-----============= acceptance-small: sanity-lfsck ============----- Thu Aug 27 08:30:29 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 oleg424-server: ls: cannot access '/home/green/git/lustre-release/lustre/tests/except/sanity-lfsck.*ex': No such file or directory excepting tests: 18b 23b /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1049: echo: write error: Device or resource busy Loading modules from /home/green/git/lustre-release/lustre detected 4 online CPUs by sysfs MODOPTS_LIBCFS= Force libcfs to create 2 CPU partitions loading modules on: 'oleg424-server' oleg424-server: oleg424-server.virtnet: executing load_modules_local oleg424-server: Loading modules from /home/green/git/lustre-release/lustre oleg424-server: /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1049: echo: write error: Device or resource busy oleg424-server: detected 4 online CPUs by sysfs oleg424-server: MODOPTS_LIBCFS= oleg424-server: Force libcfs to create 2 CPU partitions client=34683234 MDS=34683234 OSS=34683234 Stopping clients: oleg424-client.virtnet /mnt/lustre (opts:) Stopping client oleg424-client.virtnet /mnt/lustre opts: Stopping clients: oleg424-client.virtnet /mnt/lustre2 (opts:) Stopping /mnt/lustre-mds1 (opts:-f) on oleg424-server Stopping /mnt/lustre-ost1 (opts:-f) on oleg424-server Stopping /mnt/lustre-ost2 (opts:-f) on oleg424-server unloading modules via unload_modules_local on: 'oleg424-server' oleg424-server: oleg424-server.virtnet: executing unload_modules_local oleg424-server: modules unloaded. === sanity-lfsck: start setup 08:31:56 (1787833916) === Stopping clients: oleg424-client.virtnet /mnt/lustre (opts:-f) Stopping clients: oleg424-client.virtnet /mnt/lustre2 (opts:-f) pdsh@oleg424-client: oleg424-server: ssh exited with exit code 2 oleg424-server: oleg424-server.virtnet: executing set_hostid /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1049: echo: write error: Device or resource busy Loading modules from /home/green/git/lustre-release/lustre detected 4 online CPUs by sysfs MODOPTS_LIBCFS= Force libcfs to create 2 CPU partitions ptlrpc/ptlrpc options: 'lbug_on_grant_miscount=1' quota/lquota options: 'hash_lqs_cur_bits=3' mdt/mdt options: 'mdt_enable_flr_ec=1' ln: failed to create symbolic link '/sbin/.libs': Read-only file system loading modules on: 'oleg424-server' oleg424-server: oleg424-server.virtnet: executing load_modules_local oleg424-server: /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1049: echo: write error: Device or resource busy oleg424-server: Loading modules from /home/green/git/lustre-release/lustre oleg424-server: detected 4 online CPUs by sysfs oleg424-server: MODOPTS_LIBCFS= oleg424-server: Force libcfs to create 2 CPU partitions oleg424-server: ptlrpc/ptlrpc options: 'lbug_on_grant_miscount=1' oleg424-server: quota/lquota options: 'hash_lqs_cur_bits=3' oleg424-server: mdt/mdt options: 'mdt_enable_flr_ec=1' Formatting mgs, mds, osts Format mds1: lustre-mdt1/mdt1 Format ost1: lustre-ost1/ost1 Format ost2: lustre-ost2/ost2 Checking servers environments Checking clients oleg424-client.virtnet environments /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1049: echo: write error: Device or resource busy Loading modules from /home/green/git/lustre-release/lustre detected 4 online CPUs by sysfs MODOPTS_LIBCFS= Force libcfs to create 2 CPU partitions loading modules on: 'oleg424-server' oleg424-server: oleg424-server.virtnet: executing load_modules_local oleg424-server: /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1049: echo: write error: Device or resource busy oleg424-server: Loading modules from /home/green/git/lustre-release/lustre oleg424-server: detected 4 online CPUs by sysfs oleg424-server: MODOPTS_LIBCFS= oleg424-server: Force libcfs to create 2 CPU partitions Setup mgs, mdt, osts Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 Commit the device label on lustre-mdt1/mdt1 Started lustre-MDT0000 Start ost1: mount -t lustre -o localrecov lustre-ost1/ost1 /mnt/lustre-ost1 seq.cli-lustre-OST0000-super.width=65536 oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 Commit the device label on lustre-ost1/ost1 Started lustre-OST0000 Start ost2: mount -t lustre -o localrecov lustre-ost2/ost2 /mnt/lustre-ost2 seq.cli-lustre-OST0001-super.width=65536 oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 Commit the device label on lustre-ost2/ost2 Started lustre-OST0001 Starting client: oleg424-client.virtnet: -o user_xattr,flock 192.168.204.124@tcp:/lustre /mnt/lustre Starting client oleg424-client.virtnet: -o user_xattr,flock 192.168.204.124@tcp:/lustre /mnt/lustre Started clients oleg424-client.virtnet: 192.168.204.124@tcp:/lustre on /mnt/lustre type lustre (rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose) Using TIMEOUT=20 osc.lustre-OST0000-osc-ffff9465c41f2000.idle_timeout=debug osc.lustre-OST0001-osc-ffff9465c41f2000.idle_timeout=debug setting jobstats to procname_uid Setting lustre.sys.jobid_var from disable to procname_uid Waiting 90s for 'procname_uid' Updated after 2s: want 'procname_uid' got 'procname_uid' disable quota as required === sanity-lfsck: finish setup 08:34:40 (1787834080) === == sanity-lfsck test 0: Control LFSCK manually =========== 08:34:44 (1787834084) preparing... 3 * 3 files will be created Thu Aug 27 08:34:46 EDT 2026. total: 3 mkdir in 0.03 seconds: 87.41 ops/second total: 3 create in 0.04 seconds: 79.46 ops/second total: 3 mkdir in 0.04 seconds: 67.48 ops/second prepared Thu Aug 27 08:34:52 EDT 2026. fail_val=3 fail_loc=0x1600 Started LFSCK on the device lustre-MDT0000: scrub namespace name: lfsck_namespace magic: 0xa06249ff version: 2 status: scanning-phase1 flags: param: last_completed_time: N/A time_since_last_completed: N/A latest_start_time: 1787834094 time_since_latest_start: 1 seconds last_checkpoint_time: N/A time_since_last_checkpoint: N/A latest_start_position: 246, N/A, N/A last_checkpoint_position: N/A, N/A, N/A first_failure_position: N/A, N/A, N/A checked_phase1: 0 checked_phase2: 0 updated_phase1: 0 updated_phase2: 0 failed_phase1: 0 failed_phase2: 0 directories: 0 dirent_repaired: 0 linkea_repaired: 0 nlinks_repaired: 0 multiple_linked_checked: 0 multiple_linked_repaired: 0 unknown_inconsistency: 0 unmatched_pairs_repaired: 0 dangling_repaired: 0 multiple_referenced_repaired: 0 bad_file_type_repaired: 0 lost_dirent_repaired: 0 local_lost_found_scanned: 0 local_lost_found_moved: 0 local_lost_found_skipped: 0 local_lost_found_failed: 0 striped_dirs_scanned: 0 striped_dirs_repaired: 0 striped_dirs_failed: 0 striped_dirs_disabled: 0 striped_dirs_skipped: 0 striped_shards_scanned: 0 striped_shards_repaired: 0 striped_shards_failed: 0 striped_shards_skipped: 0 name_hash_repaired: 0 linkea_overflow_cleared: 0 agent_entries_repaired: 0 success_count: 0 run_time_phase1: 1 seconds run_time_phase2: 0 seconds average_speed_phase1: 0 items/sec average_speed_phase2: N/A average_speed_total: 0 items/sec real_time_speed_phase1: 0 items/sec real_time_speed_phase2: N/A current_position: 245, N/A, N/A Stopped LFSCK on the device lustre-MDT0000. Started LFSCK on the device lustre-MDT0000: scrub namespace fail_loc=0 fail_val=0 Waiting 32s for 'completed' Updated after 2s: want 'completed' got 'completed' Started LFSCK on the device lustre-MDT0000: scrub namespace stopall, should NOT crash LU-3649 Stopping