-----============= acceptance-small: replay-dual ============----- Fri Jul 17 22:24:55 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 oleg130-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 22:25:03 (1784341503) === Starting client oleg130-client.virtnet: -o user_xattr,flock 192.168.201.130@tcp:/lustre /mnt/lustre2 Mount client oleg130-client.virtnet: mount -t lustre -o user_xattr,flock 192.168.201.130@tcp:/lustre /mnt/lustre2 Started clients oleg130-client.virtnet: 192.168.201.130@tcp:/lustre on /mnt/lustre2 type lustre (rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nouser_fid2path,user_xattr,verbose) oleg130-client.virtnet: executing check_config_client /mnt/lustre oleg130-client.virtnet: Checking config lustre mounted on /mnt/lustre Checking servers environments Checking clients oleg130-client.virtnet environments Using TIMEOUT=20 osc.lustre-OST0000-osc-ffff9381c81a2000.idle_timeout=debug osc.lustre-OST0000-osc-ffff9381caf4f800.idle_timeout=debug osc.lustre-OST0001-osc-ffff9381c81a2000.idle_timeout=debug osc.lustre-OST0001-osc-ffff9381caf4f800.idle_timeout=debug disable quota as required oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all osd-ldiskfs.track_declares_assert=1 === replay-dual: finish setup 22:25:18 (1784341518) === == replay-dual test 0a: expired recovery with lost client ========================================================== 22:25:18 (1784341518) Check file is LU482_FAILED=/tmp/replay-dual.lu482.UasTfI 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 1.08 seconds: 46.13 ops/second fail_loc=0x80000514 Failing mds1 on oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 22:25:25 (1784341525) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 22:25:44 (1784341544) targets are mounted 22:25:44 (1784341544) facet_failover done Starting client: oleg130-client.virtnet: -o user_xattr,flock 192.168.201.130@tcp:/lustre /mnt/lustre2 - unlinked 0 (time 1784341659 ; total 0 ; last 0) total: 50 unlinks in 1 seconds: 50.000000 unlinks/second PASS 0a (144s) == replay-dual test 0b: lost client during waiting for next transno ========================================================== 22:27:42 (1784341662) 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 oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 22:27:49 (1784341669) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 22:28:08 (1784341688) targets are mounted 22:28:08 (1784341688) facet_failover done Starting client: oleg130-client.virtnet: -o user_xattr,flock 192.168.201.130@tcp:/lustre /mnt/lustre Starting client: oleg130-client.virtnet: -o user_xattr,flock 192.168.201.130@tcp:/lustre /mnt/lustre2 PASS 0b (198s) == replay-dual test 1: |X| simple create ================= 22:31:00 (1784341860) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1676 1269628 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1532 1269772 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre mcreate: cannot create `/mnt/lustre/fsa-oleg130-client.virtnet' with mode 0100644: File exists Failing mds1 on oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 22:31:06 (1784341866) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 22:31:24 (1784341884) targets are mounted 22:31:24 (1784341884) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 1 (33s) == replay-dual test 2: |X| mkdir adir ==================== 22:31:33 (1784341893) 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 oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 22:31:38 (1784341898) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 22:31:56 (1784341916) targets are mounted 22:31:56 (1784341916) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 2 (32s) == replay-dual test 3: |X| mkdir adir, mkdir adir/bdir === 22:32:05 (1784341925) 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 oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 22:32:11 (1784341931) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 22:32:29 (1784341949) targets are mounted 22:32:29 (1784341949) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 3 (33s) == replay-dual test 4: |X| mkdir adir (-EEXIST), mkdir adir/bdir ========================================================== 22:32:38 (1784341958) 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 oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 22:32:44 (1784341964) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 22:33:02 (1784341982) targets are mounted 22:33:02 (1784341982) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 4 (33s) == replay-dual test 5: open, unlink |X| close ============ 22:33:11 (1784341991) multiop /mnt/lustre2/a vo_tSc TMPPIPE=/tmp/multiop_open_wait_pipe.8218 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 oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 22:33:18 (1784341998) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 22:33:35 (1784342015) targets are mounted 22:33:35 (1784342015) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 5 (33s) == replay-dual test 6: open1, open2, unlink |X| close1 [fail mds1] close2 ========================================================== 22:33:44 (1784342024) multiop /mnt/lustre2/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8218 multiop /mnt/lustre/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8218 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 oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 22:33:50 (1784342030) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 22:34:07 (1784342047) targets are mounted 22:34:07 (1784342047) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 6 (32s) == replay-dual test 8: replay of resent request ========== 22:34:16 (1784342056) 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 oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 22:34:38 (1784342078) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 22:34:56 (1784342096) targets are mounted 22:34:56 (1784342096) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 8 (49s) == replay-dual test 9: resending a replayed create ======= 22:35:05 (1784342105) 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 oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 22:35:10 (1784342110) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 22:35:27 (1784342127) targets are mounted 22:35:27 (1784342127) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec fail_loc=0 PASS 9 (45s) == replay-dual test 10: resending a replayed unlink ====== 22:35:50 (1784342150) 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 oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 22:35:56 (1784342156) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 22:36:12 (1784342172) targets are mounted 22:36:12 (1784342172) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec fail_loc=0 PASS 10 (45s) == replay-dual test 11: both clients timeout during replay ========================================================== 22:36:35 (1784342195) 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 oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 22:36:40 (1784342200) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 22:36:57 (1784342217) targets are mounted 22:36:57 (1784342217) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount FULL mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 13 sec fail_loc=0 PASS 11 (39s) == replay-dual test 12: open resend timeout ============== 22:37:14 (1784342234) 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.8218 fail_loc=0x80000302 Failing mds1 on oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 22:37:19 (1784342239) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 22:37:35 (1784342255) targets are mounted 22:37:35 (1784342255) facet_failover done fail_loc=0 /mnt/lustre/f12.replay-dual /mnt/lustre/f12.replay-dual has type file OK PASS 12 (26s) == replay-dual test 13: close resend timeout ============= 22:37:40 (1784342260) multiop /mnt/lustre/f13.replay-dual vmo_c TMPPIPE=/tmp/multiop_open_wait_pipe.8218 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 oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 22:37:45 (1784342265) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 22:38:01 (1784342281) targets are mounted 22:38:01 (1784342281) 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 ========================================================== 22:38:06 (1784342286) 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: 103.22 ops/second total: 1 open/close in 0.01 seconds: 104.72 ops/second Failing mds1 on oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 22:38:11 (1784342291) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 22:38:27 (1784342307) targets are mounted 22:38:27 (1784342307) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec - unlinked 0 (time 1784342381 ; total 0 ; last 0) total: 25 unlinks in 0 seconds: inf unlinks/second Starting client: oleg130-client.virtnet: -o user_xattr,flock 192.168.201.130@tcp:/lustre /mnt/lustre2 PASS 15a (97s) == replay-dual test 15c: remove multiple OST orphans ===== 22:39:43 (1784342383) 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 oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 22:40:19 (1784342419) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 22:40:35 (1784342435) targets are mounted 22:40:35 (1784342435) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec Starting client: oleg130-client.virtnet: -o user_xattr,flock 192.168.201.130@tcp:/lustre /mnt/lustre2 PASS 15c (127s) == replay-dual test 16: fail MDS during recovery (3571) == 22:41:50 (1784342510) 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 0.22 seconds: 114.10 ops/second total: 1 open/close in 0.01 seconds: 100.74 ops/second Failing mds1 on oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 22:41:55 (1784342515) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 22:42:11 (1784342531) targets are mounted 22:42:11 (1784342531) facet_failover done Failing mds1 on oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 22:42:33 (1784342553) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 22:42:47 (1784342567) targets are mounted 22:42:47 (1784342567) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec - unlinked 0 (time 1784342642 ; total 0 ; last 0) total: 25 unlinks in 0 seconds: inf unlinks/second Starting client: oleg130-client.virtnet: -o user_xattr,flock 192.168.201.130@tcp:/lustre /mnt/lustre2 PASS 16 (133s) == replay-dual test 17: fail OST during recovery (3571) == 22:44:03 (1784342643) total: 25 open/close in 0.19 seconds: 133.00 ops/second total: 1 open/close in 0.01 seconds: 92.07 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 oleg130-server Stopping /mnt/lustre-ost1 (opts:) on oleg130-server 22:44:08 (1784342648) shut down facet: ost1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover ost1 to oleg130-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 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-OST0000 22:44:24 (1784342664) targets are mounted 22:44:24 (1784342664) facet_failover done Failing ost1 on oleg130-server Stopping /mnt/lustre-ost1 (opts:) on oleg130-server 22:44:45 (1784342685) shut down facet: ost1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover ost1 to oleg130-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 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-OST0000 22:45:00 (1784342700) targets are mounted 22:45:00 (1784342700) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid 1475 0 osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in FULL state after 0 sec - unlinked 0 (time 1784342776 ; total 0 ; last 0) total: 25 unlinks in 0 seconds: inf unlinks/second Starting client: oleg130-client.virtnet: -o user_xattr,flock 192.168.201.130@tcp:/lustre /mnt/lustre2 PASS 17 (135s) == replay-dual test 18: ldlm_handle_enqueue succeeds on evicted export (3822) ========================================================== 22:46:18 (1784342778) debug=+dlmtrace fail_loc=0x8000030b using seed 2053918319 running for 500 iterations total: 500 stats in 0 seconds: inf stats/second ldlm.namespaces.MGC192.168.201.130@tcp.