-----============= acceptance-small: replay-single ============----- Fri Sep 11 10:12:20 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 oleg601-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 10:12:38 (1789135958) === oleg601-client.virtnet: executing check_config_client /mnt/lustre oleg601-client.virtnet: Checking config lustre mounted on /mnt/lustre Checking servers environments Checking clients oleg601-client.virtnet environments Using TIMEOUT=20 osc.lustre-OST0000-osc-ffff91ef08f22000.idle_timeout=debug osc.lustre-OST0001-osc-ffff91ef08f22000.idle_timeout=debug disable quota as required oleg601-server: oleg601-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 10:13:28 (1789136008) === Cleaning up AT ... == replay-single test 100a: DNE: create striped dir, drop update rep from MDT1, fail MDT1 ========================================================== 10:13:33 (1789136013) fail_loc=0x1701 Failing mds2 on oleg601-server Stopping /mnt/lustre-mds2 (opts:) on oleg601-server 10:13:39 (1789136019) shut down facet: mds2 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds2 to oleg601-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0001 10:14:01 (1789136041) targets are mounted 10:14:01 (1789136041) facet_failover done oleg601-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 0.36 seconds: 55.04 ops/second PASS 100a (44s) == replay-single test 100b: DNE: create striped dir, fail MDT0 ========================================================== 10:14:17 (1789136057) fail_loc=0x119 Failing mds1 on oleg601-server Stopping /mnt/lustre-mds1 (opts:) on oleg601-server 10:14:24 (1789136064) shut down facet: mds1 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds1 to oleg601-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0000 10:14:47 (1789136087) targets are mounted 10:14:47 (1789136087) facet_failover done oleg601-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 0.31 seconds: 64.92 ops/second PASS 100b (47s) == replay-single test 100c: DNE: create striped dir, abort_recov_mdt mds2 ========================================================== 10:15:04 (1789136104) 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 oleg601-server Failover mds2 to oleg601-server oleg601-server.virtnet Start mds2: mount -t lustre -o localrecov -o abort_recov_mdt /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0001 total: 20 open/close in 0.26 seconds: 78.02 ops/second Failing mds2 on oleg601-server Stopping /mnt/lustre-mds2 (opts:) on oleg601-server 10:15:51 (1789136151) shut down facet: mds2 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds2 to oleg601-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0001 10:16:14 (1789136174) targets are mounted 10:16:14 (1789136174) facet_failover done oleg601-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 0.27 seconds: 72.78 ops/second PASS 100c (86s) == replay-single test 100d: DNE: cancel update logs upon recovery abort ========================================================== 10:16:30 (1789136190) striped dir -i0 -c2 -H crush /mnt/lustre/d100d.replay-single total: 100 mkdir in 1.14 seconds: 87.53 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 oleg601-server Failover mds2 to oleg601-server oleg601-server.virtnet Start mds2: mount -t lustre -o localrecov -o abort_recovery /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0001 pdsh@oleg601-client: oleg601-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 (46s) == replay-single test 100e: DNE: create striped dir on MDT0 and MDT1, fail MDT0, MDT1 ========================================================== 10:17:16 (1789136236) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2256 1269048 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2168 1269136 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 2256 1269048 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2168 1269136 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 [0x200000bd0:0x3a:0x0] 1 [0x240000bd1:0x3a:0x0] Failing mds1 on oleg601-server Stopping /mnt/lustre-mds1 (opts:) on oleg601-server Failing mds2 on oleg601-server Stopping /mnt/lustre-mds2 (opts:) on oleg601-server 10:17:40 (1789136260) shut down facet: mds1 facet_host: oleg601-server facet_failover_host: oleg601-server facet: mds2 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds1 to oleg601-server mount facets: mds1 Failover mds2 to oleg601-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 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 10:18:09 (1789136289) targets are mounted 10:18:09 (1789136289) facet_failover done oleg601-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 [0x200000bd0:0x3a:0x0] 1 [0x240000bd1:0x3a:0x0] PASS 100e (75s) == replay-single test 101: Shouldn't reassign precreated objs to other files after recovery ========================================================== 10:18:31 (1789136311) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2100 1269204 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1976 1269328 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 oleg601-server Failover mds1 to oleg601-server oleg601-server.virtnet Start mds1: mount -t lustre -o localrecov -o abort_recovery /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0000 PASS 101 (130s) == replay-single test 102a: check resend (request lost) with multiple modify RPCs in flight ========================================================== 10:20:41 (1789136441) creating 7 files ... fail_loc=0x159 launch 7 chmod in parallel (10:20:44) ... fail_loc=0 done (10:21:40) /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 ========================================================== 10:21:45 (1789136505) creating 7 files ... fail_loc=0x15a launch 7 chmod in parallel (10:21:48) ... fail_loc=0 done (10:22:43) /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 (63s) == replay-single test 102c: check replay w/o reconstruction with multiple mod RPCs in flight ========================================================== 10:22:48 (1789136568) creating 7 files ... UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2260 1269044 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2076 1269228 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605248 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605248 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210496 1% /mnt/lustre fail_loc=0x15a launch 7 chmod in parallel (10:22:57) ... fail_loc=0 Failing mds2 on oleg601-server Stopping /mnt/lustre-mds2 (opts:) on oleg601-server 10:23:03 (1789136583) shut down facet: mds2 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds2 to oleg601-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0001 10:23:27 (1789136607) targets are mounted 10:23:27 (1789136607) facet_failover done oleg601-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 (10:23:36) /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 (51s) == replay-single test 102d: check replay & reconstruction with multiple mod RPCs in flight ========================================================== 10:23:39 (1789136619) creating 7 files ... fail_loc=0x15a launch 7 chmod in parallel (10:23:41) ... fail_loc=0 Failing mds1 on oleg601-server Stopping /mnt/lustre-mds1 (opts:) on oleg601-server 10:23:46 (1789136626) shut down facet: mds1 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds1 to oleg601-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0000 10:24:06 (1789136646) targets are mounted 10:24:06 (1789136646) facet_failover done oleg601-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 (10:24:14) /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 (39s) == replay-single test 103: Check otr_next_id overflow ==== 10:24:18 (1789136658) fail_loc=0x80000162 total: 30 open/close in 0.41 seconds: 72.63 ops/second Failing mds1 on oleg601-server Stopping /mnt/lustre-mds1 (opts:) on oleg601-server 10:24:24 (1789136664) shut down facet: mds1 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds1 to oleg601-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0000 10:24:45 (1789136685) targets are mounted 10:24:45 (1789136685) facet_failover done oleg601-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 (41s) == replay-single test 110a: DNE: create striped dir, fail MDT1 ========================================================== 10:25:00 (1789136700) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2200 1269104 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2068 1269236 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605248 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605248 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210496 1% /mnt/lustre Failing mds1 on oleg601-server Stopping /mnt/lustre-mds1 (opts:) on oleg601-server 10:25:11 (1789136711) shut down facet: mds1 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds1 to oleg601-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0000 10:25:43 (1789136743) targets are mounted 10:25:43 (1789136743) facet_failover done oleg601-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 (57s) == replay-single test 110b: DNE: create striped dir, fail MDT1 and client ========================================================== 10:25:57 (1789136757) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2204 1269100 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2068 1269236 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 oleg601-server Stopping /mnt/lustre-mds1 (opts:) on oleg601-server 10:26:07 (1789136767) shut down facet: mds1 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds1 to oleg601-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0000 10:26:40 (1789136800) targets are mounted 10:26:40 (1789136800) facet_failover done pdsh@oleg601-client: oleg601-client: ssh exited with exit code 95 oleg601-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 pdsh@oleg601-client: oleg601-client: ssh exited with exit code 95 Starting client: oleg601-client.virtnet: -o user_xattr,flock 192.168.206.101@tcp:/lustre /mnt/lustre /mnt/lustre/d110b.replay-single/striped_dir has type dir OK PASS 110b (119s) == replay-single test 110c: DNE: create striped dir, fail MDT2 ========================================================== 10:27:56 (1789136876) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2208 1269096 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2064 1269240 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 oleg601-server Stopping /mnt/lustre-mds2 (opts:) on oleg601-server 10:28:05 (1789136885) shut down facet: mds2 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds2 to oleg601-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0001 10:28:30 (1789136910) targets are mounted 10:28:30 (1789136910) facet_failover done