clients: oleg424-client.virtnet /mnt/lustre (opts:) Stopping client oleg424-client.virtnet /mnt/lustre opts: Stopping clients: oleg424-client.virtnet /mnt/lustre2 (opts:) Stopping /mnt/lustre-mds1 (opts:-f) on oleg424-server Stopping /mnt/lustre-ost1 (opts:-f) on oleg424-server Stopping /mnt/lustre-ost2 (opts:-f) on oleg424-server PASS 0 (61s) == sanity-lfsck test 1a: LFSCK can find out and repair crashed FID-in-dirent ========================================================== 08:35:45 (1787834145) Checking servers environments Checking clients oleg424-client.virtnet environments /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1049: echo: write error: Device or resource busy Loading modules from /home/green/git/lustre-release/lustre detected 4 online CPUs by sysfs MODOPTS_LIBCFS= Force libcfs to create 2 CPU partitions loading modules on: 'oleg424-server' oleg424-server: oleg424-server.virtnet: executing load_modules_local oleg424-server: Loading modules from /home/green/git/lustre-release/lustre oleg424-server: /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1049: echo: write error: Device or resource busy oleg424-server: detected 4 online CPUs by sysfs oleg424-server: MODOPTS_LIBCFS= oleg424-server: Force libcfs to create 2 CPU partitions Setup mgs, mdt, osts Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 Started lustre-MDT0000 Start ost1: mount -t lustre -o localrecov lustre-ost1/ost1 /mnt/lustre-ost1 seq.cli-lustre-OST0000-super.width=65536 oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 Started lustre-OST0000 Start ost2: mount -t lustre -o localrecov lustre-ost2/ost2 /mnt/lustre-ost2 seq.cli-lustre-OST0001-super.width=65536 oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 Started lustre-OST0001 Starting client: oleg424-client.virtnet: -o user_xattr,flock 192.168.204.124@tcp:/lustre /mnt/lustre Starting client oleg424-client.virtnet: -o user_xattr,flock 192.168.204.124@tcp:/lustre /mnt/lustre Started clients oleg424-client.virtnet: 192.168.204.124@tcp:/lustre on /mnt/lustre type lustre (rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose) Using TIMEOUT=20 osc.lustre-OST0000-osc-ffff9465d1409800.idle_timeout=debug osc.lustre-OST0001-osc-ffff9465d1409800.idle_timeout=debug disable quota as required preparing... 1 * 1 files will be created Thu Aug 27 08:37:18 EDT 2026. total: 1 mkdir in 0.02 seconds: 43.11 ops/second total: 1 create in 0.01 seconds: 91.06 ops/second total: 1 mkdir in 0.03 seconds: 34.66 ops/second prepared Thu Aug 27 08:37:24 EDT 2026. fail_loc=0x1501 fail_loc=0 192.168.204.124@tcp:/lustre /mnt/lustre lustre rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose 0 0 Stopping client oleg424-client.virtnet /mnt/lustre (opts:) Started LFSCK on the device lustre-MDT0000: scrub namespace Starting client: oleg424-client.virtnet: -o user_xattr,flock 192.168.204.124@tcp:/lustre /mnt/lustre fail_loc=0x1505 fail_loc=0 PASS 1a (115s) == sanity-lfsck test 1b: LFSCK can find out and repair the missing FID-in-LMA ========================================================== 08:37:40 (1787834260) SKIP: sanity-lfsck test_1b OI Scrub not implemented for ZFS SKIP 1b (4s) == sanity-lfsck test 1c: LFSCK can find out and repair lost FID-in-dirent ========================================================== 08:37:44 (1787834264) preparing... 1 * 1 files will be created Thu Aug 27 08:37:48 EDT 2026. total: 1 mkdir in 0.01 seconds: 150.20 ops/second total: 1 create in 0.01 seconds: 132.84 ops/second total: 1 mkdir in 0.01 seconds: 131.50 ops/second prepared Thu Aug 27 08:37:54 EDT 2026. fail_loc=0x1504 fail_loc=0 192.168.204.124@tcp:/lustre /mnt/lustre lustre rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose 0 0 Stopping client oleg424-client.virtnet /mnt/lustre (opts:) Started LFSCK on the device lustre-MDT0000: scrub namespace Starting client: oleg424-client.virtnet: -o user_xattr,flock 192.168.204.124@tcp:/lustre /mnt/lustre fail_loc=0x1505 fail_loc=0 PASS 1c (29s) == sanity-lfsck test 2a: LFSCK can find out and repair crashed linkEA entry ========================================================== 08:38:13 (1787834293) preparing... 1 * 1 files will be created Thu Aug 27 08:38:17 EDT 2026. total: 1 mkdir in 0.01 seconds: 87.66 ops/second total: 1 create in 0.01 seconds: 91.30 ops/second total: 1 mkdir in 0.01 seconds: 69.08 ops/second prepared Thu Aug 27 08:38:23 EDT 2026. fail_loc=0x1603 fail_loc=0 192.168.204.124@tcp:/lustre /mnt/lustre lustre rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose 0 0 Stopping client oleg424-client.virtnet /mnt/lustre (opts:) Started LFSCK on the device lustre-MDT0000: scrub namespace Starting client: oleg424-client.virtnet: -o user_xattr,flock 192.168.204.124@tcp:/lustre /mnt/lustre PASS 2a (26s) == sanity-lfsck test 2b: LFSCK can find out and remove invalid linkEA entry ========================================================== 08:38:39 (1787834319) preparing... 1 * 1 files will be created Thu Aug 27 08:38:43 EDT 2026. total: 1 mkdir in 0.01 seconds: 131.16 ops/second total: 1 create in 0.01 seconds: 94.30 ops/second total: 1 mkdir in 0.01 seconds: 70.61 ops/second prepared Thu Aug 27 08:38:49 EDT 2026. fail_loc=0x1604 fail_loc=0 192.168.204.124@tcp:/lustre /mnt/lustre lustre rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose 0 0 Stopping client oleg424-client.virtnet /mnt/lustre (opts:) Started LFSCK on the device lustre-MDT0000: scrub namespace Starting client: oleg424-client.virtnet: -o user_xattr,flock 192.168.204.124@tcp:/lustre /mnt/lustre PASS 2b (23s) == sanity-lfsck test 2c: LFSCK can find out and remove repeated linkEA entry ========================================================== 08:39:02 (1787834342) preparing... 1 * 1 files will be created Thu Aug 27 08:39:06 EDT 2026. total: 1 mkdir in 0.02 seconds: 47.10 ops/second total: 1 create in 0.02 seconds: 49.71 ops/second total: 1 mkdir in 0.02 seconds: 47.05 ops/second prepared Thu Aug 27 08:39:12 EDT 2026. fail_loc=0x1605 fail_loc=0 192.168.204.124@tcp:/lustre /mnt/lustre lustre rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose 0 0 Stopping client oleg424-client.virtnet /mnt/lustre (opts:) Started LFSCK on the device lustre-MDT0000: scrub namespace Starting client: oleg424-client.virtnet: -o user_xattr,flock 192.168.204.124@tcp:/lustre /mnt/lustre PASS 2c (25s) == sanity-lfsck test 2d: LFSCK can recover the missing linkEA entry ========================================================== 08:39:28 (1787834368) preparing... 1 * 1 files will be created Thu Aug 27 08:39:31 EDT 2026. total: 1 mkdir in 0.01 seconds: 80.40 ops/second total: 1 create in 0.02 seconds: 48.40 ops/second total: 1 mkdir in 0.02 seconds: 51.32 ops/second prepared Thu Aug 27 08:39:38 EDT 2026. fail_loc=0x161d fail_loc=0 192.168.204.124@tcp:/lustre /mnt/lustre lustre rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose 0 0 Stopping client oleg424-client.virtnet /mnt/lustre (opts:) Started LFSCK on the device lustre-MDT0000: scrub namespace Starting client: oleg424-client.virtnet: -o user_xattr,flock 192.168.204.124@tcp:/lustre /mnt/lustre PASS 2d (29s) == sanity-lfsck test 2e: namespace LFSCK can verify remote object linkEA ========================================================== 08:39:56 (1787834396) SKIP: sanity-lfsck test_2e needs >= 2 MDTs SKIP 2e (5s) == sanity-lfsck test 3: LFSCK can verify multiple-linked objects ========================================================== 08:40:01 (1787834401) preparing... 