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffff9381ca0a6000.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffff9381ca170000.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0001-mdc-ffff9381ca0a6000.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0001-mdc-ffff9381ca170000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffff9381ca0a6000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffff9381ca170000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffff9381ca0a6000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffff9381ca170000.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.MGC192.168.201.130@tcp.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffff9381ca0a6000.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffff9381ca170000.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0001-mdc-ffff9381ca0a6000.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0001-mdc-ffff9381ca170000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffff9381ca0a6000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffff9381ca170000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffff9381ca0a6000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffff9381ca170000.early_lock_cancel=1 fail_loc=0 fail_loc=0 PASS 18 (46s) == replay-dual test 19: resend of open request =========== 22:47:04 (1784342824) 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 1784342915.78 total 87.49 last 0.00) total: 1 open/close in 87.49 seconds: 0.01 ops/second fail_loc=0 Failing mds1 on oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 22:48:37 (1784342917) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 22:48:53 (1784342933) targets are mounted 22:48:53 (1784342933) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 19 (117s) == replay-dual test 20: recovery time is not increasing == 22:49:01 (1784342941) 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 oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 22:49:06 (1784342946) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 22:49:21 (1784342961) targets are mounted 22:49:21 (1784342961) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec Starting client: oleg130-client.virtnet: -o user_xattr,flock 192.168.201.130@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 oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 22:51:51 (1784343111) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 22:52:06 (1784343126) targets are mounted 22:52:06 (1784343126) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec Starting client: oleg130-client.virtnet: -o user_xattr,flock 192.168.201.130@tcp:/lustre /mnt/lustre2 PASS 20 (333s) == replay-dual test 21a: commit on sharing =============== 22:54:34 (1784343274) mdt.lustre-MDT0000.commit_on_sharing=1 mdt.lustre-MDT0001.commit_on_sharing=1 Replay barrier on lustre-MDT0000 Failing mds1 on oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 22:54:39 (1784343279) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 22:54:54 (1784343294) targets are mounted 22:54:54 (1784343294) facet_failover done Starting client: oleg130-client.virtnet: -o user_xattr,flock 192.168.201.130@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 ========================================================== 22:57:18 (1784343438) fail_loc=0x119 Failing mds2 on oleg130-server Stopping /mnt/lustre-mds2 (opts:) on oleg130-server 22:57:21 (1784343441) shut down facet: mds2 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds2 to oleg130-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0001 22:57:35 (1784343455) targets are mounted 22:57:35 (1784343455) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 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: 73.11 ops/second total: 2 open/close in 0.01 seconds: 138.73 ops/second Failing mds1 on oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 22:57:46 (1784343466) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 22:58:05 (1784343485) targets are mounted 22:58:05 (1784343485) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 22a (57s) == replay-dual test 22b: c1 lfs mkdir -i 1 d1, M1 drop reply & fail M0/M1, c2 mkdir d1/dir ========================================================== 22:58:15 (1784343495) fail_loc=0x119 Failing mds1 on oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server Failing mds2 on oleg130-server Stopping /mnt/lustre-mds2 (opts:) on oleg130-server 22:58:23 (1784343503) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server facet: mds2 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Failover mds2 to oleg130-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 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 22:58:50 (1784343530) targets are mounted 22:58:50 (1784343530) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 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: 64.42 ops/second total: 2 open/close in 0.01 seconds: 152.33 ops/second Failing mds1 on oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 22:59:01 (1784343541) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 22:59:18 (1784343558) targets are mounted 22:59:18 (1784343558) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 22b (72s) == replay-dual test 22c: c1 lfs mkdir -i 1 d1, M1 drop update & fail M1, c2 mkdir d1/dir ========================================================== 22:59:27 (1784343567) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 22:59:31 (1784343571) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 22:59:46 (1784343586) targets are mounted 22:59:46 (1784343586) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 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 0.04 seconds: 