-----============= acceptance-small: replay-dual ============----- Thu Jul 30 01:46:36 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 oleg234-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 01:47:04 (1785390424) === Starting client oleg234-client.virtnet: -o user_xattr,flock 192.168.202.134@tcp:/lustre /mnt/lustre2 Mount client oleg234-client.virtnet: mount -t lustre -o user_xattr,flock 192.168.202.134@tcp:/lustre /mnt/lustre2 Started clients oleg234-client.virtnet: 192.168.202.134@tcp:/lustre on /mnt/lustre2 type lustre (rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose) oleg234-client.virtnet: executing check_config_client /mnt/lustre oleg234-client.virtnet: Checking config lustre mounted on /mnt/lustre Checking servers environments Checking clients oleg234-client.virtnet environments Using TIMEOUT=20 osc.lustre-OST0000-osc-ffff968989c1c800.idle_timeout=debug osc.lustre-OST0000-osc-ffff96898ad57800.idle_timeout=debug osc.lustre-OST0001-osc-ffff968989c1c800.idle_timeout=debug osc.lustre-OST0001-osc-ffff96898ad57800.idle_timeout=debug disable quota as required oleg234-server: oleg234-server.virtnet: executing set_default_debug -1 all === replay-dual: finish setup 01:47:53 (1785390473) === == replay-dual test 0a: expired recovery with lost client ========================================================== 01:47:56 (1785390476) Check file is LU482_FAILED=/tmp/replay-dual.lu482.XqQ7kz 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 2.76 seconds: 18.11 ops/second fail_loc=0x80000514 Failing mds1 on oleg234-server Stopping /mnt/lustre-mds1 (opts:) on oleg234-server 01:48:12 (1785390492) shut down facet: mds1 facet_host: oleg234-server facet_failover_host: oleg234-server Failover mds1 to oleg234-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg234-server: oleg234-server.virtnet: executing set_default_debug -1 all pdsh@oleg234-client: oleg234-server: ssh exited with exit code 1 Started lustre-MDT0000 01:48:46 (1785390526) targets are mounted 01:48:46 (1785390526) facet_failover done Starting client: oleg234-client.virtnet: -o user_xattr,flock 192.168.202.134@tcp:/lustre /mnt/lustre2 - unlinked 0 (time 1785390645 ; total 0 ; last 0) total: 50 unlinks in 3 seconds: 16.666666 unlinks/second PASS 0a (180s) == replay-dual test 0b: lost client during waiting for next transno ========================================================== 01:50:56 (1785390656) 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 oleg234-server Stopping /mnt/lustre-mds1 (opts:) on oleg234-server 01:51:15 (1785390675) shut down facet: mds1 facet_host: oleg234-server facet_failover_host: oleg234-server Failover mds1 to oleg234-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg234-server: oleg234-server.virtnet: executing set_default_debug -1 all pdsh@oleg234-client: oleg234-server: ssh exited with exit code 1 Started lustre-MDT0000 01:51:50 (1785390710) targets are mounted 01:51:50 (1785390710) facet_failover done Starting client: oleg234-client.virtnet: -o user_xattr,flock 192.168.202.134@tcp:/lustre /mnt/lustre Starting client: oleg234-client.virtnet: -o user_xattr,flock 192.168.202.134@tcp:/lustre /mnt/lustre2 PASS 0b (134s) == replay-dual test 1: |X| simple create ================= 01:53:10 (1785390790) 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 oleg234-server Stopping /mnt/lustre-mds1 (opts:) on oleg234-server 01:53:23 (1785390803) shut down facet: mds1 facet_host: oleg234-server facet_failover_host: oleg234-server Failover mds1 to oleg234-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg234-server: oleg234-server.virtnet: executing set_default_debug -1 all pdsh@oleg234-client: oleg234-server: ssh exited with exit code 1 Started lustre-MDT0000 01:54:00 (1785390840) targets are mounted 01:54:00 (1785390840) facet_failover done oleg234-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 (71s) == replay-dual test 2: |X| mkdir adir ==================== 01:54:21 (1785390861) 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 oleg234-server Stopping /mnt/lustre-mds1 (opts:) on oleg234-server 01:54:38 (1785390878) shut down facet: mds1 facet_host: oleg234-server facet_failover_host: oleg234-server