-----============= acceptance-small: replay-single ============----- Fri Sep 11 08:16:26 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 oleg611-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 08:16:46 (1789129006) === oleg611-client.virtnet: executing check_config_client /mnt/lustre oleg611-client.virtnet: Checking config lustre mounted on /mnt/lustre Checking servers environments Checking clients oleg611-client.virtnet environments Using TIMEOUT=20 osc.lustre-OST0000-osc-ffff9669896b6000.idle_timeout=debug osc.lustre-OST0001-osc-ffff9669896b6000.idle_timeout=debug disable quota as required oleg611-server: oleg611-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' === replay-single: finish setup 08:17:42 (1789129062) === Cleaning up AT ... == replay-single test 100a: DNE: create striped dir, drop update rep from MDT1, fail MDT1 ========================================================== 08:17:47 (1789129067) fail_loc=0x1701 Failing mds2 on oleg611-server Stopping /mnt/lustre-mds2 (opts:) on oleg611-server 08:17:55 (1789129075) shut down facet: mds2 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds2 to oleg611-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0001 08:18:21 (1789129101) targets are mounted 08:18:21 (1789129101) facet_failover done oleg611-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: 59.27 ops/second PASS 100a (52s) == replay-single test 100b: DNE: create striped dir, fail MDT0 ========================================================== 08:18:39 (1789129119) fail_loc=0x119 Failing mds1 on oleg611-server Stopping /mnt/lustre-mds1 (opts:) on oleg611-server 08:18:47 (1789129127) shut down facet: mds1 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds1 to oleg611-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0000 08:19:19 (1789129159) targets are mounted 08:19:19 (1789129159) facet_failover done oleg611-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 0.30 seconds: 66.83 ops/second PASS 100b (57s) == replay-single test 100c: DNE: create striped dir, abort_recov_mdt mds2 ========================================================== 08:19:36 (1789129176) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1884 1269420 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1760 1269544 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 oleg611-server Failover mds2 to oleg611-server oleg611-server.virtnet Start mds2: mount -t lustre -o localrecov -o abort_recov_mdt /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0001 total: 20 open/close in 0.45 seconds: 44.75 ops/second Failing mds2 on oleg611-server Stopping /mnt/lustre-mds2 (opts:) on oleg611-server 08:20:27 (1789129227) shut down facet: mds2 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds2 to oleg611-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0001 08:20:53 (1789129253) targets are mounted 08:20:53 (1789129253) facet_failover done oleg611-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 0.33 seconds: 60.54 ops/second PASS 100c (97s) == replay-single test 100d: DNE: cancel update logs upon recovery abort ========================================================== 08:21:13 (1789129273) striped dir -i0 -c2 -H all_char /mnt/lustre/d100d.replay-single total: 100 mkdir in 1.51 seconds: 66.35 ops/second lustre-MDT0001-osd [catalog]: [0x2400013a0:0x3:0x0] [index]: 00001 [logid]: [0x240001b70:0x2:0x0] lustre-MDT0000-osp-MDT0001 [catalog]: [0x200000bd1:0x3:0x0] [index]: 00001 [logid]: [0x200000bd2:0x2:0x0] [index]: 00002 [logid]: [0x200000bd2:0x3:0x0] Stopping /mnt/lustre-mds2 (opts:) on oleg611-server Failover mds2 to oleg611-server oleg611-server.virtnet Start mds2: mount -t lustre -o localrecov -o abort_recovery /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0001 pdsh@oleg611-client: oleg611-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 (54s) == replay-single test 100e: DNE: create striped dir on MDT0 and MDT1, fail MDT0, MDT1 ========================================================== 08:22:07 (1789129327) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2288 1269016 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2204 1269100 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 2288 1269016 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2204 1269100 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 [0x200000bd0:0x36:0x0] 1 [0x240000bd1:0x36:0x0] Failing mds1 on oleg611-server Stopping /mnt/lustre-mds1 (opts:) on oleg611-server Failing mds2 on oleg611-server Stopping /mnt/lustre-mds2 (opts:) on oleg611-server 08:22:31 (1789129351) shut down facet: mds1 facet_host: oleg611-server facet_failover_host: oleg611-server facet: mds2 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds1 to oleg611-server mount facets: mds1 Failover mds2 to oleg611-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 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 08:23:03 (1789129383) targets are mounted 08:23:03 (1789129383) facet_failover done oleg611-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 [0x200000bd0:0x36:0x0] 1 [0x240000bd1:0x36:0x0] PASS 100e (73s) == replay-single test 101: Shouldn't reassign precreated objs to other files after recovery ========================================================== 08:23:20 (1789129400) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2148 1269156 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2024 1269280 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 oleg611-server Failover mds1 