 0.41 MB/sec execute 46 sec latency 29.764 ms 1 4307 0.40 MB/sec execute 47 sec latency 312.335 ms 1 4462 0.40 MB/sec execute 48 sec latency 32.053 ms 1 4627 0.42 MB/sec execute 49 sec latency 33.650 ms test_26 fail mds1 3 times Failing mds1 on oleg322-server 1 4793 0.41 MB/sec execute 50 sec latency 32.453 ms Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 1 4944 0.46 MB/sec execute 51 sec latency 511.592 ms 10:03:27 (1783519407) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server 1 4944 0.45 MB/sec execute 52 sec latency 1511.699 ms 1 4944 0.45 MB/sec execute 53 sec latency 2511.816 ms 1 4944 0.44 MB/sec execute 54 sec latency 3511.924 ms 1 4944 0.43 MB/sec execute 55 sec latency 4512.054 ms 1 4944 0.42 MB/sec execute 56 sec latency 5512.195 ms 1 4944 0.41 MB/sec execute 57 sec latency 6512.351 ms 1 4944 0.41 MB/sec execute 58 sec latency 7512.501 ms 1 4944 0.40 MB/sec execute 59 sec latency 8512.653 ms 1 4944 0.39 MB/sec execute 60 sec latency 9512.774 ms 1 4944 0.39 MB/sec execute 61 sec latency 10512.895 ms Failover mds1 to oleg322-server mount facets: mds1 1 4944 0.38 MB/sec execute 62 sec latency 11512.995 ms 1 4944 0.38 MB/sec execute 63 sec latency 12513.104 ms 1 4944 0.37 MB/sec execute 64 sec latency 13513.290 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 4944 0.36 MB/sec execute 65 sec latency 14513.485 ms oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all 1 4944 0.36 MB/sec execute 66 sec latency 15513.671 ms pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 10:03:42 (1783519422) targets are mounted 10:03:42 (1783519422) facet_failover done 1 4944 0.35 MB/sec execute 67 sec latency 16513.852 ms 1 4944 0.35 MB/sec execute 68 sec latency 17514.001 ms 1 4944 0.34 MB/sec execute 69 sec latency 18514.127 ms 1 4944 0.34 MB/sec execute 70 sec latency 19514.255 ms 1 5025 0.33 MB/sec execute 71 sec latency 19908.765 ms oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 5162 0.33 MB/sec execute 72 sec latency 43.823 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 5296 0.33 MB/sec execute 73 sec latency 35.726 ms 1 5454 0.32 MB/sec execute 74 sec latency 25.400 ms 1 5645 0.32 MB/sec execute 75 sec latency 28.134 ms 1 5834 0.33 MB/sec execute 76 sec latency 42.302 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 3624 1267680 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 3436 1267868 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 48560 3553252 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 22020 3581964 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 70580 7135216 1% /mnt/lustre 1 5986 0.33 MB/sec execute 77 sec latency 36.779 ms 1 6154 0.34 MB/sec execute 78 sec latency 54.599 ms 1 6436 0.38 MB/sec execute 79 sec latency 519.682 ms 1 6742 0.40 MB/sec execute 80 sec latency 36.930 ms test_26 fail mds2 4 times 1 7060 0.44 MB/sec execute 81 sec latency 28.398 ms Failing mds2 on oleg322-server Stopping /mnt/lustre-mds2 (opts:) on oleg322-server 1 7238 0.44 MB/sec execute 82 sec latency 29.898 ms 10:03:59 (1783519439) shut down facet: mds2 facet_host: oleg322-server facet_failover_host: oleg322-server 1 7240 0.44 MB/sec execute 83 sec latency 990.811 ms 1 7240 0.43 MB/sec execute 84 sec latency 1990.962 ms 1 7240 0.43 MB/sec execute 85 sec latency 2991.120 ms 1 7240 0.42 MB/sec execute 86 sec latency 3991.276 ms 1 7240 0.42 MB/sec execute 87 sec latency 4991.457 ms 1 7240 0.41 MB/sec execute 88 sec latency 5991.591 ms 1 7240 0.41 MB/sec execute 89 sec latency 6991.726 ms 1 7240 0.40 MB/sec execute 90 sec latency 7991.848 ms 1 7240 0.40 MB/sec execute 91 sec latency 8992.036 ms 1 7240 0.40 MB/sec execute 92 sec latency 9992.203 ms Failover mds2 to oleg322-server 1 7240 0.39 MB/sec execute 93 sec latency 10992.338 ms mount facets: mds2 1 7240 0.39 MB/sec execute 94 sec latency 11992.480 ms 1 7240 0.38 MB/sec execute 95 sec latency 12992.582 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 