Failover mds1 to oleg234-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg234-server: oleg234-server.virtnet: executing set_default_debug -1 all pdsh@oleg234-client: oleg234-server: ssh exited with exit code 1 Started lustre-MDT0000 01:55:11 (1785390911) targets are mounted 01:55:11 (1785390911) facet_failover done oleg234-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 (70s) == replay-dual test 3: |X| mkdir adir, mkdir adir/bdir === 01:55:31 (1785390931) 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 oleg234-server Stopping /mnt/lustre-mds1 (opts:) on oleg234-server 01:55:45 (1785390945) shut down facet: mds1 facet_host: oleg234-server facet_failover_host: oleg234-server Failover mds1 to oleg234-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg234-server: oleg234-server.virtnet: executing set_default_debug -1 all pdsh@oleg234-client: oleg234-server: ssh exited with exit code 1 Started lustre-MDT0000 01:56:22 (1785390982) targets are mounted 01:56:22 (1785390982) facet_failover done oleg234-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 (76s) == replay-dual test 4: |X| mkdir adir (-EEXIST), mkdir adir/bdir ========================================================== 01:56:47 (1785391007) 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 oleg234-server Stopping /mnt/lustre-mds1 (opts:) on oleg234-server 01:57:04 (1785391024) shut down facet: mds1 facet_host: oleg234-server facet_failover_host: oleg234-server Failover mds1 to oleg234-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg234-server: oleg234-server.virtnet: executing set_default_debug -1 all pdsh@oleg234-client: oleg234-server: ssh exited with exit code 1 Started lustre-MDT0000 01:57:34 (1785391054) targets are mounted 01:57:34 (1785391054) facet_failover done oleg234-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 (70s) == replay-dual test 5: open, unlink |X| close ============ 01:57:57 (1785391077) multiop /mnt/lustre2/a vo_tSc TMPPIPE=/tmp/multiop_open_wait_pipe.7585 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 oleg234-server Stopping /mnt/lustre-mds1 (opts:) on oleg234-server 01:58:11 (1785391091) shut down facet: mds1 facet_host: oleg234-server facet_failover_host: oleg234-server Failover mds1 to oleg234-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg234-server: oleg234-server.virtnet: executing set_default_debug -1 all pdsh@oleg234-client: oleg234-server: ssh exited with exit code 1 Started lustre-MDT0000 01:58:48 (1785391128) targets are mounted 01:58:48 (1785391128) facet_failover done oleg234-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 (72s) == replay-dual test 6: open1, open2, unlink |X| close1 [fail mds1] close2 ========================================================== 01:59:09 (1785391149) multiop /mnt/lustre2/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.7585 multiop /mnt/lustre/a vo_c TMPPIPE=/tmp/multiop_open_wait_pipe.7585 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 oleg234-server Stopping /mnt/lustre-mds1 (opts:) on oleg234-server 01:59:23 (1785391163) shut down facet: mds1 facet_host: oleg234-server facet_failover_host: oleg234-server Failover mds1 to oleg234-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg234-server: oleg234-server.virtnet: executing set_default_debug -1 all pdsh@oleg234-client: oleg234-server: ssh exited with exit code 1 Started lustre-MDT0000 02:00:02 (1785391202) targets are mounted 02:00:02 (1785391202) facet_failover done oleg234-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 (75s) == replay-dual test 8: replay of resent request ========== 02:00:24 (1785391224) 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 oleg234-server Stopping /mnt/lustre-mds1 (opts:) on oleg234-server 02:00:59 (1785391259) shut down facet: mds1 facet_host: oleg234-server facet_failover_host: oleg234-server Failover mds1 to oleg234-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg234-server: oleg234-server.virtnet: executing set_default_debug -1 all pdsh@oleg234-client: oleg234-server: ssh exited with exit code 1 Started lustre-MDT0000 02:01:48 (1785391308) targets are mounted 02:01:48 (1785391308) facet_failover done