oleg601-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 (49s) == replay-single test 110d: DNE: create striped dir, fail MDT2 and client ========================================================== 10:28:45 (1789136925) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2200 1269104 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2068 1269236 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 oleg601-server Stopping /mnt/lustre-mds2 (opts:) on oleg601-server 10:28:56 (1789136936) shut down facet: mds2 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds2 to oleg601-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0001 10:29:21 (1789136961) targets are mounted 10:29:21 (1789136961) facet_failover done pdsh@oleg601-client: oleg601-client: ssh exited with exit code 95 oleg601-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 pdsh@oleg601-client: oleg601-client: ssh exited with exit code 95 Starting client: oleg601-client.virtnet: -o user_xattr,flock 192.168.206.101@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 ========================================================== 10:30:37 (1789137037) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2240 1269064 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 df:/mnt/lustre Not a Lustre filesystem Failing mds1 on oleg601-server Stopping /mnt/lustre-mds1 (opts:) on oleg601-server Failing mds2 on oleg601-server Stopping /mnt/lustre-mds2 (opts:) on oleg601-server 10:31:00 (1789137060) shut down facet: mds1 facet_host: oleg601-server facet_failover_host: oleg601-server facet: mds2 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds1 to oleg601-server mount facets: mds1 Failover mds2 to oleg601-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 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 10:31:29 (1789137089) targets are mounted 10:31:29 (1789137089) facet_failover done pdsh@oleg601-client: oleg601-client: ssh exited with exit code 95 oleg601-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@oleg601-client: oleg601-client: ssh exited with exit code 95 Starting client: oleg601-client.virtnet: -o user_xattr,flock 192.168.206.101@tcp:/lustre /mnt/lustre /mnt/lustre/d110e.replay-single/striped_dir has type dir OK PASS 110e (128s) SKIP: replay-single test_110f skipping excluded test 110f == replay-single test 110g: DNE: create striped dir, uncommit on MDT1, fail client/MDT1/MDT2 ========================================================== 10:32:46 (1789137166) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2240 1269064 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 df:/mnt/lustre Not a Lustre filesystem Failing mds1 on oleg601-server Stopping /mnt/lustre-mds1 (opts:) on oleg601-server Failing mds2 on oleg601-server Stopping /mnt/lustre-mds2 (opts:) on oleg601-server 10:33:08 (1789137188) shut down facet: mds1 facet_host: oleg601-server facet_failover_host: oleg601-server facet: mds2 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds1 to oleg601-server mount facets: mds1 Failover mds2 to oleg601-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 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 10:33:38 (1789137218) targets are mounted 10:33:38 (1789137218) facet_failover done pdsh@oleg601-client: oleg601-client: ssh exited with exit code 95 oleg601-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@oleg601-client: oleg601-client: ssh exited with exit code 95 Starting client: oleg601-client.virtnet: -o user_xattr,flock 192.168.206.101@tcp:/lustre /mnt/lustre /mnt/lustre/d110g.replay-single/striped_dir has type dir OK PASS 110g (128s) == replay-single test 111a: DNE: unlink striped dir, fail MDT1 ========================================================== 10:34:54 (1789137294) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2212 1269092 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 oleg601-server Stopping /mnt/lustre-mds1 (opts:) on oleg601-server 10:35:11 (1789137311) shut down facet: mds1 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds1 to oleg601-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0000 10:35:45 (1789137345) targets are mounted 10:35:45 (1789137345) facet_failover done oleg601-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 (66s) == replay-single test 111b: DNE: unlink striped dir, fail MDT2 ========================================================== 10:36:00 (1789137360) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2216 1269088 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 Failing mds2 on oleg601-server Stopping /mnt/lustre-mds2 (opts:) on oleg601-server 10:36:19 (1789137379) shut down facet: mds2 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds2 to oleg601-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0001 10:36:43 (1789137403) targets are mounted 10:36:43 (1789137403) facet_failover done pdsh@oleg601-client: oleg601-client: ssh exited with exit code 95 oleg601-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 pdsh@oleg601-client: oleg601-client: ssh exited with exit code 95 Starting client: oleg601-client.virtnet: -o user_xattr,flock 192.168.206.101@tcp:/lustre /mnt/lustre Can't lstat /mnt/lustre/d111b.replay-single/striped_dir: No such file or directory PASS 111b (123s) == replay-single test 111c: DNE: unlink striped dir, uncommit on MDT1, fail client/MDT1/MDT2 ========================================================== 10:38:03 (1789137483) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2216 1269088 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 df:/mnt/lustre Not a Lustre filesystem Failing mds1 on oleg601-server Stopping /mnt/lustre-mds1 (opts:) on oleg601-server Failing mds2 on oleg601-server Stopping /mnt/lustre-mds2 (opts:) on oleg601-server 10:38:24 (1789137504) shut down facet: mds1 facet_host: oleg601-server facet_failover_host: oleg601-server facet: mds2 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds1 to oleg601-server mount facets: mds1 Failover mds2 to oleg601-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 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 10:38:55 (1789137535) targets are mounted 10:38:55 (1789137535) facet_failover done pdsh@oleg601-client: oleg601-client: ssh exited with exit code 95 oleg601-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@oleg601-client: oleg601-client: ssh exited with exit code 95 Starting client: oleg601-client.virtnet: -o user_xattr,flock 192.168.206.101@tcp:/lustre /mnt/lustre Can't lstat /mnt/lustre/d111c.replay-single/striped_dir: No such file or directory PASS 111c (132s) == replay-single test 111d: DNE: unlink striped dir, uncommit on MDT2, fail client/MDT1/MDT2 ========================================================== 10:40:15 (1789137615) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2220 1269084 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 df:/mnt/lustre Not a Lustre filesystem Failing mds1 on oleg601-server Stopping /mnt/lustre-mds1 (opts:) on oleg601-server Failing mds2 on oleg601-server Stopping /mnt/lustre-mds2 (opts:) on oleg601-server 10:40:34 (1789137634) shut down facet: mds1 facet_host: oleg601-server facet_failover_host: oleg601-server facet: mds2 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds1 to oleg601-server mount facets: mds1 Failover mds2 to oleg601-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 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 10:41:02 (1789137662) targets are mounted 10:41:02 (1789137662) facet_failover done pdsh@oleg601-client: oleg601-client: ssh exited with exit code 95 oleg601-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@oleg601-client: oleg601-client: ssh exited with exit code 95 Starting client: oleg601-client.virtnet: -o user_xattr,flock 192.168.206.101@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 ========================================================== 10:42:22 (1789137742) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2268 1269036 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2156 1269148 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 2260 1269044 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2148 1269156 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 oleg601-server Stopping /mnt/lustre-mds1 (opts:) on oleg601-server Failing mds2 on oleg601-server Stopping /mnt/lustre-mds2 (opts:) on oleg601-server 10:42:47 (1789137767) shut down facet: mds1 facet_host: oleg601-server facet_failover_host: oleg601-server facet: mds2 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds1 to oleg601-server mount facets: mds1 Failover mds2 to oleg601-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 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0000 Started lustre-MDT0001 10:43:19 (1789137799) targets are mounted 10:43:19 (1789137799) facet_failover done oleg601-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 (77s) == replay-single test 111f: DNE: unlink striped dir, uncommit on MDT1, fail MDT1/MDT2 ========================================================== 10:43:39 (1789137819) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2308 1268996 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2192 1269112 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 2300 1269004 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2184 1269120 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 oleg601-server Stopping /mnt/lustre-mds1 (opts:) on oleg601-server Failing mds2 on oleg601-server Stopping /mnt/lustre-mds2 (opts:) on oleg601-server 10:44:11 (1789137851) shut down facet: mds1 facet_host: oleg601-server facet_failover_host: oleg601-server facet: mds2 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds1 to oleg601-server mount facets: mds1 Failover mds2 to oleg601-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 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 10:44:54 (1789137894) targets are mounted 10:44:54 (1789137894) facet_failover done oleg601-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 (97s) == replay-single test 111g: DNE: unlink striped dir, fail MDT1/MDT2 ========================================================== 10:45:16 (1789137916) 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 2236 1269068 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 2236 1269068 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 oleg601-server Stopping /mnt/lustre-mds1 (opts:) on oleg601-server Failing mds2 on oleg601-server Stopping /mnt/lustre-mds2 (opts:) on oleg601-server 10:45:39 (1789137939) shut down facet: mds1 facet_host: oleg601-server facet_failover_host: oleg601-server facet: mds2 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds1 to oleg601-server mount facets: mds1 Failover mds2 to oleg601-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 