-----============= acceptance-small: replay-dual ============----- Wed Jul 1 13:43:15 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 oleg442-server: ls: cannot access '/home/green/git/lustre-release/lustre/tests/except/replay-dual.*ex': No such file or directory excepting tests: 14b 21b skipping tests SLOW=no: 21b === replay-dual: start setup 13:43:22 (1782927802) === Starting client oleg442-client.virtnet: -o user_xattr,flock 192.168.204.142@tcp:/lustre /mnt/lustre2 Mount client oleg442-client.virtnet: mount -t lustre -o user_xattr,flock 192.168.204.142@tcp:/lustre /mnt/lustre2 Started clients oleg442-client.virtnet: 192.168.204.142@tcp:/lustre on /mnt/lustre2 type lustre (rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nouser_fid2path,user_xattr,verbose) oleg442-client.virtnet: executing check_config_client /mnt/lustre oleg442-client.virtnet: Checking config lustre mounted on /mnt/lustre Checking servers environments Checking clients oleg442-client.virtnet environments Using TIMEOUT=20 osc.lustre-OST0000-osc-ffffa0a9d1b55800.idle_timeout=debug osc.lustre-OST0000-osc-ffffa0a9d91a7000.idle_timeout=debug osc.lustre-OST0001-osc-ffffa0a9d1b55800.idle_timeout=debug osc.lustre-OST0001-osc-ffffa0a9d91a7000.idle_timeout=debug disable quota as required oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all osd-ldiskfs.track_declares_assert=1 === replay-dual: finish setup 13:43:35 (1782927815) === == replay-dual test 0a: expired recovery with lost client ========================================================== 13:43:35 (1782927815) Check file is LU482_FAILED=/tmp/replay-dual.lu482.QoxeMx 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 0.49 seconds: 101.38 ops/second fail_loc=0x80000514 Failing mds1 on oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 13:43:41 (1782927821) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 13:43:56 (1782927836) targets are mounted 13:43:56 (1782927836) facet_failover done Starting client: oleg442-client.virtnet: -o user_xattr,flock 192.168.204.142@tcp:/lustre /mnt/lustre2 - unlinked 0 (time 1782927952 ; total 0 ; last 0) total: 50 unlinks in 1 seconds: 50.000000 unlinks/second PASS 0a (140s) == replay-dual test 0b: lost client during waiting for next transno ========================================================== 13:45:55 (1782927955) 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 oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 13:46:00 (1782927960) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 13:46:16 (1782927976) targets are mounted 13:46:16 (1782927976) facet_failover done Starting client: oleg442-client.virtnet: -o user_xattr,flock 192.168.204.142@tcp:/lustre /mnt/lustre Starting client: oleg442-client.virtnet: -o user_xattr,flock 192.168.204.142@tcp:/lustre /mnt/lustre2 PASS 0b (100s) == replay-dual test 1: |X| simple create ================= 13:47:35 (1782928055) 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 oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 13:47:39 (1782928059) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 13:47:55 (1782928075) targets are mounted 13:47:55 (1782928075) facet_failover done oleg442-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 (28s) == replay-dual test 2: |X| mkdir adir ==================== 13:48:04 (1782928084) 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 oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 13:48:08 (1782928088) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 13:48:24 (1782928104) targets are mounted 13:48:24 (1782928104) facet_failover done oleg442-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 (28s) == replay-dual test 3: |X| mkdir adir, mkdir adir/bdir === 13:48:32 (1782928112) 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 oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 13:48:37 (1782928117) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 13:48:53 (1782928133) targets are mounted 13:48:53 (1782928133) facet_failover done oleg442-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 (29s) == replay-dual test 4: |X| mkdir adir (-EEXIST), mkdir adir/bdir ========================================================== 13:49:01 (1782928141) 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 oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 13:49:12 (1782928152) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 13:49:28 (1782928168) targets are mounted 13:49:28 (1782928168) facet_failover done oleg442-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 (36s) == replay-dual test 5: open, unlink |X| close ============ 13:49:37 (1782928177) multiop /mnt/lustre2/a vo_tSc TMPPIPE=/tmp/multiop_open_wait_pipe.8193 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 oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 13:49:41 (1782928181) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 13:49:57 (1782928197) targets are mounted 13:49:57 (1782928197) facet_failover done oleg442-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 ========================================================== 13:50:06 (1782928206) multiop /mnt/lustre2/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8193 multiop /mnt/lustre/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8193 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 oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 13:50:11 (1782928211) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 13:50:27 (1782928227) targets are mounted 13:50:27 (1782928227) facet_failover done oleg442-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 (30s) == replay-dual test 8: replay of resent request ========== 13:50:36 (1782928236) 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 oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 13:50:57 (1782928257) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 13:51:12 (1782928272) targets are mounted 13:51:12 (1782928272) facet_failover done