-----============= acceptance-small: replay-single ============----- Fri Sep 11 05:06:17 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 oleg627-server: ls: cannot access '/home/green/git/lustre-release/lustre/tests/except/replay-single.*ex': No such file or directory excepting tests: 110f 131b 59 36 === replay-single: start setup 05:06:36 (1789117596) === oleg627-client.virtnet: executing check_config_client /mnt/lustre oleg627-client.virtnet: Checking config lustre mounted on /mnt/lustre Checking servers environments Checking clients oleg627-client.virtnet environments Using TIMEOUT=20 osc.lustre-OST0000-osc-ffff8a57e08ab800.idle_timeout=debug osc.lustre-OST0001-osc-ffff8a57e08ab800.idle_timeout=debug disable quota as required oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all osd-ldiskfs.track_declares_assert=1 Setting lod.lustre-MDT0000-mdtlov.enable_compr_rotational from 0 to 1 Waiting 90s for '1' Updated after 2s: want '1' got '1' Setting lod.lustre-MDT0001-mdtlov.enable_compr_rotational from 0 to 1 Waiting 90s for '1' Updated after 2s: want '1' got '1' === replay-single: finish setup 05:07:27 (1789117647) === Cleaning up AT ... == replay-single test 100a: DNE: create striped dir, drop update rep from MDT1, fail MDT1 ========================================================== 05:07:33 (1789117653) fail_loc=0x1701 Failing mds2 on oleg627-server Stopping /mnt/lustre-mds2 (opts:) on oleg627-server 05:07:40 (1789117660) shut down facet: mds2 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds2 to oleg627-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0001 05:08:06 (1789117686) targets are mounted 05:08:06 (1789117686) facet_failover done oleg627-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 lmv_stripe_count: 2 lmv_stripe_offset: 0 lmv_hash_type: crush mdtidx FID[seq:oid:ver] 0 [0x200000400:0x2:0x0] 1 [0x240000401:0x2:0x0] total: 20 open/close in 0.34 seconds: 58.89 ops/second PASS 100a (52s) == replay-single test 100b: DNE: create striped dir, fail MDT0 ========================================================== 05:08:25 (1789117705) fail_loc=0x119 Failing mds1 on oleg627-server Stopping /mnt/lustre-mds1 (opts:) on oleg627-server 05:08:33 (1789117713) shut down facet: mds1 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds1 to oleg627-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0000 05:08:57 (1789117737) targets are mounted 05:08:57 (1789117737) facet_failover done oleg627-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 lmv_stripe_count: 2 lmv_stripe_offset: 0 lmv_hash_type: crush mdtidx FID[seq:oid:ver] 0 [0x200000400:0x5:0x0] 1 [0x240000401:0x5:0x0] total: 20 open/close in 0.45 seconds: 44.13 ops/second PASS 100b (50s) == replay-single test 100c: DNE: create striped dir, abort_recov_mdt mds2 ========================================================== 05:09:15 (1789117755) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1844 1269460 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1720 1269584 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 Stopping /mnt/lustre-mds2 (opts:) on oleg627-server Failover mds2 to oleg627-server oleg627-server.virtnet Start mds2: mount -t lustre -o localrecov -o abort_recov_mdt /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0001 total: 20 open/close in 0.40 seconds: 49.98 ops/second Failing mds2 on oleg627-server Stopping /mnt/lustre-mds2 (opts:) on oleg627-server 05:10:06 (1789117806) shut down facet: mds2 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds2 to oleg627-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0001 05:10:29 (1789117829) targets are mounted 05:10:29 (1789117829) facet_failover done oleg627-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 lmv_stripe_count: 2 lmv_stripe_offset: 1 lmv_hash_type: crush mdtidx FID[seq:oid:ver] 1 [0x240000bd0:0x3:0x0] 0 [0x200000403:0x3:0x0] total: 20 open/close in 0.28 seconds: 70.74 ops/second PASS 100c (90s) == replay-single test 100d: DNE: cancel update logs upon recovery abort ========================================================== 05:10:46 (1789117846) striped dir -i0 -c2 -H all_char /mnt/lustre/d100d.replay-single total: 100 mkdir in 1.47 seconds: 68.19 ops/second lustre-MDT0000-osd [catalog]: [0x200000400:0x1:0x0] [index]: 00002 [logid]: [0x200000bd0:0x1:0x0] lustre-MDT0001-osp-MDT0000 [catalog]: [0x240000401:0x1:0x0] [index]: 00003 [logid]: [0x240000bd1:0x1:0x0] [index]: 00004 [logid]: [0x240000bd1:0x2:0x0] Stopping /mnt/lustre-mds1 (opts:) on oleg627-server Failover mds1 to oleg627-server oleg627-server.virtnet Start mds1: mount -t lustre -o localrecov -o abort_recovery /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0000 pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 find: '/mnt/lustre/d100d.replay-single': No such file or directory find: '/mnt/lustre/d100d.replay-single': No such file or directory PASS 100d (60s) == replay-single test 100e: DNE: create striped dir on MDT0 and MDT1, fail MDT0, MDT1 ========================================================== 05:11:46 (1789117906) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2292 1269012 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2148 1269156 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 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2292 1269012 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2148 1269156 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 lmv_stripe_count: 2 lmv_stripe_offset: 0 lmv_hash_type: crush mdtidx FID[seq:oid:ver] 0 [0x2000013a0:0x2:0x0] 1 [0x240001b71:0x2:0x0] Failing mds1 on oleg627-server Stopping /mnt/lustre-mds1 (opts:) on oleg627-server Failing mds2 on oleg627-server Stopping /mnt/lustre-mds2 (opts:) on oleg627-server 05:12:10 (1789117930) shut down facet: mds1 facet_host: oleg627-server facet_failover_host: oleg627-server facet: mds2 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds1 to oleg627-server mount facets: mds1 Failover mds2 to oleg627-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 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 05:12:59 (1789117979) targets are mounted 05:12:59 (1789117979) facet_failover done oleg627-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 lmv_stripe_count: 2 lmv_stripe_offset: 0 lmv_hash_type: crush mdtidx FID[seq:oid:ver] 0 [0x2000013a0:0x2:0x0] 1 [0x240001b71:0x2:0x0] PASS 100e (88s) == replay-single test 101: Shouldn't reassign precreated objs to other files after recovery ========================================================== 05:13:14 (1789117994) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2432 1268872 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2248 1269056 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 Stopping /mnt/lustre-mds1 (opts:) on oleg627-server Failover mds1 to oleg627-server oleg627-server.virtnet Start mds1: mount -t lustre -o localrecov -o abort_recovery /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0000 