-----============= acceptance-small: replay-single ============----- Thu Aug 27 15:52:54 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 oleg350-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 15:53:12 (1787860392) === oleg350-client.virtnet: executing check_config_client /mnt/lustre oleg350-client.virtnet: Checking config lustre mounted on /mnt/lustre Checking servers environments Checking clients oleg350-client.virtnet environments Using TIMEOUT=20 osc.lustre-OST0000-osc-ffff9f18e0251000.idle_timeout=debug osc.lustre-OST0001-osc-ffff9f18e0251000.idle_timeout=debug disable quota as required oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all osd-ldiskfs.track_declares_assert=1 === replay-single: finish setup 15:53:52 (1787860432) === Cleaning up AT ... == replay-single test 100a: DNE: create striped dir, drop update rep from MDT1, fail MDT1 ========================================================== 15:53:58 (1787860438) fail_loc=0x1701 Failing mds2 on oleg350-server Stopping /mnt/lustre-mds2 (opts:) on oleg350-server 15:54:05 (1787860445) shut down facet: mds2 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds2 to oleg350-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0001 15:54:29 (1787860469) targets are mounted 15:54:29 (1787860469) facet_failover done oleg350-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 0.31 seconds: 63.87 ops/second PASS 100a (49s) == replay-single test 100b: DNE: create striped dir, fail MDT0 ========================================================== 15:54:47 (1787860487) fail_loc=0x119 Failing mds1 on oleg350-server Stopping /mnt/lustre-mds1 (opts:) on oleg350-server 15:54:53 (1787860493) shut down facet: mds1 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds1 to oleg350-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0000 15:55:27 (1787860527) targets are mounted 15:55:27 (1787860527) facet_failover done oleg350-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 0.42 seconds: 47.81 ops/second PASS 100b (59s) == replay-single test 100c: DNE: create striped dir, abort_recov_mdt mds2 ========================================================== 15:55:46 (1787860546) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1844 1269460 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1720 1269584 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Stopping /mnt/lustre-mds2 (opts:) on oleg350-server Failover mds2 to oleg350-server oleg350-server.virtnet Start mds2: mount -t lustre -o localrecov -o abort_recov_mdt /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0001 total: 20 open/close in 0.32 seconds: 61.81 ops/second Failing mds2 on oleg350-server Stopping /mnt/lustre-mds2 (opts:) on oleg350-server 15:56:33 (1787860593) shut down facet: mds2 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds2 to oleg350-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0001 15:56:57 (1787860617) targets are mounted 15:56:57 (1787860617) facet_failover done oleg350-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 0.37 seconds: 53.87 ops/second PASS 100c (86s) == replay-single test 100d: DNE: cancel update logs upon recovery abort ========================================================== 15:57:13 (1787860633) striped dir -i0 -c2 -H all_char /mnt/lustre/d100d.replay-single total: 100 mkdir in 1.56 seconds: 64.00 ops/second lustre-MDT0000-osd [catalog]: [0x200000400:0x1:0x0] [index]: 00002 [logid]: [0x200000bd0:0x1:0x0] lustre-MDT0001-osp-MDT0000 [catalog]: [0x240000401:0x1:0x0] [index]: 00003 [logid]: [0x240000bd1:0x1:0x0] [index]: 00004 [logid]: [0x240000bd1:0x2:0x0] Stopping /mnt/lustre-mds1 (opts:) on oleg350-server Failover mds1 to oleg350-server oleg350-server.virtnet Start mds1: mount -t lustre -o localrecov -o abort_recovery /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0000 pdsh@oleg350-client: oleg350-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 (51s) == replay-single test 100e: DNE: create striped dir on MDT0 and MDT1, fail MDT0, MDT1 ========================================================== 15:58:04 (1787860684) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2292 1269012 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2148 1269156 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2292 1269012 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2148 1269156 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre lmv_stripe_count: 2 lmv_stripe_offset: 0 lmv_hash_type: crush mdtidx FID[seq:oid:ver] 0 [0x2000013a0:0x2:0x0] 1 [0x240001b71:0x2:0x0] Failing mds1 on oleg350-server Stopping /mnt/lustre-mds1 (opts:) on oleg350-server Failing mds2 on oleg350-server Stopping /mnt/lustre-mds2 (opts:) on oleg350-server 15:58:30 (1787860710) shut down facet: mds1 facet_host: oleg350-server facet_failover_host: oleg350-server facet: mds2 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds1 to oleg350-server mount facets: mds1 Failover mds2 to oleg350-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 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 15:58:58 (1787860738) targets are mounted 15:58:58 (1787860738) facet_failover done oleg350-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid,mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec lmv_stripe_count: 2 lmv_stripe_offset: 0 lmv_hash_type: crush mdtidx FID[seq:oid:ver] 0 [0x2000013a0:0x2:0x0] 1 [0x240001b71:0x2:0x0] PASS 100e (81s) == replay-single test 101: Shouldn't reassign precreated objs to other files after recovery ========================================================== 15:59:25 (1787860765) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2432 1268872 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2248 1269056 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3088 