oleg234-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 (113s) == replay-dual test 9: resending a replayed create ======= 02:02:18 (1785391338) 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 oleg234-server Stopping /mnt/lustre-mds1 (opts:) on oleg234-server 02:02:37 (1785391357) shut down facet: mds1 facet_host: oleg234-server facet_failover_host: oleg234-server Failover mds1 to oleg234-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg234-server: oleg234-server.virtnet: executing set_default_debug -1 all pdsh@oleg234-client: oleg234-server: ssh exited with exit code 1 Started lustre-MDT0000 02:03:11 (1785391391) targets are mounted 02:03:11 (1785391391) facet_failover done oleg234-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 (82s) == replay-dual test 10: resending a replayed unlink ====== 02:03:40 (1785391420) 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 oleg234-server Stopping /mnt/lustre-mds1 (opts:) on oleg234-server 02:03:54 (1785391434) shut down facet: mds1 facet_host: oleg234-server facet_failover_host: oleg234-server Failover mds1 to oleg234-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg234-server: oleg234-server.virtnet: executing set_default_debug -1 all pdsh@oleg234-client: oleg234-server: ssh exited with exit code 1 Started lustre-MDT0000 02:04:31 (1785391471) targets are mounted 02:04:31 (1785391471) facet_failover done oleg234-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 (92s) == replay-dual test 11: both clients timeout during replay ========================================================== 02:05:12 (1785391512) 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 oleg234-server Stopping /mnt/lustre-mds1 (opts:) on oleg234-server 02:05:28 (1785391528) shut down facet: mds1 facet_host: oleg234-server facet_failover_host: oleg234-server Failover mds1 to oleg234-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg234-server: oleg234-server.virtnet: executing set_default_debug -1 all pdsh@oleg234-client: oleg234-server: ssh exited with exit code 1 Started lustre-MDT0000 02:06:07 (1785391567) targets are mounted 02:06:07 (1785391567) facet_failover done oleg234-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 4 sec fail_loc=0 PASS 11 (83s) == replay-dual test 12: open resend timeout ============== 02:06:35 (1785391595) 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.7585 fail_loc=0x80000302 Failing mds1 on oleg234-server Stopping /mnt/lustre-mds1 (opts:) on oleg234-server 02:06:54 (1785391614) shut down facet: mds1 facet_host: oleg234-server facet_failover_host: oleg234-server Failover mds1 to oleg234-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg234-server: oleg234-server.virtnet: executing set_default_debug -1 all pdsh@oleg234-client: oleg234-server: ssh exited with exit code 1 Started lustre-MDT0000 02:07:26 (1785391646) targets are mounted 02:07:26 (1785391646) facet_failover done fail_loc=0 /mnt/lustre/f12.replay-dual /mnt/lustre/f12.replay-dual has type file OK PASS 12 (72s) == replay-dual test 13: close resend timeout ============= 02:07:47 (1785391667) multiop /mnt/lustre/f13.replay-dual vmo_c TMPPIPE=/tmp/multiop_open_wait_pipe.7585 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 oleg234-server Stopping /mnt/lustre-mds1 (opts:) on oleg234-server 02:08:04 (1785391684) shut down facet: mds1 facet_host: oleg234-server facet_failover_host: oleg234-server Failover mds1 to oleg234-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg234-server: oleg234-server.virtnet: executing set_default_debug -1 all pdsh@oleg234-client: oleg234-server: ssh exited with exit code 1 Started lustre-MDT0000 02:08:41 (1785391721) targets are mounted 02:08:41 (1785391721) facet_failover done fail_loc=0 /mnt/lustre/f13.replay-dual /mnt/lustre/f13.replay-dual has type file OK PASS 13 (79s) SKIP: replay-dual test_14b skipping ALWAYS excluded test 14b == replay-dual test 15a: timeout waiting for lost client during replay, 1 client completes ========================================================== 02:09:08 (1785391748) 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 1.04 seconds: 24.08 ops/second total: 1 open/close in 0.07 seconds: 13.66 ops/second