to oleg611-server oleg611-server.virtnet Start mds1: mount -t lustre -o localrecov -o abort_recovery /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0000 PASS 101 (140s) == replay-single test 102a: check resend (request lost) with multiple modify RPCs in flight ========================================================== 08:25:40 (1789129540) creating 7 files ... fail_loc=0x159 launch 7 chmod in parallel (08:25:43) ... fail_loc=0 done (08:26:39) /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 (64s) == replay-single test 102b: check resend (reply lost) with multiple modify RPCs in flight ========================================================== 08:26:45 (1789129605) creating 7 files ... fail_loc=0x15a launch 7 chmod in parallel (08:26:48) ... fail_loc=0 done (08:27:44) /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 (67s) == replay-single test 102c: check replay w/o reconstruction with multiple mod RPCs in flight ========================================================== 08:27:51 (1789129671) creating 7 files ... UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2272 1269032 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2088 1269216 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605304 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605248 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210552 1% /mnt/lustre fail_loc=0x15a launch 7 chmod in parallel (08:28:03) ... fail_loc=0 Failing mds2 on oleg611-server Stopping /mnt/lustre-mds2 (opts:) on oleg611-server 08:28:09 (1789129689) shut down facet: mds2 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds2 to oleg611-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0001 08:28:37 (1789129717) targets are mounted 08:28:37 (1789129717) facet_failover done oleg611-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 (08:28:50) /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 (65s) == replay-single test 102d: check replay & reconstruction with multiple mod RPCs in flight ========================================================== 08:28:56 (1789129736) creating 7 files ... fail_loc=0x15a launch 7 chmod in parallel (08:28:59) ... fail_loc=0 Failing mds1 on oleg611-server Stopping /mnt/lustre-mds1 (opts:) on oleg611-server 08:29:06 (1789129746) shut down facet: mds1 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds1 to oleg611-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0000 08:29:40 (1789129780) targets are mounted 08:29:40 (1789129780) facet_failover done oleg611-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 (08:29:52) /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 (61s) == replay-single test 103: Check otr_next_id overflow ==== 08:29:57 (1789129797) fail_loc=0x80000162 total: 30 open/close in 0.41 seconds: 72.81 ops/second Failing mds1 on oleg611-server Stopping /mnt/lustre-mds1 (opts:) on oleg611-server 08:30:05 (1789129805) shut down facet: mds1 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds1 to oleg611-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0000 08:30:37 (1789129837) targets are mounted 08:30:37 (1789129837) facet_failover done oleg611-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 (59s) == replay-single test 110a: DNE: create striped dir, fail MDT1 ========================================================== 08:30:56 (1789129856) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2212 1269092 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2080 1269224 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 oleg611-server Stopping /mnt/lustre-mds1 (opts:) on oleg611-server 08:31:09 (1789129869) shut down facet: mds1 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds1 to oleg611-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0000 08:31:45 (1789129905) targets are mounted 08:31:45 (1789129905) facet_failover done oleg611-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 (67s) == replay-single test 110b: DNE: create striped dir, fail MDT1 and client ========================================================== 08:32:04 (1789129924) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2216 1269088 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2080 1269224 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 oleg611-server Stopping /mnt/lustre-mds1 (opts:) on oleg611-server 08:32:20 (1789129940) shut down facet: mds1 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds1 to oleg611-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0000 08:32:54 (1789129974) targets are mounted 08:32:54 (1789129974) facet_failover done pdsh@oleg611-client: oleg611-client: ssh exited with exit code 95 oleg611-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 pdsh@oleg611-client: oleg611-client: ssh exited with exit code 95 Starting client: oleg611-client.virtnet: -o user_xattr,flock 192.168.206.111@tcp:/lustre /mnt/lustre /mnt/lustre/d110b.replay-single/striped_dir has type dir OK PASS 110b (132s) == replay-single test 110c: DNE: create striped dir, fail MDT2 ========================================================== 08:34:16 (1789130056) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2220 1269084 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2076 1269228 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 oleg611-server Stopping /mnt/lustre-mds2 (opts:) on oleg611-server 08:34:31 (1789130071) shut down facet: mds2 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds2 to oleg611-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0001 