PASS 101 (135s) == replay-single test 102a: check resend (request lost) with multiple modify RPCs in flight ========================================================== 05:15:29 (1789118129) creating 7 files ... fail_loc=0x159 launch 7 chmod in parallel (05:15:31) ... fail_loc=0 done (05:16:27) /mnt/lustre/d102a.replay-single/file-1 has perms 0600 OK /mnt/lustre/d102a.replay-single/file-2 has perms 0600 OK /mnt/lustre/d102a.replay-single/file-3 has perms 0600 OK /mnt/lustre/d102a.replay-single/file-4 has perms 0600 OK /mnt/lustre/d102a.replay-single/file-5 has perms 0600 OK /mnt/lustre/d102a.replay-single/file-6 has perms 0600 OK /mnt/lustre/d102a.replay-single/file-7 has perms 0600 OK PASS 102a (63s) == replay-single test 102b: check resend (reply lost) with multiple modify RPCs in flight ========================================================== 05:16:32 (1789118192) creating 7 files ... fail_loc=0x15a launch 7 chmod in parallel (05:16:35) ... fail_loc=0 done (05:17:30) /mnt/lustre/d102b.replay-single/file-1 has perms 0600 OK /mnt/lustre/d102b.replay-single/file-2 has perms 0600 OK /mnt/lustre/d102b.replay-single/file-3 has perms 0600 OK /mnt/lustre/d102b.replay-single/file-4 has perms 0600 OK /mnt/lustre/d102b.replay-single/file-5 has perms 0600 OK /mnt/lustre/d102b.replay-single/file-6 has perms 0600 OK /mnt/lustre/d102b.replay-single/file-7 has perms 0600 OK PASS 102b (65s) == replay-single test 102c: check replay w/o reconstruction with multiple mod RPCs in flight ========================================================== 05:17:37 (1789118257) creating 7 files ... UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2296 1269008 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2056 1269248 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3596680 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3596736 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7193416 1% /mnt/lustre fail_loc=0x15a launch 7 chmod in parallel (05:17:47) ... fail_loc=0 Failing mds1 on oleg627-server Stopping /mnt/lustre-mds1 (opts:) on oleg627-server 05:17:52 (1789118272) shut down facet: mds1 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds1 to oleg627-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0000 05:18:25 (1789118305) targets are mounted 05:18:25 (1789118305) facet_failover done oleg627-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 done (05:18:37) /mnt/lustre/d102c.replay-single/file-1 has perms 0600 OK /mnt/lustre/d102c.replay-single/file-2 has perms 0600 OK /mnt/lustre/d102c.replay-single/file-3 has perms 0600 OK /mnt/lustre/d102c.replay-single/file-4 has perms 0600 OK /mnt/lustre/d102c.replay-single/file-5 has perms 0600 OK /mnt/lustre/d102c.replay-single/file-6 has perms 0600 OK /mnt/lustre/d102c.replay-single/file-7 has perms 0600 OK PASS 102c (66s) == replay-single test 102d: check replay & reconstruction with multiple mod RPCs in flight ========================================================== 05:18:43 (1789118323) creating 7 files ... fail_loc=0x15a launch 7 chmod in parallel (05:18:46) ... fail_loc=0 Failing mds2 on oleg627-server Stopping /mnt/lustre-mds2 (opts:) on oleg627-server 05:18:53 (1789118333) shut down facet: mds2 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds2 to oleg627-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0001 05:19:16 (1789118356) targets are mounted 05:19:16 (1789118356) facet_failover done oleg627-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 done (05:19:25) /mnt/lustre/d102d.replay-single/file-1 has perms 0600 OK /mnt/lustre/d102d.replay-single/file-2 has perms 0600 OK /mnt/lustre/d102d.replay-single/file-3 has perms 0600 OK /mnt/lustre/d102d.replay-single/file-4 has perms 0600 OK /mnt/lustre/d102d.replay-single/file-5 has perms 0600 OK /mnt/lustre/d102d.replay-single/file-6 has perms 0600 OK /mnt/lustre/d102d.replay-single/file-7 has perms 0600 OK PASS 102d (47s) == replay-single test 103: Check otr_next_id overflow ==== 05:19:30 (1789118370) fail_loc=0x80000162 total: 30 open/close in 0.45 seconds: 66.20 ops/second Failing mds1 on oleg627-server Stopping /mnt/lustre-mds1 (opts:) on oleg627-server 05:19:36 (1789118376) shut down facet: mds1 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds1 to oleg627-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0000 05:19:57 (1789118397) targets are mounted 05:19:57 (1789118397) facet_failover done oleg627-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 103 (40s) == replay-single test 110a: DNE: create striped dir, fail MDT1 ========================================================== 05:20:10 (1789118410) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2236 1269068 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2056 1269248 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3596680 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3596736 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7193416 1% /mnt/lustre Failing mds1 on oleg627-server Stopping /mnt/lustre-mds1 (opts:) on oleg627-server 05:20:21 (1789118421) shut down facet: mds1 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds1 to oleg627-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0000 05:20:55 (1789118455) targets are mounted 05:20:55 (1789118455) facet_failover done oleg627-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 /mnt/lustre/d110a.replay-single/striped_dir has type dir OK PASS 110a (60s) == replay-single test 110b: DNE: create striped dir, fail MDT1 and client ========================================================== 05:21:11 (1789118471) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2240 1269064 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2060 1269244 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210944 1% /mnt/lustre Failing mds1 on oleg627-server Stopping /mnt/lustre-mds1 (opts:) on oleg627-server 05:21:23 (1789118483) shut down facet: mds1 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds1 to oleg627-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0000 05:21:57 (1789118517) targets are mounted 05:21:57 (1789118517) facet_failover done pdsh@oleg627-client: oleg627-client: ssh exited with exit code 95 oleg627-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 pdsh@oleg627-client: oleg627-client: ssh exited with exit code 95 Starting client: oleg627-client.virtnet: -o user_xattr,flock 192.168.206.127@tcp:/lustre /mnt/lustre /mnt/lustre/d110b.replay-single/striped_dir has type dir OK PASS 110b (124s) == replay-single test 110c: DNE: create striped dir, fail MDT2 ========================================================== 05:23:15 (1789118595) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2244 1269060 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2056 1269248 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210944 1% /mnt/lustre Failing mds2 on oleg627-server Stopping /mnt/lustre-mds2 (opts:) on