Failing mds1 on oleg234-server Stopping /mnt/lustre-mds1 (opts:) on oleg234-server 02:09:21 (1785391761) shut down facet: mds1 facet_host: oleg234-server facet_failover_host: oleg234-server Failover mds1 to oleg234-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg234-server: oleg234-server.virtnet: executing set_default_debug -1 all pdsh@oleg234-client: oleg234-server: ssh exited with exit code 1 Started lustre-MDT0000 02:09:56 (1785391796) targets are mounted 02:09:56 (1785391796) facet_failover done oleg234-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 1785391874 ; total 0 ; last 0) total: 25 unlinks in 1 seconds: 25.000000 unlinks/second Starting client: oleg234-client.virtnet: -o user_xattr,flock 192.168.202.134@tcp:/lustre /mnt/lustre2 PASS 15a (135s) == replay-dual test 15c: remove multiple OST orphans ===== 02:11:23 (1785391883) 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 oleg234-server Stopping /mnt/lustre-mds1 (opts:) on oleg234-server 02:13:53 (1785392033) shut down facet: mds1 facet_host: oleg234-server facet_failover_host: oleg234-server Failover mds1 to oleg234-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg234-server: oleg234-server.virtnet: executing set_default_debug -1 all pdsh@oleg234-client: oleg234-server: ssh exited with exit code 1 Started lustre-MDT0000 02:14:29 (1785392069) targets are mounted 02:14:29 (1785392069) facet_failover done oleg234-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: oleg234-client.virtnet: -o user_xattr,flock 192.168.202.134@tcp:/lustre /mnt/lustre2 PASS 15c (278s) == replay-dual test 16: fail MDS during recovery (3571) == 02:16:02 (1785392162) 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 1.65 seconds: 15.18 ops/second total: 1 open/close in 0.06 seconds: 16.76 ops/second Failing mds1 on oleg234-server Stopping /mnt/lustre-mds1 (opts:) on oleg234-server 02:16:22 (1785392182) shut down facet: mds1 facet_host: oleg234-server facet_failover_host: oleg234-server Failover mds1 to oleg234-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg234-server: oleg234-server.virtnet: executing set_default_debug -1 all pdsh@oleg234-client: oleg234-server: ssh exited with exit code 1 Started lustre-MDT0000 02:17:05 (1785392225) targets are mounted 02:17:05 (1785392225) facet_failover done Failing mds1 on oleg234-server Stopping /mnt/lustre-mds1 (opts:) on oleg234-server 02:17:34 (1785392254) shut down facet: mds1 facet_host: oleg234-server facet_failover_host: oleg234-server Failover mds1 to oleg234-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg234-server: oleg234-server.virtnet: executing set_default_debug -1 all pdsh@oleg234-client: oleg234-server: ssh exited with exit code 1 Started lustre-MDT0000 02:18:10 (1785392290) targets are mounted 02:18:10 (1785392290) facet_failover done oleg234-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 1785392372 ; total 0 ; last 0) total: 25 unlinks in 1 seconds: 25.000000 unlinks/second Starting client: oleg234-client.virtnet: -o user_xattr,flock 192.168.202.134@tcp:/lustre /mnt/lustre2 PASS 16 (220s) == replay-dual test 17: fail OST during recovery (3571) == 02:19:43 (1785392383) total: 25 open/close in 1.46 seconds: 17.08 ops/second total: 1 open/close in 0.08 seconds: 12.20 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 oleg234-server Stopping /mnt/lustre-ost1 (opts:) on oleg234-server 02:20:00 (1785392400) shut down facet: ost1 facet_host: oleg234-server facet_failover_host: oleg234-server Failover ost1 to oleg234-server mount facets: ost1 Start ost1: mount -t lustre -o localrecov lustre-ost1/ost1 /mnt/lustre-ost1 seq.cli-lustre-OST0000-super.width=65536 oleg234-server: oleg234-server.virtnet: executing set_default_debug -1 all pdsh@oleg234-client: oleg234-server: ssh exited with exit code 1 Started lustre-OST0000 02:20:29 (1785392429) targets are mounted 02:20:29 (1785392429) facet_failover done Failing ost1 on oleg234-server Stopping /mnt/lustre-ost1 (opts:) on oleg234-server 02:20:56 (1785392456) shut down facet: ost1 facet_host: oleg234-server facet_failover_host: oleg234-server Failover ost1 to oleg234-server mount facets: ost1 Start ost1: mount -t lustre -o