4 * 4 files will be created Thu Aug 27 08:40:07 EDT 2026. total: 4 mkdir in 0.03 seconds: 140.47 ops/second total: 4 create in 0.03 seconds: 158.73 ops/second total: 4 mkdir in 0.03 seconds: 116.62 ops/second prepared Thu Aug 27 08:40:14 EDT 2026. fail_loc=0x1603 fail_loc=0x1604 fail_loc=0 Started LFSCK on the device lustre-MDT0000: scrub namespace PASS 3 (27s) == sanity-lfsck test 4: FID-in-dirent can be rebuilt after MDT file-level backup/restore ========================================================== 08:40:28 (1787834428) SKIP: sanity-lfsck test_4 OI Scrub not implemented for ZFS SKIP 4 (3s) == sanity-lfsck test 5: LFSCK can handle IGIF object upgrading ========================================================== 08:40:32 (1787834432) SKIP: sanity-lfsck test_5 OI Scrub not implemented for ZFS SKIP 5 (4s) == sanity-lfsck test 6a: LFSCK resumes from last checkpoint (1) ========================================================== 08:40:35 (1787834435) preparing... 5 * 5 files will be created Thu Aug 27 08:40:40 EDT 2026. total: 5 mkdir in 0.07 seconds: 71.60 ops/second total: 5 create in 0.08 seconds: 63.28 ops/second total: 5 mkdir in 0.12 seconds: 41.48 ops/second prepared Thu Aug 27 08:40:48 EDT 2026. fail_val=1 fail_loc=0x1600 Started LFSCK on the device lustre-MDT0000: scrub namespace fail_loc=0x80001608 fail_val=1 fail_loc=0x1600 Started LFSCK on the device lustre-MDT0000: scrub namespace fail_loc=0 fail_val=0 PASS 6a (40s) == sanity-lfsck test 6b: LFSCK resumes from last checkpoint (2) ========================================================== 08:41:15 (1787834475) preparing... 5 * 5 files will be created Thu Aug 27 08:41:20 EDT 2026. total: 5 mkdir in 0.04 seconds: 127.55 ops/second total: 5 create in 0.03 seconds: 143.28 ops/second total: 5 mkdir in 0.03 seconds: 144.70 ops/second prepared Thu Aug 27 08:41:25 EDT 2026. fail_val=1 fail_loc=0x1601 Started LFSCK on the device lustre-MDT0000: scrub namespace fail_loc=0x80001609 Waiting 32s for 'failed' Updated after 2s: want 'failed' got 'failed' fail_val=1 fail_loc=0x1601 Started LFSCK on the device lustre-MDT0000: scrub namespace Additional debug for 6b name: lfsck_namespace magic: 0xa06249ff version: 2 status: scanning-phase1 flags: param: last_completed_time: 1787834468 time_since_last_completed: 38 seconds latest_start_time: 1787834502 time_since_latest_start: 4 seconds last_checkpoint_time: 1787834495 time_since_last_checkpoint: 11 seconds latest_start_position: 1892, N/A, N/A last_checkpoint_position: 1889, [0x200000bd7:0xe5:0x0], 0xffffffffffffffff first_failure_position: N/A, N/A, N/A checked_phase1: 8 checked_phase2: 0 updated_phase1: 0 updated_phase2: 0 failed_phase1: 0 failed_phase2: 0 directories: 4 dirent_repaired: 0 linkea_repaired: 0 nlinks_repaired: 0 multiple_linked_checked: 0 multiple_linked_repaired: 0 unknown_inconsistency: 0 unmatched_pairs_repaired: 0 dangling_repaired: 0 multiple_referenced_repaired: 0 bad_file_type_repaired: 0 lost_dirent_repaired: 0 local_lost_found_scanned: 0 local_lost_found_moved: 0 local_lost_found_skipped: 0 local_lost_found_failed: 0 striped_dirs_scanned: 0 striped_dirs_repaired: 0 striped_dirs_failed: 0 striped_dirs_disabled: 0 striped_dirs_skipped: 0 striped_shards_scanned: 0 striped_shards_repaired: 0 striped_shards_failed: 0 striped_shards_skipped: 0 name_hash_repaired: 0 linkea_overflow_cleared: 0 agent_entries_repaired: 0 success_count: 10 run_time_phase1: 12 seconds run_time_phase2: 0 seconds average_speed_phase1: 0 items/sec average_speed_phase2: N/A average_speed_total: 0 items/sec real_time_speed_phase1: 0 items/sec real_time_speed_phase2: N/A current_position: 1918, [0x200000bd7:0x136:0x0], 0x2a367860253a8000 fail_loc=0 fail_val=0 PASS 6b (39s) == sanity-lfsck test 7a: non-stopped LFSCK should auto restarts after MDS remount (1) ========================================================== 08:41:55 (1787834515) preparing... 5 * 5 files will be created Thu Aug 27 08:41:59 EDT 2026. total: 5 mkdir in 0.06 seconds: 90.89 ops/second total: 5 create in 0.05 seconds: 95.43 ops/second total: 5 mkdir in 0.05 seconds: 100.03 ops/second prepared Thu Aug 27 08:42:05 EDT 2026. 192.168.204.124@tcp:/lustre /mnt/lustre lustre rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose 0 0 Stopping client oleg424-client.virtnet /mnt/lustre (opts:) fail_val=1 fail_loc=0x1601 Started LFSCK on the device lustre-MDT0000: scrub namespace stop mds1 fail_loc=0 fail_val=0 start mds1 oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 PASS 7a (71s) == sanity-lfsck test 7b: non-stopped LFSCK should auto restarts after MDS remount (2) ========================================================== 08:43:05 (1787834585) Checking servers environments Checking clients oleg424-client.virtnet environments /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1049: echo: write error: Device or resource busy Loading modules from /home/green/git/lustre-release/lustre detected 4 online CPUs by sysfs MODOPTS_LIBCFS= Force libcfs to create 2 CPU partitions loading modules on: 'oleg424-server' oleg424-server: oleg424-server.virtnet: executing load_modules_local oleg424-server: Loading modules from /home/green/git/lustre-release/lustre oleg424-server: /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1049: echo: write error: Device or resource busy oleg424-server: detected 4 online CPUs by sysfs oleg424-server: MODOPTS_LIBCFS= oleg424-server: Force libcfs to create 2 CPU partitions Setup mgs, mdt, osts Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg424-server: mount.lustre: according to /etc/mtab lustre-mdt1/mdt1 is already mounted on /mnt/lustre-mds1 pdsh@oleg424-client: oleg424-server: ssh exited with exit code 17 Start of lustre-mdt1/mdt1 on mds1 failed 17 Start ost1: mount -t lustre -o localrecov lustre-ost1/ost1 /mnt/lustre-ost1 oleg424-server: mount.lustre: according to /etc/mtab lustre-ost1/ost1 is already mounted on /mnt/lustre-ost1 pdsh@oleg424-client: oleg424-server: ssh exited with exit code 17 seq.cli-lustre-OST0000-super.width=65536 Start of lustre-ost1/ost1 on ost1 failed 17 Start ost2: mount -t lustre -o localrecov lustre-ost2/ost2 /mnt/lustre-ost2 oleg424-server: mount.lustre: according to /etc/mtab lustre-ost2/ost2 is already mounted on /mnt/lustre-ost2 pdsh@oleg424-client: oleg424-server: ssh exited with exit code 17 seq.cli-lustre-OST0001-super.width=65536 Start of lustre-ost2/ost2 on ost2 failed 17 Starting client: oleg424-client.virtnet: -o user_xattr,flock 192.168.204.124@tcp:/lustre /mnt/lustre Starting client oleg424-client.virtnet: -o user_xattr,flock 192.168.204.124@tcp:/lustre /mnt/lustre Started clients oleg424-client.virtnet: 192.168.204.124@tcp:/lustre on /mnt/lustre type lustre (rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose) Using TIMEOUT=20 osc.lustre-OST0000-osc-ffff9465c36f7800.idle_timeout=debug osc.lustre-OST0001-osc-ffff9465c36f7800.idle_timeout=debug disable quota as required preparing... 