7210952 1% /mnt/lustre Stopping /mnt/lustre-mds1 (opts:) on oleg350-server Failover mds1 to oleg350-server oleg350-server.virtnet Start mds1: mount -t lustre -o localrecov -o abort_recovery /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0000 PASS 101 (148s) == replay-single test 102a: check resend (request lost) with multiple modify RPCs in flight ========================================================== 16:01:53 (1787860913) creating 7 files ... fail_loc=0x159 launch 7 chmod in parallel (16:01:56) ... fail_loc=0 done (16:02:51) /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 (66s) == replay-single test 102b: check resend (reply lost) with multiple modify RPCs in flight ========================================================== 16:03:00 (1787860980) creating 7 files ... fail_loc=0x15a launch 7 chmod in parallel (16:03:03) ... fail_loc=0 done (16:03:58) /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 (64s) == replay-single test 102c: check replay w/o reconstruction with multiple mod RPCs in flight ========================================================== 16:04:05 (1787861045) creating 7 files ... UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2472 1268832 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2020 1269284 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3598080 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3598108 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7196188 1% /mnt/lustre fail_loc=0x15a launch 7 chmod in parallel (16:04:19) ... fail_loc=0 Failing mds1 on oleg350-server Stopping /mnt/lustre-mds1 (opts:) on oleg350-server 16:04:26 (1787861066) shut down facet: mds1 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds1 to oleg350-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0000 16:04:59 (1787861099) targets are mounted 16:04:59 (1787861099) facet_failover done oleg350-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 (16:05:11) /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 (71s) == replay-single test 102d: check replay & reconstruction with multiple mod RPCs in flight ========================================================== 16:05:17 (1787861117) creating 7 files ... fail_loc=0x15a launch 7 chmod in parallel (16:05:20) ... fail_loc=0 Failing mds2 on oleg350-server Stopping /mnt/lustre-mds2 (opts:) on oleg350-server 16:05:27 (1787861127) shut down facet: mds2 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds2 to oleg350-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0001 16:05:52 (1787861152) targets are mounted 16:05:52 (1787861152) facet_failover done oleg350-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 (16:06:04) /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 (53s) == replay-single test 103: Check otr_next_id overflow ==== 16:06:10 (1787861170) fail_loc=0x80000162 total: 30 open/close in 0.61 seconds: 48.99 ops/second Failing mds1 on oleg350-server Stopping /mnt/lustre-mds1 (opts:) on oleg350-server 16:06:18 (1787861178) shut down facet: mds1 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds1 to oleg350-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0000 16:06:42 (1787861202) targets are mounted 16:06:42 (1787861202) facet_failover done oleg350-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 (50s) == replay-single test 110a: DNE: create striped dir, fail MDT1 ========================================================== 16:07:00 (1787861220) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2412 1268892 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2024 1269280 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3598080 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3598108 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7196188 1% /mnt/lustre Failing mds1 on oleg350-server Stopping /mnt/lustre-mds1 (opts:) on oleg350-server 16:07:14 (1787861234) shut down facet: mds1 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds1 to oleg350-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0000 16:07:48 (1787861268) targets are mounted 16:07:48 (1787861268) facet_failover done oleg350-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 (63s) == replay-single test 110b: DNE: create striped dir, fail MDT1 and client ========================================================== 16:08:03 (1787861283) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2416 1268888 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2024 1269280 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 oleg350-server Stopping /mnt/lustre-mds1 (opts:) on oleg350-server 16:08:16 (1787861296) shut down facet: mds1 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds1 to oleg350-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0000 16:08:52 (1787861332) targets are mounted 16:08:52 (1787861332) facet_failover done pdsh@oleg350-client: oleg350-client: ssh exited with exit code 95 oleg350-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 pdsh@oleg350-client: oleg350-client: ssh exited with exit code 95 Starting client: oleg350-client.virtnet: -o user_xattr,flock 192.168.203.150@tcp:/lustre /mnt/lustre /mnt/lustre/d110b.replay-single/striped_dir has type dir OK PASS 110b (127s) == replay-single test 110c: DNE: create striped dir, fail MDT2 ========================================================== 16:10:10 (1787861410) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2420 1268884 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2020 1269284 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 oleg350-server Stopping /mnt/lustre-mds2 (opts:) on oleg350-server 16:10:24 (1787861424) shut down facet: mds2 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds2 to oleg350-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0001 