-----============= acceptance-small: replay-dual ============----- Thu Aug 27 08:53:53 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 oleg251-server: ls: cannot access '/home/green/git/lustre-release/lustre/tests/except/replay-dual.*ex': No such file or directory excepting tests: 14b 21b 21b skipping tests SLOW=no: 21b === replay-dual: start setup 08:54:15 (1787835255) === Starting client oleg251-client.virtnet: -o user_xattr,flock 192.168.202.151@tcp:/lustre /mnt/lustre2 Mount client oleg251-client.virtnet: mount -t lustre -o user_xattr,flock 192.168.202.151@tcp:/lustre /mnt/lustre2 Started clients oleg251-client.virtnet: 192.168.202.151@tcp:/lustre on /mnt/lustre2 type lustre (rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose) oleg251-client.virtnet: executing check_config_client /mnt/lustre oleg251-client.virtnet: Checking config lustre mounted on /mnt/lustre Checking servers environments Checking clients oleg251-client.virtnet environments Using TIMEOUT=20 osc.lustre-OST0000-osc-ffff8b4403856000.idle_timeout=debug osc.lustre-OST0000-osc-ffff8b44118ad000.idle_timeout=debug osc.lustre-OST0001-osc-ffff8b4403856000.idle_timeout=debug osc.lustre-OST0001-osc-ffff8b44118ad000.idle_timeout=debug disable quota as required oleg251-server: oleg251-server.virtnet: executing set_default_debug -1 all === replay-dual: finish setup 08:54:52 (1787835292) === == replay-dual test 0a: expired recovery with lost client ========================================================== 08:54:54 (1787835294) Check file is LU482_FAILED=/tmp/replay-dual.lu482.CL7E69 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210688 2048 2206592 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 4096 7534592 1% /mnt/lustre total: 50 open/close in 2.14 seconds: 23.39 ops/second fail_loc=0x80000514 Failing mds1 on oleg251-server Stopping /mnt/lustre-mds1 (opts:) on oleg251-server 08:55:08 (1787835308) shut down facet: mds1 facet_host: oleg251-server facet_failover_host: oleg251-server Failover mds1 to oleg251-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg251-server: oleg251-server.virtnet: executing set_default_debug -1 all pdsh@oleg251-client: oleg251-server: ssh exited with exit code 1 Started lustre-MDT0000 08:55:43 (1787835343) targets are mounted 08:55:43 (1787835343) facet_failover done Starting client: oleg251-client.virtnet: -o user_xattr,flock 192.168.202.151@tcp:/lustre /mnt/lustre2 - unlinked 0 (time 1787835451 ; total 0 ; last 0) total: 50 unlinks in 2 seconds: 25.000000 unlinks/second PASS 0a (165s) == replay-dual test 0b: lost client during waiting for next transno ========================================================== 08:57:39 (1787835459) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210688 2048 2206592 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 4096 7534592 1% /mnt/lustre Failing mds1 on oleg251-server Stopping /mnt/lustre-mds1 (opts:) on oleg251-server 08:57:50 (1787835470) shut down facet: mds1 facet_host: oleg251-server facet_failover_host: oleg251-server Failover mds1 to oleg251-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg251-server: oleg251-server.virtnet: executing set_default_debug -1 all pdsh@oleg251-client: oleg251-server: ssh exited with exit code 1 Started lustre-MDT0000 08:58:25 (1787835505) targets are mounted 08:58:25 (1787835505) facet_failover done Starting client: oleg251-client.virtnet: -o user_xattr,flock 192.168.202.151@tcp:/lustre /mnt/lustre Starting client: oleg251-client.virtnet: -o user_xattr,flock 192.168.202.151@tcp:/lustre /mnt/lustre2 PASS 0b (217s) == replay-dual test 1: |X| simple create ================= 09:01:16 (1787835676) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210688 2048 2206592 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 4096 7534592 1% /mnt/lustre Failing mds1 on oleg251-server Stopping /mnt/lustre-mds1 (opts:) on oleg251-server 09:01:27 (1787835687) shut down facet: mds1 facet_host: oleg251-server facet_failover_host: oleg251-server Failover mds1 to oleg251-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg251-server: oleg251-server.virtnet: executing set_default_debug -1 all pdsh@oleg251-client: oleg251-server: ssh exited with exit code 1 Started lustre-MDT0000 09:01:51 (1787835711) targets are mounted 09:01:51 (1787835711) facet_failover done oleg251-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 1 (56s) == replay-dual test 2: |X| mkdir adir ==================== 09:02:12 (1787835732) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210688 2048 2206592 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 4096 7534592 1% /mnt/lustre Failing mds1 on oleg251-server Stopping /mnt/lustre-mds1 (opts:) on oleg251-server 09:02:27 (1787835747) shut down facet: mds1 facet_host: oleg251-server facet_failover_host: oleg251-server Failover mds1 to oleg251-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg251-server: oleg251-server.virtnet: executing set_default_debug -1 all pdsh@oleg251-client: oleg251-server: ssh exited with exit code 1 Started lustre-MDT0000 09:02:53 (1787835773) targets are mounted 09:02:53 (1787835773) facet_failover done oleg251-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 2 (59s) == replay-dual test 3: |X| mkdir adir, mkdir adir/bdir === 09:03:11 (1787835791) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210688 2048 2206592 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 4096 7534592 1% /mnt/lustre Failing mds1 on oleg251-server Stopping /mnt/lustre-mds1 (opts:) on oleg251-server 09:03:22 (1787835802) shut down facet: mds1 facet_host: oleg251-server facet_failover_host: oleg251-server Failover mds1 to oleg251-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg251-server: oleg251-server.virtnet: executing set_default_debug -1 all pdsh@oleg251-client: oleg251-server: ssh exited with exit code 1 Started lustre-MDT0000 09:03:57 (1787835837) targets are mounted 09:03:57 (1787835837) facet_failover done oleg251-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 3 (65s) == replay-dual test 4: |X| mkdir adir (-EEXIST), mkdir adir/bdir ========================================================== 09:04:16 (1787835856) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210688 2048 2206592 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 4096 7534592 1% /mnt/lustre mkdir: cannot create directory '/mnt/lustre/adir': File exists Failing mds1 on oleg251-server Stopping /mnt/lustre-mds1 (opts:) on oleg251-server 09:04:26 (1787835866) shut down facet: mds1 facet_host: oleg251-server facet_failover_host: oleg251-server Failover mds1 to oleg251-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg251-server: oleg251-server.virtnet: executing set_default_debug -1 all pdsh@oleg251-client: oleg251-server: ssh exited with exit code 1 Started lustre-MDT0000 09:04:51 (1787835891) targets are mounted 09:04:51 (1787835891) facet_failover done oleg251-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 4 (52s) == replay-dual test 5: open, unlink |X| close ============ 09:05:08 (1787835908) multiop /mnt/lustre2/a vo_tSc TMPPIPE=/tmp/multiop_open_wait_pipe.7627 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210688 2048 2206592 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 4096 7534592 1% /mnt/lustre Failing mds1 on oleg251-server Stopping /mnt/lustre-mds1 (opts:) on oleg251-server 09:05:20 (1787835920) shut down facet: mds1 facet_host: oleg251-server facet_failover_host: oleg251-server Failover mds1 to oleg251-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg251-server: oleg251-server.virtnet: executing set_default_debug -1 all pdsh@oleg251-client: oleg251-server: ssh exited with exit code 1 Started lustre-MDT0000 09:05:56 (1787835956) targets are mounted 09:05:56 (1787835956) facet_failover done oleg251-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 5 (65s) == replay-dual test 6: open1, open2, unlink |X| close1 [fail mds1] close2 ========================================================== 09:06:13 (1787835973) multiop /mnt/lustre2/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.7627 multiop /mnt/lustre/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.7627 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210688 2048 2206592 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 4096 7534592 1% /mnt/lustre Failing mds1 on oleg251-server Stopping /mnt/lustre-mds1 (opts:) on oleg251-server 09:06:24 (1787835984) shut down facet: mds1 facet_host: oleg251-server facet_failover_host: oleg251-server Failover mds1 to oleg251-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg251-server: oleg251-server.virtnet: executing set_default_debug -1 all pdsh@oleg251-client: oleg251-server: ssh exited with exit code 1 Started lustre-MDT0000 09:06:59 (1787836019) targets are mounted 09:06:59 (1787836019) facet_failover done oleg251-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 6 (68s) == replay-dual test 8: replay of resent request ========== 09:07:21 (1787836041) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210688 2048 2206592 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 4096 7534592 1% /mnt/lustre fail_loc=0x119 fail_loc=0 Failing mds1 on oleg251-server Stopping /mnt/lustre-mds1 (opts:) on oleg251-server 09:07:52 (1787836072) shut down facet: mds1 facet_host: oleg251-server facet_failover_host: oleg251-server Failover mds1 to oleg251-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg251-server: oleg251-server.virtnet: executing set_default_debug -1 all pdsh@oleg251-client: oleg251-server: ssh exited with exit code 1 Started lustre-MDT0000 09:08:23 (1787836103) targets are mounted 09:08:23 (1787836103) facet_failover done oleg251-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 8 (86s) == replay-dual test 9: resending a replayed create ======= 09:08:48 (1787836128) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210688 2048 2206592 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 4096 7534592 1% /mnt/lustre fail_loc=0x80000119 Failing mds1 on oleg251-server Stopping /mnt/lustre-mds1 (opts:) on oleg251-server 09:09:00 (1787836140) shut down facet: mds1 facet_host: oleg251-server facet_failover_host: oleg251-server Failover mds1 to oleg251-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg251-server: oleg251-server.virtnet: executing set_default_debug -1 all pdsh@oleg251-client: oleg251-server: ssh exited with exit code 1 Started lustre-MDT0000 09:09:26 (1787836166) targets are mounted 09:09:26 (1787836166) facet_failover done oleg251-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 fail_loc=0 PASS 9 (75s) == replay-dual test 10: resending a replayed unlink ====== 09:10:03 (1787836203) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210688 2048 2206592 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 4096 7534592 1% /mnt/lustre fail_loc=0x80000119 Failing mds1 on oleg251-server Stopping /mnt/lustre-mds1 (opts:) on oleg251-server 09:10:17 (1787836217) shut down facet: mds1 facet_host: oleg251-server facet_failover_host: oleg251-server Failover mds1 to oleg251-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg251-server: oleg251-server.virtnet: executing set_default_debug -1 all pdsh@oleg251-client: oleg251-server: ssh exited with exit code 1 Started lustre-MDT0000 09:10:54 (1787836254) targets are mounted 09:10:54 (1787836254) facet_failover done oleg251-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 fail_loc=0 PASS 10 (90s) == replay-dual test 11: both clients timeout during replay ========================================================== 09:11:33 (1787836293) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210688 2048 2206592 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 4096 7534592 1% /mnt/lustre fail_loc=0x0119 Failing mds1 on oleg251-server Stopping /mnt/lustre-mds1 (opts:) on oleg251-server 09:11:46 (1787836306) shut down facet: mds1 facet_host: oleg251-server facet_failover_host: oleg251-server Failover mds1 to oleg251-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg251-server: oleg251-server.virtnet: executing set_default_debug -1 all pdsh@oleg251-client: oleg251-server: ssh exited with exit