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 10:46:08 (1789137968) targets are mounted 10:46:08 (1789137968) facet_failover done oleg601-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 (73s) == replay-single test 112a: DNE: cross MDT rename, fail MDT1 ========================================================== 10:46:29 (1789137989) SKIP: replay-single test_112a needs >= 4 MDTs SKIP 112a (3s) == replay-single test 112b: DNE: cross MDT rename, fail MDT2 ========================================================== 10:46:32 (1789137992) SKIP: replay-single test_112b needs >= 4 MDTs SKIP 112b (3s) == replay-single test 112c: DNE: cross MDT rename, fail MDT3 ========================================================== 10:46:35 (1789137995) SKIP: replay-single test_112c needs >= 4 MDTs SKIP 112c (2s) == replay-single test 112d: DNE: cross MDT rename, fail MDT4 ========================================================== 10:46:37 (1789137997) SKIP: replay-single test_112d needs >= 4 MDTs SKIP 112d (3s) == replay-single test 112e: DNE: cross MDT rename, fail MDT1 and MDT2 ========================================================== 10:46:40 (1789138000) SKIP: replay-single test_112e needs >= 4 MDTs SKIP 112e (2s) == replay-single test 112f: DNE: cross MDT rename, fail MDT1 and MDT3 ========================================================== 10:46:43 (1789138003) SKIP: replay-single test_112f needs >= 4 MDTs SKIP 112f (2s) == replay-single test 112g: DNE: cross MDT rename, fail MDT1 and MDT4 ========================================================== 10:46:45 (1789138005) SKIP: replay-single test_112g needs >= 4 MDTs SKIP 112g (3s) == replay-single test 112h: DNE: cross MDT rename, fail MDT2 and MDT3 ========================================================== 10:46:48 (1789138008) SKIP: replay-single test_112h needs >= 4 MDTs SKIP 112h (3s) == replay-single test 112i: DNE: cross MDT rename, fail MDT2 and MDT4 ========================================================== 10:46:51 (1789138011) SKIP: replay-single test_112i needs >= 4 MDTs SKIP 112i (2s) == replay-single test 112j: DNE: cross MDT rename, fail MDT3 and MDT4 ========================================================== 10:46:53 (1789138013) SKIP: replay-single test_112j needs >= 4 MDTs SKIP 112j (3s) == replay-single test 112k: DNE: cross MDT rename, fail MDT1,MDT2,MDT3 ========================================================== 10:46:56 (1789138016) SKIP: replay-single test_112k needs >= 4 MDTs SKIP 112k (2s) == replay-single test 112l: DNE: cross MDT rename, fail MDT1,MDT2,MDT4 ========================================================== 10:46:58 (1789138018) SKIP: replay-single test_112l needs >= 4 MDTs SKIP 112l (2s) == replay-single test 112m: DNE: cross MDT rename, fail MDT1,MDT3,MDT4 ========================================================== 10:47:00 (1789138020) SKIP: replay-single test_112m needs >= 4 MDTs SKIP 112m (2s) == replay-single test 112n: DNE: cross MDT rename, fail MDT2,MDT3,MDT4 ========================================================== 10:47:03 (1789138023) SKIP: replay-single test_112n needs >= 4 MDTs SKIP 112n (3s) == replay-single test 115: failover for create/unlink striped directory ========================================================== 10:47:05 (1789138025) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2232 1269072 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 striped dir -i1 -c2 -H crush2 /mnt/lustre/d115.replay-single/test_0 striped dir -i1 -c2 -H fnv_1a_64 /mnt/lustre/d115.replay-single/test_1 striped dir -i1 -c2 -H all_char /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 crush /mnt/lustre/d115.replay-single/test_4 Failing mds2 on oleg601-server Stopping /mnt/lustre-mds2 (opts:) on oleg601-server 10:47:16 (1789138036) shut down facet: mds2 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds2 to oleg601-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0001 10:47:40 (1789138060) targets are mounted 10:47:40 (1789138060) facet_failover done oleg601-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 2284 1269020 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2172 1269132 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 crush /mnt/lustre/d115.replay-single/test_1 striped dir -i0 -c2 -H crush /mnt/lustre/d115.replay-single/test_2 striped dir -i0 -c2 -H crush /mnt/lustre/d115.replay-single/test_3 striped dir -i0 -c2 -H all_char /mnt/lustre/d115.replay-single/test_4 Failing mds1 on oleg601-server Stopping /mnt/lustre-mds1 (opts:) on oleg601-server 10:47:59 (1789138079) shut down facet: mds1 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds1 to oleg601-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0000 10:48:32 (1789138112) targets are mounted 10:48:32 (1789138112) facet_failover done oleg601-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 (100s) == replay-single test 116a: large update log master MDT recovery ========================================================== 10:48:45 (1789138125) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2336 1268968 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2192 1269112 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 oleg601-server Stopping /mnt/lustre-mds1 (opts:) on oleg601-server 10:48:56 (1789138136) shut down facet: mds1 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds1 to