oleg627-server 05:23:27 (1789118607) shut down facet: mds2 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds2 to oleg627-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0001 05:23:53 (1789118633) targets are mounted 05:23:53 (1789118633) facet_failover done oleg627-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 /mnt/lustre/d110c.replay-single/striped_dir has type dir OK PASS 110c (52s) == replay-single test 110d: DNE: create striped dir, fail MDT2 and client ========================================================== 05:24:07 (1789118647) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2284 1269020 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2104 1269200 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210944 1% /mnt/lustre Failing mds2 on oleg627-server Stopping /mnt/lustre-mds2 (opts:) on oleg627-server 05:24:17 (1789118657) shut down facet: mds2 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds2 to oleg627-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0001 05:24:42 (1789118682) targets are mounted 05:24:42 (1789118682) facet_failover done pdsh@oleg627-client: oleg627-client: ssh exited with exit code 95 oleg627-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 pdsh@oleg627-client: oleg627-client: ssh exited with exit code 95 Starting client: oleg627-client.virtnet: -o user_xattr,flock 192.168.206.127@tcp:/lustre /mnt/lustre /mnt/lustre/d110d.replay-single/striped_dir has type dir OK PASS 110d (111s) == replay-single test 110e: DNE: create striped dir, uncommit on MDT2, fail client/MDT1/MDT2 ========================================================== 05:25:58 (1789118758) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2276 1269028 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2100 1269204 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210944 1% /mnt/lustre df:/mnt/lustre Not a Lustre filesystem Failing mds1 on oleg627-server Stopping /mnt/lustre-mds1 (opts:) on oleg627-server Failing mds2 on oleg627-server Stopping /mnt/lustre-mds2 (opts:) on oleg627-server 05:26:19 (1789118779) shut down facet: mds1 facet_host: oleg627-server facet_failover_host: oleg627-server facet: mds2 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds1 to oleg627-server mount facets: mds1 Failover mds2 to oleg627-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 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 05:26:47 (1789118807) targets are mounted 05:26:47 (1789118807) facet_failover done pdsh@oleg627-client: oleg627-client: ssh exited with exit code 95 oleg627-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 pdsh@oleg627-client: oleg627-client: ssh exited with exit code 95 Starting client: oleg627-client.virtnet: -o user_xattr,flock 192.168.206.127@tcp:/lustre /mnt/lustre /mnt/lustre/d110e.replay-single/striped_dir has type dir OK PASS 110e (124s) SKIP: replay-single test_110f skipping excluded test 110f == replay-single test 110g: DNE: create striped dir, uncommit on MDT1, fail client/MDT1/MDT2 ========================================================== 05:28:03 (1789118883) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2276 1269028 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2100 1269204 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210944 1% /mnt/lustre df:/mnt/lustre Not a Lustre filesystem Failing mds1 on oleg627-server Stopping /mnt/lustre-mds1 (opts:) on oleg627-server Failing mds2 on oleg627-server Stopping /mnt/lustre-mds2 (opts:) on oleg627-server 05:28:22 (1789118902) shut down facet: mds1 facet_host: oleg627-server facet_failover_host: oleg627-server facet: mds2 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds1 to oleg627-server mount facets: mds1 Failover mds2 to oleg627-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 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0000 Started lustre-MDT0001 05:28:51 (1789118931) targets are mounted 05:28:51 (1789118931) facet_failover done pdsh@oleg627-client: oleg627-client: ssh exited with exit code 95 oleg627-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 pdsh@oleg627-client: oleg627-client: ssh exited with exit code 95 Starting client: oleg627-client.virtnet: -o user_xattr,flock 192.168.206.127@tcp:/lustre /mnt/lustre /mnt/lustre/d110g.replay-single/striped_dir has type dir OK PASS 110g (124s) == replay-single test 111a: DNE: unlink striped dir, fail MDT1 ========================================================== 05:30:07 (1789119007) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2248 1269056 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2112 1269192 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210944 1% /mnt/lustre Failing mds1 on oleg627-server Stopping /mnt/lustre-mds1 (opts:) on oleg627-server 05:30:17 (1789119017) shut down facet: mds1 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds1 to oleg627-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0000 05:30:52 (1789119052) targets are mounted 05:30:52 (1789119052) facet_failover done oleg627-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 Can't lstat /mnt/lustre/d111a.replay-single/striped_dir: No such file or directory PASS 111a (58s) == replay-single test 111b: DNE: unlink striped dir, fail MDT2 ========================================================== 05:31:05 (1789119065) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2252 1269052 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2116 1269188 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210944 1% /mnt/lustre Failing mds2 on oleg627-server Stopping /mnt/lustre-mds2 (opts:) on oleg627-server 05:31:16 (1789119076) shut down facet: mds2 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds2 to oleg627-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0001 05:31:39 (1789119099) targets are mounted 05:31:39 (1789119099) facet_failover done pdsh@oleg627-client: oleg627-client: ssh exited with exit code 95 oleg627-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 pdsh@oleg627-client: oleg627-client: ssh exited with exit code 95 Starting client: oleg627-client.virtnet: -o user_xattr,flock 192.168.206.127@tcp:/lustre /mnt/lustre Can't lstat /mnt/lustre/d111b.replay-single/striped_dir: No such file or directory PASS 111b (113s) == replay-single test 111c: DNE: unlink striped dir, uncommit on MDT1, fail client/MDT1/MDT2 ========================================================== 05:32:58 (1789119178) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2252 1269052 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2116 1269188 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210944 1% /mnt/lustre df:/mnt/lustre Not a Lustre filesystem Failing mds1 on oleg627-server Stopping /mnt/lustre-mds1 (opts:) on oleg627-server Failing mds2 on oleg627-server Stopping /mnt/lustre-mds2 (opts:) on oleg627-server 05:33:21 (1789119201) shut down facet: mds1 facet_host: oleg627-server facet_failover_host: oleg627-server facet: mds2 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds1 to oleg627-server mount facets: mds1 Failover mds2 to oleg627-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 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0000 Started lustre-MDT0001 05:33:53 (1789119233) targets are mounted 05:33:53 (1789119233) facet_failover done pdsh@oleg627-client: oleg627-client: ssh exited with exit code 95 oleg627-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 pdsh@oleg627-client: oleg627-client: ssh exited with exit code 95 Starting client: oleg627-client.virtnet: -o user_xattr,flock 192.168.206.127@tcp:/lustre /mnt/lustre Can't lstat /mnt/lustre/d111c.replay-single/striped_dir: No such file or directory PASS 111c (127s) == replay-single test 111d: DNE: unlink striped dir, uncommit on MDT2, fail client/MDT1/MDT2 ========================================================== 05:35:05 (1789119305) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2256 1269048 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2124 1269180 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210944 1% /mnt/lustre df:/mnt/lustre Not a Lustre filesystem Failing mds1 on oleg627-server Stopping /mnt/lustre-mds1 (opts:) on oleg627-server Failing mds2 on oleg627-server Stopping /mnt/lustre-mds2 (opts:) on oleg627-server 05:35:27 (1789119327) shut down facet: mds1 facet_host: oleg627-server facet_failover_host: oleg627-server facet: mds2 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds1 to oleg627-server mount facets: mds1 Failover mds2 to oleg627-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 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 05:35:57 (1789119357) targets are mounted 05:35:57 (1789119357) facet_failover done pdsh@oleg627-client: oleg627-client: ssh exited with exit code 95 oleg627-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 pdsh@oleg627-client: oleg627-client: ssh exited with exit code 95 Starting client: oleg627-client.virtnet: -o user_xattr,flock 192.168.206.127@tcp:/lustre /mnt/lustre Can't lstat /mnt/lustre/d111d.replay-single/striped_dir: No such file or directory PASS 111d (127s) == replay-single test 111e: DNE: unlink striped dir, uncommit on MDT2, fail MDT1/MDT2 ========================================================== 05:37:12 (1789119432) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2260 1269044 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2124 1269180 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210944 1% /mnt/lustre UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2252 1269052 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2116 1269188 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210944 1% /mnt/lustre Failing mds1 on oleg627-server Stopping /mnt/lustre-mds1 (opts:) on oleg627-server Failing mds2 on oleg627-server Stopping /mnt/lustre-mds2 (opts:) on oleg627-server 05:37:37 (1789119457) shut down facet: mds1 facet_host: oleg627-server facet_failover_host: oleg627-server facet: mds2 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds1 to oleg627-server mount facets: mds1 Failover mds2 to oleg627-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 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 05:38:06 (1789119486) targets are mounted 05:38:06 (1789119486) facet_failover done oleg627-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 Can't lstat /mnt/lustre/d111e.replay-single/striped_dir: No such file or directory PASS 111e (76s) == replay-single test 111f: DNE: unlink striped dir, uncommit on MDT1, fail MDT1/MDT2 ========================================================== 05:38:28 (1789119508) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2300 1269004 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2160 1269144 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210944 1% /mnt/lustre UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2292 1269012 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2152 1269152 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210944 1% /mnt/lustre Failing mds1 on oleg627-server Stopping /mnt/lustre-mds1 (opts:) on oleg627-server Failing mds2 on oleg627-server Stopping /mnt/lustre-mds2 (opts:) on oleg627-server 05:39:02 (1789119542) shut down facet: mds1 facet_host: oleg627-server facet_failover_host: oleg627-server facet: mds2 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds1 to oleg627-server mount facets: mds1 Failover mds2 to oleg627-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 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0000 Started lustre-MDT0001 05:39:46 (1789119586) targets are mounted 05:39:46 (1789119586) facet_failover done oleg627-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 Can't lstat /mnt/lustre/d111f.replay-single/striped_dir: No such file or directory PASS 111f (111s) == replay-single test 111g: DNE: unlink striped dir, fail MDT1/MDT2 ========================================================== 05:40:19 (1789119619) UUID Inodes IUsed IFree IUse% Mounted on lustre-MDT0000_UUID 1024000 312 1023688 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1024000 284 1023716 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 262144 412 261732 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 262144 412 261732 1% /mnt/lustre[OST:1] filesystem_summary: 524060 596 523464 1% /mnt/lustre UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2268 1269036 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2128 1269176 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210944 1% /mnt/lustre UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2268 1269036 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2128 1269176 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210944 1% /mnt/lustre Failing mds1 on oleg627-server Stopping /mnt/lustre-mds1 (opts:) on oleg627-server Failing mds2 on oleg627-server Stopping /mnt/lustre-mds2 (opts:) on oleg627-server 05:40:43 (1789119643) shut down facet: mds1 facet_host: oleg627-server facet_failover_host: oleg627-server facet: mds2 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds1 to oleg627-server mount facets: mds1 Failover mds2 to oleg627-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 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 05:41:14 (1789119674) targets are mounted 05:41:14 (1789119674) facet_failover done oleg627-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 Can't lstat /mnt/lustre/d111g.replay-single/striped_dir: No such file or directory PASS 111g (74s) == replay-single test 112a: DNE: cross MDT rename, fail MDT1 ========================================================== 05:41:33 (1789119693) SKIP: replay-single test_112a needs >= 4 MDTs SKIP 112a (3s) == replay-single test 112b: DNE: cross MDT rename, fail MDT2 ========================================================== 05:41:36 (1789119696) SKIP: replay-single test_112b