oleg442-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 (45s) == replay-dual test 9: resending a replayed create ======= 13:51:21 (1782928281) 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 oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 13:51:25 (1782928285) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 13:51:40 (1782928300) targets are mounted 13:51:40 (1782928300) facet_failover done oleg442-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec fail_loc=0 PASS 9 (42s) == replay-dual test 10: resending a replayed unlink ====== 13:52:03 (1782928323) 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 oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 13:52:07 (1782928327) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 13:52:22 (1782928342) targets are mounted 13:52:22 (1782928342) facet_failover done oleg442-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 ========================================================== 13:52:44 (1782928364) 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 oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 13:52:48 (1782928368) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 13:53:03 (1782928383) targets are mounted 13:53:03 (1782928383) facet_failover done oleg442-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 (38s) == replay-dual test 12: open resend timeout ============== 13:53:22 (1782928402) 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.8193 fail_loc=0x80000302 Failing mds1 on oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 13:53:26 (1782928406) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 13:53:41 (1782928421) targets are mounted 13:53:41 (1782928421) facet_failover done fail_loc=0 /mnt/lustre/f12.replay-dual /mnt/lustre/f12.replay-dual has type file OK PASS 12 (24s) == replay-dual test 13: close resend timeout ============= 13:53:46 (1782928426) multiop /mnt/lustre/f13.replay-dual vmo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8193 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 oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 13:53:51 (1782928431) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 13:54:06 (1782928446) targets are mounted 13:54:06 (1782928446) facet_failover done fail_loc=0 /mnt/lustre/f13.replay-dual /mnt/lustre/f13.replay-dual has type file OK PASS 13 (25s) SKIP: replay-dual test_14b skipping ALWAYS excluded test 14b == replay-dual test 15a: timeout waiting for lost client during replay, 1 client completes ========================================================== 13:54:11 (1782928451) 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 0.23 seconds: 110.00 ops/second total: 1 open/close in 0.01 seconds: 101.54 ops/second Failing mds1 on oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 13:54:16 (1782928456) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 13:54:31 (1782928471) targets are mounted 13:54:31 (1782928471) facet_failover done oleg442-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 1782928544 ; total 0 ; last 0) total: 25 unlinks in 0 seconds: inf unlinks/second Starting client: oleg442-client.virtnet: -o user_xattr,flock 192.168.204.142@tcp:/lustre /mnt/lustre2 PASS 15a (95s) == replay-dual test 15c: remove multiple OST orphans ===== 13:55:46 (1782928546) 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 oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 13:56:19 (1782928579) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 13:56:35 (1782928595) targets are mounted 13:56:35 (1782928595) facet_failover done oleg442-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: oleg442-client.virtnet: -o user_xattr,flock 192.168.204.142@tcp:/lustre /mnt/lustre2 PASS 15c (125s) == replay-dual test 16: fail MDS during recovery (3571) == 13:57:51 (1782928671) 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: 122.87 ops/second total: 1 open/close in 0.01 seconds: 118.54 ops/second Failing mds1 on oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 13:57:55 (1782928675) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 13:58:11 (1782928691) targets are mounted 13:58:11 (1782928691) facet_failover done Failing mds1 on oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 13:58:33 (1782928713) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 13:58:47 (1782928727) targets are mounted 13:58:48 (1782928728) facet_failover done oleg442-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 1782928802 ; total 0 ; last 0) total: 25 unlinks in 0 seconds: inf unlinks/second Starting client: oleg442-client.virtnet: -o user_xattr,flock 192.168.204.142@tcp:/lustre /mnt/lustre2 PASS 16 (133s) == replay-dual test 17: fail OST during recovery (3571) == 14:00:04 (1782928804) total: 25 open/close in 0.23 seconds: 110.73 ops/second total: 1 open/close in 0.01 seconds: 76.83 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 oleg442-server Stopping /mnt/lustre-ost1 (opts:) on oleg442-server 14:00:08 (1782928808) shut down facet: ost1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover ost1 to oleg442-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 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-OST0000 14:00:25 (1782928825) targets are mounted 14:00:25 (1782928825) facet_failover done Failing ost1 on oleg442-server Stopping /mnt/lustre-ost1 (opts:) on oleg442-server 14:00:46 (1782928846) shut down facet: ost1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover ost1 to oleg442-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 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-OST0000 14:01:01 (1782928861) targets are mounted 14:01:01 (1782928861) facet_failover done oleg442-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 1782928936 ; total 0 ; last 0) total: 25 unlinks in 1 seconds: 25.000000 unlinks/second Starting client: oleg442-client.virtnet: -o user_xattr,flock 192.168.204.142@tcp:/lustre /mnt/lustre2 PASS 17 (134s) == replay-dual test 18: ldlm_handle_enqueue succeeds on evicted export (3822) ========================================================== 14:02:18 (1782928938) debug=+dlmtrace fail_loc=0x8000030b using seed 3819912782 running for 500 iterations total: 500 stats in 0 seconds: inf stats/second ldlm.namespaces.MGC192.168.204.142@tcp.