48.91 ops/second total: 2 open/close in 0.02 seconds: 96.55 ops/second Failing mds1 on oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 22:59:58 (1784343598) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 23:00:14 (1784343614) targets are mounted 23:00:14 (1784343614) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 22c (56s) == replay-dual test 22d: c1 lfs mkdir -i 1 d1, M1 drop update & fail M0/M1,c2 mkdir d1/dir ========================================================== 23:00:23 (1784343623) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server Failing mds2 on oleg130-server Stopping /mnt/lustre-mds2 (opts:) on oleg130-server 23:00:37 (1784343637) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server facet: mds2 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Failover mds2 to oleg130-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 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 23:00:58 (1784343658) targets are mounted 23:00:58 (1784343658) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 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: 49.65 ops/second total: 2 open/close in 0.02 seconds: 103.05 ops/second Failing mds1 on oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 23:01:16 (1784343676) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 23:01:33 (1784343693) targets are mounted 23:01:33 (1784343693) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 22d (80s) == replay-dual test 23a: c1 rmdir d1, M1 drop reply and fail, client2 mkdir d1 ========================================================== 23:01:43 (1784343703) fail_loc=0x119 fail_loc=0 Failing mds2 on oleg130-server Stopping /mnt/lustre-mds2 (opts:) on oleg130-server 23:01:53 (1784343713) shut down facet: mds2 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds2 to oleg130-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0001 23:02:08 (1784343728) targets are mounted 23:02:08 (1784343728) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 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 0.04 seconds: 52.42 ops/second Failing mds1 on oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 23:02:20 (1784343740) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 23:02:37 (1784343757) targets are mounted 23:02:37 (1784343757) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 23a (63s) == replay-dual test 23b: c1 rmdir d1, M1 drop reply and fail M0/M1, c2 mkdir d1 ========================================================== 23:02:46 (1784343766) fail_loc=0x119 fail_loc=0 Failing mds1 on oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server Failing mds2 on oleg130-server Stopping /mnt/lustre-mds2 (opts:) on oleg130-server 23:02:58 (1784343778) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server facet: mds2 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Failover mds2 to oleg130-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 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 Started lustre-MDT0001 23:03:20 (1784343800) targets are mounted 23:03:20 (1784343800) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 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 0.04 seconds: 54.41 ops/second Failing mds1 on oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 23:03:43 (1784343823) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 23:04:02 (1784343842) targets are mounted 23:04:02 (1784343842) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 23b (85s) == replay-dual test 23c: c1 rmdir d1, M0 drop update reply and fail M0, c2 mkdir d1 ========================================================== 23:04:11 (1784343851) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 23:04:15 (1784343855) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 23:04:30 (1784343870) targets are mounted 23:04:30 (1784343870) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 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: 78.30 ops/second Failing mds1 on oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 23:04:42 (1784343882) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 23:04:59 (1784343899) targets are mounted 23:04:59 (1784343899) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 23c (57s) == replay-dual test 23d: c1 rmdir d1, M0 drop update reply and fail M0/M1, c2 mkdir d1 ========================================================== 23:05:08 (1784343908) fail_loc=0x1701 fail_loc=0 Failing mds1 on oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server Failing mds2 on oleg130-server Stopping /mnt/lustre-mds2 (opts:) on oleg130-server 23:05:22 (1784343922) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server facet: mds2 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Failover mds2 to oleg130-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 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 Started lustre-MDT0001 23:05:42 (1784343942) targets are mounted 23:05:42 (1784343942) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 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 0.03 seconds: 57.22 ops/second Failing mds1 on oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 23:05:56 (1784343956) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 23:06:13 (1784343973) targets are mounted 23:06:13 (1784343973) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 23d (73s) == replay-dual test 24: reconstruct on non-existing object ========================================================== 23:06:21 (1784343981) 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 ==================== 23:07:49 (1784344069) 1+0 records in 1+0 records out 512 bytes copied, 0.00462701 s, 111 kB/s fail_loc=0x304 fail_loc=0x80000325 Failing ost1 on oleg130-server Stopping /mnt/lustre-ost1 (opts:) on oleg130-server 23:07:53 (1784344073) shut down facet: ost1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover ost1 to oleg130-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 