needs >= 4 MDTs SKIP 112b (4s) == replay-single test 112c: DNE: cross MDT rename, fail MDT3 ========================================================== 05:41:40 (1789119700) SKIP: replay-single test_112c needs >= 4 MDTs SKIP 112c (3s) == replay-single test 112d: DNE: cross MDT rename, fail MDT4 ========================================================== 05:41:43 (1789119703) SKIP: replay-single test_112d needs >= 4 MDTs SKIP 112d (3s) == replay-single test 112e: DNE: cross MDT rename, fail MDT1 and MDT2 ========================================================== 05:41:46 (1789119706) SKIP: replay-single test_112e needs >= 4 MDTs SKIP 112e (3s) == replay-single test 112f: DNE: cross MDT rename, fail MDT1 and MDT3 ========================================================== 05:41:49 (1789119709) SKIP: replay-single test_112f needs >= 4 MDTs SKIP 112f (3s) == replay-single test 112g: DNE: cross MDT rename, fail MDT1 and MDT4 ========================================================== 05:41:53 (1789119713) SKIP: replay-single test_112g needs >= 4 MDTs SKIP 112g (3s) == replay-single test 112h: DNE: cross MDT rename, fail MDT2 and MDT3 ========================================================== 05:41:56 (1789119716) SKIP: replay-single test_112h needs >= 4 MDTs SKIP 112h (2s) == replay-single test 112i: DNE: cross MDT rename, fail MDT2 and MDT4 ========================================================== 05:41:59 (1789119719) SKIP: replay-single test_112i needs >= 4 MDTs SKIP 112i (3s) == replay-single test 112j: DNE: cross MDT rename, fail MDT3 and MDT4 ========================================================== 05:42:02 (1789119722) SKIP: replay-single test_112j needs >= 4 MDTs SKIP 112j (3s) == replay-single test 112k: DNE: cross MDT rename, fail MDT1,MDT2,MDT3 ========================================================== 05:42:05 (1789119725) SKIP: replay-single test_112k needs >= 4 MDTs SKIP 112k (4s) == replay-single test 112l: DNE: cross MDT rename, fail MDT1,MDT2,MDT4 ========================================================== 05:42:09 (1789119729) SKIP: replay-single test_112l needs >= 4 MDTs SKIP 112l (3s) == replay-single test 112m: DNE: cross MDT rename, fail MDT1,MDT3,MDT4 ========================================================== 05:42:12 (1789119732) SKIP: replay-single test_112m needs >= 4 MDTs SKIP 112m (3s) == replay-single test 112n: DNE: cross MDT rename, fail MDT2,MDT3,MDT4 ========================================================== 05:42:15 (1789119735) SKIP: replay-single test_112n needs >= 4 MDTs SKIP 112n (3s) == replay-single test 115: failover for create/unlink striped directory ========================================================== 05:42:18 (1789119738) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2264 1269040 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2120 1269184 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210944 1% /mnt/lustre striped dir -i1 -c2 -H crush2 /mnt/lustre/d115.replay-single/test_0 striped dir -i1 -c2 -H all_char /mnt/lustre/d115.replay-single/test_1 striped dir -i1 -c2 -H crush2 /mnt/lustre/d115.replay-single/test_2 striped dir -i1 -c2 -H all_char /mnt/lustre/d115.replay-single/test_3 striped dir -i1 -c2 -H all_char /mnt/lustre/d115.replay-single/test_4 Failing mds2 on oleg627-server Stopping /mnt/lustre-mds2 (opts:) on oleg627-server 05:42:38 (1789119758) shut down facet: mds2 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds2 to oleg627-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0001 05:43:03 (1789119783) targets are mounted 05:43:03 (1789119783) facet_failover done oleg627-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 2268 1269036 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2140 1269164 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210944 1% /mnt/lustre striped dir -i0 -c2 -H crush2 /mnt/lustre/d115.replay-single/test_0 striped dir -i0 -c2 -H crush2 /mnt/lustre/d115.replay-single/test_1 striped dir -i0 -c2 -H all_char /mnt/lustre/d115.replay-single/test_2 striped dir -i0 -c2 -H fnv_1a_64 /mnt/lustre/d115.replay-single/test_3 striped dir -i0 -c2 -H crush /mnt/lustre/d115.replay-single/test_4 Failing mds1 on oleg627-server Stopping /mnt/lustre-mds1 (opts:) on oleg627-server 05:43:24 (1789119804) shut down facet: mds1 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds1 to oleg627-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0000 05:43:55 (1789119835) targets are mounted 05:43:55 (1789119835) facet_failover done oleg627-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 115 (113s) == replay-single test 116a: large update log master MDT recovery ========================================================== 05:44:11 (1789119851) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2368 1268936 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2240 1269064 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210944 1% /mnt/lustre fail_loc=0x80001702 Failing mds1 on oleg627-server Stopping /mnt/lustre-mds1 (opts:) on oleg627-server 05:44:27 (1789119867) shut down facet: mds1 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds1 to oleg627-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0000 05:44:58 (1789119898) targets are mounted 05:44:58 (1789119898) facet_failover done oleg627-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 /mnt/lustre/d116a.replay-single/striped_dir has type dir OK PASS 116a (64s) == replay-single test 116b: large update log slave MDT recovery ========================================================== 05:45:15 (1789119915) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2372 1268932 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2196 1269108 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210944 1% /mnt/lustre fail_loc=0x80001702 Failing mds2 on oleg627-server Stopping /mnt/lustre-mds2 (opts:) on oleg627-server 05:45:28 (1789119928) shut down facet: mds2 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds2 to oleg627-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0001 05:45:53 (1789119953) targets are mounted 05:45:53 (1789119953) facet_failover done oleg627-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 /mnt/lustre/d116b.replay-single/striped_dir has type dir OK PASS 116b (53s) == replay-single test 117: DNE: cross MDT unlink, fail MDT1 and MDT2 ========================================================== 05:46:08 (1789119968) SKIP: replay-single test_117 needs >= 4 MDTs SKIP 117 (3s) == replay-single test 118: invalidate osp update will not cause update log corruption ========================================================== 05:46:11 (1789119971) fail_loc=0x1705 lfs setdirstripe: dirstripe error on '/mnt/lustre/d118.replay-single/striped_dir': Input/output error lfs setdirstripe: cannot create dir '/mnt/lustre/d118.replay-single/striped_dir': Input/output error lfs setdirstripe: dirstripe error on '/mnt/lustre/d118.replay-single/striped_dir1': Input/output