oleg601-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0000 10:49:18 (1789138158) targets are mounted 10:49:18 (1789138158) facet_failover done oleg601-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 (45s) == replay-single test 116b: large update log slave MDT recovery ========================================================== 10:49:30 (1789138170) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2388 1268916 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2360 1268944 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 oleg601-server Stopping /mnt/lustre-mds2 (opts:) on oleg601-server 10:49:42 (1789138182) shut down facet: mds2 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds2 to oleg601-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0001 10:50:04 (1789138204) targets are mounted 10:50:04 (1789138204) facet_failover done oleg601-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 (46s) == replay-single test 117: DNE: cross MDT unlink, fail MDT1 and MDT2 ========================================================== 10:50:17 (1789138217) SKIP: replay-single test_117 needs >= 4 MDTs SKIP 117 (2s) == replay-single test 118: invalidate osp update will not cause update log corruption ========================================================== 10:50:19 (1789138219) 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 2468 1268836 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2452 1268852 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 oleg601-server Stopping /mnt/lustre-mds1 (opts:) on oleg601-server 10:50:32 (1789138232) shut down facet: mds1 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds1 to oleg601-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0000 10:51:09 (1789138269) targets are mounted 10:51:09 (1789138269) facet_failover done oleg601-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 (65s) == replay-single test 119: timeout of normal replay does not cause DNE replay fails ========================================================== 10:51:24 (1789138284) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2368 1268936 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2336 1268968 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 oleg601-server Failover mds1 to oleg601-server oleg601-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 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0000 oleg601-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 60 sec mdt.lustre-MDT0000.recovery_time_hard=180 PASS 119 (108s) == replay-single test 120: DNE fail abort should stop both normal and DNE replay ========================================================== 10:53:12 (1789138392) Replay barrier on lustre-MDT0000 Stopping /mnt/lustre-mds1 (opts:) on oleg601-server Failover mds1 to oleg601-server oleg601-server.virtnet Start mds1: mount -t lustre -o localrecov -o abort_recovery /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-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 (45s) == replay-single test 121: lock replay timed out and race ========================================================== 10:53:57 (1789138437) multiop /mnt/lustre/f121.replay-single vs_s TMPPIPE=/tmp/multiop_open_wait_pipe.8245 Stopping /mnt/lustre-mds1 (opts:) on oleg601-server Failover mds1 to oleg601-server oleg601-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 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0000 pdsh@oleg601-client: oleg601-client: ssh exited with exit code 5 fail_loc=0x0 at_max=600 PASS 121 (214s) == replay-single test 130a: DoM file create (setstripe) replay ========================================================== 10:57:31 (1789138651) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2708 1268596 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2640 1268664 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 oleg601-server Stopping /mnt/lustre-mds1 (opts:) on oleg601-server 10:57:43 (1789138663) shut down facet: mds1 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds1 to oleg601-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0000 10:58:10 (1789138690) targets are mounted 10:58:10 (1789138690) facet_failover done oleg601-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 (53s) == replay-single test 130b: DoM file create (inherited) replay ========================================================== 10:58:24 (1789138704) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2712 1268592 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2640 1268664 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 oleg601-server Stopping /mnt/lustre-mds1 (opts:) on oleg601-server 10:58:36 (1789138716) shut down facet: mds1 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds1 to oleg601-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0000 10:59:02 (1789138742) targets are mounted 10:59:02 (1789138742) facet_failover done oleg601-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 (53s) == replay-single test 131a: DoM file write lock replay === 10:59:17 (1789138757) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2712 1268592 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2640 1268664 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, 0.00286967 s, 2.8 kB/s Failing mds1 on oleg601-server Stopping /mnt/lustre-mds1 (opts:) on oleg601-server 10:59:29 (1789138769) shut down facet: mds1 