2 * 2 files will be created Thu Aug 27 08:44:03 EDT 2026. total: 2 mkdir in 0.02 seconds: 89.69 ops/second total: 2 create in 0.04 seconds: 55.33 ops/second total: 2 mkdir in 0.02 seconds: 99.43 ops/second prepared Thu Aug 27 08:44:10 EDT 2026. fail_loc=0x1604 fail_val=1 fail_loc=0x1602 Started LFSCK on the device lustre-MDT0000: scrub namespace 192.168.204.124@tcp:/lustre /mnt/lustre lustre rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose 0 0 Stopping client oleg424-client.virtnet /mnt/lustre (opts:) stop mds1 fail_loc=0 fail_val=0 start mds1 oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 PASS 7b (103s) == sanity-lfsck test 8: LFSCK state machine ============== 08:44:48 (1787834688) formatall oleg424-server: oleg424-server.virtnet: executing set_hostid /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1049: echo: write error: Device or resource busy oleg424-server: oleg424-server.virtnet: executing load_modules_local oleg424-server: /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1049: echo: write error: Device or resource busy setupall /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1049: echo: write error: Device or resource busy oleg424-server: oleg424-server.virtnet: executing load_modules_local oleg424-server: /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1049: echo: write error: Device or resource busy oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 Using TIMEOUT=20 preparing... 20 * 20 files will be created Thu Aug 27 08:47:45 EDT 2026. total: 20 mkdir in 0.24 seconds: 82.41 ops/second total: 20 create in 0.24 seconds: 85.04 ops/second total: 20 mkdir in 0.38 seconds: 52.65 ops/second prepared Thu Aug 27 08:47:56 EDT 2026. fail_loc=0x1603 fail_loc=0x1604 192.168.204.124@tcp:/lustre /mnt/lustre lustre rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose 0 0 Stopping client oleg424-client.virtnet /mnt/lustre (opts:) fail_val=2 fail_loc=0x1601 Started LFSCK on the device lustre-MDT0000: scrub namespace Stopped LFSCK on the device lustre-MDT0000. Started LFSCK on the device lustre-MDT0000: scrub namespace fail_loc=0x80001609 Waiting 32s for 'failed' Updated after 2s: want 'failed' got 'failed' fail_loc=0x1600 Started LFSCK on the device lustre-MDT0000: scrub namespace fail_loc=0x160a stop mds1 fail_loc=0x160b start mds1 oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 fail_loc=0x1601 Started LFSCK on the device lustre-MDT0000: scrub namespace stop mds1 fail_loc=0x160b start mds1 oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 stop mds1 start mds1 without resume LFSCK oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 fail_val=2 fail_loc=0x1602 Started LFSCK on the device lustre-MDT0000: scrub namespace fail_loc=0 fail_val=0 PASS 8 (294s) == sanity-lfsck test 9a: LFSCK speed control (1) ========= 08:49:42 (1787834982) Checking servers environments Checking clients oleg424-client.virtnet environments /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1049: echo: write error: Device or resource busy Loading modules from /home/green/git/lustre-release/lustre detected 4 online CPUs by sysfs MODOPTS_LIBCFS= Force libcfs to create 2 CPU partitions loading modules on: 'oleg424-server' oleg424-server: oleg424-server.virtnet: executing load_modules_local oleg424-server: Loading modules from /home/green/git/lustre-release/lustre oleg424-server: /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1049: echo: write error: Device or resource busy oleg424-server: detected 4 online CPUs by sysfs oleg424-server: MODOPTS_LIBCFS= oleg424-server: Force libcfs to create 2 CPU partitions Setup mgs, mdt, osts Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg424-server: mount.lustre: according to /etc/mtab lustre-mdt1/mdt1 is already mounted on /mnt/lustre-mds1 pdsh@oleg424-client: oleg424-server: ssh exited with exit code 17 Start of lustre-mdt1/mdt1 on mds1 failed 17 Start ost1: mount -t lustre -o localrecov lustre-ost1/ost1 /mnt/lustre-ost1 oleg424-server: mount.lustre: according to /etc/mtab lustre-ost1/ost1 is already mounted on /mnt/lustre-ost1 pdsh@oleg424-client: oleg424-server: ssh exited with exit code 17 seq.cli-lustre-OST0000-super.width=65536 Start of lustre-ost1/ost1 on ost1 failed 17 Start ost2: mount -t lustre -o localrecov lustre-ost2/ost2 /mnt/lustre-ost2 oleg424-server: mount.lustre: according to /etc/mtab lustre-ost2/ost2 is already mounted on /mnt/lustre-ost2 pdsh@oleg424-client: oleg424-server: ssh exited with exit code 17 seq.cli-lustre-OST0001-super.width=65536 Start of lustre-ost2/ost2 on ost2 failed 17 Starting client: oleg424-client.virtnet: -o user_xattr,flock 192.168.204.124@tcp:/lustre /mnt/lustre Starting client oleg424-client.virtnet: -o user_xattr,flock 192.168.204.124@tcp:/lustre /mnt/lustre Started clients oleg424-client.virtnet: 192.168.204.124@tcp:/lustre on /mnt/lustre type lustre (rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose) Using TIMEOUT=20 osc.lustre-OST0000-osc-ffff9465ca553800.idle_timeout=debug osc.lustre-OST0001-osc-ffff9465ca553800.idle_timeout=debug disable quota as required - open/close 588 (time 1787835059.19 total 10.01 last 58.72) - open/close 1189 (time 1787835069.20 total 20.02 last 60.04) - open/close 1825 (time 1787835079.23 total 30.05 last 63.42) - open/close 2381 (time 1787835089.23 total 40.05 last 55.59) - open/close 3027 (time 1787835099.24 total 50.06 last 64.56) - open/close 3604 (time 1787835109.25 total 60.07 last 57.63) - open/close 4315 (time 1787835119.25 total 70.07 last 71.09) - open/close 4934 (time 1787835129.26 total 80.08 last 61.86) total: 5000 open/close in 81.07 seconds: 61.68 ops/second Started LFSCK on the device lustre-MDT0000: scrub layout PASS 9a (184s) == sanity-lfsck test 9b: LFSCK speed control (2) ========= 08:52:47 (1787835167) preparing... 0 * 0 files will be created Thu Aug 27 08:53:48 EDT 2026. prepared Thu Aug 27 08:53:54 EDT 2026. Preparing another 50 * 50 files (with error) at Thu Aug 27 08:53:54 EDT 2026. fail_loc=0x1604 total: 50 mkdir in 0.47 seconds: 105.59 ops/second total: 50 create in 0.39 seconds: 127.56 ops/second fail_loc=0x160c Started LFSCK on the device lustre-MDT0000: scrub namespace Waiting 25s for 'stopped' Updated after 2s: want 'stopped' got 'stopped' fail_loc=0 Prepared at Thu Aug 27 08:54:29 EDT 2026. Started LFSCK on the device lustre-MDT0000: scrub namespace PASS 9b (139s) == sanity-lfsck test 10: System is available during LFSCK scanning ========================================================== 08:55:06 (1787835306) SKIP: sanity-lfsck test_10 lookup(..)