08:34:59 (1789130099) targets are mounted 08:34:59 (1789130099) facet_failover done oleg611-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 (61s) == replay-single test 110d: DNE: create striped dir, fail MDT2 and client ========================================================== 08:35:17 (1789130117) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2260 1269044 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2080 1269224 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 oleg611-server Stopping /mnt/lustre-mds2 (opts:) on oleg611-server 08:35:30 (1789130130) shut down facet: mds2 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds2 to oleg611-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0001 08:36:00 (1789130160) targets are mounted 08:36:00 (1789130160) facet_failover done pdsh@oleg611-client: oleg611-client: ssh exited with exit code 95 oleg611-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 pdsh@oleg611-client: oleg611-client: ssh exited with exit code 95 Starting client: oleg611-client.virtnet: -o user_xattr,flock 192.168.206.111@tcp:/lustre /mnt/lustre /mnt/lustre/d110d.replay-single/striped_dir has type dir OK PASS 110d (122s) == replay-single test 110e: DNE: create striped dir, uncommit on MDT2, fail client/MDT1/MDT2 ========================================================== 08:37:19 (1789130239) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2252 1269052 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2076 1269228 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 oleg611-server Stopping /mnt/lustre-mds1 (opts:) on oleg611-server Failing mds2 on oleg611-server Stopping /mnt/lustre-mds2 (opts:) on oleg611-server 08:37:44 (1789130264) shut down facet: mds1 facet_host: oleg611-server facet_failover_host: oleg611-server facet: mds2 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds1 to oleg611-server mount facets: mds1 Failover mds2 to oleg611-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 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 08:38:15 (1789130295) targets are mounted 08:38:15 (1789130295) facet_failover done pdsh@oleg611-client: oleg611-client: ssh exited with exit code 95 oleg611-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@oleg611-client: oleg611-client: ssh exited with exit code 95 Starting client: oleg611-client.virtnet: -o user_xattr,flock 192.168.206.111@tcp:/lustre /mnt/lustre /mnt/lustre/d110e.replay-single/striped_dir has type dir OK PASS 110e (133s) SKIP: replay-single test_110f skipping excluded test 110f == replay-single test 110g: DNE: create striped dir, uncommit on MDT1, fail client/MDT1/MDT2 ========================================================== 08:39:34 (1789130374) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2252 1269052 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2076 1269228 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 oleg611-server Stopping /mnt/lustre-mds1 (opts:) on oleg611-server Failing mds2 on oleg611-server Stopping /mnt/lustre-mds2 (opts:) on oleg611-server 08:40:00 (1789130400) shut down facet: mds1 facet_host: oleg611-server facet_failover_host: oleg611-server facet: mds2 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds1 to oleg611-server mount facets: mds1 Failover mds2 to oleg611-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 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0000 Started lustre-MDT0001 08:40:30 (1789130430) targets are mounted 08:40:30 (1789130430) facet_failover done pdsh@oleg611-client: oleg611-client: ssh exited with exit code 95 oleg611-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@oleg611-client: oleg611-client: ssh exited with exit code 95 Starting client: oleg611-client.virtnet: -o user_xattr,flock 192.168.206.111@tcp:/lustre /mnt/lustre /mnt/lustre/d110g.replay-single/striped_dir has type dir OK PASS 110g (132s) == replay-single test 111a: DNE: unlink striped dir, fail MDT1 ========================================================== 08:41:46 (1789130506) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2264 1269040 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2088 1269216 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 oleg611-server Stopping /mnt/lustre-mds1 (opts:) on oleg611-server 08:42:01 (1789130521) shut down facet: mds1 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds1 to oleg611-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0000 08:42:31 (1789130551) targets are mounted 08:42:31 (1789130551) facet_failover done oleg611-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 (61s) == replay-single test 111b: DNE: unlink striped dir, fail MDT2 ========================================================== 08:42:47 (1789130567) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2268 1269036 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2092 1269212 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 oleg611-server Stopping /mnt/lustre-mds2 (opts:) on oleg611-server 08:43:02 (1789130582) shut down facet: mds2 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds2 to oleg611-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0001 08:43:30 (1789130610) targets are mounted 08:43:30 (1789130610) facet_failover done pdsh@oleg611-client: oleg611-client: ssh exited with exit code 95 oleg611-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 pdsh@oleg611-client: oleg611-client: ssh exited with exit code 95 Starting client: oleg611-client.virtnet: -o user_xattr,flock 192.168.206.111@tcp:/lustre /mnt/lustre Can't lstat /mnt/lustre/d111b.replay-single/striped_dir: No such file or directory PASS 111b (122s) == replay-single test 111c: DNE: unlink striped dir, uncommit on MDT1, fail client/MDT1/MDT2 ========================================================== 08:44:49 (1789130689) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2312 1268992 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2092 1269212 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 oleg611-server Stopping /mnt/lustre-mds1 (opts:) on oleg611-server Failing mds2 on oleg611-server Stopping /mnt/lustre-mds2 (opts:) on oleg611-server 08:45:21 (1789130721) shut down facet: mds1 facet_host: oleg611-server facet_failover_host: oleg611-server facet: mds2 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds1 to oleg611-server mount facets: mds1 Failover mds2 to oleg611-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 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 08:46:06 (1789130766) targets are mounted 08:46:06 (1789130766) facet_failover done pdsh@oleg611-client: oleg611-client: ssh exited with exit code 95 oleg611-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@oleg611-client: oleg611-client: ssh exited with exit code 95 Starting client: oleg611-client.virtnet: -o user_xattr,flock 192.168.206.111@tcp:/lustre /mnt/lustre Can't lstat /mnt/lustre/d111c.replay-single/striped_dir: No such file or directory PASS 111c (156s) == replay-single test 111d: DNE: unlink striped dir, uncommit on MDT2, fail client/MDT1/MDT2 ========================================================== 08:47:25 (1789130845) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2272 1269032 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2096 1269208 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 oleg611-server Stopping /mnt/lustre-mds1 (opts:) on oleg611-server Failing mds2 on oleg611-server Stopping /mnt/lustre-mds2 (opts:) on oleg611-server 08:47:53 (1789130873) shut down facet: mds1 facet_host: oleg611-server facet_failover_host: oleg611-server facet: mds2 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds1 to oleg611-server mount facets: mds1 Failover mds2 to oleg611-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 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 08:48:24 (1789130904) targets are mounted 08:48:24 (1789130904) facet_failover done pdsh@oleg611-client: oleg611-client: ssh exited with exit code 95 oleg611-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@oleg611-client: oleg611-client: ssh exited with exit code 95 Starting client: oleg611-client.virtnet: -o user_xattr,flock 192.168.206.111@tcp:/lustre /mnt/lustre Can't lstat /mnt/lustre/d111d.replay-single/striped_dir: No such file or directory PASS 111d (132s) == replay-single test 111e: DNE: unlink striped dir, uncommit on MDT2, fail MDT1/MDT2 ========================================================== 08:49:38 (1789130978) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2276 1269028 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2096 1269208 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 2088 1269216 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 oleg611-server Stopping /mnt/lustre-mds1 (opts:) on oleg611-server Failing mds2 on oleg611-server Stopping /mnt/lustre-mds2 (opts:) on oleg611-server 08:50:04 (1789131004) shut down facet: mds1 facet_host: oleg611-server facet_failover_host: oleg611-server facet: mds2 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds1 to oleg611-server mount facets: mds1 Failover mds2 to oleg611-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 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 08:50:35 (1789131035) targets are mounted 08:50:35 (1789131035) facet_failover done oleg611-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 (83s) == replay-single test 111f: DNE: unlink striped dir, uncommit on MDT1, fail MDT1/MDT2 ========================================================== 08:51:00 (1789131060) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2316 1268988 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2132 1269172 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 2308 1268996 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 Failing mds1 on oleg611-server Stopping /mnt/lustre-mds1 (opts:) on oleg611-server Failing mds2 on oleg611-server Stopping /mnt/lustre-mds2 (opts:) on oleg611-server 08:51:32 (1789131092) shut down facet: mds1 facet_host: oleg611-server facet_failover_host: oleg611-server facet: mds2 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds1 to oleg611-server mount facets: mds1 Failover mds2 to oleg611-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 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 08:52:16 (1789131136) targets are mounted 08:52:16 (1789131136) facet_failover done oleg611-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 ========================================================== 08:52:52 (1789131172) 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 2284 1269020 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 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2284 1269020 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 Failing mds1 on oleg611-server Stopping /mnt/lustre-mds1 (opts:) on oleg611-server Failing mds2 on oleg611-server Stopping /mnt/lustre-mds2 (opts:) on oleg611-server 08:53:18 (1789131198) shut down