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds1 to oleg601-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0000 11:00:07 (1789138807) targets are mounted 11:00:07 (1789138807) facet_failover done oleg601-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 (63s) SKIP: replay-single test_131b skipping excluded test 131b == replay-single test 132a: PFL new component instantiate replay ========================================================== 11:00:22 (1789138822) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2716 1268588 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2640 1268664 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, 0.0532778 s, 19.7 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 oleg601-server Stopping /mnt/lustre-mds1 (opts:) on oleg601-server 11:00:33 (1789138833) shut down facet: mds1 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds1 to oleg601-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0000 11:01:08 (1789138868) targets are mounted 11:01:08 (1789138868) facet_failover done oleg601-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 (61s) == replay-single test 133: check resend of ongoing requests for lwp during failover ========================================================== 11:01:23 (1789138883) seq.srv-lustre-MDT0001.space=clear Starting client: oleg601-client.virtnet: -o user_xattr,flock 192.168.206.101@tcp:/lustre /mnt/lustre fail_val=700 fail_loc=0x80000123 Failing mds1 on oleg601-server Stopping /mnt/lustre-mds1 (opts:) on oleg601-server 11:01:34 (1789138894) shut down facet: mds1 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds1 to oleg601-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0000 11:01:57 (1789138917) targets are mounted 11:01:57 (1789138917) facet_failover done PASS 133 (39s) == replay-single test 134: replay creation of a file created in a pool ========================================================== 11:02:02 (1789138922) Creating new pool pool_134 oleg601-server: Pool lustre.pool_134 created Adding targets to pool oleg601-server: OST lustre-OST0001_UUID added to pool lustre.pool_134 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2824 1268480 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2696 1268608 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 oleg601-server Stopping /mnt/lustre-mds1 (opts:) on oleg601-server 11:02:24 (1789138944) shut down facet: mds1 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds1 to oleg601-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0000 11:02:59 (1789138979) targets are mounted 11:02:59 (1789138979) facet_failover done oleg601-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 oleg601-server: OST lustre-OST0001_UUID removed from pool lustre.pool_134 oleg601-server: Pool lustre.pool_134 destroyed PASS 134 (82s) == replay-single test 135: Server failure in lock replay phase ========================================================== 11:03:25 (1789139005) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2780 1268524 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2696 1268608 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 oleg601-server Failover ost1 to oleg601-server oleg601-server.virtnet fail_loc=0 oleg601-server: oleg601-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 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-OST0000 oleg601-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 oleg601-server Failover ost1 to oleg601-server oleg601-server.virtnet oleg601-server: oleg601-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 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-OST0000 Stopping /mnt/lustre-ost1 (opts:-f) on oleg601-server Stopping /mnt/lustre-ost2 (opts:-f) on oleg601-server Start ost1: mount -t lustre -o localrecov /dev/mapper/ost1_flakey /mnt/lustre-ost1 seq.cli-lustre-OST0000-super.width=65536 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-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 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-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 (132s) == replay-single test 136: MDS to disconnect all OSPs first, then cleanup ldlm ========================================================== 11:05:37 (1789139137) SKIP: replay-single test_136 needs > 2 MDTs SKIP 136 (3s) == replay-single test 137a: DNE: create under striped dir, fail MDT1 ========================================================== 11:05:40 (1789139140) llite.lustre-ffff91ef0a5d4800.intent_mkdir=1 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2788 1268516 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2712 1268592 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 oleg601-server Stopping /mnt/lustre-mds1 (opts:) on oleg601-server 11:05:52 (1789139152) shut down facet: mds1 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds1 to oleg601-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0000 11:06:26 (1789139186) targets are mounted 11:06:26 (1789139186) facet_failover done oleg601-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 (61s) == replay-single test 137b: DNE: create under striped dir, fail MDT2 ========================================================== 11:06:41 (1789139201) llite.lustre-ffff91ef0a5d4800.intent_mkdir=1 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2796 1268508 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2712 