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffffa0a9c5335000.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffffa0a9c56d7800.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0001-mdc-ffffa0a9c5335000.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0001-mdc-ffffa0a9c56d7800.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffffa0a9c5335000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffffa0a9c56d7800.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffffa0a9c5335000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffffa0a9c56d7800.early_lock_cancel=0 fail_loc=0x80000305 Error in opening file "/mnt/lustre2/d18.replay-dual/f18.replay-dual"(flags=O_RDONLY) 2: No such file or directory ldlm.namespaces.MGC192.168.204.142@tcp.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffffa0a9c5335000.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffffa0a9c56d7800.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0001-mdc-ffffa0a9c5335000.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0001-mdc-ffffa0a9c56d7800.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffffa0a9c5335000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffffa0a9c56d7800.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffffa0a9c5335000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffffa0a9c56d7800.early_lock_cancel=1 fail_loc=0 fail_loc=0 PASS 18 (47s) == replay-dual test 19: resend of open request =========== 14:03:05 (1782928985) 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 1782929075.09 total 85.96 last 0.00) total: 1 open/close in 85.96 seconds: 0.01 ops/second fail_loc=0 Failing mds1 on oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 14:04:37 (1782929077) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 14:04:53 (1782929093) targets are mounted 14:04:53 (1782929093) facet_failover done oleg442-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 == 14:05:01 (1782929101) 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 oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 14:05:06 (1782929106) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 14:05:21 (1782929121) targets are mounted 14:05:21 (1782929121) facet_failover done oleg442-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: oleg442-client.virtnet: -o user_xattr,flock 192.168.204.142@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 oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 14:07:49 (1782929269) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 14:08:04 (1782929284) targets are mounted 14:08:04 (1782929284) facet_failover done oleg442-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: oleg442-client.virtnet: -o user_xattr,flock 192.168.204.142@tcp:/lustre /mnt/lustre2 PASS 20 (331s) == replay-dual test 21a: commit on sharing =============== 14:10:32 (1782929432) mdt.lustre-MDT0000.commit_on_sharing=1 mdt.lustre-MDT0001.commit_on_sharing=1 Replay barrier on lustre-MDT0000 Failing mds1 on oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 14:10:40 (1782929440) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 14:10:59 (1782929459) targets are mounted 14:10:59 (1782929459) facet_failover done Starting client: oleg442-client.virtnet: -o user_xattr,flock 192.168.204.142@tcp:/lustre /mnt/lustre2 mdt.lustre-MDT0000.commit_on_sharing=0 mdt.lustre-MDT0001.commit_on_sharing=0 PASS 21a (167s) 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 ========================================================== 14:13:19 (1782929599) fail_loc=0x119 Failing mds2 on oleg442-server Stopping /mnt/lustre-mds2 (opts:) on oleg442-server 14:13:23 (1782929603) shut down facet: mds2 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds2 to oleg442-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0001 14:13:38 (1782929618) targets are mounted 14:13:38 (1782929618) facet_failover done oleg442-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 0.05 seconds: 40.04 ops/second total: 2 open/close in 0.02 seconds: 83.94 ops/second Failing mds1 on oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 14:13:50 (1782929630) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 14:14:07 (1782929647) targets are mounted 14:14:07 (1782929647) facet_failover done oleg442-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 (57s) == replay-dual test 22b: c1 lfs mkdir -i 1 d1, M1 drop reply & fail M0/M1, c2 mkdir d1/dir ========================================================== 14:14:16 (1782929656) fail_loc=0x119 Failing mds1 on oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server Failing mds2 on oleg442-server Stopping /mnt/lustre-mds2 (opts:) on oleg442-server 14:14:21 (1782929661) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server facet: mds2 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Failover mds2 to oleg442-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 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 Started lustre-MDT0001 14:14:48 (1782929688) targets are mounted 14:14:48 (1782929688) facet_failover done oleg442-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 0.05 seconds: 40.90 ops/second total: 2 open/close in 0.03 seconds: 79.00 ops/second Failing mds1 on oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 14:15:03 (1782929703) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 14:15:21 (1782929721) targets are mounted 14:15:21 (1782929721) facet_failover done oleg442-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 (75s) == replay-dual test 22c: c1 lfs mkdir -i 1 d1, M1 drop update & fail M1, c2 mkdir d1/dir ========================================================== 