16:10:52 (1787861452) targets are mounted 16:10:52 (1787861452) facet_failover done oleg350-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 (59s) == replay-single test 110d: DNE: create striped dir, fail MDT2 and client ========================================================== 16:11:09 (1787861469) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2460 1268844 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2024 1269280 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 oleg350-server Stopping /mnt/lustre-mds2 (opts:) on oleg350-server 16:11:23 (1787861483) shut down facet: mds2 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds2 to oleg350-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0001 16:11:51 (1787861511) targets are mounted 16:11:51 (1787861511) facet_failover done pdsh@oleg350-client: oleg350-client: ssh exited with exit code 95 oleg350-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 pdsh@oleg350-client: oleg350-client: ssh exited with exit code 95 Starting client: oleg350-client.virtnet: -o user_xattr,flock 192.168.203.150@tcp:/lustre /mnt/lustre /mnt/lustre/d110d.replay-single/striped_dir has type dir OK PASS 110d (124s) == replay-single test 110e: DNE: create striped dir, uncommit on MDT2, fail client/MDT1/MDT2 ========================================================== 16:13:13 (1787861593) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2412 1268892 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2020 1269284 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 oleg350-server Stopping /mnt/lustre-mds1 (opts:) on oleg350-server Failing mds2 on oleg350-server Stopping /mnt/lustre-mds2 (opts:) on oleg350-server 16:13:43 (1787861623) shut down facet: mds1 facet_host: oleg350-server facet_failover_host: oleg350-server facet: mds2 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds1 to oleg350-server mount facets: mds1 Failover mds2 to oleg350-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 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 16:14:35 (1787861675) targets are mounted 16:14:36 (1787861676) facet_failover done pdsh@oleg350-client: oleg350-client: ssh exited with exit code 95 oleg350-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@oleg350-client: oleg350-client: ssh exited with exit code 95 Starting client: oleg350-client.virtnet: -o user_xattr,flock 192.168.203.150@tcp:/lustre /mnt/lustre /mnt/lustre/d110e.replay-single/striped_dir has type dir OK PASS 110e (153s) SKIP: replay-single test_110f skipping excluded test 110f == replay-single test 110g: DNE: create striped dir, uncommit on MDT1, fail client/MDT1/MDT2 ========================================================== 16:15:48 (1787861748) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2452 1268852 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2020 1269284 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 oleg350-server Stopping /mnt/lustre-mds1 (opts:) on oleg350-server Failing mds2 on oleg350-server Stopping /mnt/lustre-mds2 (opts:) on oleg350-server 16:16:16 (1787861776) shut down facet: mds1 facet_host: oleg350-server facet_failover_host: oleg350-server facet: mds2 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds1 to oleg350-server mount facets: mds1 Failover mds2 to oleg350-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 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 16:17:07 (1787861827) targets are mounted 16:17:07 (1787861827) facet_failover done pdsh@oleg350-client: oleg350-client: ssh exited with exit code 95 oleg350-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@oleg350-client: oleg350-client: ssh exited with exit code 95 Starting client: oleg350-client.virtnet: -o user_xattr,flock 192.168.203.150@tcp:/lustre /mnt/lustre /mnt/lustre/d110g.replay-single/striped_dir has type dir OK PASS 110g (156s) == replay-single test 111a: DNE: unlink striped dir, fail MDT1 ========================================================== 16:18:25 (1787861905) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2464 1268840 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2032 1269272 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 oleg350-server Stopping /mnt/lustre-mds1 (opts:) on oleg350-server 16:18:40 (1787861920) shut down facet: mds1 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds1 to oleg350-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0000 16:19:16 (1787861956) targets are mounted 16:19:16 (1787861956) facet_failover done oleg350-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 (71s) == replay-single test 111b: DNE: unlink striped dir, fail MDT2 ========================================================== 16:19:35 (1787861975) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2468 1268836 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2036 1269268 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 oleg350-server Stopping /mnt/lustre-mds2 (opts:) on oleg350-server 16:19:52 (1787861992) shut down facet: mds2 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds2 to oleg350-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0001 16:20:22 (1787862022) targets are mounted 16:20:22 (1787862022) facet_failover done pdsh@oleg350-client: oleg350-client: ssh exited with exit code 95 oleg350-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 pdsh@oleg350-client: oleg350-client: ssh exited with exit code 95 Starting client: oleg350-client.virtnet: -o user_xattr,flock 192.168.203.150@tcp:/lustre /mnt/lustre Can't lstat /mnt/lustre/d111b.replay-single/striped_dir: No such file or directory PASS 111b (126s) == replay-single test 111c: DNE: unlink striped dir, uncommit on MDT1, fail client/MDT1/MDT2 ========================================================== 