7240 0.38 MB/sec execute 96 sec latency 13992.706 ms 1 7240 0.38 MB/sec execute 97 sec latency 14992.832 ms oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all 1 7240 0.37 MB/sec execute 98 sec latency 15992.959 ms pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0001 10:04:14 (1783519454) targets are mounted 10:04:14 (1783519454) facet_failover done 1 7240 0.37 MB/sec execute 99 sec latency 16993.091 ms 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec 1 cleanup 103 sec 0 cleanup 104 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 1049 35.173 20578.839 Close 813 2.690 19.986 Rename 49 448.562 20267.056 Unlink 179 9.378 44.886 Qpathinfo 1009 44.437 20059.265 Qfileinfo 186 1.083 3.661 Qfsinfo 179 0.504 5.138 Sfileinfo 91 15.230 28.895 Find 397 4.764 19.205 WriteX 548 4.240 24.771 ReadX 1859 0.256 40.833 LockX 4 2.268 2.754 UnlockX 4 2.391 2.584 Flush 68 17.912 312.319 Throughput 0.367531 MB/sec 1 clients 1 procs max_latency=20578.850 ms stopping dbench on /mnt/lustre at Wed Jul 8 10:04:19 EDT 2026 with return code 0 oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec removed 'client.txt' /mnt/lustre dbench successfully finished striped dir -i0 -c2 -H crush2 /mnt/lustre2/d26.replay-dual/run_dbench looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt '/usr/share/dbench/client.txt' -> 'client.txt' running 'dbench 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100' on /mnt/lustre at Wed Jul 8 10:04:22 EDT 2026 waiting for dbench pid 69719 dbench version 4.00 - Copyright Andrew Tridgell 1999-2004 Running for 100 seconds with load 'client.txt' and minimum warmup 20 secs 0 of 1 processes prepared for launch 0 sec 1 of 1 processes prepared for launch 0 sec releasing clients 1 105 4.91 MB/sec warmup 1 sec latency 37.805 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 3876 1267428 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 3620 1267684 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 14632 3590344 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 37192 3567632 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 51824 7157976 1% /mnt/lustre 1 207 4.05 MB/sec warmup 2 sec latency 141.492 ms 1 339 4.09 MB/sec warmup 3 sec latency 37.297 ms 1 464 4.04 MB/sec warmup 4 sec latency 48.547 ms 1 661 4.23 MB/sec warmup 5 sec latency 31.729 ms 1 801 3.58 MB/sec warmup 6 sec latency 77.354 ms test_26 fail mds1 5 times Failing mds1 on oleg322-server 1 884 3.10 MB/sec warmup 7 sec latency 425.343 ms Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 1 910 2.72 MB/sec warmup 8 sec latency 631.258 ms 10:04:31 (1783519471) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server 1 910 2.42 MB/sec warmup 9 sec latency 1479.347 ms 1 910 2.18 MB/sec warmup 10 sec latency 2479.541 ms 1 910 1.98 MB/sec warmup 11 sec latency 3479.725 ms 1 910 1.81 MB/sec warmup 12 sec latency 4479.931 ms 1 910 1.67 MB/sec warmup 13 sec latency 5480.084 ms 1 910 1.55 MB/sec warmup 14 sec latency 6480.314 ms 1 910 1.45 MB/sec warmup 15 sec latency 7480.520 ms 1 910 1.36 MB/sec warmup 16 sec latency 8480.779 ms 1 910 1.28 MB/sec warmup 17 sec latency 9481.012 ms 1 910 1.21 MB/sec warmup 18 sec latency 10481.216 ms Failover mds1 to oleg322-server mount facets: mds1 1 910 1.14 MB/sec warmup 19 sec latency 11481.388 ms 1 910 0.00 MB/sec execute 1 sec latency 13481.630 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 910 0.00 MB/sec execute 2 sec latency 14481.793 ms 1 910 0.00 MB/sec execute 3 sec latency 15481.928 ms oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 1 910 0.00 MB/sec execute 4 sec latency 16482.057 ms Started lustre-MDT0000 10:04:46 (1783519486) targets are mounted 10:04:46 (1783519486) facet_failover done 1 910 0.00 MB/sec execute 5 sec latency 17482.224 ms 1 910 0.00 MB/sec execute 6 sec latency 18482.407 ms 1 910 0.00 MB/sec execute 7 sec latency 19482.577 ms 1 910 0.00 MB/sec execute 8 sec latency 20482.748 ms 