/linkea on ZFS issue SKIP 10 (4s) == sanity-lfsck test 11a: LFSCK can rebuild lost last_id ========================================================== 08:55:10 (1787835310) total: 64 open/close in 1.10 seconds: 58.01 ops/second stopall remove LAST_ID on ost1: idx=0 removed '/mnt/lustre-ost1/O/0/LAST_ID' oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 fail_val=3 fail_loc=0x160e trigger LFSCK for layout on ost1 to rebuild the LAST_ID(s) Started LFSCK on the device lustre-OST0000: scrub layout fail_val=0 fail_loc=0 Waiting 32s for 'completed' Updated after 2s: want 'completed' got 'completed' the LAST_ID(s) should have been rebuilt PASS 11a (167s) == sanity-lfsck test 11b: LFSCK can rebuild crashed last_id ========================================================== 08:57:57 (1787835477) Checking servers environments Checking clients oleg424-client.virtnet environments /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1049: echo: write error: Device or resource busy Loading modules from /home/green/git/lustre-release/lustre detected 4 online CPUs by sysfs MODOPTS_LIBCFS= Force libcfs to create 2 CPU partitions loading modules on: 'oleg424-server' oleg424-server: oleg424-server.virtnet: executing load_modules_local oleg424-server: Loading modules from /home/green/git/lustre-release/lustre oleg424-server: /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1049: echo: write error: Device or resource busy oleg424-server: detected 4 online CPUs by sysfs oleg424-server: MODOPTS_LIBCFS= oleg424-server: Force libcfs to create 2 CPU partitions Setup mgs, mdt, osts Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 Started lustre-MDT0000 Start ost1: mount -t lustre -o localrecov lustre-ost1/ost1 /mnt/lustre-ost1 oleg424-server: mount.lustre: according to /etc/mtab lustre-ost1/ost1 is already mounted on /mnt/lustre-ost1 pdsh@oleg424-client: oleg424-server: ssh exited with exit code 17 seq.cli-lustre-OST0000-super.width=65536 Start of lustre-ost1/ost1 on ost1 failed 17 Start ost2: mount -t lustre -o localrecov lustre-ost2/ost2 /mnt/lustre-ost2 seq.cli-lustre-OST0001-super.width=65536 oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 Started lustre-OST0001 Starting client: oleg424-client.virtnet: -o user_xattr,flock 192.168.204.124@tcp:/lustre /mnt/lustre Starting client oleg424-client.virtnet: -o user_xattr,flock 192.168.204.124@tcp:/lustre /mnt/lustre Started clients oleg424-client.virtnet: 192.168.204.124@tcp:/lustre on /mnt/lustre type lustre (rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose) Using TIMEOUT=20 osc.lustre-OST0000-osc-ffff9465c92ef000.idle_timeout=debug osc.lustre-OST0001-osc-ffff9465c92ef000.idle_timeout=debug disable quota as required set fail_loc=0x160d to skip the updating LAST_ID on-disk fail_loc=0x160d - precreated_ost_obj_count lustre-OST0000-osc-MDT0000 prealloc_last_id: 2785 prealloc_next_id: 2754 count: 32 total: 64 open/close in 1.18 seconds: 54.19 ops/second 192.168.204.124@tcp:/lustre /mnt/lustre lustre rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose 0 0 Stopping client oleg424-client.virtnet /mnt/lustre (opts:) Stopping /mnt/lustre-ost1 (opts:) on oleg424-server fail_loc=0x215 Start ost1: mount -t lustre -o localrecov lustre-ost1/ost1 /mnt/lustre-ost1 seq.cli-lustre-OST0000-super.width=65536 oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 Started lustre-OST0000 the on-disk LAST_ID should be smaller than the expected one trigger LFSCK for layout on ost1 to rebuild the on-disk LAST_ID Started LFSCK on the device lustre-OST0000: scrub layout Stopping /mnt/lustre-ost1 (opts:) on oleg424-server Start ost1: mount -t lustre -o localrecov lustre-ost1/ost1 /mnt/lustre-ost1 seq.cli-lustre-OST0000-super.width=65536 oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 Started lustre-OST0000 the on-disk LAST_ID should have been rebuilt fail_loc=0 Stopping clients: oleg424-client.virtnet /mnt/lustre (opts:) Stopping clients: oleg424-client.virtnet /mnt/lustre2 (opts:) Stopping /mnt/lustre-mds1 (opts:-f) on oleg424-server Stopping /mnt/lustre-ost1 (opts:-f) on oleg424-server Stopping /mnt/lustre-ost2 (opts:-f) on oleg424-server PASS 11b (150s) == sanity-lfsck test 12a: single command to trigger LFSCK on all devices ========================================================== 09:00:27 (1787835627) SKIP: sanity-lfsck test_12a needs >= 2 MDTs SKIP 12a (4s) == sanity-lfsck test 12b: auto detect Lustre device ====== 09:00:31 (1787835631) Checking servers environments Checking clients oleg424-client.virtnet environments /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1049: echo: write error: Device or resource busy Loading modules from /home/green/git/lustre-release/lustre detected 4 online CPUs by sysfs MODOPTS_LIBCFS= Force libcfs to create 2 CPU partitions loading modules on: 'oleg424-server' oleg424-server: oleg424-server.virtnet: executing load_modules_local oleg424-server: Loading modules from /home/green/git/lustre-release/lustre oleg424-server: /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1049: echo: write error: Device or resource busy oleg424-server: detected 4 online CPUs by sysfs oleg424-server: MODOPTS_LIBCFS= oleg424-server: Force libcfs to create 2 CPU partitions Setup mgs, mdt, osts Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 Started lustre-MDT0000 Start ost1: mount -t lustre -o localrecov lustre-ost1/ost1 /mnt/lustre-ost1 seq.cli-lustre-OST0000-super.width=65536 oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 Started lustre-OST0000 Start ost2: mount -t lustre -o localrecov lustre-ost2/ost2 /mnt/lustre-ost2 seq.cli-lustre-OST0001-super.width=65536 oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 Started lustre-OST0001 Starting client: oleg424-client.virtnet: -o user_xattr,flock 192.168.204.124@tcp:/lustre /mnt/lustre Starting client oleg424-client.virtnet: -o user_xattr,flock 192.168.204.124@tcp:/lustre /mnt/lustre Started clients oleg424-client.virtnet: 192.168.204.124@tcp:/lustre on /mnt/lustre type lustre (rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose) Using TIMEOUT=20 osc.lustre-OST0000-osc-ffff9465c3624000.idle_timeout=debug osc.lustre-OST0001-osc-ffff9465c3624000.idle_timeout=debug disable quota as required Start LFSCK without '-M' specified. Started LFSCK on the device lustre-MDT0000: scrub layout namespace PASS 12b (83s) == sanity-lfsck test 13: LFSCK can repair crashed lmm_oi ========================================================== 09:01:54 (1787835714) ##### The lmm_oi in layout EA should be consistent with the MDT-object FID; otherwise, the LFSCK should re-generate the lmm_oi from the MDT-object FID. ##### Inject failure stub to simulate bad lmm_oi fail_loc=0x160f total: 1 open/close in 0.03 seconds: 36.34 ops/second fail_loc=0 Trigger layout LFSCK to find out the bad lmm_oi and fix them Started LFSCK on the device lustre-MDT0000: scrub layout PASS 13 (12s) == sanity-lfsck test 14a: LFSCK can repair MDT-object with dangling LOV EA reference (1) ========================================================== 09:02:06 (1787835726) ##### The OST-object referenced by the MDT-object should be there; otherwise, the LFSCK should re-create the missing OST-object. without '--delay-create-ostobj' option. ##### Inject failure stub to simulate dangling referenced MDT-object fail_loc=0x1610 - precreated_ost_obj_count lustre-OST0000-osc-MDT0000 prealloc_last_id: 2881 prealloc_next_id: 2851 count: 31 total: 47 open/close in 0.92 seconds: 51.22 ops/second touch: setting times of '/mnt/lustre/d14a.sanity-lfsck/guard0': No such file or directory touch: setting times of '/mnt/lustre/d14a.sanity-lfsck/guard1': No such file or directory fail_loc=0 debug=-1 debug_mb=150 debug=-1 debug_mb=150 - precreated_ost_obj_count lustre-OST0000-osc-MDT0000 prealloc_last_id: 2945 prealloc_next_id: 2916 count: 30 total: 30 open/close in 1.00 seconds: 30.13 ops/second 'ls' should fail because of dangling referenced MDT-object Trigger layout LFSCK to find out dangling reference Started LFSCK on the device lustre-MDT0000: scrub layout 'stat' should fail because of not repair dangling by default Trigger layout LFSCK to repair dangling reference Started LFSCK on the device lustre-MDT0000: scrub layout 'stat' should success after layout LFSCK repairing debug_mb=21 debug_mb=21 stopall to cleanup object cache setupall /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1049: echo: write error: Device or resource busy oleg424-server: oleg424-server.virtnet: executing load_modules_local oleg424-server: /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1049: echo: write error: Device or resource busy oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 Using TIMEOUT=20 PASS 14a (159s) == sanity-lfsck test 14b: LFSCK can repair MDT-object with dangling LOV EA reference (2) ========================================================== 09:04:45 (1787835885) ##### The OST-object referenced by the MDT-object should be there; otherwise, the LFSCK should re-create the missing OST-object. with '--delay-create-ostobj' option. ##### Inject failure stub to simulate dangling referenced MDT-object fail_loc=0x1610 - precreated_ost_obj_count lustre-OST0000-osc-MDT0000 prealloc_last_id: 3009 prealloc_next_id: 2978 count: 32 total: 63 open/close in 1.12 seconds: 56.30 ops/second touch: setting times of '/mnt/lustre/d14b.sanity-lfsck/guard': No such file or directory fail_loc=0 debug=-1 debug_mb=150 debug=-1 debug_mb=150 - precreated_ost_obj_count lustre-OST0000-osc-MDT0000 prealloc_last_id: 3073 prealloc_next_id: 3042 count: 32 total: 32 open/close in 0.98 seconds: 32.54 ops/second 'ls' should fail because of dangling referenced MDT-object Trigger layout LFSCK to find out dangling reference Started LFSCK on the device lustre-MDT0000: scrub layout 'stat' should fail because of not repair dangling by default Trigger layout LFSCK to repair dangling reference Started LFSCK on the device lustre-MDT0000: scrub layout 'stat' should success after layout LFSCK repairing debug_mb=21 debug_mb=21 stopall to cleanup object cache setupall /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1049: echo: write error: Device or resource busy oleg424-server: oleg424-server.virtnet: executing load_modules_local oleg424-server: /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1049: echo: write error: Device or resource busy oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 Using TIMEOUT=20 PASS 14b (140s) == sanity-lfsck test 15a: LFSCK can repair unmatched MDT-object/OST-object pairs (1) ========================================================== 09:07:06 (1787836026) ##### If the OST-object referenced by the MDT-object back points to some non-exist MDT-object, then the LFSCK should repair the OST-object to back point to the right MDT-object. ##### Inject failure stub to make the OST-object to back point to non-exist MDT-object. fail_loc=0x1611 1+0 records in 1+0 records out 1048576 bytes (1.0 MB, 1.0 MiB) copied, 0.0763158 s, 13.7 MB/s 257+0 records in 257+0 records out 1052672 bytes (1.1 MB, 1.0 MiB) copied, 0.128994 s, 8.2 MB/s fail_loc=0 Trigger layout LFSCK to find out unmatched pairs and fix them Started LFSCK on the device lustre-MDT0000: scrub layout PASS 15a (16s) == sanity-lfsck test 15b: LFSCK can repair unmatched MDT-object/OST-object pairs (2) ========================================================== 09:07:22 (1787836042) ##### If the OST-object referenced by the MDT-object back points to other MDT-object that doesn't recognize the OST-object, then the LFSCK should repair it to back point to the right MDT-object (the first one). ##### 1+0 records in 1+0 records out 1048576 bytes (1.0 MB, 1.0 MiB) copied, 0.0248069 s, 42.3 MB/s Inject failure stub to make the OST-object to back point to other MDT-object fail_loc=0x1612 1+0 records in 1+0 records out 1048576 bytes (1.0 MB, 1.0 MiB) copied, 0.102138 s, 10.3 MB/s 2+0 records in 2+0 records out 2097152 bytes (2.1 MB, 2.0 MiB) copied, 0.199837 s, 10.5 MB/s fail_loc=0 Trigger layout LFSCK to find out unmatched pairs and fix them Started LFSCK on the device lustre-MDT0000: scrub layout PASS 15b (15s) == sanity-lfsck test 15c: LFSCK can repair unmatched MDT-object/OST-object pairs (3) ========================================================== 09:07:37 (1787836057) SKIP: sanity-lfsck test_15c needs >= 2 MDTs SKIP 15c (3s) == sanity-lfsck test 15d: LFSCK don't crash upon dir migration failure ========================================================== 09:07:40 (1787836060) SKIP: sanity-lfsck test_15d needs >= 2 MDTs SKIP 15d (4s) == sanity-lfsck test 16: LFSCK can repair inconsistent MDT-object/OST-object owner ========================================================== 09:07:45 (1787836065) ##### If the OST-object's owner information does not match the owner information stored in the MDT-object, then the LFSCK trust the MDT-object and update the OST-object's owner information. ##### 1+0 records in 1+0 records out 1048576 bytes (1.0 MB, 1.0 MiB) copied, 0.0657363 s, 16.0 MB/s running as uid/gid/euid/egid 500/500/500/500, groups: 500 [createmany] [-o] [/mnt/lustre/d16.sanity-lfsck/d1/o] [100] total: 100 open/close in 1.88 seconds: 53.25 ops/second Inject failure stub to skip OST-object owner changing fail_loc=0x1613 fail_loc=0 Trigger layout LFSCK to find out inconsistent OST-object owner and fix them Started LFSCK on the device lustre-MDT0000: scrub layout PASS 16 (16s) == sanity-lfsck test 17: LFSCK can repair multiple references ========================================================== 09:08:00 (1787836080) ##### If more than one MDT-objects reference the same OST-object, and the OST-object only recognizes one MDT-object, then the LFSCK should create new OST-objects for such non-recognized MDT-objects. ##### Inject failure stub to make two MDT-objects to refernce the OST-object fail_val=0 fail_loc=0x1614 1+0 records in 1+0 records out 1048576 bytes (1.0 MB, 1.0 MiB) copied, 0.0706264 s, 14.8 MB/s total: 1 open/close in 0.04 seconds: 22.55 ops/second fail_loc=0 fail_val=0 /mnt/lustre/d17.sanity-lfsck/f0 and /mnt/lustre/d17.sanity-lfsck/guard use the same OST-objects /mnt/lustre/d17.sanity-lfsck/f1 and /mnt/lustre/d17.sanity-lfsck/guard use the same OST-objects Trigger layout LFSCK to find out multiple refenced MDT-objects and fix them Started LFSCK on the device lustre-MDT0000: scrub layout /mnt/lustre/d17.sanity-lfsck/f0 and /mnt/lustre/d17.sanity-lfsck/guard should use diff OST-objects 2+0 records in 2+0 records out 2097152 bytes (2.1 MB, 2.0 MiB) copied, 0.0776241 s, 27.0 MB/s /mnt/lustre/d17.sanity-lfsck/f1 and /mnt/lustre/d17.sanity-lfsck/guard should use diff OST-objects 2+0 records in 2+0 records out 2097152 bytes (2.1 MB, 2.0 MiB) copied, 0.0412564 s, 50.8 MB/s PASS 17 (16s) == sanity-lfsck test 18a: Find out orphan OST-object and repair it (1) ========================================================== 09:08:16 (1787836096) ##### The target MDT-object is there, but related stripe information is lost or partly lost. The LFSCK should regenerate the missing layout EA entries. ##### 2+0 records in 2+0 records out 2097152 bytes (2.1 MB, 2.0 MiB) copied, 0.128378 s, 16.3 MB/s [0x200003ab1:0x80:0x0] /mnt/lustre/d18a.sanity-lfsck/a1/f1 lmm_stripe_count: 1 lmm_stripe_size: 4194304 lmm_pattern: raid0 lmm_layout_gen: 0 lmm_stripe_offset: 0 obdidx objid objid group 0 3217 0xc91 0x240000400 2+0 records in 2+0 records out 2097152 bytes (2.1 MB, 2.0 MiB) copied, 0.0919978 s, 22.8 MB/s [0x200003ab1:0x81:0x0] /mnt/lustre/d18a.sanity-lfsck/f3 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: [0x240000400:0xc92:0x0] } lcme_id: 2 lcme_mirror_id: 0 lcme_flags: init lcme_extent.e_start: 1048576 lcme_extent.e_end: EOF lmm_stripe_count: 1 lmm_stripe_size: 1048576 