facet: mds1 facet_host: oleg611-server facet_failover_host: oleg611-server facet: mds2 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds1 to oleg611-server mount facets: mds1 Failover mds2 to oleg611-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 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 08:53:48 (1789131228) targets are mounted 08:53:48 (1789131228) facet_failover done oleg611-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 (75s) == replay-single test 112a: DNE: cross MDT rename, fail MDT1 ========================================================== 08:54:06 (1789131246) SKIP: replay-single test_112a needs >= 4 MDTs SKIP 112a (4s) == replay-single test 112b: DNE: cross MDT rename, fail MDT2 ========================================================== 08:54:10 (1789131250) SKIP: replay-single test_112b needs >= 4 MDTs SKIP 112b (3s) == replay-single test 112c: DNE: cross MDT rename, fail MDT3 ========================================================== 08:54:14 (1789131254) SKIP: replay-single test_112c needs >= 4 MDTs SKIP 112c (3s) == replay-single test 112d: DNE: cross MDT rename, fail MDT4 ========================================================== 08:54:18 (1789131258) SKIP: replay-single test_112d needs >= 4 MDTs SKIP 112d (4s) == replay-single test 112e: DNE: cross MDT rename, fail MDT1 and MDT2 ========================================================== 08:54:21 (1789131261) SKIP: replay-single test_112e needs >= 4 MDTs SKIP 112e (3s) == replay-single test 112f: DNE: cross MDT rename, fail MDT1 and MDT3 ========================================================== 08:54:24 (1789131264) SKIP: replay-single test_112f needs >= 4 MDTs SKIP 112f (3s) == replay-single test 112g: DNE: cross MDT rename, fail MDT1 and MDT4 ========================================================== 08:54:28 (1789131268) SKIP: replay-single test_112g needs >= 4 MDTs SKIP 112g (4s) == replay-single test 112h: DNE: cross MDT rename, fail MDT2 and MDT3 ========================================================== 08:54:31 (1789131271) SKIP: replay-single test_112h needs >= 4 MDTs SKIP 112h (4s) == replay-single test 112i: DNE: cross MDT rename, fail MDT2 and MDT4 ========================================================== 08:54:35 (1789131275) SKIP: replay-single test_112i needs >= 4 MDTs SKIP 112i (4s) == replay-single test 112j: DNE: cross MDT rename, fail MDT3 and MDT4 ========================================================== 08:54:39 (1789131279) SKIP: replay-single test_112j needs >= 4 MDTs SKIP 112j (3s) == replay-single test 112k: DNE: cross MDT rename, fail MDT1,MDT2,MDT3 ========================================================== 08:54:42 (1789131282) SKIP: replay-single test_112k needs >= 4 MDTs SKIP 112k (3s) == replay-single test 112l: DNE: cross MDT rename, fail MDT1,MDT2,MDT4 ========================================================== 08:54:45 (1789131285) SKIP: replay-single test_112l needs >= 4 MDTs SKIP 112l (3s) == replay-single test 112m: DNE: cross MDT rename, fail MDT1,MDT3,MDT4 ========================================================== 08:54:49 (1789131289) SKIP: replay-single test_112m needs >= 4 MDTs SKIP 112m (3s) == replay-single test 112n: DNE: cross MDT rename, fail MDT2,MDT3,MDT4 ========================================================== 08:54:53 (1789131293) SKIP: replay-single test_112n needs >= 4 MDTs SKIP 112n (4s) == replay-single test 115: failover for create/unlink striped directory ========================================================== 08:54:57 (1789131297) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2280 1269024 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2092 1269212 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 fnv_1a_64 /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 fnv_1a_64 /mnt/lustre/d115.replay-single/test_4 Failing mds2 on oleg611-server Stopping /mnt/lustre-mds2 (opts:) on oleg611-server 08:55:13 (1789131313) shut down facet: mds2 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds2 to oleg611-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0001 08:55:39 (1789131339) targets are mounted 08:55:39 (1789131339) facet_failover done oleg611-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 2312 1268992 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2188 1269116 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 crush /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 crush2 /mnt/lustre/d115.replay-single/test_2 striped dir -i0 -c2 -H all_char /mnt/lustre/d115.replay-single/test_3 striped dir -i0 -c2 -H crush2 /mnt/lustre/d115.replay-single/test_4 Failing mds1 on oleg611-server Stopping /mnt/lustre-mds1 (opts:) on oleg611-server 08:56:04 (1789131364) shut down facet: mds1 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds1 to oleg611-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0000 08:56:37 (1789131397) targets are mounted 08:56:37 (1789131397) facet_failover done oleg611-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 (115s) == replay-single test 116a: large update log master MDT recovery ========================================================== 08:56:52 (1789131412) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2384 1268920 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2212 1269092 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 oleg611-server Stopping /mnt/lustre-mds1 (opts:) on oleg611-server 08:57:08 (1789131428) shut down facet: mds1 