1268592 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 oleg601-server Stopping /mnt/lustre-mds2 (opts:) on oleg601-server 11:06:53 (1789139213) shut down facet: mds2 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds2 to oleg601-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0001 11:07:20 (1789139240) targets are mounted 11:07:20 (1789139240) facet_failover done oleg601-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 ========================================================== 11:07:36 (1789139256) llite.lustre-ffff91ef0a5d4800.intent_mkdir=1 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2792 1268512 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2724 1268580 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 2792 1268512 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2724 1268580 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 oleg601-server Stopping /mnt/lustre-mds2 (opts:) on oleg601-server Failing mds1 on oleg601-server Stopping /mnt/lustre-mds1 (opts:) on oleg601-server 11:07:58 (1789139278) shut down facet: mds2 facet_host: oleg601-server facet_failover_host: oleg601-server facet: mds1 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds1 to oleg601-server Failover mds2 to oleg601-server mount facets: mds2 mount facets: mds1 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 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0000 Started lustre-MDT0001 11:08:33 (1789139313) targets are mounted 11:08:33 (1789139313) facet_failover done oleg601-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 (75s) == replay-single test 160: mdt.recovery_reconnect_histogram testing ========================================================== 11:08:51 (1789139331) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2780 1268524 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2712 1268592 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 oleg601-server Stopping /mnt/lustre-mds1 (opts:) on oleg601-server 11:09:05 (1789139345) shut down facet: mds1 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds1 to oleg601-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0000 11:09:39 (1789139379) targets are mounted 11:09:39 (1789139379) facet_failover done oleg601-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: 1789139374 recovery_finish: 1789139379 recovery_time: 5 reconnect_delay_seconds_samples: 1 client_reconnect_histogram: - { delay_sec: 1, clients: 1, pct: 100, cum_pct: 100 } client_reconnect_top: - { nid: "192.168.206.1@tcp", delay_sec: 0 } mdt.lustre-MDT0000.exports.192.168.206.1@tcp.reconnect_delay=0 PASS 160 (69s) == replay-single test 200: Dropping one OBD_PING should not cause disconnect ========================================================== 11:10:00 (1789139400) SKIP: replay-single test_200 Need remote client SKIP 200 (3s) == replay-single test 201: MDT umount cascading disconnects timeouts ========================================================== 11:10:03 (1789139403) fail_loc=0x245 fail_val=8 fail_loc=0x245 fail_val=8 Stopping /mnt/lustre-mds2 (opts:) on oleg601-server Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0001 Umount took 20 seconds PASS 201 (41s) == replay-single test 202: pfl replay should recovery layout generation ========================================================== 11:10:44 (1789139444) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2748 1268556 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2664 1268640 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 oleg601-server Stopping /mnt/lustre-mds1 (opts:) on oleg601-server 11:10:56 (1789139456) shut down facet: mds1 facet_host: oleg601-server facet_failover_host: oleg601-server Failover mds1 to oleg601-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg601-server: oleg601-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg601-client: oleg601-server: ssh exited with exit code 1 Started lustre-MDT0000 11:11:30 (1789139490) targets are mounted 11:11:30 (1789139490) facet_failover done oleg601-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 (60s) == replay-single test 203: resend can hit original request ========================================================== 11:11:44 (1789139504) Starting client: oleg601-client.virtnet: -o user_xattr,flock 192.168.206.101@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 11:11:47.000000000 -0400 Modify: 2026-09-11 11:11:47.000000000 -0400 Change: 2026-09-11 11:11:47.000000000 -0400 Birth: 2026-09-11 11:11:48.000000000 -0400 fail_loc=0 fail_val=0 192.168.206.101@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 oleg601-client.virtnet /mnt/lustre2 (opts:) PASS 203 (11s) == replay-single test complete, duration 3574 sec ======== 11:11:56 (1789139516) osc.lustre-OST0000-osc-ffff91ef0a5d4800.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-ffff91ef0a5d4800.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 1789139519.359204337 secs.nsecs start_time 1789139111.085186546 secs.nsecs elapsed_time 408.274017791 secs.nsecs uncompressed_objects 831 samples [reqs] obdfilter.lustre-OST0001.stats_compr= snapshot_time 1789139519.359263487 secs.nsecs start_time 1789139124.971532357 secs.nsecs elapsed_time 394.387731130 secs.nsecs uncompressed_objects 830 samples [reqs] === replay-single: start cleanup 11:11:58 (1789139518) === === replay-single: finish cleanup 11:12:05 (1789139525) ===