lmm_pattern: raid0 lmm_layout_gen: 0 lmm_stripe_offset: 1 lmm_objects: - 0: { l_ost_idx: 1, l_fid: [0x280000400:0xae6:0x0] } Inject failure, to make the MDT-object lost its layout EA fail_loc=0x1615 fail_loc=0 The file size should be incorrect since layout EA is lost Trigger layout LFSCK on all devices to find out orphan OST-object Started LFSCK on the device lustre-MDT0000: scrub layout [0x200003ab1:0x80:0x0] /mnt/lustre/d18a.sanity-lfsck/a1/f1 lmm_stripe_count: 1 lmm_stripe_size: 4194304 lmm_pattern: raid0 lmm_layout_gen: 1 lmm_stripe_offset: 0 obdidx objid objid group 0 3217 0xc91 0x240000400 [0x200003ab1:0x81:0x0] /mnt/lustre/d18a.sanity-lfsck/f3 lcm_layout_gen: 1 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: 1 lmm_stripe_offset: 0 lmm_objects: - 0: { l_ost_idx: 0, l_fid: [0x240000400:0xc92:0x0] } lcme_id: 2 lcme_mirror_id: 0 lcme_flags: init lcme_extent.e_start: 1048576 lcme_extent.e_end: EOF lmm_stripe_count: 1 lmm_stripe_size: 1048576 lmm_pattern: raid0 lmm_layout_gen: 1 lmm_stripe_offset: 1 lmm_objects: - 0: { l_ost_idx: 1, l_fid: [0x280000400:0xae6:0x0] } The file size should be correct after layout LFSCK scanning PASS 18a (19s) SKIP: sanity-lfsck test_18b skipping excluded test 18b == sanity-lfsck test 18c: Find out orphan OST-object and repair it (3) ========================================================== 09:08:37 (1787836117) ##### The target MDT-object is lost, and the OST-object FID is missing. The LFSCK should re-create the MDT-object with new FID under the directory .lustre/lost+found/MDTxxxx. ##### Inject failure, to simulate the case of missing parent FID fail_loc=0x1617 2+0 records in 2+0 records out 2097152 bytes (2.1 MB, 2.0 MiB) copied, 0.123243 s, 17.0 MB/s /mnt/lustre/d18c.sanity-lfsck/a1/f1 lmm_stripe_count: 1 lmm_stripe_size: 4194304 lmm_pattern: raid0 lmm_layout_gen: 0 lmm_stripe_offset: 0 obdidx objid objid group 0 3219 0xc93 0x240000400 2+0 records in 2+0 records out 2097152 bytes (2.1 MB, 2.0 MiB) copied, 0.231973 s, 9.0 MB/s /mnt/lustre/d18c.sanity-lfsck/f3 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: [0x240000400:0xc94:0x0] } lcme_id: 2 lcme_mirror_id: 0 lcme_flags: init lcme_extent.e_start: 1048576 lcme_extent.e_end: EOF lmm_stripe_count: 1 lmm_stripe_size: 1048576 lmm_pattern: raid0 lmm_layout_gen: 0 lmm_stripe_offset: 1 lmm_objects: - 0: { l_ost_idx: 1, l_fid: [0x280000400:0xae7:0x0] } fail_loc=0 Inject failure, to simulate the case of missing the MDT-object fail_loc=0x1616 fail_loc=0 Trigger layout LFSCK on all devices to find out orphan OST-object Started LFSCK on the device lustre-MDT0000: scrub layout total 13 144115188109410307 dr-x------ 3 root root 6656 Dec 31 1969 . 144115205289279489 drwx------ 2 root root 6656 Aug 27 08:48 MDT0000 There should NOT be some stub under .lustre/lost+found/MDT0001/ There should be some stub under .lustre/lost+found/MDT0000/ PASS 18c (22s) == sanity-lfsck test 18d: Find out orphan OST-object and repair it (4) ========================================================== 09:08:59 (1787836139) ##### The target MDT-object layout EA is corrupted, but the right OST-object is still alive as orphan. The layout LFSCK will not create new OST-object to occupy such slot. ##### [0x200003ab1:0x8c:0x0] /mnt/lustre/d18d.sanity-lfsck/a1/f1 lmm_stripe_count: 1 lmm_stripe_size: 4194304 lmm_pattern: raid0 lmm_layout_gen: 0 lmm_stripe_offset: 0 obdidx objid objid group 0 3221 0xc95 0x240000400 [0x200003ab1:0x8d:0x0] /mnt/lustre/d18d.sanity-lfsck/a1/f2 lmm_stripe_count: 1 lmm_stripe_size: 4194304 lmm_pattern: raid0 lmm_layout_gen: 0 lmm_stripe_offset: 0 obdidx objid objid group 0 3222 0xc96 0x240000400 [0x200003ab1:0x8e:0x0] /mnt/lustre/d18d.sanity-lfsck/a1/f3 lmm_stripe_count: 1 lmm_stripe_size: 4194304 lmm_pattern: raid0 lmm_layout_gen: 0 lmm_stripe_offset: 0 obdidx objid objid group 0 3223 0xc97 0x240000400 [0x200003ab1:0x8f:0x0] /mnt/lustre/d18d.sanity-lfsck/a1/f4 lcm_layout_gen: 2 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: [0x240000400:0xc98:0x0] } lcme_id: 2 lcme_mirror_id: 0 lcme_flags: 0 lcme_extent.e_start: 1048576 lcme_extent.e_end: EOF lmm_stripe_count: 1 lmm_stripe_size: 1048576 lmm_pattern: raid0 lmm_layout_gen: 0 lmm_stripe_offset: -1 Inject failure to make /mnt/lustre/d18d.sanity-lfsck/a1/f1 and /mnt/lustre/d18d.sanity-lfsck/a1/f2 to reference the same OST-object (which is f1's OST-object). Then drop /mnt/lustre/d18d.sanity-lfsck/a1/f1 and its OST-object, so f2 becomes dangling reference case, but f2's old OST-object is there. The failure also makes /mnt/lustre/d18d.sanity-lfsck/a1/f3 and /mnt/lustre/d18d.sanity-lfsck/a1/f4 to reference the same OST-object (which is f3's OST-object). Then drop /mnt/lustre/d18d.sanity-lfsck/a1/f3 and its OST-object, so f4 becomes dangling reference case, but f4's old OST-object is there. fail_loc=0x1618 fail_loc=0 stopall to cleanup object cache setupall /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1049: echo: write error: Device or resource busy oleg424-server: oleg424-server.virtnet: executing load_modules_local oleg424-server: /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1049: echo: write error: Device or resource busy oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 Using TIMEOUT=20 Trigger layout LFSCK on all devices to find out orphan OST-object Started LFSCK on the device lustre-MDT0000: scrub layout The file size should be correct after layout LFSCK scanning The LFSCK should find back the original data. foo [0x200003ab1:0x8d:0x0] /mnt/lustre/d18d.sanity-lfsck/a1/f2 lmm_stripe_count: 1 lmm_stripe_size: 4194304 lmm_pattern: raid0 lmm_layout_gen: 1 lmm_stripe_offset: 0 obdidx objid objid group 0 3222 0xc96 0x240000400 foo [0x200003ab1:0x8f:0x0] /mnt/lustre/d18d.sanity-lfsck/a1/f4 lcm_layout_gen: 2 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: 1 lmm_stripe_offset: 0 lmm_objects: - 0: { l_ost_idx: 0, l_fid: [0x240000400:0xc98:0x0] } lcme_id: 2 lcme_mirror_id: 0 lcme_flags: 0 lcme_extent.e_start: 1048576 lcme_extent.e_end: EOF lmm_stripe_count: 1 lmm_stripe_size: 1048576 lmm_pattern: raid0 lmm_layout_gen: 0 lmm_stripe_offset: -1 PASS 18d (144s) == sanity-lfsck test 18e: Find out orphan OST-object and repair it (5) ========================================================== 09:11:24 (1787836284) ##### The target MDT-object layout EA slot is occpuied by some new created OST-object when repair dangling reference case. Such conflict OST-object has been modified by others. To keep the new data, the LFSCK will create a new file to refernece this old orphan OST-object. ##### [0x200004281:0x4:0x0] /mnt/lustre/d18e.sanity-lfsck/a1/f1 lmm_stripe_count: 1 lmm_stripe_size: 4194304 lmm_pattern: raid0 lmm_layout_gen: 0 lmm_stripe_offset: 0 obdidx objid objid group 0 3266 0xcc2 0x240000400 [0x200004281:0x5:0x0] /mnt/lustre/d18e.sanity-lfsck/a1/f2 lmm_stripe_count: 1 lmm_stripe_size: 4194304 lmm_pattern: raid0 lmm_layout_gen: 0 lmm_stripe_offset: 0 obdidx objid objid group 0 3267 0xcc3 0x240000400 [0x200004281:0x6:0x0] /mnt/lustre/d18e.sanity-lfsck/a1/f3 lmm_stripe_count: 1 lmm_stripe_size: 4194304 lmm_pattern: raid0 lmm_layout_gen: 0 lmm_stripe_offset: 0 obdidx objid objid group 0 3268 0xcc4 0x240000400 [0x200004281:0x7:0x0] /mnt/lustre/d18e.sanity-lfsck/a1/f4 lcm_layout_gen: 2 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: [0x240000400:0xcc5:0x0] } lcme_id: 