code 1 Started lustre-MDT0000 09:12:11 (1787836331) targets are mounted 09:12:11 (1787836331) facet_failover done oleg251-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 9 sec fail_loc=0 PASS 11 (63s) == replay-dual test 12: open resend timeout ============== 09:12:36 (1787836356) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210688 2048 2206592 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 4096 7534592 1% /mnt/lustre multiop /mnt/lustre/f12.replay-dual vmo_c TMPPIPE=/tmp/multiop_open_wait_pipe.7627 fail_loc=0x80000302 Failing mds1 on oleg251-server Stopping /mnt/lustre-mds1 (opts:) on oleg251-server 09:12:50 (1787836370) shut down facet: mds1 facet_host: oleg251-server facet_failover_host: oleg251-server Failover mds1 to oleg251-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg251-server: oleg251-server.virtnet: executing set_default_debug -1 all pdsh@oleg251-client: oleg251-server: ssh exited with exit code 1 Started lustre-MDT0000 09:13:27 (1787836407) targets are mounted 09:13:27 (1787836407) facet_failover done fail_loc=0 /mnt/lustre/f12.replay-dual /mnt/lustre/f12.replay-dual has type file OK PASS 12 (73s) == replay-dual test 13: close resend timeout ============= 09:13:50 (1787836430) multiop /mnt/lustre/f13.replay-dual vmo_c TMPPIPE=/tmp/multiop_open_wait_pipe.7627 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210688 2048 2206592 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 4096 7534592 1% /mnt/lustre fail_loc=0x80000115 Failing mds1 on oleg251-server Stopping /mnt/lustre-mds1 (opts:) on oleg251-server 09:14:01 (1787836441) shut down facet: mds1 facet_host: oleg251-server facet_failover_host: oleg251-server Failover mds1 to oleg251-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg251-server: oleg251-server.virtnet: executing set_default_debug -1 all pdsh@oleg251-client: oleg251-server: ssh exited with exit code 1 Started lustre-MDT0000 09:14:24 (1787836464) targets are mounted 09:14:24 (1787836464) facet_failover done fail_loc=0 /mnt/lustre/f13.replay-dual /mnt/lustre/f13.replay-dual has type file OK PASS 13 (42s) SKIP: replay-dual test_14b skipping ALWAYS excluded test 14b == replay-dual test 15a: timeout waiting for lost client during replay, 1 client completes ========================================================== 09:14:33 (1787836473) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210688 2048 2206592 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 4096 7534592 1% /mnt/lustre total: 25 open/close in 0.86 seconds: 28.95 ops/second total: 1 open/close in 0.06 seconds: 15.63 ops/second Failing mds1 on oleg251-server Stopping /mnt/lustre-mds1 (opts:) on oleg251-server 09:14:47 (1787836487) shut down facet: mds1 facet_host: oleg251-server facet_failover_host: oleg251-server Failover mds1 to oleg251-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg251-server: oleg251-server.virtnet: executing set_default_debug -1 all pdsh@oleg251-client: oleg251-server: ssh exited with exit code 1 Started lustre-MDT0000 09:15:17 (1787836517) targets are mounted 09:15:17 (1787836517) facet_failover done oleg251-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 - unlinked 0 (time 1787836604 ; total 0 ; last 0) total: 25 unlinks in 1 seconds: 25.000000 unlinks/second Starting client: oleg251-client.virtnet: -o user_xattr,flock 192.168.202.151@tcp:/lustre /mnt/lustre2 PASS 15a (138s) == replay-dual test 15c: remove multiple OST orphans ===== 09:16:51 (1787836611) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210688 2048 2206592 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 4096 7534592 1% /mnt/lustre Failing mds1 on oleg251-server Stopping /mnt/lustre-mds1 (opts:) on oleg251-server 09:19:01 (1787836741) shut down facet: mds1 facet_host: oleg251-server facet_failover_host: oleg251-server Failover mds1 to oleg251-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg251-server: oleg251-server.virtnet: executing set_default_debug -1 all pdsh@oleg251-client: oleg251-server: ssh exited with exit code 1 Started lustre-MDT0000 