localrecov lustre-ost1/ost1 /mnt/lustre-ost1 seq.cli-lustre-OST0000-super.width=65536 oleg234-server: oleg234-server.virtnet: executing set_default_debug -1 all pdsh@oleg234-client: oleg234-server: ssh exited with exit code 1 Started lustre-OST0000 02:21:29 (1785392489) targets are mounted 02:21:29 (1785392489) facet_failover done oleg234-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 1785392568 ; total 0 ; last 0) total: 25 unlinks in 1 seconds: 25.000000 unlinks/second Starting client: oleg234-client.virtnet: -o user_xattr,flock 192.168.202.134@tcp:/lustre /mnt/lustre2 PASS 17 (193s) == replay-dual test 18: ldlm_handle_enqueue succeeds on evicted export (3822) ========================================================== 02:22:56 (1785392576) debug=+dlmtrace fail_loc=0x8000030b using seed 2430726493 running for 500 iterations total: 500 stats in 2 seconds: 250.000000 stats/second ldlm.namespaces.MGC192.168.202.134@tcp.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffff968982caf800.early_lock_cancel=0 ldlm.namespaces.lustre-MDT0000-mdc-ffff968989c19800.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffff968982caf800.early_lock_cancel=0 ldlm.namespaces.lustre-OST0000-osc-ffff968989c19800.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffff968982caf800.early_lock_cancel=0 ldlm.namespaces.lustre-OST0001-osc-ffff968989c19800.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.MGC192.168.202.134@tcp.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffff968982caf800.early_lock_cancel=1 ldlm.namespaces.lustre-MDT0000-mdc-ffff968989c19800.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffff968982caf800.early_lock_cancel=1 ldlm.namespaces.lustre-OST0000-osc-ffff968989c19800.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffff968982caf800.early_lock_cancel=1 ldlm.namespaces.lustre-OST0001-osc-ffff968989c19800.early_lock_cancel=1 fail_loc=0 fail_loc=0 PASS 18 (64s) == replay-dual test 19: resend of open request =========== 02:24:00 (1785392640) 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 1785392735.85 total 86.05 last 0.00) total: 1 open/close in 86.05 seconds: 0.01 ops/second fail_loc=0 Failing mds1 on oleg234-server Stopping /mnt/lustre-mds1 (opts:) on oleg234-server 02:25:45 (1785392745) shut down facet: mds1 facet_host: oleg234-server facet_failover_host: oleg234-server Failover mds1 to oleg234-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg234-server: oleg234-server.virtnet: executing set_default_debug -1 all pdsh@oleg234-client: oleg234-server: ssh exited with exit code 1 Started lustre-MDT0000 02:26:20 (1785392780) targets are mounted 02:26:20 (1785392780) facet_failover done oleg234-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 (171s) == replay-dual test 20: recovery time is not increasing == 02:26:51 (1785392811) 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 oleg234-server Stopping /mnt/lustre-mds1 (opts:) on oleg234-server 02:27:09 (1785392829) shut down facet: mds1 facet_host: oleg234-server facet_failover_host: oleg234-server Failover mds1 to oleg234-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg234-server: oleg234-server.virtnet: executing set_default_debug -1 all pdsh@oleg234-client: oleg234-server: ssh exited with exit code 1 Started lustre-MDT0000 02:27:44 (1785392864) targets are mounted 02:27:44 (1785392864) facet_failover done oleg234-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: oleg234-client.virtnet: -o user_xattr,flock 192.168.202.134@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 oleg234-server Stopping /mnt/lustre-mds1 (opts:) on oleg234-server 02:30:26 (1785393026) shut down facet: mds1 facet_host: oleg234-server facet_failover_host: oleg234-server Failover mds1 to oleg234-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg234-server: oleg234-server.virtnet: executing set_default_debug -1 all pdsh@oleg234-client: oleg234-server: ssh exited with exit code 1 Started lustre-MDT0000 02:30:56 (1785393056) targets are mounted 02:30:56 (1785393056) facet_failover done oleg234-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: oleg234-client.virtnet: -o user_xattr,flock 192.168.202.134@tcp:/lustre /mnt/lustre2