2 lcme_mirror_id: 0 lcme_flags: 0 lcme_extent.e_start: 1048576 lcme_extent.e_end: EOF lmm_stripe_count: 1 lmm_stripe_size: 1048576 lmm_pattern: raid0 lmm_layout_gen: 0 lmm_stripe_offset: -1 Inject failure to make /mnt/lustre/d18e.sanity-lfsck/a1/f1 and /mnt/lustre/d18e.sanity-lfsck/a1/f2 to reference the same OST-object (which is f1's OST-object). Then drop /mnt/lustre/d18e.sanity-lfsck/a1/f1 and its OST-object, so f2 becomes dangling reference case, but f2's old OST-object is there. Also the failure makes /mnt/lustre/d18e.sanity-lfsck/a1/f3 and /mnt/lustre/d18e.sanity-lfsck/a1/f4 to reference the same OST-object (which is f3's OST-object). Then drop /mnt/lustre/d18e.sanity-lfsck/a1/f3 and its OST-object, so f4 becomes dangling reference case, but f4's old OST-object is there. fail_loc=0x1618 fail_loc=0 stopall to cleanup object cache setupall /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1049: echo: write error: Device or resource busy oleg424-server: oleg424-server.virtnet: executing load_modules_local oleg424-server: /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1049: echo: write error: Device or resource busy oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 oleg424-server: oleg424-server.virtnet: executing set_default_debug vfstrace rpctrace dlmtrace neterror ha config ioctl super lfsck all pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 Using TIMEOUT=20 fail_val=10 fail_loc=0x1602 debug=-1 debug_mb=150 debug=-1 debug_mb=150 Trigger layout LFSCK on all devices to find out orphan OST-object Started LFSCK on the device lustre-MDT0000: scrub layout Write new data to f2/f4 to modify the new created OST-object. fail_val=0 fail_loc=0 Waiting 120s for 'completed' Updated after 7s: want 'completed' got 'completed' debug_mb=21 debug_mb=21 There should be stub file under .lustre/lost+found/MDT0000/ The stub file should keep the original f2 or f4 data foo [0x200000402:0x5:0x0] /mnt/lustre/.lustre/lost+found/MDT0000/[0x200000402:0x5:0x0]-[0x200004281:0x5:0x0]-0-C-0 lmm_stripe_count: 1 lmm_stripe_size: 4194304 lmm_pattern: raid0 lmm_layout_gen: 1 lmm_stripe_offset: 0 obdidx objid objid group 0 3267 0xcc3 0x240000400 foo [0x200000402:0x6:0x0] /mnt/lustre/.lustre/lost+found/MDT0000/[0x200000402:0x6:0x0]-[0x200004281:0x7:0x0]-0-C-0 lcm_layout_gen: 3 lcm_mirror_count: 1 lcm_entry_count: 1 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: 1 lmm_stripe_offset: 0 lmm_objects: - 0: { l_ost_idx: 0, l_fid: [0x240000400:0xcc5:0x0] } The f2/f4 should contains new data. dummy [0x200004281:0x5:0x0] /mnt/lustre/d18e.sanity-lfsck/a1/f2 lmm_stripe_count: 1 lmm_stripe_size: 4194304 lmm_pattern: raid0 lmm_layout_gen: 0 lmm_stripe_offset: 0 obdidx objid objid group 0 3266 0xcc2 0x240000400 dummy [0x200004281:0x7:0x0] /mnt/lustre/d18e.sanity-lfsck/a1/f4 lcm_layout_gen: 2 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: [0x240000400:0xcc4:0x0] } lcme_id: 2 lcme_mirror_id: 0 lcme_flags: 0 lcme_extent.e_start: 1048576 lcme_extent.e_end: EOF lmm_stripe_count: 1 lmm_stripe_size: 1048576 lmm_pattern: raid0 lmm_layout_gen: 0 lmm_stripe_offset: -1 PASS 18e (175s) == sanity-lfsck test 18f: Skip the failed OST(s) when handle orphan OST-objects ========================================================== 09:14:19 (1787836459) ##### The target MDT-object is lost. The LFSCK should re-create the MDT-object under .lustre/lost+found/MDTxxxx. If some OST fail to verify some OST-object(s) during the first stage-scanning, the LFSCK should skip orphan OST-objects for such OST. Others should not be affected. ##### 2+0 records in 2+0 records out 2097152 bytes (2.1 MB, 2.0 MiB) copied, 0.116175 s, 18.1 MB/s 2+0 records in 2+0 records out 2097152 bytes (2.1 MB, 2.0 MiB) copied, 0.0879223 s, 23.9 MB/s 2+0 records in 2+0 records out 2097152 bytes (2.1 MB, 2.0 MiB) copied, 0.123652 s, 17.0 MB/s /mnt/lustre/d18f.sanity-lfsck/a1/f1 lmm_stripe_count: 1 lmm_stripe_size: 4194304 lmm_pattern: raid0 lmm_layout_gen: 0 lmm_stripe_offset: 0 obdidx objid objid group 0 3299 0xce3 0x240000400 /mnt/lustre/d18f.sanity-lfsck/a2/f2 lmm_stripe_count: 2 lmm_stripe_size: 1048576 lmm_pattern: raid0 lmm_layout_gen: 0 lmm_stripe_offset: 0 obdidx objid objid group 0 3300 0xce4 0x240000400 1 2850 0xb22 0x280000400 Inject failure, to simulate the case of missing the MDT-object fail_loc=0x1616 fail_loc=0 Inject failure, to simulate the OST0 fail to handle MDT0 LFSCK request during the first-stage scanning. fail_loc=0x161c fail_val=0 Trigger layout LFSCK on all devices to find out orphan OST-object Started LFSCK on the device lustre-MDT0000: scrub layout fail_loc=0 fail_val=0 Trigger layout LFSCK on all devices again to cleanup Started LFSCK on the device lustre-MDT0000: scrub layout PASS 18f (28s) == sanity-lfsck test 18g: Find out orphan OST-object and repair it (7) ========================================================== 09:14:47 (1787836487) ##### The target MDT-object is lost, but related OI mapping is there The LFSCK should recreate the lost MDT-object without affected by the stale OI mapping. ##### 2+0 records in 2+0 records out 2097152 bytes (2.1 MB, 2.0 MiB) copied, 0.0680706 s, 30.8 MB/s [0x200004a51:0xe:0x0] /mnt/lustre/d18g.sanity-lfsck/a1/f1 lmm_stripe_count: 2 lmm_stripe_size: 1048576 lmm_pattern: raid0 lmm_layout_gen: 0 lmm_stripe_offset: 0 obdidx objid objid group 0 3301 0xce5 0x240000400 1 2851 0xb23 0x280000400 Inject failure to simulate lost MDT-object but keep OI mapping fail_loc=0x162e fail_loc=0 Trigger layout LFSCK on all devices to find out orphan OST-object Started LFSCK on the device lustre-MDT0000: scrub layout Move the files from ./lustre/lost+found/MDTxxxx to namespace [0x200004a51:0xe:0x0] /mnt/lustre/d18g.sanity-lfsck/a1/f1 lmm_stripe_count: 2 lmm_stripe_size: 1048576 lmm_pattern: raid0 lmm_layout_gen: 2 lmm_stripe_offset: 0 obdidx objid objid group 0 3301 0xce5 0x240000400 1 2851 0xb23 0x280000400 PASS 18g (18s) == sanity-lfsck test 18h: LFSCK can repair crashed PFL extent range ========================================================== 09:15:05 (1787836505) ##### The PFL extent crashed. During the first cycle LFSCK scanning, the layout LFSCK will keep the bad PFL file(s) there without scanning its OST-object(s). Then in the second stage scanning, the OST will return related OST-object(s) to the MDT as orphan. And then the LFSCK on the MDT can rebuild the PFL extent with the 'orphan(s)' stripe information. ##### 0+1 records in 0+1 records out 319248 bytes (319 kB, 312 KiB) copied, 0.0163847 s, 19.5 MB/s Inject failure stub to simulate bad PFL extent range fail_loc=0x162f fail_loc=0 dd: error writing '/mnt/lustre/d18h.sanity-lfsck/f0': No data available 1+0 records in 0+0 records out 0 bytes copied, 0.0209383 s, 0.0 kB/s Trigger layout LFSCK to find out the bad lmm_oi and fix them Started LFSCK on the device lustre-MDT0000: scrub layout Data in /mnt/lustre/d18h.sanity-lfsck/f0 should not be broken Write should succeed after LFSCK repairing the bad PFL range 1+0 records in 1+0 records out 1048576 bytes (1.0 MB, 1.0 MiB) copied, 0.0205873 s, 50.9 MB/s PASS 18h (24s) == sanity-lfsck test 18i: LFSCK can repair crashed PFL with compression ========================================================== 09:15:29 (1787836529) WARNING: (-Z) option specified, however no layout defined (-E), compression feature will not be enabled.