14:15:31 (1782929731) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 14:15:36 (1782929736) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 14:15:52 (1782929752) targets are mounted 14:15:52 (1782929752) facet_failover done oleg442-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 0.05 seconds: 38.04 ops/second total: 2 open/close in 0.03 seconds: 76.05 ops/second Failing mds1 on oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 14:16:06 (1782929766) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 14:16:24 (1782929784) targets are mounted 14:16:24 (1782929784) facet_failover done oleg442-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 (62s) == replay-dual test 22d: c1 lfs mkdir -i 1 d1, M1 drop update & fail M0/M1,c2 mkdir d1/dir ========================================================== 14:16:33 (1782929793) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server Failing mds2 on oleg442-server Stopping /mnt/lustre-mds2 (opts:) on oleg442-server 14:16:48 (1782929808) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server facet: mds2 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Failover mds2 to oleg442-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 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 14:17:09 (1782929829) targets are mounted 14:17:09 (1782929829) facet_failover done oleg442-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 0.06 seconds: 31.14 ops/second total: 2 open/close in 0.03 seconds: 76.38 ops/second Failing mds1 on oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 14:17:22 (1782929842) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 14:17:39 (1782929859) targets are mounted 14:17:39 (1782929859) facet_failover done oleg442-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 (75s) == replay-dual test 23a: c1 rmdir d1, M1 drop reply and fail, client2 mkdir d1 ========================================================== 14:17:49 (1782929869) fail_loc=0x119 fail_loc=0 Failing mds2 on oleg442-server Stopping /mnt/lustre-mds2 (opts:) on oleg442-server 14:17:58 (1782929878) shut down facet: mds2 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds2 to oleg442-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0001 14:18:13 (1782929893) targets are mounted 14:18:13 (1782929893) facet_failover done oleg442-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 0.03 seconds: 66.86 ops/second Failing mds1 on oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 14:18:25 (1782929905) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 14:18:41 (1782929921) targets are mounted 14:18:41 (1782929921) facet_failover done oleg442-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 (62s) == replay-dual test 23b: c1 rmdir d1, M1 drop reply and fail M0/M1, c2 mkdir d1 ========================================================== 14:18:51 (1782929931) fail_loc=0x119 fail_loc=0 Failing mds1 on oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server Failing mds2 on oleg442-server Stopping /mnt/lustre-mds2 (opts:) on oleg442-server 14:19:03 (1782929943) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server facet: mds2 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Failover mds2 to oleg442-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 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 14:19:24 (1782929964) targets are mounted 14:19:24 (1782929964) facet_failover done oleg442-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 0.03 seconds: 61.03 ops/second Failing mds1 on oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 14:19:36 (1782929976) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 14:19:53 (1782929993) targets are mounted 14:19:53 (1782929993) facet_failover done oleg442-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 (71s) == replay-dual test 23c: c1 rmdir d1, M0 drop update reply and fail M0, c2 mkdir d1 ========================================================== 14:20:02 (1782930002) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 14:20:06 (1782930006) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 14:20:22 (1782930022) targets are mounted 14:20:22 (1782930022) facet_failover done oleg442-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 0.03 seconds: 63.87 ops/second Failing mds1 on oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 14:20:34 (1782930034) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 14:20:51 (1782930051) targets are mounted 14:20:51 (1782930051) facet_failover done oleg442-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 (58s) == replay-dual test 23d: c1 rmdir d1, M0 drop update reply and fail M0/M1, c2 mkdir d1 ========================================================== 14:21:00 (1782930060) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server Failing mds2 on oleg442-server Stopping /mnt/lustre-mds2 (opts:) on oleg442-server 14:21:14 (1782930074) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server facet: mds2 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Failover mds2 to oleg442-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 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 14:21:35 (1782930095) targets are mounted 14:21:35 (1782930095) facet_failover done oleg442-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: 88.68 ops/second Failing mds1 on oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 14:21:46 (1782930106) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 14:22:03 (1782930123) targets are mounted 14:22:03 (1782930123) facet_failover done oleg442-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 (71s) == replay-dual test 24: reconstruct on non-existing object ========================================================== 14:22:11 (1782930131) 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 ==================== 14:23:39 (1782930219) 1+0 records in 1+0 records out 512 bytes copied, 0.00418629 