09:19:31 (1787836771) targets are mounted 09:19:31 (1787836771) facet_failover done oleg251-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 Starting client: oleg251-client.virtnet: -o user_xattr,flock 192.168.202.151@tcp:/lustre /mnt/lustre2 PASS 15c (244s) == replay-dual test 16: fail MDS during recovery (3571) == 09:20:55 (1787836855) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210688 2048 2206592 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 4096 7534592 1% /mnt/lustre total: 25 open/close in 1.23 seconds: 20.29 ops/second total: 1 open/close in 0.03 seconds: 36.99 ops/second Failing mds1 on oleg251-server Stopping /mnt/lustre-mds1 (opts:) on oleg251-server 09:21:08 (1787836868) shut down facet: mds1 facet_host: oleg251-server facet_failover_host: oleg251-server Failover mds1 to oleg251-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg251-server: oleg251-server.virtnet: executing set_default_debug -1 all pdsh@oleg251-client: oleg251-server: ssh exited with exit code 1 Started lustre-MDT0000 09:21:39 (1787836899) targets are mounted 09:21:39 (1787836899) facet_failover done Failing mds1 on oleg251-server Stopping /mnt/lustre-mds1 (opts:) on oleg251-server 09:22:05 (1787836925) shut down facet: mds1 facet_host: oleg251-server facet_failover_host: oleg251-server Failover mds1 to oleg251-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg251-server: oleg251-server.virtnet: executing set_default_debug -1 all pdsh@oleg251-client: oleg251-server: ssh exited with exit code 1 Started lustre-MDT0000 09:22:30 (1787836950) targets are mounted 09:22:30 (1787836950) facet_failover done oleg251-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 - unlinked 0 (time 1787837025 ; total 0 ; last 0) total: 25 unlinks in 1 seconds: 25.000000 unlinks/second Starting client: oleg251-client.virtnet: -o user_xattr,flock 192.168.202.151@tcp:/lustre /mnt/lustre2 PASS 16 (179s) == replay-dual test 17: fail OST during recovery (3571) == 09:23:54 (1787837034) total: 25 open/close in 0.93 seconds: 26.92 ops/second total: 1 open/close in 0.03 seconds: 29.12 ops/second UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210688 2048 2206592 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 4096 7534592 1% /mnt/lustre Failing ost1 on oleg251-server Stopping /mnt/lustre-ost1 (opts:) on oleg251-server 09:24:06 (1787837046) shut down facet: ost1 facet_host: oleg251-server facet_failover_host: oleg251-server Failover ost1 to oleg251-server mount facets: ost1 Start ost1: mount -t lustre -o localrecov lustre-ost1/ost1 /mnt/lustre-ost1 seq.cli-lustre-OST0000-super.width=65536 oleg251-server: oleg251-server.virtnet: executing set_default_debug -1 all pdsh@oleg251-client: oleg251-server: ssh exited with exit code 1 Started lustre-OST0000 09:24:34 (1787837074) targets are mounted 09:24:34 (1787837074) facet_failover done Failing ost1 on oleg251-server Stopping /mnt/lustre-ost1 (opts:) on oleg251-server 09:24:59 (1787837099) shut down facet: ost1 facet_host: oleg251-server facet_failover_host: oleg251-server Failover ost1 to oleg251-server mount facets: ost1 Start ost1: mount -t lustre -o localrecov lustre-ost1/ost1 /mnt/lustre-ost1 seq.cli-lustre-OST0000-super.width=65536 oleg251-server: oleg251-server.virtnet: executing set_default_debug -1 all pdsh@oleg251-client: oleg251-server: ssh exited with exit code 1 Started lustre-OST0000 09:25:25 (1787837125) targets are mounted 09:25:25 (1787837125) facet_failover done oleg251-client.virtnet: executing wait_import_state_mount (FULL|IDLE) osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid 1475 0 osc.lustre-OST0000-osc-[-0-9a-f]*.ost_server_uuid in FULL state after 0 sec - unlinked 0 (time 1787837200 ; total 0 ; last 0) total: 25 unlinks in 1 seconds: 25.000000 unlinks/second Starting client: oleg251-client.virtnet: -o user_xattr,flock 192.168.202.151@tcp:/lustre /mnt/lustre2 PASS 17 (172s) == replay-dual test 18: ldlm_handle_enqueue succeeds on evicted export (3822) ========================================================== 09:26:46 (1787837206) debug=+dlmtrace fail_loc=0x8000030b using seed 603431572 running for 500 iterations total: 500 stats in 1 seconds: 500.000000 stats/second ldlm.namespaces.MGC192.168.202.151@tcp.