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-OST0000 23:08:09 (1784344089) targets are mounted 23:08:09 (1784344089) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid 1475 0 osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in FULL state after 0 sec /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 6934: 64027 Terminated LUSTRE="/home/green/git/lustre-release/lustre" bash -c "multiop /mnt/lustre2/f25.replay-dual Ow512" fail_loc=0 PASS 25 (28s) == replay-dual test 26: dbench and tar with mds failover ========================================================== 23:08:17 (1784344097) Starting client oleg130-client.virtnet: -o user_xattr,flock 192.168.201.130@tcp:/lustre /mnt/lustre Started clients oleg130-client.virtnet: 192.168.201.130@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 65463 Started dbench loop with 65464 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 Fri Jul 17 23:08:19 EDT 2026 waiting for dbench pid 65507 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] 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 1544 3579592 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3108 7185048 1% /mnt/lustre 1 102 4.72 MB/sec warmup 1 sec latency 47.382 ms 1 184 3.69 MB/sec warmup 2 sec latency 92.890 ms 1 280 3.48 MB/sec warmup 3 sec latency 164.219 ms 1 374 3.33 MB/sec warmup 4 sec latency 59.112 ms 1 478 3.34 MB/sec warmup 5 sec latency 59.985 ms test_26 fail mds1 1 times 1 615 3.50 MB/sec warmup 6 sec latency 67.069 ms Failing mds1 on oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 1 731 3.04 MB/sec warmup 7 sec latency 46.349 ms 1 810 2.68 MB/sec warmup 8 sec latency 154.135 ms 23:08:28 (1784344108) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server 1 896 2.41 MB/sec warmup 9 sec latency 376.139 ms 1 995 2.19 MB/sec warmup 10 sec latency 157.829 ms 1 995 1.99 MB/sec warmup 11 sec latency 1159.424 ms 1 995 1.83 MB/sec warmup 12 sec latency 2159.838 ms 1 995 1.68 MB/sec warmup 13 sec latency 3160.004 ms 1 995 1.56 MB/sec warmup 14 sec latency 4160.441 ms 1 995 1.46 MB/sec warmup 15 sec latency 5160.670 ms 1 995 1.37 MB/sec warmup 16 sec latency 6160.864 ms 1 995 1.29 MB/sec warmup 17 sec latency 7161.053 ms 1 995 1.22 MB/sec warmup 18 sec latency 8161.377 ms Failover mds1 to oleg130-server mount facets: mds1 1 995 1.15 MB/sec warmup 19 sec latency 9161.556 ms 1 995 0.00 MB/sec execute 1 sec latency 11162.401 ms 1 995 0.00 MB/sec execute 2 sec latency 12162.626 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 995 0.00 MB/sec execute 3 sec latency 13162.757 ms 1 995 0.00 MB/sec execute 4 sec latency 14162.904 ms oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 23:08:44 (1784344124) targets are mounted 23:08:44 (1784344124) facet_failover done 1 995 0.00 MB/sec execute 5 sec latency 15163.087 ms 1 995 0.00 MB/sec execute 6 sec latency 16163.209 ms 1 995 0.00 MB/sec execute 7 sec latency 17163.353 ms 1 995 0.00 MB/sec execute 8 sec latency 18163.537 ms 1 995 0.00 MB/sec execute 9 sec latency 19164.488 ms 1 1077 0.10 MB/sec execute 10 sec latency 19293.835 ms oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 1174 0.10 MB/sec execute 11 sec latency 61.361 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 1267 0.10 MB/sec execute 12 sec latency 38.473 ms 1 1481 0.32 MB/sec execute 13 sec latency 135.671 ms 1 1646 0.31 MB/sec execute 14 sec latency 30.316 ms 1 1802 0.29 MB/sec execute 15 sec latency 35.143 ms 1 1974 0.28 MB/sec execute 16 sec latency 37.598 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2352 1268952 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2096 1269208 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 4968 3594180 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 42952 3555760 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 47920 7149940 1% /mnt/lustre 1 2083 0.28 MB/sec execute 17 sec latency 66.082 ms 1 2206 0.27 MB/sec execute 18 sec latency 42.593 ms 1 2354 0.32 MB/sec execute 19 sec latency 36.259 ms 1 2452 0.31 MB/sec execute 20 sec latency 52.570 ms test_26 fail mds2 2 times 1 2622 0.34 MB/sec execute 21 sec latency 39.840 ms Failing mds2 on oleg130-server Stopping /mnt/lustre-mds2 (opts:) on oleg130-server 1 2929 0.53 MB/sec execute 22 sec latency 51.100 ms 1 3207 0.54 MB/sec execute 23 sec latency 41.870 ms 23:09:02 (1784344142) shut down facet: mds2 facet_host: oleg130-server facet_failover_host: oleg130-server 1 3501 0.68 MB/sec execute 24 sec latency 31.833 ms 1 3695 0.67 MB/sec execute 25 sec latency 19.606 ms 1 3848 0.69 MB/sec execute 26 sec latency 37.832 ms 1 3985 0.67 MB/sec execute 27 sec latency 35.577 ms 1 4083 0.65 MB/sec execute 28 sec latency 299.343 ms 1 4083 0.63 MB/sec execute 29 sec latency 1299.578 ms 1 4083 0.61 MB/sec execute 30 sec latency 2299.786 ms 1 4083 0.59 MB/sec execute 31 sec latency 3299.987 ms 1 4083 0.57 MB/sec execute 32 sec latency 4300.774 ms 1 4083 0.55 MB/sec execute 33 sec latency 5300.973 ms Failover mds2 to oleg130-server mount facets: mds2 1 4083 0.53 MB/sec execute 34 sec latency 6301.141 ms 1 4083 0.52 MB/sec execute 35 sec latency 7301.306 ms 1 4083 0.50 MB/sec execute 36 sec latency 8301.471 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 4083 0.49 MB/sec execute 37 sec latency 9301.650 ms 1 4083 0.48 MB/sec execute 38 sec latency 10302.055 ms 1 4083 0.47 MB/sec execute 39 sec latency 11302.261 ms oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0001 23:09:19 (1784344159) targets are mounted 23:09:19 (1784344159) facet_failover done 1 4083 0.45 MB/sec execute 40 sec latency 12302.446 ms 1 4083 0.44 MB/sec execute 41 sec latency 13302.572 ms 1 4083 0.43 MB/sec execute 42 sec latency 14302.764 ms 1 4083 0.42 MB/sec execute 43 sec latency 15302.892 ms 1 4214 0.42 MB/sec execute 44 sec latency 15480.599 ms oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 1 4312 0.41 MB/sec execute 45 sec latency 51.594 