s, 122 kB/s fail_loc=0x304 fail_loc=0x80000325 Failing ost1 on oleg442-server Stopping /mnt/lustre-ost1 (opts:) on oleg442-server 14:23:42 (1782930222) shut down facet: ost1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover ost1 to oleg442-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 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-OST0000 14:23:57 (1782930237) targets are mounted 14:23:57 (1782930237) facet_failover done oleg442-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: 63972 Terminated LUSTRE="/home/green/git/lustre-release/lustre" bash -c "multiop /mnt/lustre2/f25.replay-dual Ow512" fail_loc=0 PASS 25 (24s) == replay-dual test 26: dbench and tar with mds failover ========================================================== 14:24:03 (1782930243) Starting client oleg442-client.virtnet: -o user_xattr,flock 192.168.204.142@tcp:/lustre /mnt/lustre Started clients oleg442-client.virtnet: 192.168.204.142@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 65407 Started dbench loop with 65408 striped dir -i0 -c2 -H all_char /mnt/lustre2/d26.replay-dual/run_dbench striped dir -i0 -c2 -H fnv_1a_64 /mnt/lustre/d26.replay-dual/run_tar looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt '/usr/share/dbench/client.txt' -> 'client.txt' running 'dbench 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100' on /mnt/lustre at Wed Jul 1 14:24:05 EDT 2026 waiting for dbench pid 65452 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 1992 1269312 1% /mnt/lustre[MDT:0] 1 108 5.11 MB/sec warmup 1 sec latency 33.295 ms lustre-MDT0001_UUID 1414116 1784 1269520 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1564 3605456 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 26120 3579592 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 27684 7185048 1% /mnt/lustre 1 197 3.92 MB/sec warmup 2 sec latency 183.425 ms 1 318 3.83 MB/sec warmup 3 sec latency 44.213 ms 1 428 3.78 MB/sec warmup 4 sec latency 75.219 ms 1 573 3.85 MB/sec warmup 5 sec latency 45.735 ms test_26 fail mds1 1 times Failing mds1 on oleg442-server 1 705 3.53 MB/sec warmup 6 sec latency 35.911 ms Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 1 778 3.05 MB/sec warmup 7 sec latency 353.510 ms 14:24:13 (1782930253) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server 1 884 2.71 MB/sec warmup 8 sec latency 230.516 ms 1 995 2.43 MB/sec warmup 9 sec latency 452.791 ms 1 995 2.19 MB/sec warmup 10 sec latency 1137.286 ms 1 995 1.99 MB/sec warmup 11 sec latency 2137.486 ms 1 995 1.83 MB/sec warmup 12 sec latency 3137.669 ms 1 995 1.69 MB/sec warmup 13 sec latency 4137.851 ms 1 995 1.56 MB/sec warmup 14 sec latency 5138.043 ms 1 995 1.46 MB/sec warmup 15 sec latency 6138.222 ms 1 995 1.37 MB/sec warmup 16 sec latency 7138.431 ms 1 995 1.29 MB/sec warmup 17 sec latency 8138.652 ms Failover mds1 to oleg442-server mount facets: mds1 1 995 1.22 MB/sec warmup 18 sec latency 9138.862 ms 1 995 1.15 MB/sec warmup 19 sec latency 10139.005 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 995 0.00 MB/sec execute 1 sec latency 12139.227 ms 1 995 0.00 MB/sec execute 2 sec latency 13139.408 ms oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 14:24:28 (1782930268) targets are mounted 14:24:28 (1782930268) facet_failover done 1 995 0.00 MB/sec execute 3 sec latency 14139.627 ms 1 995 0.00 MB/sec execute 4 sec latency 15139.791 ms 1 995 0.00 MB/sec execute 5 sec latency 16139.944 ms 1 995 0.00 MB/sec execute 6 sec latency 17140.133 ms 1 1000 0.02 MB/sec execute 7 sec latency 17975.974 ms 1 1128 0.13 MB/sec execute 8 sec latency 160.433 ms oleg442-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 1251 0.13 MB/sec execute 9 sec latency 37.619 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 1467 0.41 MB/sec execute 10 sec latency 111.252 ms 1 1625 0.39 MB/sec execute 11 sec latency 193.167 ms 1 1738 0.36 MB/sec execute 12 sec latency 67.566 ms 1 1908 0.35 MB/sec execute 13 sec latency 32.126 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2416 1268888 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2128 1269176 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 12988 3588832 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 46724 3556316 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 59712 7145148 1% /mnt/lustre 1 2046 0.34 MB/sec execute 14 sec latency 45.851 ms 1 2181 0.32 MB/sec execute 15 sec latency 32.857 ms 1 2377 0.38 MB/sec execute 16 sec latency 35.656 ms 1 2507 0.40 MB/sec execute 17 sec latency 47.142 ms test_26 fail mds2 2 times 1 2884 0.57 MB/sec execute 18 sec latency 29.910 ms Failing mds2 on oleg442-server Stopping /mnt/lustre-mds2 (opts:) on oleg442-server 1 3170 0.64 MB/sec execute 19 sec latency 32.856 ms 1 3494 0.82 MB/sec execute 20 sec latency 81.187 ms 14:24:45 (1782930285) shut down facet: mds2 facet_host: oleg442-server facet_failover_host: oleg442-server 1 3716 0.80 MB/sec execute 21 sec latency 16.112 ms 1 3915 0.83 MB/sec execute 22 sec latency 22.685 ms 1 4083 0.79 MB/sec execute 23 sec latency 25.022 ms 1 4083 0.76 MB/sec execute 24 sec latency 1011.716 ms 1 4083 0.73 MB/sec execute 25 sec latency 2011.961 ms 1 4083 0.70 MB/sec execute 26 sec latency 3012.146 ms 1 4083 0.67 MB/sec execute 27 sec latency 4012.334 ms 1 4083 0.65 MB/sec execute 28 sec latency 5012.534 ms 1 4083 0.63 MB/sec execute 29 sec latency 6012.718 ms 1 4083 0.61 MB/sec execute 30 sec latency 7012.940 ms Failover mds2 to oleg442-server mount facets: mds2 1 4083 0.59 MB/sec execute 31 sec latency 8013.126 ms 1 4083 0.57 MB/sec execute 32 sec latency 9013.281 ms 1 4083 0.55 MB/sec execute 33 sec latency 10013.451 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 4083 0.53 MB/sec execute 34 sec latency 11013.619 ms oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all 1 4083 0.52 MB/sec execute 35 sec latency 12013.770 ms pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0001 14:25:01 (1782930301) targets are