error lfs setdirstripe: cannot create dir '/mnt/lustre/d118.replay-single/striped_dir1': Input/output error fail_loc=0x0 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2500 1268804 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2288 1269016 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210944 1% /mnt/lustre Failing mds1 on oleg627-server Stopping /mnt/lustre-mds1 (opts:) on oleg627-server 05:46:27 (1789119987) shut down facet: mds1 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds1 to oleg627-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0000 05:47:01 (1789120021) targets are mounted 05:47:01 (1789120021) facet_failover done oleg627-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 118 (64s) == replay-single test 119: timeout of normal replay does not cause DNE replay fails ========================================================== 05:47:15 (1789120035) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2436 1268868 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2228 1269076 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210944 1% /mnt/lustre Stopping /mnt/lustre-mds1 (opts:) on oleg627-server Failover mds1 to oleg627-server oleg627-server.virtnet fail_loc=0x80000714 fail_val=65 Start mds1: mount -t lustre -o localrecov -o recovery_time_hard=60 /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0000 oleg627-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 62 sec mdt.lustre-MDT0000.recovery_time_hard=180 PASS 119 (110s) == replay-single test 120: DNE fail abort should stop both normal and DNE replay ========================================================== 05:49:05 (1789120145) Replay barrier on lustre-MDT0000 Stopping /mnt/lustre-mds1 (opts:) on oleg627-server Failover mds1 to oleg627-server oleg627-server.virtnet Start mds1: mount -t lustre -o localrecov -o abort_recovery /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0000 find: '/mnt/lustre/d120.replay-single': No such file or directory find: '/mnt/lustre/d120.replay-single': No such file or directory PASS 120 (42s) == replay-single test 121: lock replay timed out and race ========================================================== 05:49:47 (1789120187) multiop /mnt/lustre/f121.replay-single vs_s TMPPIPE=/tmp/multiop_open_wait_pipe.8220 Stopping /mnt/lustre-mds1 (opts:) on oleg627-server Failover mds1 to oleg627-server oleg627-server.virtnet fail_loc=0x721 fail_val=0 at_max=0 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0000 pdsh@oleg627-client: oleg627-client: ssh exited with exit code 5 fail_loc=0x0 at_max=600 PASS 121 (216s) == replay-single test 130a: DoM file create (setstripe) replay ========================================================== 05:53:23 (1789120403) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2776 1268528 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2532 1268772 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210944 1% /mnt/lustre Failing mds1 on oleg627-server Stopping /mnt/lustre-mds1 (opts:) on oleg627-server 05:53:33 (1789120413) shut down facet: mds1 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds1 to oleg627-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0000 05:54:05 (1789120445) targets are mounted 05:54:05 (1789120445) facet_failover done oleg627-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 130a (55s) == replay-single test 130b: DoM file create (inherited) replay ========================================================== 05:54:19 (1789120459) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2780 1268524 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2532 1268772 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210944 1% /mnt/lustre Failing mds1 on oleg627-server Stopping /mnt/lustre-mds1 (opts:) on oleg627-server 05:54:32 (1789120472) shut down facet: mds1 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds1 to oleg627-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0000 05:55:03 (1789120503) targets are mounted 05:55:03 (1789120503) facet_failover done oleg627-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 130b (57s) == replay-single test 131a: DoM file write lock replay === 05:55:16 (1789120516) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2780 1268524 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2532 1268772 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210944 1% /mnt/lustre 1+0 records in 1+0 records out 8 bytes copied, 0.00415853 s, 1.9 kB/s Failing mds1 on oleg627-server Stopping /mnt/lustre-mds1 (opts:) on oleg627-server 05:55:28 (1789120528) shut down facet: mds1 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds1 to oleg627-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0000 05:56:02 (1789120562) targets are mounted 05:56:02 (1789120562) facet_failover done oleg627-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 131a (62s) SKIP: replay-single test_131b skipping excluded test 131b == replay-single test 132a: PFL new component instantiate replay ========================================================== 05:56:20 (1789120580) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2784 1268520 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2532 1268772 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210944 1% /mnt/lustre 1+0 records in 1+0 records out 1048576 bytes (1.0 MB, 1.0 MiB) copied, 0.0714452 s, 14.7 MB/s /mnt/lustre/f132a.replay-single lcm_layout_gen: 3 lcm_mirror_count: 1 lcm_entry_count: 2 lcme_id: 1 lcme_mirror_id: 0 lcme_flags: init lcme_extent.e_start: 0 lcme_extent.e_end: 1048576 lmm_stripe_count: 1 lmm_stripe_size: 1048576 lmm_pattern: raid0 lmm_layout_gen: 0 lmm_stripe_offset: 0 lmm_objects: - 0: { l_ost_idx: 0, l_fid: [0x280000401:0x722:0x0] } lcme_id: 2 lcme_mirror_id: 0 lcme_flags: init lcme_extent.e_start: 1048576 lcme_extent.e_end: EOF lmm_stripe_count: 2 lmm_stripe_size: 4194304 lmm_pattern: raid0 lmm_layout_gen: 0 lmm_stripe_offset: 1 lmm_objects: - 0: { l_ost_idx: 1, l_fid: [0x2c0000401:0x722:0x0] } - 1: { l_ost_idx: 0, l_fid: [0x280000401:0x723:0x0] } Failing mds1 on oleg627-server Stopping /mnt/lustre-mds1 (opts:) on oleg627-server 05:56:33 (1789120593) shut down facet: mds1 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds1 to oleg627-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0000 05:57:04 (1789120624) targets are mounted 05:57:04 (1789120624) facet_failover done oleg627-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 /mnt/lustre/f132a.replay-single lcm_layout_gen: 4 lcm_mirror_count: 1 lcm_entry_count: 2 lcme_id: 1 lcme_mirror_id: 0 lcme_flags: init lcme_extent.e_start: 0 lcme_extent.e_end: 1048576 lmm_stripe_count: 1 lmm_stripe_size: 1048576 lmm_pattern: raid0 lmm_layout_gen: 65535 lmm_stripe_offset: 0 lmm_objects: - 0: { l_ost_idx: 0, l_fid: [0x280000401:0x722:0x0] } lcme_id: 2 lcme_mirror_id: 0 lcme_flags: init lcme_extent.e_start: 1048576 lcme_extent.e_end: EOF lmm_stripe_count: 2 lmm_stripe_size: 4194304 lmm_pattern: raid0 lmm_layout_gen: 65535 lmm_stripe_offset: 1 lmm_objects: - 0: { l_ost_idx: 1, l_fid: [0x2c0000401:0x722:0x0] } - 1: { l_ost_idx: 0, l_fid: [0x280000401:0x723:0x0] } PASS 132a (58s) == replay-single test 133: check resend of ongoing requests for lwp during failover ========================================================== 05:57:17 (1789120637) seq.srv-lustre-MDT0001.space=clear Starting client: oleg627-client.virtnet: -o user_xattr,flock 192.168.206.127@tcp:/lustre /mnt/lustre fail_val=700 fail_loc=0x80000123 Failing mds1 on oleg627-server Stopping /mnt/lustre-mds1 (opts:) on oleg627-server 05:57:25 (1789120645) shut down facet: mds1 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds1 to oleg627-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0000 05:57:55 (1789120675) targets are mounted 05:57:55 (1789120675) facet_failover done PASS 133 (45s) == replay-single test 134: replay creation of a file created in a pool ========================================================== 05:58:02 (1789120682) Creating new pool pool_134 oleg627-server: Pool lustre.pool_134 created Adding targets to pool oleg627-server: OST lustre-OST0001_UUID added to pool lustre.pool_134 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2860 1268444 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2540 1268764 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 2572 3604448 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 4120 7209920 1% /mnt/lustre Failing mds1 on oleg627-server Stopping /mnt/lustre-mds1 (opts:) on oleg627-server 05:58:22 (1789120702) shut down facet: mds1 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds1 to oleg627-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0000 05:58:58 (1789120738) targets are mounted 05:58:58 (1789120738) facet_failover done oleg627-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 Destroy the created pools: pool_134 lustre.pool_134 oleg627-server: OST lustre-OST0001_UUID removed from pool lustre.pool_134 oleg627-server: Pool lustre.pool_134 destroyed PASS 134 (80s) == replay-single test 135: Server failure in lock replay phase ========================================================== 05:59:22 (1789120762) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2816 1268488 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2540 1268764 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 2572 3604448 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 4120 7209920 1% /mnt/lustre ldlm.cancel_unused_locks_before_replay=0 debug_mb=100 debug=+info +ha +dlmtrace fail_loc=0x414 fail_val=60 Stopping /mnt/lustre-ost1 (opts:) on oleg627-server Failover ost1 to oleg627-server oleg627-server.virtnet fail_loc=0 oleg627-server: oleg627-server.virtnet: executing load_module ../libcfs/libcfs/libcfs fail_loc=0x32d fail_val=20 debug_mb=100 debug=+info +ha +dlmtrace Start ost1: mount -t lustre -o localrecov /dev/mapper/ost1_flakey /mnt/lustre-ost1 seq.cli-lustre-OST0000-super.width=65536 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-OST0000 oleg627-client.virtnet: executing wait_import_state_mount REPLAY_LOCKS osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid 1475 0 osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in REPLAY_LOCKS state after 0 sec Stopping /mnt/lustre-ost1 (opts:) on oleg627-server Failover ost1 to oleg627-server oleg627-server.virtnet oleg627-server: oleg627-server.virtnet: executing load_module ../libcfs/libcfs/libcfs fail_loc=0 Start ost1: mount -t lustre -o localrecov /dev/mapper/ost1_flakey /mnt/lustre-ost1 seq.cli-lustre-OST0000-super.width=65536 End of sync oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-OST0000 Stopping /mnt/lustre-ost1 (opts:-f) on oleg627-server Stopping /mnt/lustre-ost2 (opts:-f) on oleg627-server Start ost1: mount -t lustre -o localrecov /dev/mapper/ost1_flakey /mnt/lustre-ost1 seq.cli-lustre-OST0000-super.width=65536 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-OST0000 Start ost2: mount -t lustre -o localrecov /dev/mapper/ost2_flakey /mnt/lustre-ost2 seq.cli-lustre-OST0001-super.width=65536 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-OST0001 debug_mb=21 debug=super ioctl neterror warning dlmtrace error emerg ha rpctrace vfstrace config console lfsck ldlm.cancel_unused_locks_before_replay=1 PASS 135 (140s) == replay-single test 136: MDS to disconnect all OSPs first, then cleanup ldlm ========================================================== 06:01:42 (1789120902) SKIP: replay-single test_136 needs > 2 MDTs SKIP 136 (3s) == replay-single test 137a: DNE: create under striped dir, fail MDT1 ========================================================== 06:01:45 (1789120905) llite.lustre-ffff8a57c649f000.intent_mkdir=1 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2824 1268480 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2556 1268748 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1564 3605456 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 2588 3604432 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 4152 7209888 1% /mnt/lustre Failing mds1 on oleg627-server Stopping /mnt/lustre-mds1 (opts:) on oleg627-server 06:01:55 (1789120915) shut down facet: mds1 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds1 to oleg627-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0000 06:02:28 (1789120948) targets are mounted 06:02:28 (1789120948) facet_failover done oleg627-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 /mnt/lustre/d137a.replay-single/striped_dir/dir0 has type dir OK lmv_stripe_count: 0 lmv_stripe_offset: 0 lmv_hash_type: none /mnt/lustre/d137a.replay-single/striped_dir/dir1 has type dir OK lmv_stripe_count: 0 lmv_stripe_offset: 1 lmv_hash_type: none PASS 137a (57s) == replay-single test 137b: DNE: create under striped dir, fail MDT2 ========================================================== 06:02:42 (1789120962) llite.lustre-ffff8a57c649f000.intent_mkdir=1 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2828 1268476 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2556 1268748 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1564 3605456 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 2588 3604432 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 4152 7209888 1% /mnt/lustre Failing mds2 on oleg627-server Stopping /mnt/lustre-mds2 (opts:) on oleg627-server 06:02:55 (1789120975) shut down facet: mds2 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds2 to oleg627-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0001 06:03:18 (1789120998) targets are mounted 06:03:18 (1789120998) facet_failover done oleg627-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 /mnt/lustre/d137b.replay-single/striped_dir/dir0 has type dir OK lmv_stripe_count: 0 lmv_stripe_offset: 0 lmv_hash_type: none /mnt/lustre/d137b.replay-single/striped_dir/dir1 has type dir OK