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 4432 0.41 MB/sec execute 46 sec latency 43.633 ms 1 4531 0.40 MB/sec execute 47 sec latency 40.684 ms 1 4670 0.42 MB/sec execute 48 sec latency 35.673 ms 1 4791 0.41 MB/sec execute 49 sec latency 41.564 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2772 1268532 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2448 1268856 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 11248 3594060 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 57116 3547468 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 68364 7141528 1% /mnt/lustre 1 4962 0.46 MB/sec execute 50 sec latency 60.225 ms 1 5058 0.46 MB/sec execute 51 sec latency 42.446 ms 1 5170 0.45 MB/sec execute 52 sec latency 42.008 ms 1 5280 0.44 MB/sec execute 53 sec latency 47.578 ms 1 5373 0.44 MB/sec execute 54 sec latency 43.022 ms test_26 fail mds1 3 times 1 5537 0.43 MB/sec execute 55 sec latency 46.923 ms Failing mds1 on oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 1 5657 0.43 MB/sec execute 56 sec latency 40.178 ms 1 5787 0.42 MB/sec execute 57 sec latency 211.588 ms 23:09:37 (1784344177) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server 1 5820 0.41 MB/sec execute 58 sec latency 851.908 ms 1 5820 0.41 MB/sec execute 59 sec latency 1852.286 ms 1 5820 0.40 MB/sec execute 60 sec latency 2852.439 ms 1 5820 0.39 MB/sec execute 61 sec latency 3854.652 ms 1 5820 0.39 MB/sec execute 62 sec latency 4854.834 ms 1 5820 0.38 MB/sec execute 63 sec latency 5855.073 ms 1 5820 0.37 MB/sec execute 64 sec latency 6855.260 ms 1 5820 0.37 MB/sec execute 65 sec latency 7855.587 ms 1 5820 0.36 MB/sec execute 66 sec latency 8855.769 ms 1 5820 0.36 MB/sec execute 67 sec latency 9855.940 ms Failover mds1 to oleg130-server mount facets: mds1 1 5820 0.35 MB/sec execute 68 sec latency 10856.115 ms 1 5820 0.35 MB/sec execute 69 sec latency 11856.281 ms 1 5820 0.34 MB/sec execute 70 sec latency 12856.434 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 5820 0.34 MB/sec execute 71 sec latency 13856.543 ms 1 5820 0.33 MB/sec execute 72 sec latency 14856.672 ms 1 5820 0.33 MB/sec execute 73 sec latency 15856.842 ms oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 1 5820 0.32 MB/sec execute 74 sec latency 16857.134 ms Started lustre-MDT0000 23:09:53 (1784344193) targets are mounted 23:09:53 (1784344193) facet_failover done 1 5820 0.32 MB/sec execute 75 sec latency 17858.013 ms 1 5820 0.32 MB/sec execute 76 sec latency 18858.186 ms 1 5820 0.31 MB/sec execute 77 sec latency 19858.357 ms 1 5825 0.31 MB/sec execute 78 sec latency 20825.732 ms 1 5944 0.32 MB/sec execute 79 sec latency 59.926 ms oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 6024 0.32 MB/sec execute 80 sec latency 57.566 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 6153 0.32 MB/sec execute 81 sec latency 45.901 ms 1 6476 0.37 MB/sec execute 82 sec latency 35.378 ms 1 6764 0.38 MB/sec execute 83 sec latency 42.473 ms 1 6964 0.39 MB/sec execute 84 sec latency 37.030 ms 1 7173 0.42 MB/sec execute 85 sec latency 48.820 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 3296 1268008 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 3040 1268264 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 12460 3593552 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 60656 3542952 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 73116 7136504 2% /mnt/lustre 1 7280 0.42 MB/sec execute 86 sec latency 34.135 ms 1 7400 0.42 MB/sec execute 87 sec latency 51.553 ms 1 7518 0.42 MB/sec execute 88 sec latency 41.695 ms 1 7609 0.42 MB/sec execute 89 sec latency 50.982 ms 1 7753 0.42 MB/sec execute 90 sec latency 32.681 ms test_26 fail mds2 4 times Failing mds2 on oleg130-server 1 7875 0.41 MB/sec execute 91 sec latency 51.012 ms Stopping /mnt/lustre-mds2 (opts:) on oleg130-server 1 7912 0.41 MB/sec execute 92 sec latency 605.446 ms 23:10:12 (1784344212) shut down facet: mds2 facet_host: oleg130-server facet_failover_host: oleg130-server 1 7912 0.41 MB/sec execute 93 sec latency 1605.649 ms 1 7912 0.40 MB/sec execute 94 sec latency 2605.839 ms 1 7912 0.40 MB/sec execute 95 sec latency 3606.010 ms 1 7912 0.39 MB/sec execute 96 sec latency 4606.186 ms 1 7912 0.39 MB/sec execute 97 sec latency 5606.359 ms 1 7912 0.39 MB/sec execute 98 sec latency 6606.516 ms 1 7912 0.38 MB/sec execute 99 sec latency 7607.703 ms 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec Failover mds2 to oleg130-server mount facets: mds2 1 cleanup 103 sec 1 cleanup 104 sec 1 cleanup 105 sec Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 cleanup 106 sec 1 cleanup 107 sec 1 cleanup 108 sec oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0001 23:10:28 (1784344228) targets are mounted 23:10:28 (1784344228) facet_failover done 1 cleanup 109 sec 1 cleanup 110 sec 1 cleanup 111 sec 1 cleanup 112 sec 1 cleanup 113 sec 1 cleanup 114 sec 0 cleanup 114 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 1188 52.848 20825.720 Close 866 3.861 25.135 Rename 50 31.324 61.341 Unlink 242 10.748 33.253 Qpathinfo 1118 19.489 15480.579 Qfileinfo 191 1.113 5.155 Qfsinfo 200 0.658 8.671 Sfileinfo 90 260.347 21466.572 Find 416 4.878 29.435 WriteX 587 4.945 29.025 ReadX 1883 0.297 87.341 LockX 4 2.703 3.249 UnlockX 4 2.630 3.126 Flush 79 18.269 59.911 Throughput 0.381717 MB/sec 1 clients 1 procs max_latency=20825.732 ms stopping dbench on /mnt/lustre at Fri Jul 17 23:10:33 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 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 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 Fri Jul 17 23:10:36 EDT 2026 waiting for dbench pid 69717 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 1 111 5.24 MB/sec warmup 1 sec latency 92.216 ms 1 193 3.82 MB/sec warmup 2 sec latency 146.872 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 3820 1267484 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 3672 1267632 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 