mounted 14:25:01 (1782930301) facet_failover done 1 4083 0.50 MB/sec execute 36 sec latency 13013.933 ms 1 4083 0.49 MB/sec execute 37 sec latency 14014.092 ms 1 4083 0.48 MB/sec execute 38 sec latency 15014.231 ms 1 4083 0.47 MB/sec execute 39 sec latency 16014.363 ms 1 4162 0.45 MB/sec execute 40 sec latency 16438.163 ms oleg442-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1 4306 0.45 MB/sec execute 41 sec latency 41.409 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 4448 0.45 MB/sec execute 42 sec latency 30.408 ms 1 4594 0.47 MB/sec execute 43 sec latency 31.455 ms 1 4764 0.46 MB/sec execute 44 sec latency 39.116 ms 1 4970 0.52 MB/sec execute 45 sec latency 38.537 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2960 1268344 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2748 1268556 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 22908 3580164 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 47428 3557312 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 70336 7137476 1% /mnt/lustre 1 5127 0.51 MB/sec execute 46 sec latency 31.867 ms 1 5254 0.50 MB/sec execute 47 sec latency 41.239 ms 1 5386 0.49 MB/sec execute 48 sec latency 47.559 ms 1 5567 0.48 MB/sec execute 49 sec latency 30.313 ms 1 5730 0.48 MB/sec execute 50 sec latency 30.349 ms test_26 fail mds1 3 times Failing mds1 on oleg442-server 1 5938 0.49 MB/sec execute 51 sec latency 23.711 ms Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 1 5977 0.49 MB/sec execute 52 sec latency 691.528 ms 14:25:18 (1782930318) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server 1 5977 0.48 MB/sec execute 53 sec latency 1691.720 ms 1 5977 0.47 MB/sec execute 54 sec latency 2691.865 ms 1 5977 0.46 MB/sec execute 55 sec latency 3692.037 ms 1 5977 0.45 MB/sec execute 56 sec latency 4692.210 ms 1 5977 0.44 MB/sec execute 57 sec latency 5692.421 ms 1 5977 0.44 MB/sec execute 58 sec latency 6692.565 ms 1 5977 0.43 MB/sec execute 59 sec latency 7692.748 ms 1 5977 0.42 MB/sec execute 60 sec latency 8692.953 ms 1 5977 0.41 MB/sec execute 61 sec latency 9693.146 ms 1 5977 0.41 MB/sec execute 62 sec latency 10693.320 ms Failover mds1 to oleg442-server mount facets: mds1 1 5977 0.40 MB/sec execute 63 sec latency 11693.530 ms 1 5977 0.40 MB/sec execute 64 sec latency 12693.723 ms 1 5977 0.39 MB/sec execute 65 sec latency 13693.910 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 5977 0.38 MB/sec execute 66 sec latency 14694.040 ms 1 5977 0.38 MB/sec execute 67 sec latency 15694.225 ms oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 14:25:33 (1782930333) targets are mounted 14:25:33 (1782930333) facet_failover done 1 5977 0.37 MB/sec execute 68 sec latency 16694.404 ms 1 5977 0.37 MB/sec execute 69 sec latency 17694.517 ms 1 5977 0.36 MB/sec execute 70 sec latency 18694.646 ms 1 5977 0.36 MB/sec execute 71 sec latency 19694.785 ms 1 5988 0.35 MB/sec execute 72 sec latency 20588.236 ms 1 6170 0.36 MB/sec execute 73 sec latency 34.840 ms oleg442-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 6545 0.42 MB/sec execute 74 sec latency 43.307 ms 1 6886 0.43 MB/sec execute 75 sec latency 38.789 ms 1 7165 0.47 MB/sec execute 76 sec latency 35.601 ms 1 7352 0.48 MB/sec execute 77 sec latency 24.228 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 3576 1267728 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 3368 1267936 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 25008 3580256 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 48264 3557108 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 73272 7137364 2% /mnt/lustre 1 7504 0.48 MB/sec execute 78 sec latency 60.230 ms 1 7648 0.47 MB/sec execute 79 sec latency 24.580 ms 1 7707 0.47 MB/sec execute 80 sec latency 575.667 ms 1 7886 0.47 MB/sec execute 81 sec latency 54.010 ms 1 8031 0.46 MB/sec execute 82 sec latency 34.578 ms test_26 fail mds2 4 times Failing mds2 on oleg442-server 1 8195 0.47 MB/sec execute 83 sec latency 27.720 ms Stopping /mnt/lustre-mds2 (opts:) on oleg442-server 1 8284 0.47 MB/sec execute 84 sec latency 489.042 ms 1 8284 0.46 MB/sec execute 85 sec latency 1489.182 ms 1 8284 0.46 MB/sec execute 86 sec latency 2489.308 ms 1 8284 0.45 MB/sec execute 87 sec latency 3489.471 ms 1 8284 0.45 MB/sec execute 88 sec latency 4489.693 ms 1 8284 0.44 MB/sec execute 89 sec latency 5490.076 ms 14:25:55 (1782930355) shut down facet: mds2 facet_host: oleg442-server facet_failover_host: oleg442-server 1 8284 0.44 MB/sec execute 90 sec latency 6490.231 ms 1 8284 0.43 MB/sec execute 91 sec latency 7490.442 ms 1 8284 0.43 MB/sec execute 92 sec latency 8490.629 ms 1 8284 0.42 MB/sec execute 93 sec latency 9490.803 ms 1 8284 0.42 MB/sec execute 94 sec latency 10490.986 ms 1 8284 0.41 MB/sec execute 95 sec latency 11491.186 ms 1 8284 0.41 MB/sec execute 96 sec latency 12491.404 ms 1 8284 0.41 MB/sec execute 97 sec latency 13491.812 ms 1 8284 0.40 MB/sec execute 98 sec latency 14492.086 ms 1 8284 0.40 MB/sec execute 99 sec latency 15492.280 ms Failover mds2 to oleg442-server mount facets: mds2 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec 1 cleanup 103 sec Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 cleanup 104 sec oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all 1 cleanup 105 sec pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0001 14:26:11 (1782930371) targets are mounted 14:26:11 (1782930371) facet_failover done 1 cleanup 106 sec 1 cleanup 107 sec 1 cleanup 108 sec 1 cleanup 109 sec 1 cleanup 110 sec 0 cleanup 111 sec 0 cleanup 111 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 1249 29.492 17975.961 Close 922 2.694 16.312 Rename 55 24.303 43.293 Unlink 251 116.625 26445.293 Qpathinfo 1166 18.868 16438.144 Qfileinfo 198 1.051 5.631 Qfsinfo 215 0.472 3.132 Sfileinfo 107 208.487 20588.223 Find 442 4.519 29.561 WriteX 630 4.012 36.744 ReadX 1961 0.278 71.220 LockX 4 2.589 3.095 UnlockX 4 2.543 3.201 Flush 86 13.853 47.125 Throughput 0.397362 