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds1 to oleg611-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0000 08:57:39 (1789131459) targets are mounted 08:57:39 (1789131459) facet_failover done oleg611-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 (61s) == replay-single test 116b: large update log slave MDT recovery ========================================================== 08:57:54 (1789131474) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2388 1268916 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2168 1269136 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 oleg611-server Stopping /mnt/lustre-mds2 (opts:) on oleg611-server 08:58:08 (1789131488) shut down facet: mds2 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds2 to oleg611-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0001 08:58:36 (1789131516) targets are mounted 08:58:36 (1789131516) facet_failover done oleg611-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 (60s) == replay-single test 117: DNE: cross MDT unlink, fail MDT1 and MDT2 ========================================================== 08:58:53 (1789131533) SKIP: replay-single test_117 needs >= 4 MDTs SKIP 117 (4s) == replay-single test 118: invalidate osp update will not cause update log corruption ========================================================== 08:58:57 (1789131537) 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 2516 1268788 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2260 1269044 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 oleg611-server Stopping /mnt/lustre-mds1 (opts:) on oleg611-server 08:59:12 (1789131552) shut down facet: mds1 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds1 to oleg611-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0000 08:59:46 (1789131586) targets are mounted 08:59:46 (1789131586) facet_failover done oleg611-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 ========================================================== 09:00:01 (1789131601) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2452 1268852 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2200 1269104 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 oleg611-server Failover mds1 to oleg611-server oleg611-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 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0000 oleg611-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 61 sec mdt.lustre-MDT0000.recovery_time_hard=180 PASS 119 (115s) == replay-single test 120: DNE fail abort should stop both normal and DNE replay ========================================================== 09:01:57 (1789131717) Replay barrier on lustre-MDT0000 Stopping /mnt/lustre-mds1 (opts:) on oleg611-server Failover mds1 to oleg611-server oleg611-server.virtnet Start mds1: mount -t lustre -o localrecov -o abort_recovery /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-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 (54s) == replay-single test 121: lock replay timed out and race ========================================================== 09:02:50 (1789131770) multiop /mnt/lustre/f121.replay-single vs_s TMPPIPE=/tmp/multiop_open_wait_pipe.8239 Stopping /mnt/lustre-mds1 (opts:) on oleg611-server Failover mds1 to oleg611-server oleg611-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 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0000 pdsh@oleg611-client: oleg611-client: ssh exited with exit code 5 fail_loc=0x0 at_max=600 PASS 121 (219s) == replay-single test 130a: DoM file create (setstripe) replay ========================================================== 09:06:30 (1789131990) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2792 1268512 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2504 1268800 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 oleg611-server Stopping /mnt/lustre-mds1 (opts:) on oleg611-server 09:06:42 (1789132002) shut down facet: mds1 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds1 to oleg611-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0000 09:07:18 (1789132038) targets are mounted 09:07:18 (1789132038) facet_failover done oleg611-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 (64s) == replay-single test 130b: DoM file create (inherited) replay ========================================================== 09:07:34 (1789132054) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2796 1268508 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2504 1268800 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 oleg611-server Stopping /mnt/lustre-mds1 (opts:) on oleg611-server 09:07:47 (1789132067) shut down facet: mds1 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds1 to oleg611-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0000 09:08:18 (1789132098) targets are mounted 09:08:18 (1789132098) facet_failover done oleg611-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 (60s) == replay-single test 131a: DoM file write lock replay === 09:08:34 (1789132114) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2796 1268508 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2504 1268800 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, 0.00480784 s, 1.7 kB/s Failing mds1 on oleg611-server Stopping /mnt/lustre-mds1 (opts:) on oleg611-server 09:08:47 (1789132127) shut down facet: mds1 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds1 to oleg611-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0000 09:09:22 (1789132162) targets