1 1041 0.13 MB/sec execute 9 sec latency 20492.949 ms oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 1207 0.13 MB/sec execute 10 sec latency 33.029 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 1422 0.39 MB/sec execute 11 sec latency 32.404 ms 1 1543 0.36 MB/sec execute 12 sec latency 133.003 ms 1 1646 0.34 MB/sec execute 13 sec latency 63.609 ms 1 1779 0.32 MB/sec execute 14 sec latency 138.495 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 3180 1268124 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2988 1268316 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 13624 3591560 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 44640 3559292 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 58264 7150852 1% /mnt/lustre 1 1912 0.31 MB/sec execute 15 sec latency 52.348 ms 1 2083 0.30 MB/sec execute 16 sec latency 27.056 ms 1 2342 0.36 MB/sec execute 17 sec latency 22.439 ms 1 2458 0.36 MB/sec execute 18 sec latency 69.523 ms test_26 fail mds2 6 times 1 2655 0.44 MB/sec execute 19 sec latency 47.638 ms Failing mds2 on oleg322-server Stopping /mnt/lustre-mds2 (opts:) on oleg322-server 1 2978 0.59 MB/sec execute 20 sec latency 62.139 ms 1 3015 0.56 MB/sec execute 21 sec latency 648.069 ms 10:05:03 (1783519503) shut down facet: mds2 facet_host: oleg322-server facet_failover_host: oleg322-server 1 3015 0.54 MB/sec execute 22 sec latency 1648.203 ms 1 3015 0.51 MB/sec execute 23 sec latency 2648.374 ms 1 3015 0.49 MB/sec execute 24 sec latency 3648.544 ms 1 3015 0.47 MB/sec execute 25 sec latency 4648.703 ms 1 3015 0.45 MB/sec execute 26 sec latency 5648.873 ms 1 3015 0.44 MB/sec execute 27 sec latency 6649.009 ms 1 3015 0.42 MB/sec execute 28 sec latency 7649.216 ms 1 3015 0.41 MB/sec execute 29 sec latency 8649.359 ms 1 3015 0.39 MB/sec execute 30 sec latency 9649.497 ms 1 3015 0.38 MB/sec execute 31 sec latency 10649.647 ms Failover mds2 to oleg322-server mount facets: mds2 1 3015 0.37 MB/sec execute 32 sec latency 11649.754 ms 1 3015 0.36 MB/sec execute 33 sec latency 12649.901 ms 1 3015 0.35 MB/sec execute 34 sec latency 13650.067 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 3015 0.34 MB/sec execute 35 sec latency 14650.245 ms 1 3015 0.33 MB/sec execute 36 sec latency 15650.435 ms oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 1 3015 0.32 MB/sec execute 37 sec latency 16650.613 ms Started lustre-MDT0001 10:05:19 (1783519519) targets are mounted 10:05:19 (1783519519) facet_failover done 1 3015 0.31 MB/sec execute 38 sec latency 17652.181 ms 1 3015 0.30 MB/sec execute 39 sec latency 18652.331 ms 1 3015 0.29 MB/sec execute 40 sec latency 19652.485 ms 1 3019 0.29 MB/sec execute 41 sec latency 20625.769 ms 1 3359 0.33 MB/sec execute 42 sec latency 55.366 ms oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 3644 0.39 MB/sec execute 43 sec latency 24.274 ms 1 3824 0.41 MB/sec execute 44 sec latency 23.570 ms 1 3982 0.41 MB/sec execute 45 sec latency 23.591 ms striped dir -i0 -c2 -H all_char /mnt/lustre/d26.replay-dual/run_tar 1 4103 0.40 MB/sec execute 46 sec latency 68.171 ms 1 4263 0.39 MB/sec execute 47 sec latency 107.544 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2392 1268912 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2148 1269156 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 11900 3594160 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 39460 3564720 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 51360 7158880 1% /mnt/lustre 1 4370 0.39 MB/sec execute 48 sec latency 73.542 ms 1 4483 0.39 MB/sec execute 49 sec latency 217.144 ms 1 4631 0.40 MB/sec execute 50 sec latency 351.581 ms 1 4808 0.40 MB/sec execute 51 sec latency 30.812 ms test_26 fail mds1 7 times Failing mds1 on oleg322-server 1 5031 0.45 MB/sec execute 52 sec latency 87.974 ms Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 1 5123 0.44 MB/sec execute 53 sec latency 473.390 ms 10:05:36 (1783519536) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server 1 5123 0.43 MB/sec execute 54 sec latency 1473.528 ms 1 5123 0.43 MB/sec execute 55 sec latency 2473.650 ms 1 5123 0.42 MB/sec execute 56 sec latency 3473.792 ms 1 5123 0.41 MB/sec execute 57 sec latency 4473.949 ms 1 5123 0.40 MB/sec execute 58 sec latency 5474.114 ms 1 5123 0.40 MB/sec execute 59 sec latency 6474.251 ms 1 5123 0.39 MB/sec execute 60 sec latency 7474.401 ms 1 5123 0.38 MB/sec execute 61 sec latency 8474.546 ms 1 5123 0.38 MB/sec execute 62 sec latency 9474.675 ms 1 5123 0.37 MB/sec execute 63 sec latency 10474.798 ms Failover mds1 to oleg322-server mount facets: mds1 1 5123 0.37 MB/sec execute 64 sec latency 11474.932 ms 1 5123 0.36 MB/sec execute 65 sec latency 12475.096 ms 1 5123 0.36 MB/sec execute 66 sec latency 13475.245 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 5123 0.35 MB/sec execute 67 sec latency 14475.420 ms 1 5123 0.34 MB/sec execute 68 sec latency 15475.587 ms oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 10:05:51 (1783519551) targets are mounted 10:05:51 (1783519551) facet_failover done 1 5123 0.34 MB/sec execute 69 sec latency 16475.752 ms 1 5123 0.34 MB/sec execute 70 sec latency 17475.858 ms 1 5123 0.33 MB/sec execute 71 sec latency 18475.961 ms 1 5123 0.33 MB/sec execute 72 sec latency 19476.103 ms 1 5151 0.32 MB/sec execute 73 sec latency 20129.486 ms 1 5288 0.32 MB/sec execute 74 sec latency 38.135 ms oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 5426 0.32 MB/sec execute 75 sec latency 28.237 ms 1 5641 0.32 MB/sec execute 76 sec latency 23.536 ms 1 5861 0.33 MB/sec execute 77 sec latency 29.951 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 6026 0.33 MB/sec execute 78 sec latency 32.216 ms 1 6320 0.37 MB/sec execute 79 sec latency 87.924 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Wed Jul 8 10:06:01 EDT 2026 with return code 0 69719 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 69719 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished PASS 26 (234s) == replay-dual test 28: lock replay should be ordered: waiting after granted ========================================================== 10:06:08 (1783519568) Waiting for MDT destroys to complete 1+0 records in 1+0 records out 4096 bytes (4.1 kB, 4.0 KiB) copied, 0.00485597 s, 843 kB/s fail_loc=0x80000324 fail_loc=0x32a Failing ost1 on oleg322-server Stopping /mnt/lustre-ost1 (opts:) on oleg322-server 10:06:19 (1783519579) shut down facet: ost1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover ost1 to oleg322-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, 0.00400148 s, 1.0 MB/s oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-OST0000 10:06:34 (1783519594) targets are mounted 10:06:34 (1783519594) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in FULL state after 0 sec PASS 28 (35s) == replay-dual test 29: replay vs update with the same xid ========================================================== 10:06:43 (1783519603) SKIP: replay-dual test_29 needs >= 2 clients SKIP 29 (1s) == replay-dual test 30: layout lock replay is not blocked on IO ========================================================== 10:06:44 (1783519604) 10+0 records in 10+0 records out 40960 bytes (41 kB, 40 KiB) copied, 0.0111379 s, 3.7 MB/s 10+0 records in 10+0 records out 40960 bytes (41 kB, 40 KiB) copied, 0.0130352 s, 3.1 MB/s fail_loc=0x32e fail_val=4 Failing mds1 on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server 10:06:47 (1783519607) shut down facet: mds1 facet_host: oleg322-server facet_failover_host: oleg322-server Failover mds1 to oleg322-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 10:07:01 (1783519621) targets are mounted 10:07:01 (1783519621) facet_failover done 160+0 records in 160+0 records out 81920 bytes (82 kB, 80 KiB) copied, 20.4424 s, 4.0 kB/s oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 30 (26s) == replay-dual test 