MB/sec 1 clients 1 procs max_latency=20588.236 ms stopping dbench on /mnt/lustre at Wed Jul 1 14:26:16 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre oleg442-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid removed 'client.txt' /mnt/lustre dbench successfully finished mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec striped dir -i0 -c2 -H crush /mnt/lustre2/d26.replay-dual/run_dbench looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt '/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 1 14:26:19 EDT 2026 waiting for dbench pid 69656 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 91 4.19 MB/sec warmup 1 sec latency 27.776 ms 1 200 3.92 MB/sec warmup 2 sec latency 143.580 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 3872 1267432 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 3660 1267644 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 39100 3566828 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 12836 3594156 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 51936 7160984 1% /mnt/lustre 1 315 3.83 MB/sec warmup 3 sec latency 72.262 ms 1 453 3.98 MB/sec warmup 4 sec latency 43.755 ms 1 520 3.60 MB/sec warmup 5 sec latency 471.049 ms 1 723 3.55 MB/sec warmup 6 sec latency 39.250 ms test_26 fail mds1 5 times 1 884 3.10 MB/sec warmup 7 sec latency 64.291 ms Failing mds1 on oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 1 914 2.72 MB/sec warmup 8 sec latency 704.813 ms 1 957 2.42 MB/sec warmup 9 sec latency 748.335 ms 14:26:28 (1782930388) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server 1 957 2.18 MB/sec warmup 10 sec latency 1748.486 ms 1 957 1.98 MB/sec warmup 11 sec latency 2748.643 ms 1 957 1.82 MB/sec warmup 12 sec latency 3748.844 ms 1 957 1.68 MB/sec warmup 13 sec latency 4749.017 ms 1 957 1.56 MB/sec warmup 14 sec latency 5749.174 ms 1 957 1.45 MB/sec warmup 15 sec latency 6749.355 ms 1 957 1.36 MB/sec warmup 16 sec latency 7749.549 ms 1 957 1.28 MB/sec warmup 17 sec latency 8749.750 ms 1 957 1.21 MB/sec warmup 18 sec latency 9749.959 ms 1 957 1.15 MB/sec warmup 19 sec latency 10750.177 ms Failover mds1 to oleg442-server mount facets: mds1 1 957 0.00 MB/sec execute 1 sec latency 12750.542 ms 1 957 0.00 MB/sec execute 2 sec latency 13750.656 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 957 0.00 MB/sec execute 3 sec latency 14750.814 ms oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all 1 957 0.00 MB/sec execute 4 sec latency 15751.023 ms pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 14:26:44 (1782930404) targets are mounted 14:26:44 (1782930404) facet_failover done 1 957 0.00 MB/sec execute 5 sec latency 16751.223 ms 1 957 0.00 MB/sec execute 6 sec latency 17751.443 ms 1 957 0.00 MB/sec execute 7 sec latency 18751.662 ms 1 957 0.00 MB/sec execute 8 sec latency 19751.931 ms 1 974 0.00 MB/sec execute 9 sec latency 20556.944 ms 1 1161 0.12 MB/sec execute 10 sec latency 33.005 ms oleg442-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 1391 0.38 MB/sec execute 11 sec latency 33.925 ms 1 1512 0.35 MB/sec execute 12 sec latency 126.981 ms 1 1625 0.33 MB/sec execute 13 sec latency 48.234 ms 1 1775 0.32 MB/sec execute 14 sec latency 132.856 ms 1 1965 0.31 MB/sec execute 15 sec latency 146.651 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 3328 1267976 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2896 1268408 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 41636 3556628 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 17040 3583780 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 58676 7140408 1% /mnt/lustre 1 2081 0.30 MB/sec execute 16 sec latency 44.664 ms 1 2206 0.29 MB/sec execute 17 sec latency 37.721 ms 1 2400 0.34 MB/sec execute 18 sec latency 49.309 ms 1 2582 0.38 MB/sec execute 19 sec latency 42.089 ms test_26 fail mds2 6 times 1 2919 0.58 MB/sec execute 20 sec latency 70.183 ms Failing mds2 on oleg442-server Stopping /mnt/lustre-mds2 (opts:) on oleg442-server 1 3209 0.59 MB/sec execute 21 sec latency 57.951 ms 1 3246 0.59 MB/sec execute 22 sec latency 894.337 ms 14:27:01 (1782930421) shut down facet: mds2 facet_host: oleg442-server facet_failover_host: oleg442-server 1 3246 0.56 MB/sec execute 23 sec latency 1894.549 ms 1 3246 0.54 MB/sec execute 24 sec latency 2894.732 ms 1 3246 0.52 MB/sec execute 25 sec latency 3894.896 ms 1 3246 0.50 MB/sec execute 26 sec latency 4895.086 ms 1 3246 0.48 MB/sec execute 27 sec latency 5895.285 ms 1 3246 0.46 MB/sec execute 28 sec latency 6895.545 ms 1 3246 0.45 MB/sec execute 29 sec latency 7895.739 ms 1 3246 0.43 MB/sec execute 30 sec latency 8895.918 ms 1 3246 0.42 MB/sec execute 31 sec latency 9896.102 ms 1 3246 0.40 MB/sec execute 32 sec latency 10896.319 ms Failover mds2 to oleg442-server mount facets: mds2 1 3246 0.39 MB/sec execute 33 sec latency 11896.520 ms 1 3246 0.38 MB/sec execute 34 sec latency 12896.702 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 3246 0.37 MB/sec execute 35 sec latency 13896.847 ms 1 3246 0.36 MB/sec execute 36 sec latency 14897.051 ms oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all 1 3246 0.35 MB/sec execute 37 sec latency 15897.264 ms pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0001 14:27:16 (1782930436) targets are mounted 14:27:16 (1782930436) facet_failover done 1 3246 0.34 MB/sec execute 38 sec latency 16897.465 ms 1 3246 0.33 MB/sec execute 39 sec latency 17897.625 ms 1 3246 0.32 MB/sec execute 40 sec latency 18897.786 ms 1 3246 0.32 MB/sec execute 41 sec latency 19897.926 ms 1 3339 0.32 MB/sec execute 42 sec latency 20561.346 ms oleg442-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1 3622 0.39 MB/sec execute 43 sec latency 26.646 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 3781 0.41 MB/sec execute 44 sec latency 25.575 ms 1 3920 0.41 MB/sec execute 45 sec latency 28.537 ms 1 4049 0.40 MB/sec execute 46 sec latency 29.184 ms 1 4131 0.39 MB/sec execute 47 sec latency 186.570 