27808 3577796 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 24012 3582780 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 51820 7160576 1% /mnt/lustre 1 289 3.57 MB/sec warmup 3 sec latency 65.742 ms 1 389 3.46 MB/sec warmup 4 sec latency 55.211 ms 1 501 3.49 MB/sec warmup 5 sec latency 43.618 ms 1 664 3.52 MB/sec warmup 6 sec latency 60.651 ms 1 776 3.05 MB/sec warmup 7 sec latency 98.810 ms test_26 fail mds1 5 times 1 874 2.71 MB/sec warmup 8 sec latency 77.454 ms Failing mds1 on oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 1 892 2.41 MB/sec warmup 9 sec latency 580.767 ms 1 910 2.17 MB/sec warmup 10 sec latency 838.650 ms 23:10:47 (1784344247) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server 1 910 1.98 MB/sec warmup 11 sec latency 1838.846 ms 1 910 1.81 MB/sec warmup 12 sec latency 2838.975 ms 1 910 1.67 MB/sec warmup 13 sec latency 3839.157 ms 1 910 1.55 MB/sec warmup 14 sec latency 4839.379 ms 1 910 1.45 MB/sec warmup 15 sec latency 5839.542 ms 1 910 1.36 MB/sec warmup 16 sec latency 6839.691 ms 1 910 1.28 MB/sec warmup 17 sec latency 7839.847 ms 1 910 1.21 MB/sec warmup 18 sec latency 8839.985 ms 1 910 1.14 MB/sec warmup 19 sec latency 9840.197 ms Failover mds1 to oleg130-server mount facets: mds1 1 910 0.00 MB/sec execute 1 sec latency 11840.587 ms 1 910 0.00 MB/sec execute 2 sec latency 12840.747 ms 1 910 0.00 MB/sec execute 3 sec latency 13840.957 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 910 0.00 MB/sec execute 4 sec latency 14841.114 ms 1 910 0.00 MB/sec execute 5 sec latency 15841.292 ms 1 910 0.00 MB/sec execute 6 sec latency 16841.457 ms oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 23:11:03 (1784344263) targets are mounted 23:11:03 (1784344263) facet_failover done 1 910 0.00 MB/sec execute 7 sec latency 17841.827 ms 1 910 0.00 MB/sec execute 8 sec latency 18841.925 ms 1 910 0.00 MB/sec execute 9 sec latency 19842.087 ms 1 910 0.00 MB/sec execute 10 sec latency 20843.201 ms 1 936 0.00 MB/sec execute 11 sec latency 21527.234 ms 1 1064 0.09 MB/sec execute 12 sec latency 47.592 ms oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 1190 0.10 MB/sec execute 13 sec latency 42.441 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 1391 0.30 MB/sec execute 14 sec latency 38.782 ms 1 1486 0.29 MB/sec execute 15 sec latency 153.827 ms 1 1605 0.27 MB/sec execute 16 sec latency 34.077 ms 1 1736 0.27 MB/sec execute 17 sec latency 40.117 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 3680 1267624 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 3544 1267760 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 39304 3567212 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 34392 3571852 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 73696 7139064 2% /mnt/lustre 1 1862 0.26 MB/sec execute 18 sec latency 50.347 ms 1 2000 0.25 MB/sec execute 19 sec latency 46.640 ms 1 2128 0.25 MB/sec execute 20 sec latency 44.202 ms 1 2292 0.29 MB/sec execute 21 sec latency 37.012 ms 1 2412 0.28 MB/sec execute 22 sec latency 73.285 ms test_26 fail mds2 6 times 1 2508 0.30 MB/sec execute 23 sec latency 51.094 ms Failing mds2 on oleg130-server Stopping /mnt/lustre-mds2 (opts:) on oleg130-server 1 2768 0.43 MB/sec execute 24 sec latency 84.744 ms 1 2775 0.41 MB/sec execute 25 sec latency 940.348 ms 23:11:22 (1784344282) shut down facet: mds2 facet_host: oleg130-server facet_failover_host: oleg130-server 1 2775 0.39 MB/sec execute 26 sec latency 1940.622 ms 1 2775 0.38 MB/sec execute 27 sec latency 2940.782 ms 1 2775 0.36 MB/sec execute 28 sec latency 3940.950 ms 1 2775 0.35 MB/sec execute 29 sec latency 4941.105 ms 1 2775 0.34 MB/sec execute 30 sec latency 5941.280 ms 1 2775 0.33 MB/sec execute 31 sec latency 6941.480 ms 1 2775 0.32 MB/sec execute 32 sec latency 7941.638 ms 1 2775 0.31 MB/sec execute 33 sec latency 8941.813 ms 1 2775 0.30 MB/sec execute 34 sec latency 9941.990 ms 1 2775 0.29 MB/sec execute 35 sec latency 10942.155 ms Failover mds2 to oleg130-server mount facets: mds2 1 2775 0.28 MB/sec execute 36 sec latency 11942.330 ms 1 2775 0.28 MB/sec execute 37 sec latency 12942.524 ms 1 2775 0.27 MB/sec execute 38 sec latency 13942.698 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 2775 0.26 MB/sec execute 39 sec latency 14942.919 ms 1 2775 0.26 MB/sec execute 40 sec latency 15943.112 ms oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 1 2775 0.25 MB/sec execute 41 sec latency 16943.266 ms Started lustre-MDT0001 23:11:38 (1784344298) targets are mounted 23:11:38 (1784344298) facet_failover done 1 2775 0.24 MB/sec execute 42 sec latency 17943.434 ms 1 2775 0.24 MB/sec execute 43 sec latency 18943.605 ms 1 2775 0.23 MB/sec execute 44 sec latency 19943.783 ms 1 2775 0.23 MB/sec execute 45 sec latency 20943.966 ms 1 2984 0.26 MB/sec execute 46 sec latency 21204.877 ms oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 1 3275 0.29 MB/sec execute 47 sec latency 39.651 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 3529 0.35 MB/sec execute 48 sec latency 30.415 ms 1 3697 0.35 MB/sec execute 49 sec latency 23.799 ms 1 3856 0.36 MB/sec execute 50 sec latency 29.431 ms 1 3975 0.36 MB/sec execute 51 sec latency 91.873 ms 1 4067 0.35 MB/sec execute 52 sec latency 123.620 ms 1 4181 0.35 MB/sec execute 53 sec latency 37.166 ms 1 4294 0.35 MB/sec execute 54 sec latency 66.840 ms 1 4434 0.34 MB/sec execute 55 sec latency 35.707 ms 1 4549 0.34 MB/sec execute 56 sec latency 39.870 ms 1 4701 0.36 MB/sec execute 57 sec latency 59.661 ms 1 4840 0.35 MB/sec execute 58 sec latency 34.336 ms 1 5047 0.40 MB/sec execute 59 sec latency 57.831 ms dbench killed by signal 15 stopping dbench on /mnt/lustre at Fri Jul 17 23:11:56 EDT 2026 with return code 0 69717 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 69717 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished PASS 26 (222s) == replay-dual test 28: lock replay should be ordered: waiting after