16:21:41 (1787862101) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2512 1268792 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2036 1269268 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 oleg350-server Stopping /mnt/lustre-mds1 (opts:) on oleg350-server Failing mds2 on oleg350-server Stopping /mnt/lustre-mds2 (opts:) on oleg350-server 16:22:13 (1787862133) shut down facet: mds1 facet_host: oleg350-server facet_failover_host: oleg350-server facet: mds2 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds1 to oleg350-server mount facets: mds1 Failover mds2 to oleg350-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 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0000 Started lustre-MDT0001 16:23:00 (1787862180) targets are mounted 16:23:00 (1787862180) facet_failover done pdsh@oleg350-client: oleg350-client: ssh exited with exit code 95 oleg350-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@oleg350-client: oleg350-client: ssh exited with exit code 95 Starting client: oleg350-client.virtnet: -o user_xattr,flock 192.168.203.150@tcp:/lustre /mnt/lustre Can't lstat /mnt/lustre/d111c.replay-single/striped_dir: No such file or directory PASS 111c (158s) == replay-single test 111d: DNE: unlink striped dir, uncommit on MDT2, fail client/MDT1/MDT2 ========================================================== 16:24:19 (1787862259) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2472 1268832 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2040 1269264 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 oleg350-server Stopping /mnt/lustre-mds1 (opts:) on oleg350-server Failing mds2 on oleg350-server Stopping /mnt/lustre-mds2 (opts:) on oleg350-server 16:24:44 (1787862284) shut down facet: mds1 facet_host: oleg350-server facet_failover_host: oleg350-server facet: mds2 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds1 to oleg350-server mount facets: mds1 Failover mds2 to oleg350-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 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 16:25:33 (1787862333) targets are mounted 16:25:34 (1787862334) facet_failover done pdsh@oleg350-client: oleg350-client: ssh exited with exit code 95 oleg350-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@oleg350-client: oleg350-client: ssh exited with exit code 95 Starting client: oleg350-client.virtnet: -o user_xattr,flock 192.168.203.150@tcp:/lustre /mnt/lustre Can't lstat /mnt/lustre/d111d.replay-single/striped_dir: No such file or directory PASS 111d (148s) == replay-single test 111e: DNE: unlink striped dir, uncommit on MDT2, fail MDT1/MDT2 ========================================================== 16:26:47 (1787862407) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2516 1268788 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 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2508 1268796 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 oleg350-server Stopping /mnt/lustre-mds1 (opts:) on oleg350-server Failing mds2 on oleg350-server Stopping /mnt/lustre-mds2 (opts:) on oleg350-server 16:27:13 (1787862433) shut down facet: mds1 facet_host: oleg350-server facet_failover_host: oleg350-server facet: mds2 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds1 to oleg350-server mount facets: mds1 Failover mds2 to oleg350-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 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 16:27:45 (1787862465) targets are mounted 16:27:45 (1787862465) facet_failover done oleg350-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 ========================================================== 16:28:04 (1787862484) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2556 1268748 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2112 1269192 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210944 1% /mnt/lustre UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2476 1268828 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2036 1269268 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 oleg350-server Stopping /mnt/lustre-mds1 (opts:) on oleg350-server Failing mds2 on oleg350-server Stopping /mnt/lustre-mds2 (opts:) on oleg350-server 16:28:28 (1787862508) shut down facet: mds1 facet_host: oleg350-server facet_failover_host: oleg350-server facet: mds2 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds1 to oleg350-server mount facets: mds1 Failover mds2 to oleg350-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 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 16:29:18 (1787862558) targets are mounted 16:29:18 (1787862558) facet_failover done oleg350-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 (102s) == replay-single test 111g: DNE: unlink striped dir, fail MDT1/MDT2 ========================================================== 16:29:46 (1787862586) UUID Inodes IUsed IFree IUse% Mounted on lustre-MDT0000_UUID 1024000 313 1023687 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1024000 282 1023718 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: 524059 595 523464 1% /mnt/lustre UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2484 1268820 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2048 1269256 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 2484 1268820 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2048 1269256 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 oleg350-server Stopping /mnt/lustre-mds1 (opts:) on oleg350-server Failing mds2 on oleg350-server Stopping /mnt/lustre-mds2 (opts:) on oleg350-server 16:30:11 (1787862611) shut down facet: mds1 facet_host: oleg350-server facet_failover_host: oleg350-server facet: mds2 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds1 to