lmv_stripe_count: 0 lmv_stripe_offset: 1 lmv_hash_type: none PASS 137b (49s) == replay-single test 137c: DNE: create under striped dir, fail MDT1/MDT2 ========================================================== 06:03:32 (1789121012) llite.lustre-ffff8a57c649f000.intent_mkdir=1 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2824 1268480 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2568 1268736 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1564 3605456 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 2588 3604432 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 4152 7209888 1% /mnt/lustre UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2824 1268480 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2568 1268736 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1564 3605456 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 2588 3604432 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 4152 7209888 1% /mnt/lustre Failing mds2 on oleg627-server Stopping /mnt/lustre-mds2 (opts:) on oleg627-server Failing mds1 on oleg627-server Stopping /mnt/lustre-mds1 (opts:) on oleg627-server 06:03:54 (1789121034) shut down facet: mds2 facet_host: oleg627-server facet_failover_host: oleg627-server facet: mds1 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds1 to oleg627-server Failover mds2 to oleg627-server mount facets: mds2 mount facets: mds1 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 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 06:04:27 (1789121067) targets are mounted 06:04:27 (1789121067) facet_failover done oleg627-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 /mnt/lustre/d137c.replay-single/striped_dir/dir0 has type dir OK lmv_stripe_count: 0 lmv_stripe_offset: 0 lmv_hash_type: none /mnt/lustre/d137c.replay-single/striped_dir/dir1 has type dir OK lmv_stripe_count: 0 lmv_stripe_offset: 1 lmv_hash_type: none PASS 137c (72s) == replay-single test 160: mdt.recovery_reconnect_histogram testing ========================================================== 06:04:44 (1789121084) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2812 1268492 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2556 1268748 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1564 3605456 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 2588 3604432 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 4152 7209888 1% /mnt/lustre Failing mds1 on oleg627-server Stopping /mnt/lustre-mds1 (opts:) on oleg627-server 06:04:56 (1789121096) shut down facet: mds1 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds1 to oleg627-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0000 06:05:30 (1789121130) targets are mounted 06:05:30 (1789121130) facet_failover done oleg627-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 recovery_start: 1789121125 recovery_finish: 1789121129 recovery_time: 4 reconnect_delay_seconds_samples: 1 client_reconnect_histogram: - { delay_sec: 1, clients: 1, pct: 100, cum_pct: 100 } client_reconnect_top: - { nid: "192.168.206.27@tcp", delay_sec: 0 } mdt.lustre-MDT0000.exports.192.168.206.27@tcp.reconnect_delay=0 PASS 160 (65s) == replay-single test 200: Dropping one OBD_PING should not cause disconnect ========================================================== 06:05:49 (1789121149) SKIP: replay-single test_200 Need remote client SKIP 200 (3s) == replay-single test 201: MDT umount cascading disconnects timeouts ========================================================== 06:05:52 (1789121152) fail_loc=0x245 fail_val=8 fail_loc=0x245 fail_val=8 Stopping /mnt/lustre-mds2 (opts:) on oleg627-server Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0001 Umount took 19 seconds PASS 201 (40s) == replay-single test 202: pfl replay should recovery layout generation ========================================================== 06:06:32 (1789121192) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2780 1268524 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2508 1268796 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1564 3605456 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 2588 3604432 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 4152 7209888 1% /mnt/lustre Failing mds1 on oleg627-server Stopping /mnt/lustre-mds1 (opts:) on oleg627-server 06:06:47 (1789121207) shut down facet: mds1 facet_host: oleg627-server facet_failover_host: oleg627-server Failover mds1 to oleg627-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg627-server: oleg627-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg627-client: oleg627-server: ssh exited with exit code 1 Started lustre-MDT0000 06:07:20 (1789121240) targets are mounted 06:07:20 (1789121240) facet_failover done oleg627-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 202 (63s) == replay-single test 203: resend can hit original request ========================================================== 06:07:36 (1789121256) Starting client: oleg627-client.virtnet: -o user_xattr,flock 192.168.206.127@tcp:/lustre /mnt/lustre2 fail_loc=0x80002403 fail_val=2 STAT SETSTRIPE File: /mnt/lustre/f203.replay-single Size: 0 Blocks: 0 IO Block: 4194304 regular empty file Device: 2c54f966h/743766374d Inode: 144116279014326273 Links: 1 Access: (0644/-rw-r--r--) Uid: ( 0/ root) Gid: ( 0/ root) Access: 2026-09-11 06:07:39.000000000 -0400 Modify: 2026-09-11 06:07:39.000000000 -0400 Change: 2026-09-11 06:07:39.000000000 -0400 Birth: 2026-09-11 06:07:39.000000000 -0400 fail_loc=0 fail_val=0 192.168.206.127@tcp:/lustre /mnt/lustre2 lustre rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose 0 0 Stopping client oleg627-client.virtnet /mnt/lustre2 (opts:) PASS 203 (13s) == replay-single test complete, duration 3690 sec ======== 06:07:48 (1789121268) osc.lustre-OST0000-osc-ffff8a57c649f000.stats_compr= write_pages_compressible: 0 write_pages_incompressible: 0 write_chunks_compressible: 0 write_chunks_incompressible: 0 write_bytes_compr: 0 write_bytes_raw: 0 write_bytes_incompr: 0 read_pages_compressed: 0 read_chunks_compressed: 0 read_bytes_compr: 0 read_bytes_raw: 0 osc.lustre-OST0001-osc-ffff8a57c649f000.stats_compr= write_pages_compressible: 0 write_pages_incompressible: 0 write_chunks_compressible: 0 write_chunks_incompressible: 0 write_bytes_compr: 0 write_bytes_raw: 0 write_bytes_incompr: 0 read_pages_compressed: 0 read_chunks_compressed: 0 read_bytes_compr: 0 read_bytes_raw: 0 obdfilter.lustre-OST0000.stats_compr= snapshot_time 1789121271.768889865 secs.nsecs start_time 1789120876.141742257 secs.nsecs elapsed_time 395.627147608 secs.nsecs uncompressed_objects 655 samples [reqs] obdfilter.lustre-OST0001.stats_compr= snapshot_time 1789121271.768963332 secs.nsecs start_time 1789120889.283279105 secs.nsecs elapsed_time 382.485684227 secs.nsecs uncompressed_objects 658 samples [reqs] === replay-single: start cleanup 06:07:51 (1789121271) === === replay-single: finish cleanup 06:07:58 (1789121278) ===