granted ========================================================== 23:11:59 (1784344319) Waiting for MDT destroys to complete 1+0 records in 1+0 records out 4096 bytes (4.1 kB, 4.0 KiB) copied, 0.00986018 s, 415 kB/s fail_loc=0x80000324 fail_loc=0x32a Failing ost1 on oleg130-server Stopping /mnt/lustre-ost1 (opts:) on oleg130-server 23:12:18 (1784344338) shut down facet: ost1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover ost1 to oleg130-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, 0.0128308 s, 319 kB/s oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-OST0000 23:12:42 (1784344362) targets are mounted 23:12:42 (1784344362) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid 1475 0 osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in FULL state after 0 sec PASS 28 (62s) == replay-dual test 29: replay vs update with the same xid ========================================================== 23:13:01 (1784344381) SKIP: replay-dual test_29 needs >= 2 clients SKIP 29 (3s) == replay-dual test 30: layout lock replay is not blocked on IO ========================================================== 23:13:04 (1784344384) 10+0 records in 10+0 records out 40960 bytes (41 kB, 40 KiB) copied, 0.0401723 s, 1.0 MB/s 10+0 records in 10+0 records out 40960 bytes (41 kB, 40 KiB) copied, 0.0673431 s, 608 kB/s fail_loc=0x32e fail_val=4 Failing mds1 on oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server 23:13:11 (1784344391) shut down facet: mds1 facet_host: oleg130-server facet_failover_host: oleg130-server Failover mds1 to oleg130-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 23:13:41 (1784344421) targets are mounted 23:13:41 (1784344421) facet_failover done 160+0 records in 160+0 records out 81920 bytes (82 kB, 80 KiB) copied, 37.0696 s, 2.2 kB/s oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec PASS 30 (47s) == replay-dual test 31: deadlock on file_remove_privs and occupied mod rpc slots ========================================================== 23:13:51 (1784344431) Failing ost1 on oleg130-server Stopping /mnt/lustre-ost1 (opts:) on oleg130-server 23:13:54 (1784344434) shut down facet: ost1 facet_host: oleg130-server facet_failover_host: oleg130-server Creating to objid 2593 on ost lustre-OST0000... total: 32 open/close in 0.54 seconds: 58.97 ops/second at_max=0 fail_loc=0x80001420 file /mnt/lustre2/d31.replay-dual/mdtdir/f31.replay-dual is not ready, wait 0.5 second... file /mnt/lustre2/d31.replay-dual/mdtdir/f31.replay-dual is ready Failover ost1 to oleg130-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 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-OST0000 23:14:13 (1784344453) targets are mounted 23:14:13 (1784344453) facet_failover done oleg130-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid 1475 0 osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in IDLE FULL state after 0 sec pids: 76246 76248 76253 76254 76255 76256 76257 76258 76259 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2128 1269176 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 342 1023658 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1024000 272 1023728 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 262144 510 261634 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 262144 400 261744 1% /mnt/lustre[OST:1] filesystem_summary: 523992 614 523378 1% /mnt/lustre at_max=600 PASS 31 (33s) == replay-dual test 32: gap in update llog shouldn't break recovery ========================================================== 23:14:24 (1784344464) fail_loc=0x0000131d fail_val=10 fail_loc=0x726 Stopping /mnt/lustre-mds2 (opts:) on oleg130-server Stopping /mnt/lustre-mds1 (opts:) on oleg130-server fail_loc=0 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0000 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0001 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2232 1269072 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1956 1269348 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 (27s) == replay-dual test 33: Check for OBD_INCOMPAT_MULTI_RPCS in last_rcvd after abort_recovery ========================================================== 23:14:51 (1784344491) at_min=60 Stopping /mnt/lustre-mds2 (opts:) on oleg130-server last_rcvd in /dev/mapper/mds2_flakey: incompat = 0x61c Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0001 oleg130-client.virtnet: executing wait_import_state_mount REPLAY_WAIT mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0001-mdc-*.mds_server_uuid in REPLAY_WAIT state after 0 sec oleg130-client.virtnet: executing wait_import_state_mount FULL mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec affected facets: mds2 oleg130-server: oleg130-server.virtnet: executing _wait_recovery_complete *.lustre-MDT0001.recovery_status 1475 oleg130-server: *.lustre-MDT0001.recovery_status status: COMPLETE Stopping /mnt/lustre-mds2 (opts:) on oleg130-server last_rcvd in /dev/mapper/mds2_flakey: incompat = 0x61c Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg130-server: oleg130-server.virtnet: executing set_default_debug -1 all pdsh@oleg130-client: oleg130-server: ssh exited with exit code 1 Started lustre-MDT0001 Starting client: oleg130-client.virtnet: -o user_xattr,flock 192.168.201.130@tcp:/lustre /mnt/lustre2 oleg130-client.virtnet: executing wait_import_state_mount FULL mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec affected facets: mds2 oleg130-server: oleg130-server.virtnet: executing _wait_recovery_complete *.lustre-MDT0001.recovery_status 1475 oleg130-server: *.lustre-MDT0001.recovery_status status: COMPLETE at_min=5 PASS 33 (60s) == replay-dual test complete, duration 3055 sec ========== 23:15:51 (1784344551) === replay-dual: start cleanup 23:15:52 (1784344552) === Stopping clients: oleg130-client.virtnet /mnt/lustre2 (opts:) Stopping client oleg130-client.virtnet /mnt/lustre2 opts: === replay-dual: finish cleanup 23:15:58 (1784344558) ===