are mounted 09:09:22 (1789132162) facet_failover done oleg611-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 (66s) SKIP: replay-single test_131b skipping excluded test 131b == replay-single test 132a: PFL new component instantiate replay ========================================================== 09:09:42 (1789132182) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2800 1268504 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2504 1268800 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, 0.0713416 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: [0x280000401:0x702:0x0] } 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: [0x2c0000401:0x702:0x0] } - 1: { l_ost_idx: 0, l_fid: [0x280000401:0x703:0x0] } Failing mds1 on oleg611-server Stopping /mnt/lustre-mds1 (opts:) on oleg611-server 09:09:55 (1789132195) shut down facet: mds1 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds1 to oleg611-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0000 09:10:29 (1789132229) targets are mounted 09:10:29 (1789132229) facet_failover done oleg611-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: [0x280000401:0x702:0x0] } 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: [0x2c0000401:0x702:0x0] } - 1: { l_ost_idx: 0, l_fid: [0x280000401:0x703:0x0] } PASS 132a (64s) == replay-single test 133: check resend of ongoing requests for lwp during failover ========================================================== 09:10:46 (1789132246) seq.srv-lustre-MDT0001.space=clear Starting client: oleg611-client.virtnet: -o user_xattr,flock 192.168.206.111@tcp:/lustre /mnt/lustre fail_val=700 fail_loc=0x80000123 Failing mds1 on oleg611-server Stopping /mnt/lustre-mds1 (opts:) on oleg611-server 09:10:57 (1789132257) shut down facet: mds1 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds1 to oleg611-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0000 09:11:22 (1789132282) targets are mounted 09:11:22 (1789132282) facet_failover done PASS 133 (42s) == replay-single test 134: replay creation of a file created in a pool ========================================================== 09:11:28 (1789132288) Creating new pool pool_134 oleg611-server: Pool lustre.pool_134 created Adding targets to pool oleg611-server: OST lustre-OST0001_UUID added to pool lustre.pool_134 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2876 1268428 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2512 1268792 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 oleg611-server Stopping /mnt/lustre-mds1 (opts:) on oleg611-server 09:11:52 (1789132312) shut down facet: mds1 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds1 to oleg611-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0000 09:12:25 (1789132345) targets are mounted 09:12:25 (1789132345) facet_failover done oleg611-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 oleg611-server: OST lustre-OST0001_UUID removed from pool lustre.pool_134 oleg611-server: Pool lustre.pool_134 destroyed PASS 134 (84s) == replay-single test 135: Server failure in lock replay phase ========================================================== 09:12:52 (1789132372) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2832 1268472 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2512 1268792 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 oleg611-server Failover ost1 to oleg611-server oleg611-server.virtnet fail_loc=0 oleg611-server: oleg611-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 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-OST0000 oleg611-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 oleg611-server Failover ost1 to oleg611-server oleg611-server.virtnet oleg611-server: oleg611-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 End of sync seq.cli-lustre-OST0000-super.width=65536 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-OST0000 Stopping /mnt/lustre-ost1 (opts:-f) on oleg611-server Stopping /mnt/lustre-ost2 (opts:-f) on oleg611-server Start ost1: mount -t lustre -o localrecov /dev/mapper/ost1_flakey /mnt/lustre-ost1 seq.cli-lustre-OST0000-super.width=65536 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-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 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-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 (143s) == replay-single test 136: MDS to disconnect all OSPs first, then cleanup ldlm ========================================================== 09:15:15 (1789132515) SKIP: replay-single test_136 needs > 2 MDTs SKIP 136 (4s) == replay-single test 137a: DNE: create under striped dir, fail MDT1 ========================================================== 09:15:19 (1789132519) llite.lustre-ffff966988713800.intent_mkdir=1 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2840 1268464 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2528 1268776 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 oleg611-server Stopping /mnt/lustre-mds1 (opts:) on oleg611-server 09:15:36 (1789132536) shut down facet: mds1 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds1 to oleg611-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0000 09:16:07 (1789132567) targets are mounted 09:16:07 (1789132567) facet_failover done oleg611-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 (64s) == replay-single test 137b: DNE: create under striped dir, fail MDT2 ========================================================== 09:16:23 (1789132583) llite.lustre-ffff966988713800.intent_mkdir=1 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2844 1268460 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2528 1268776 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 oleg611-server Stopping /mnt/lustre-mds2 (opts:) on oleg611-server 09:16:36 (1789132596) shut down facet: mds2 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds2 to oleg611-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0001 09:17:01 (1789132621) targets are mounted 09:17:01 (1789132621) facet_failover done oleg611-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 (55s) == replay-single test 137c: DNE: create under striped dir, fail MDT1/MDT2 ========================================================== 09:17:18 (1789132638) llite.lustre-ffff966988713800.intent_mkdir=1 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2840 1268464 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2540 1268764 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 2840 1268464 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2540 1268764 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 oleg611-server Stopping /mnt/lustre-mds2 (opts:) on oleg611-server Failing mds1 on oleg611-server Stopping /mnt/lustre-mds1 (opts:) on oleg611-server 09:17:44 (1789132664) shut down facet: mds2 facet_host: oleg611-server facet_failover_host: oleg611-server facet: mds1 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds1 to oleg611-server Failover mds2 to oleg611-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 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 09:18:21 (1789132701) targets are mounted 09:18:21 (1789132701) facet_failover done oleg611-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 (81s) == replay-single test 160: mdt.recovery_reconnect_histogram testing ========================================================== 09:18:39 (1789132719) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2828 1268476 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2528 1268776 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 oleg611-server Stopping /mnt/lustre-mds1 (opts:) on oleg611-server 09:18:52 (1789132732) shut down facet: mds1 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds1 to oleg611-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0000 09:19:27 (1789132767) targets are mounted 09:19:27 (1789132767) facet_failover done oleg611-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: 1789132762 recovery_finish: 1789132766 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: "192.168.206.11@tcp", delay_sec: 0 } mdt.lustre-MDT0000.exports.192.168.206.11@tcp.reconnect_delay=0 PASS 160 (71s) == replay-single test 200: Dropping one OBD_PING should not cause disconnect ========================================================== 09:19:50 (1789132790) SKIP: replay-single test_200 Need remote client SKIP 200 (3s) == replay-single test 201: MDT umount cascading disconnects timeouts ========================================================== 09:19:53 (1789132793) fail_loc=0x245 fail_val=8 fail_loc=0x245 fail_val=8 Stopping /mnt/lustre-mds2 (opts:) on oleg611-server Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0001 Umount took 19 seconds PASS 201 (43s) == replay-single test 202: pfl replay should recovery layout generation ========================================================== 09:20:36 (1789132836) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2796 1268508 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2480 1268824 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 oleg611-server Stopping /mnt/lustre-mds1 (opts:) on oleg611-server 09:20:50 (1789132850) shut down facet: mds1 facet_host: oleg611-server facet_failover_host: oleg611-server Failover mds1 to oleg611-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg611-server: oleg611-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg611-client: oleg611-server: ssh exited with exit code 1 Started lustre-MDT0000 09:21:23 (1789132883) targets are mounted 09:21:23 (1789132883) facet_failover done oleg611-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 ========================================================== 09:21:40 (1789132900) Starting client: oleg611-client.virtnet: -o user_xattr,flock 192.168.206.111@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: 144116245459894273 Links: 1 Access: (0644/-rw-r--r--) Uid: ( 0/ root) Gid: ( 0/ root) Access: 2026-09-11 09:21:43.000000000 -0400 Modify: 2026-09-11 09:21:43.000000000 -0400 Change: 2026-09-11 09:21:43.000000000 -0400 Birth: 2026-09-11 09:21:43.000000000 -0400 fail_loc=0 fail_val=0 192.168.206.111@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 oleg611-client.virtnet /mnt/lustre2 (opts:) PASS 203 (14s) == replay-single test complete, duration 3926 sec ======== 09:21:53 (1789132913) osc.lustre-OST0000-osc-ffff966988713800.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-ffff966988713800.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 1789132915.877393298 secs.nsecs start_time 1789132485.726794026 secs.nsecs elapsed_time 430.150599272 secs.nsecs uncompressed_objects 894 samples [reqs] obdfilter.lustre-OST0001.stats_compr= snapshot_time 1789132915.877497734 secs.nsecs start_time 1789132500.635386182 secs.nsecs elapsed_time 415.242111552 secs.nsecs uncompressed_objects 900 samples [reqs] === replay-single: start cleanup 09:21:56 (1789132916) === === replay-single: finish cleanup 09:22:04 (1789132924) ===