31: deadlock on file_remove_privs and occupied mod rpc slots ========================================================== 10:07:10 (1783519630) Failing ost1 on oleg322-server Stopping /mnt/lustre-ost1 (opts:) on oleg322-server 10:07:12 (1783519632) shut down facet: ost1 facet_host: oleg322-server facet_failover_host: oleg322-server Creating to objid 2657 on ost lustre-OST0000... total: 32 open/close in 0.20 seconds: 156.88 ops/second at_max=0 fail_loc=0x80001420 file /mnt/lustre2/d31.replay-dual/mdtdir/f31.replay-dual is ready Failover ost1 to oleg322-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 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-OST0000 10:07:27 (1783519647) targets are mounted 10:07:27 (1783519647) facet_failover done oleg322-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in IDLE FULL state after 0 sec pids: 77238 77239 77244 77245 77246 77247 77248 77249 77250 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2172 1269132 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1892 1269412 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 344 1023656 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1024000 261 1023739 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 262144 514 261630 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 262144 415 261729 1% /mnt/lustre[OST:1] filesystem_summary: 523964 605 523359 1% /mnt/lustre at_max=600 PASS 31 (23s) == replay-dual test 32: gap in update llog shouldn't break recovery ========================================================== 10:07:34 (1783519654) fail_loc=0x0000131d fail_val=10 fail_loc=0x726 Stopping /mnt/lustre-mds2 (opts:) on oleg322-server Stopping /mnt/lustre-mds1 (opts:) on oleg322-server fail_loc=0 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0000 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0001 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2276 1269000 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 (18s) == replay-dual test 33: Check for OBD_INCOMPAT_MULTI_RPCS in last_rcvd after abort_recovery ========================================================== 10:07:52 (1783519672) at_min=60 Stopping /mnt/lustre-mds2 (opts:) on oleg322-server last_rcvd in /dev/mapper/mds2_flakey: incompat = 0x61c Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0001 oleg322-client.virtnet: executing wait_import_state_mount REPLAY_WAIT mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0001-mdc-*.mds_server_uuid in REPLAY_WAIT state after 0 sec oleg322-client.virtnet: executing wait_import_state_mount FULL mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec affected facets: mds2 oleg322-server: oleg322-server.virtnet: executing _wait_recovery_complete *.lustre-MDT0001.recovery_status 1475 oleg322-server: *.lustre-MDT0001.recovery_status status: COMPLETE Stopping /mnt/lustre-mds2 (opts:) on oleg322-server last_rcvd in /dev/mapper/mds2_flakey: incompat = 0x61c Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg322-server: oleg322-server.virtnet: executing set_default_debug -1 all pdsh@oleg322-client: oleg322-server: ssh exited with exit code 1 Started lustre-MDT0001 Starting client: oleg322-client.virtnet: -o user_xattr,flock 192.168.203.122@tcp:/lustre /mnt/lustre2 oleg322-client.virtnet: executing wait_import_state_mount FULL mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL DISCONN state after 2 sec affected facets: mds2 oleg322-server: oleg322-server.virtnet: executing _wait_recovery_complete *.lustre-MDT0001.recovery_status 1475 oleg322-server: *.lustre-MDT0001.recovery_status status: COMPLETE at_min=5 PASS 33 (43s) == replay-dual test complete, duration 2785 sec ========== 10:08:35 (1783519715) === replay-dual: start cleanup 10:08:35 (1783519715) === Stopping clients: oleg322-client.virtnet /mnt/lustre2 (opts:) Stopping client oleg322-client.virtnet /mnt/lustre2 opts: === replay-dual: finish cleanup 10:08:38 (1783519718) ===