oleg350-server mount facets: mds1 Failover mds2 to oleg350-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 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 16:30:42 (1787862642) targets are mounted 16:30:42 (1787862642) facet_failover done oleg350-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 ========================================================== 16:31:01 (1787862661) SKIP: replay-single test_112a needs >= 4 MDTs SKIP 112a (3s) == replay-single test 112b: DNE: cross MDT rename, fail MDT2 ========================================================== 16:31:04 (1787862664) SKIP: replay-single test_112b needs >= 4 MDTs SKIP 112b (3s) == replay-single test 112c: DNE: cross MDT rename, fail MDT3 ========================================================== 16:31:07 (1787862667) SKIP: replay-single test_112c needs >= 4 MDTs SKIP 112c (4s) == replay-single test 112d: DNE: cross MDT rename, fail MDT4 ========================================================== 16:31:11 (1787862671) SKIP: replay-single test_112d needs >= 4 MDTs SKIP 112d (3s) == replay-single test 112e: DNE: cross MDT rename, fail MDT1 and MDT2 ========================================================== 16:31:14 (1787862674) SKIP: replay-single test_112e needs >= 4 MDTs SKIP 112e (4s) == replay-single test 112f: DNE: cross MDT rename, fail MDT1 and MDT3 ========================================================== 16:31:18 (1787862678) SKIP: replay-single test_112f needs >= 4 MDTs SKIP 112f (3s) == replay-single test 112g: DNE: cross MDT rename, fail MDT1 and MDT4 ========================================================== 16:31:21 (1787862681) SKIP: replay-single test_112g needs >= 4 MDTs SKIP 112g (4s) == replay-single test 112h: DNE: cross MDT rename, fail MDT2 and MDT3 ========================================================== 16:31:25 (1787862685) SKIP: replay-single test_112h needs >= 4 MDTs SKIP 112h (3s) == replay-single test 112i: DNE: cross MDT rename, fail MDT2 and MDT4 ========================================================== 16:31:28 (1787862688) SKIP: replay-single test_112i needs >= 4 MDTs SKIP 112i (3s) == replay-single test 112j: DNE: cross MDT rename, fail MDT3 and MDT4 ========================================================== 16:31:31 (1787862691) SKIP: replay-single test_112j needs >= 4 MDTs SKIP 112j (3s) == replay-single test 112k: DNE: cross MDT rename, fail MDT1,MDT2,MDT3 ========================================================== 16:31:34 (1787862694) SKIP: replay-single test_112k needs >= 4 MDTs SKIP 112k (3s) == replay-single test 112l: DNE: cross MDT rename, fail MDT1,MDT2,MDT4 ========================================================== 16:31:37 (1787862697) SKIP: replay-single test_112l needs >= 4 MDTs SKIP 112l (4s) == replay-single test 112m: DNE: cross MDT rename, fail MDT1,MDT3,MDT4 ========================================================== 16:31:41 (1787862701) SKIP: replay-single test_112m needs >= 4 MDTs SKIP 112m (3s) == replay-single test 112n: DNE: cross MDT rename, fail MDT2,MDT3,MDT4 ========================================================== 16:31:44 (1787862704) SKIP: replay-single test_112n needs >= 4 MDTs SKIP 112n (3s) == replay-single test 115: failover for create/unlink striped directory ========================================================== 16:31:47 (1787862707) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2480 1268824 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2040 1269264 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210944 1% /mnt/lustre striped dir -i1 -c2 -H crush2 /mnt/lustre/d115.replay-single/test_0 striped dir -i1 -c2 -H all_char /mnt/lustre/d115.replay-single/test_1 striped dir -i1 -c2 -H crush2 /mnt/lustre/d115.replay-single/test_2 striped dir -i1 -c2 -H all_char /mnt/lustre/d115.replay-single/test_3 striped dir -i1 -c2 -H all_char /mnt/lustre/d115.replay-single/test_4 Failing mds2 on oleg350-server Stopping /mnt/lustre-mds2 (opts:) on oleg350-server 16:32:01 (1787862721) shut down facet: mds2 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds2 to oleg350-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0001 16:32:27 (1787862747) targets are mounted 16:32:27 (1787862747) facet_failover done oleg350-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 2532 1268772 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 striped dir -i0 -c2 -H crush /mnt/lustre/d115.replay-single/test_0 striped dir -i0 -c2 -H all_char /mnt/lustre/d115.replay-single/test_1 striped dir -i0 -c2 -H fnv_1a_64 /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 crush /mnt/lustre/d115.replay-single/test_4 Failing mds1 on oleg350-server Stopping /mnt/lustre-mds1 (opts:) on oleg350-server 16:32:51 (1787862771) shut down facet: mds1 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds1 to oleg350-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0000 16:33:27 (1787862807) targets are mounted 16:33:27 (1787862807) facet_failover done oleg350-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 (117s) == replay-single test 116a: large update log master MDT recovery ========================================================== 16:33:45 (1787862825) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2584 1268720 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2160 1269144 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1548 3605472 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3096 7210944 1% /mnt/lustre fail_loc=0x80001702 Failing mds1 on oleg350-server Stopping /mnt/lustre-mds1 (opts:) on oleg350-server 16:33:59 (1787862839) shut down facet: mds1 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds1 to oleg350-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0000 16:34:33 (1787862873) targets are mounted 