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffff8b4408d0e000.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffff8b4413684800.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffff8b4408d0e000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffff8b4413684800.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffff8b4408d0e000.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffff8b4413684800.early_lock_cancel=0 fail_loc=0x80000305 Error in opening file "/mnt/lustre2/d18.replay-dual/f18.replay-dual"(flags=O_RDONLY) 2: No such file or directory ldlm.namespaces.MGC192.168.202.151@tcp.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffff8b4408d0e000.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffff8b4413684800.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffff8b4408d0e000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffff8b4413684800.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffff8b4408d0e000.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffff8b4413684800.early_lock_cancel=1 fail_loc=0 fail_loc=0 PASS 18 (59s) == replay-dual test 19: resend of open request =========== 09:27:45 (1787837265) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210688 2176 2206464 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 4096 7534592 1% /mnt/lustre fail_loc=0x157 - open/close 0 (time 1787837360.04 total 87.41 last 0.00) total: 1 open/close in 87.41 seconds: 0.01 ops/second fail_loc=0 Failing mds1 on oleg251-server Stopping /mnt/lustre-mds1 (opts:) on oleg251-server 09:29:25 (1787837365) shut down facet: mds1 facet_host: oleg251-server facet_failover_host: oleg251-server Failover mds1 to oleg251-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg251-server: oleg251-server.virtnet: executing set_default_debug -1 all pdsh@oleg251-client: oleg251-server: ssh exited with exit code 1 Started lustre-MDT0000 09:29:50 (1787837390) targets are mounted 09:29:50 (1787837390) facet_failover done oleg251-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 19 (143s) == replay-dual test 20: recovery time is not increasing == 09:30:08 (1787837408) UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210688 2176 2206464 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 4096 7534592 1% /mnt/lustre Failing mds1 on oleg251-server Stopping /mnt/lustre-mds1 (opts:) on oleg251-server 09:30:20 (1787837420) shut down facet: mds1 facet_host: oleg251-server facet_failover_host: oleg251-server Failover mds1 to oleg251-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg251-server: oleg251-server.virtnet: executing set_default_debug -1 all pdsh@oleg251-client: oleg251-server: ssh exited with exit code 1 Started lustre-MDT0000 09:30:53 (1787837453) targets are mounted 09:30:53 (1787837453) facet_failover done oleg251-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 Starting client: oleg251-client.virtnet: -o user_xattr,flock 192.168.202.151@tcp:/lustre /mnt/lustre2 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210688 2176 2206464 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3767296 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 4096 7534592 1% /mnt/lustre Failing mds1 on oleg251-server Stopping /mnt/lustre-mds1 (opts:) on oleg251-server 09:33:47 (1787837627) shut down facet: mds1 facet_host: oleg251-server facet_failover_host: oleg251-server Failover mds1 to oleg251-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg251-server: oleg251-server.virtnet: executing set_default_debug -1 all pdsh@oleg251-client: oleg251-server: ssh exited with exit code 1 Started lustre-MDT0000 09:34:23 (1787837663) targets are mounted 09:34:23 (1787837663) facet_failover done oleg251-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 Starting client: oleg251-client.virtnet: -o user_xattr,flock 192.168.202.151@tcp:/lustre /mnt/lustre2 PASS 20 (404s)