ms dbench killed by signal 15 stopping dbench on /mnt/lustre at Wed Jul 1 14:27:27 EDT 2026 with return code 0 69656 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 69656 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished PASS 26 (206s) == replay-dual test 28: lock replay should be ordered: waiting after granted ========================================================== 14:27:29 (1782930449) Waiting for MDT destroys to complete 1+0 records in 1+0 records out 4096 bytes (4.1 kB, 4.0 KiB) copied, 0.00783452 s, 523 kB/s fail_loc=0x80000324 fail_loc=0x32a Failing ost1 on oleg442-server Stopping /mnt/lustre-ost1 (opts:) on oleg442-server 14:27:45 (1782930465) shut down facet: ost1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover ost1 to oleg442-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, 0.00366246 s, 1.1 MB/s oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-OST0000 14:28:00 (1782930480) targets are mounted 14:28:00 (1782930480) facet_failover done oleg442-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 (40s) == replay-dual test 29: replay vs update with the same xid ========================================================== 14:28:09 (1782930489) SKIP: replay-dual test_29 needs >= 2 clients SKIP 29 (1s) == replay-dual test 30: layout lock replay is not blocked on IO ========================================================== 14:28:10 (1782930490) 10+0 records in 10+0 records out 40960 bytes (41 kB, 40 KiB) copied, 0.0118266 s, 3.5 MB/s 10+0 records in 10+0 records out 40960 bytes (41 kB, 40 KiB) copied, 0.0107133 s, 3.8 MB/s fail_loc=0x32e fail_val=4 Failing mds1 on oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server 14:28:13 (1782930493) shut down facet: mds1 facet_host: oleg442-server facet_failover_host: oleg442-server Failover mds1 to oleg442-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 14:28:28 (1782930508) targets are mounted 14:28:28 (1782930508) facet_failover done 160+0 records in 160+0 records out 81920 bytes (82 kB, 80 KiB) copied, 20.8649 s, 3.9 kB/s oleg442-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 (27s) == replay-dual test 31: deadlock on file_remove_privs and occupied mod rpc slots ========================================================== 14:28:37 (1782930517) Failing ost1 on oleg442-server Stopping /mnt/lustre-ost1 (opts:) on oleg442-server 14:28:39 (1782930519) shut down facet: ost1 facet_host: oleg442-server facet_failover_host: oleg442-server Creating to objid 2593 on ost lustre-OST0000... total: 32 open/close in 0.21 seconds: 154.70 ops/second at_max=0 fail_loc=0x80001420 file /mnt/lustre2/d31.replay-dual/mdtdir/f31.replay-dual is ready Failover ost1 to oleg442-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 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-OST0000 14:28:53 (1782930533) targets are mounted 14:28:53 (1782930533) facet_failover done oleg442-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: 76250 76251 76256 76257 76258 76259 76260 76261 76262 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2132 1269172 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1820 1269484 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 342 1023658 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1024000 265 1023735 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 262144 504 261640 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 262144 407 261737 1% /mnt/lustre[OST:1] filesystem_summary: 523984 607 523377 1% /mnt/lustre at_max=600 PASS 31 (23s) == replay-dual test 32: gap in update llog shouldn't break recovery ========================================================== 14:29:00 (1782930540) fail_loc=0x0000131d fail_val=10 fail_loc=0x726 Stopping /mnt/lustre-mds2 (opts:) on oleg442-server Stopping /mnt/lustre-mds1 (opts:) on oleg442-server fail_loc=0 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0000 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0001 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2188 1269116 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1920 1269384 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1568 3605452 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605472 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3112 7210924 1% /mnt/lustre PASS 32 (18s) == replay-dual test 33: Check for OBD_INCOMPAT_MULTI_RPCS in last_rcvd after abort_recovery ========================================================== 14:29:18 (1782930558) at_min=60 Stopping /mnt/lustre-mds2 (opts:) on oleg442-server last_rcvd in /dev/mapper/mds2_flakey: incompat = 0x61c Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0001 oleg442-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 oleg442-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 oleg442-server: oleg442-server.virtnet: executing _wait_recovery_complete *.lustre-MDT0001.recovery_status 1475 oleg442-server: *.lustre-MDT0001.recovery_status status: COMPLETE Stopping /mnt/lustre-mds2 (opts:) on oleg442-server last_rcvd in /dev/mapper/mds2_flakey: incompat = 0x61c Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg442-server: oleg442-server.virtnet: executing set_default_debug -1 all pdsh@oleg442-client: oleg442-server: ssh exited with exit code 1 Started lustre-MDT0001 Starting client: oleg442-client.virtnet: -o user_xattr,flock 192.168.204.142@tcp:/lustre /mnt/lustre2 oleg442-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 oleg442-server: oleg442-server.virtnet: executing _wait_recovery_complete *.lustre-MDT0001.recovery_status 1475 oleg442-server: *.lustre-MDT0001.recovery_status status: COMPLETE at_min=5 PASS 33 (42s) == replay-dual test complete, duration 2804 sec ========== 14:30:00 (1782930600) === replay-dual: start cleanup 14:30:00 (1782930600) === Stopping clients: oleg442-client.virtnet /mnt/lustre2 (opts:) Stopping client oleg442-client.virtnet /mnt/lustre2 opts: === replay-dual: finish cleanup 14:30:03 (1782930603) ===