16:34:33 (1787862873) facet_failover done oleg350-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 (65s) == replay-single test 116b: large update log slave MDT recovery ========================================================== 16:34:50 (1787862890) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2588 1268716 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 fail_loc=0x80001702 Failing mds2 on oleg350-server Stopping /mnt/lustre-mds2 (opts:) on oleg350-server 16:35:04 (1787862904) shut down facet: mds2 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds2 to oleg350-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0001 16:35:33 (1787862933) targets are mounted 16:35:33 (1787862933) facet_failover done oleg350-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 (57s) == replay-single test 117: DNE: cross MDT unlink, fail MDT1 and MDT2 ========================================================== 16:35:47 (1787862947) SKIP: replay-single test_117 needs >= 4 MDTs SKIP 117 (3s) == replay-single test 118: invalidate osp update will not cause update log corruption ========================================================== 16:35:50 (1787862950) 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 2716 1268588 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2208 1269096 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 oleg350-server Stopping /mnt/lustre-mds1 (opts:) on oleg350-server 16:36:04 (1787862964) shut down facet: mds1 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds1 to oleg350-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0000 16:36:39 (1787862999) targets are mounted 16:36:39 (1787862999) facet_failover done oleg350-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 ========================================================== 16:36:54 (1787863014) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2648 1268656 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 Stopping /mnt/lustre-mds1 (opts:) on oleg350-server Failover mds1 to oleg350-server oleg350-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 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0000 oleg350-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 57 sec mdt.lustre-MDT0000.recovery_time_hard=180 PASS 119 (117s) == replay-single test 120: DNE fail abort should stop both normal and DNE replay ========================================================== 16:38:51 (1787863131) Replay barrier on lustre-MDT0000 Stopping /mnt/lustre-mds1 (opts:) on oleg350-server Failover mds1 to oleg350-server oleg350-server.virtnet Start mds1: mount -t lustre -o localrecov -o abort_recovery /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-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 (52s) == replay-single test 121: lock replay timed out and race ========================================================== 16:39:43 (1787863183) multiop /mnt/lustre/f121.replay-single vs_s TMPPIPE=/tmp/multiop_open_wait_pipe.8230 Stopping /mnt/lustre-mds1 (opts:) on oleg350-server Failover mds1 to oleg350-server oleg350-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 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0000 pdsh@oleg350-client: oleg350-client: ssh exited with exit code 5 fail_loc=0x0 at_max=600 PASS 121 (220s) == replay-single test 130a: DoM file create (setstripe) replay ========================================================== 16:43:23 (1787863403) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2988 1268316 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 oleg350-server Stopping /mnt/lustre-mds1 (opts:) on oleg350-server 16:43:39 (1787863419) shut down facet: mds1 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds1 to oleg350-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0000 16:44:16 (1787863456) targets are mounted 16:44:16 (1787863456) facet_failover done oleg350-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 (72s) == replay-single test 130b: DoM file create (inherited) replay ========================================================== 16:44:35 (1787863475) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2992 1268312 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 oleg350-server Stopping /mnt/lustre-mds1 (opts:) on oleg350-server 16:44:51 (1787863491) shut down facet: mds1 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds1 to oleg350-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0000 16:45:24 (1787863524) targets are mounted 16:45:24 (1787863524) facet_failover done oleg350-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 (67s) == replay-single test 131a: DoM file write lock replay === 16:45:42 (1787863542) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2992 1268312 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 1+0 records in 1+0 records out 8 bytes copied, 0.0147322 s, 0.5 kB/s Failing mds1 on oleg350-server Stopping /mnt/lustre-mds1 (opts:) on oleg350-server 16:45:57 (1787863557) shut down facet: mds1 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds1 to oleg350-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0000 16:46:31 (1787863591) targets are mounted 16:46:31 (1787863591) facet_failover done oleg350-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 (67s) SKIP: replay-single test_131b skipping excluded test 131b == replay-single test 132a: PFL new component instantiate replay ========================================================== 16:46:52 (1787863612) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2996 1268308 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 1+0 records in 1+0 records out 1048576 bytes (1.0 MB, 1.0 MiB) copied, 0.0594907 s, 17.6 MB/s /mnt/lustre/f132a.replay-single lcm_layout_gen: 3 lcm_mirror_count: 1 lcm_entry_count: 2 lcme_id: 1 lcme_mirror_id: 0 lcme_flags: init lcme_extent.e_start: 0 lcme_extent.e_end: 1048576 lmm_stripe_count: 1 lmm_stripe_size: 1048576 lmm_pattern: raid0 lmm_layout_gen: 0 lmm_stripe_offset: 0 lmm_objects: - 0: { l_ost_idx: 0, l_fid: [0x280000401:0x722:0x0] } lcme_id: 2 lcme_mirror_id: 0 lcme_flags: init lcme_extent.e_start: 1048576 lcme_extent.e_end: EOF lmm_stripe_count: 2 lmm_stripe_size: 4194304 lmm_pattern: raid0 lmm_layout_gen: 0 lmm_stripe_offset: 1 lmm_objects: - 0: { l_ost_idx: 1, l_fid: [0x2c0000401:0x722:0x0] } - 1: { l_ost_idx: 0, l_fid: [0x280000401:0x723:0x0] } Failing mds1 on oleg350-server Stopping /mnt/lustre-mds1 (opts:) on oleg350-server 16:47:11 (1787863631) shut down facet: mds1 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds1 to oleg350-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0000 16:47:44 (1787863664) targets are mounted 16:47:44 (1787863664) facet_failover done oleg350-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec /mnt/lustre/f132a.replay-single lcm_layout_gen: 4 lcm_mirror_count: 1 lcm_entry_count: 2 lcme_id: 1 lcme_mirror_id: 0 lcme_flags: init lcme_extent.e_start: 0 lcme_extent.e_end: 1048576 lmm_stripe_count: 1 lmm_stripe_size: 1048576 lmm_pattern: raid0 lmm_layout_gen: 65535 lmm_stripe_offset: 0 lmm_objects: - 0: { l_ost_idx: 0, l_fid: [0x280000401:0x722:0x0] } lcme_id: 2 lcme_mirror_id: 0 lcme_flags: init lcme_extent.e_start: 1048576 lcme_extent.e_end: EOF lmm_stripe_count: 2 lmm_stripe_size: 4194304 lmm_pattern: raid0 lmm_layout_gen: 65535 lmm_stripe_offset: 1 lmm_objects: - 0: { l_ost_idx: 1, l_fid: [0x2c0000401:0x722:0x0] } - 1: { l_ost_idx: 0, l_fid: [0x280000401:0x723:0x0] } PASS 132a (71s) == replay-single test 133: check resend of ongoing requests for lwp during failover ========================================================== 16:48:03 (1787863683) seq.srv-lustre-MDT0001.space=clear Starting client: oleg350-client.virtnet: -o user_xattr,flock 192.168.203.150@tcp:/lustre /mnt/lustre fail_val=700 fail_loc=0x80000123 Failing mds1 on oleg350-server Stopping /mnt/lustre-mds1 (opts:) on oleg350-server 16:48:15 (1787863695) shut down facet: mds1 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds1 to oleg350-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0000 16:48:40 (1787863720) targets are mounted 16:48:40 (1787863720) facet_failover done PASS 133 (44s) == replay-single test 134: replay creation of a file created in a pool ========================================================== 16:48:47 (1787863727) Creating new pool pool_134 oleg350-server: Pool lustre.pool_134 created Adding targets to pool oleg350-server: OST lustre-OST0001_UUID added to pool lustre.pool_134 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 3072 1268232 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2460 1268844 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 oleg350-server Stopping /mnt/lustre-mds1 (opts:) on oleg350-server 16:49:11 (1787863751) shut down facet: mds1 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds1 to oleg350-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0000 16:49:42 (1787863782) targets are mounted 16:49:42 (1787863782) facet_failover done oleg350-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 oleg350-server: OST lustre-OST0001_UUID removed from pool lustre.pool_134 oleg350-server: Pool lustre.pool_134 destroyed PASS 134 (81s) == replay-single test 135: Server failure in lock replay phase ========================================================== 16:50:09 (1787863809) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 3028 1268276 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2460 1268844 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 oleg350-server Failover ost1 to oleg350-server oleg350-server.virtnet fail_loc=0 oleg350-server: oleg350-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 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-OST0000 oleg350-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 oleg350-server Failover ost1 to oleg350-server oleg350-server.virtnet oleg350-server: oleg350-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 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-OST0000 Stopping /mnt/lustre-ost1 (opts:-f) on oleg350-server Stopping /mnt/lustre-ost2 (opts:-f) on oleg350-server Start ost1: mount -t lustre -o localrecov /dev/mapper/ost1_flakey /mnt/lustre-ost1 seq.cli-lustre-OST0000-super.width=65536 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-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 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-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 (155s) == replay-single test 136: MDS to disconnect all OSPs first, then cleanup ldlm ========================================================== 16:52:43 (1787863963) SKIP: replay-single test_136 needs > 2 MDTs SKIP 136 (4s) == replay-single test 137a: DNE: create under striped dir, fail MDT1 ========================================================== 16:52:47 (1787863967) llite.lustre-ffff9f18d8e9c000.intent_mkdir=1 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 3036 1268268 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2476 1268828 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 oleg350-server Stopping /mnt/lustre-mds1 (opts:) on oleg350-server 16:53:01 (1787863981) shut down facet: mds1 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds1 to oleg350-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0000 16:53:35 (1787864015) targets are mounted 16:53:35 (1787864015) facet_failover done oleg350-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 (67s) == replay-single test 137b: DNE: create under striped dir, fail MDT2 ========================================================== 16:53:55 (1787864035) llite.lustre-ffff9f18d8e9c000.intent_mkdir=1 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 3040 1268264 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2476 1268828 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 oleg350-server Stopping /mnt/lustre-mds2 (opts:) on oleg350-server 16:54:09 (1787864049) shut down facet: mds2 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds2 to oleg350-server mount facets: mds2 Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0001 16:54:35 (1787864075) targets are mounted 16:54:35 (1787864075) facet_failover done oleg350-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 (57s) == replay-single test 137c: DNE: create under striped dir, fail MDT1/MDT2 ========================================================== 16:54:52 (1787864092) llite.lustre-ffff9f18d8e9c000.intent_mkdir=1 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 3036 1268268 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2488 1268816 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 3036 1268268 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2488 1268816 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 oleg350-server Stopping /mnt/lustre-mds2 (opts:) on oleg350-server Failing mds1 on oleg350-server Stopping /mnt/lustre-mds1 (opts:) on oleg350-server 16:55:19 (1787864119) shut down facet: mds2 facet_host: oleg350-server facet_failover_host: oleg350-server facet: mds1 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds1 to oleg350-server Failover mds2 to oleg350-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 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0001 Started lustre-MDT0000 16:55:55 (1787864155) targets are mounted 16:55:55 (1787864155) facet_failover done oleg350-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 (88s) == replay-single test 160: mdt.recovery_reconnect_histogram testing ========================================================== 16:56:20 (1787864180) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 3024 1268280 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2476 1268828 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 oleg350-server Stopping /mnt/lustre-mds1 (opts:) on oleg350-server 16:56:33 (1787864193) shut down facet: mds1 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds1 to oleg350-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0000 16:57:08 (1787864228) targets are mounted 16:57:08 (1787864228) facet_failover done oleg350-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: 1787864221 recovery_finish: 1787864226 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: "192.168.203.50@tcp", delay_sec: 0 } mdt.lustre-MDT0000.exports.192.168.203.50@tcp.reconnect_delay=0 PASS 160 (69s) == replay-single test 200: Dropping one OBD_PING should not cause disconnect ========================================================== 16:57:29 (1787864249) SKIP: replay-single test_200 Need remote client SKIP 200 (4s) == replay-single test 201: MDT umount cascading disconnects timeouts ========================================================== 16:57:33 (1787864253) fail_loc=0x245 fail_val=8 fail_loc=0x245 fail_val=8 Stopping /mnt/lustre-mds2 (opts:) on oleg350-server Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-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 ========================================================== 16:58:14 (1787864294) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2992 1268312 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2428 1268876 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 oleg350-server Stopping /mnt/lustre-mds1 (opts:) on oleg350-server 16:58:32 (1787864312) shut down facet: mds1 facet_host: oleg350-server facet_failover_host: oleg350-server Failover mds1 to oleg350-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg350-server: oleg350-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg350-client: oleg350-server: ssh exited with exit code 1 Started lustre-MDT0000 16:59:10 (1787864350) targets are mounted 16:59:10 (1787864350) facet_failover done oleg350-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 (73s) == replay-single test 203: resend can hit original request ========================================================== 16:59:27 (1787864367) Starting client: oleg350-client.virtnet: -o user_xattr,flock 192.168.203.150@tcp:/lustre /mnt/lustre2 fail_loc=0x80002403 fail_val=2 STAT SETSTRIPE File: /mnt/lustre/f203.replay-single Size: 0 Blocks: 0 IO Block: 4194304 regular empty file Device: 2c54f966h/743766374d Inode: 144116279014326273 Links: 1 Access: (0644/-rw-r--r--) Uid: ( 0/ root) Gid: ( 0/ root) Access: 2026-08-27 16:59:30.000000000 -0400 Modify: 2026-08-27 16:59:30.000000000 -0400 Change: 2026-08-27 16:59:30.000000000 -0400 Birth: 2026-08-27 16:59:31.000000000 -0400 fail_loc=0 fail_val=0 192.168.203.150@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 oleg350-client.virtnet /mnt/lustre2 (opts:) PASS 203 (12s) == replay-single test complete, duration 4003 sec ======== 16:59:39 (1787864379) osc.lustre-OST0000-osc-ffff9f18d8e9c000.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-ffff9f18d8e9c000.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 1787864383.436878130 secs.nsecs start_time 1787863928.056637465 secs.nsecs elapsed_time 455.380240665 secs.nsecs uncompressed_objects 748 samples [reqs] obdfilter.lustre-OST0001.stats_compr= snapshot_time 1787864383.436940138 secs.nsecs start_time 1787863946.446258867 secs.nsecs elapsed_time 436.990681271 secs.nsecs uncompressed_objects 751 samples [reqs] === replay-single: start cleanup 16:59:43 (1787864383) === === replay-single: finish cleanup 16:59:50 (1787864390) ===