== replay-dual test 26: dbench and tar with mds failover ========================================================== 09:15:37 (1774530937) Starting client oleg301-client.virtnet: -o user_xattr,flock oleg301-server@tcp:/lustre /mnt/lustre Started clients oleg301-client.virtnet: 192.168.203.101@tcp:/lustre on /mnt/lustre type lustre (rw,checksum,flock,user_xattr,lruresize,lazystatfs,nouser_fid2path,verbose,encrypt) Started tar loop with pid 45065 Started dbench loop with 45066 looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt '/usr/share/dbench/client.txt' -> 'client.txt' running 'dbench 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100' on /mnt/lustre at Thu Mar 26 09:15:39 EDT 2026 waiting for dbench pid 45094 dbench version 4.00 - Copyright Andrew Tridgell 1999-2004 Running for 100 seconds with load 'client.txt' and minimum warmup 20 secs failed to create barrier semaphore 0 of 1 processes prepared for launch 0 sec 1 of 1 processes prepared for launch 0 sec releasing clients UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 3200 2205312 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 3072 3727360 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 3072 3710976 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 6144 7438336 1% /mnt/lustre 1 169 6.87 MB/sec warmup 1 sec latency 34.214 ms 1 330 6.00 MB/sec warmup 2 sec latency 33.799 ms 1 493 5.74 MB/sec warmup 3 sec latency 29.920 ms test_26 fail mds1 1 times 1 664 5.29 MB/sec warmup 4 sec latency 105.918 ms Failing mds1 on oleg301-server Stopping /mnt/lustre-mds1 (opts:) on oleg301-server 1 785 4.29 MB/sec warmup 5 sec latency 182.147 ms reboot facets: mds1 1 785 3.57 MB/sec warmup 6 sec latency 1182.320 ms 1 785 3.06 MB/sec warmup 7 sec latency 2182.522 ms 1 785 2.68 MB/sec warmup 8 sec latency 3182.647 ms 1 785 2.38 MB/sec warmup 9 sec latency 4182.798 ms 1 785 2.14 MB/sec warmup 10 sec latency 5182.964 ms 1 785 1.95 MB/sec warmup 11 sec latency 6183.117 ms 1 785 1.79 MB/sec warmup 12 sec latency 7183.302 ms 1 785 1.65 MB/sec warmup 13 sec latency 8183.504 ms 1 785 1.53 MB/sec warmup 14 sec latency 9183.679 ms 1 785 1.43 MB/sec warmup 15 sec latency 10183.859 ms Failover mds1 to oleg301-server 1 785 1.34 MB/sec warmup 16 sec latency 11183.994 ms mount facets: mds1 1 785 1.26 MB/sec warmup 17 sec latency 12184.179 ms Starting mds1: -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 785 1.19 MB/sec warmup 18 sec latency 13184.457 ms 1 785 1.13 MB/sec warmup 19 sec latency 14184.675 ms 1 785 0.00 MB/sec execute 1 sec latency 16185.130 ms 1 785 0.00 MB/sec execute 2 sec latency 17187.544 ms 1 785 0.00 MB/sec execute 3 sec latency 18189.410 ms oleg301-server: oleg301-server.virtnet: executing set_default_debug -1 all 8 1 785 0.00 MB/sec execute 4 sec latency 19189.566 ms pdsh@oleg301-client: oleg301-server: ssh exited with exit code 1 Started lustre-MDT0000 1 785 0.00 MB/sec execute 5 sec latency 20189.729 ms 1 785 0.00 MB/sec execute 6 sec latency 21189.901 ms 1 785 0.00 MB/sec execute 7 sec latency 22190.214 ms 1 785 0.00 MB/sec execute 8 sec latency 23190.392 ms 1 785 0.00 MB/sec execute 9 sec latency 24190.551 ms 1 785 0.00 MB/sec execute 10 sec latency 25190.703 ms 1 785 0.00 MB/sec execute 11 sec latency 26190.888 ms 1 785 0.00 MB/sec execute 12 sec latency 27191.052 ms 1 785 0.00 MB/sec execute 13 sec latency 28191.417 ms 1 785 0.00 MB/sec execute 14 sec latency 29191.590 ms 1 785 0.00 MB/sec execute 15 sec latency 30191.786 ms 1 808 0.00 MB/sec execute 16 sec latency 30891.641 ms 1 962 0.02 MB/sec execute 17 sec latency 92.768 ms oleg301-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 1128 0.09 MB/sec execute 18 sec latency 49.220 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 1384 0.24 MB/sec execute 19 sec latency 24.535 ms 1 1529 0.23 MB/sec execute 20 sec latency 75.420 ms 1 1679 0.23 MB/sec execute 21 sec latency 52.409 ms 1 1884 0.22 MB/sec execute 22 sec latency 30.429 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 4096 2204416 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 32768 3681280 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 40960 3684352 2% /mnt/lustre[OST:1] filesystem_summary: 7542784 73728 7365632 1% /mnt/lustre 1 2080 0.23 MB/sec execute 23 sec latency 76.784 ms 1 2327 0.27 MB/sec execute 24 sec latency 24.102 ms 1 2437 0.27 MB/sec execute 25 sec latency 68.756 ms test_26 fail mds1 2 times 1 2604 0.29 MB/sec execute 26 sec latency 47.357 ms Failing mds1 on oleg301-server Stopping /mnt/lustre-mds1 (opts:) on oleg301-server 1 2926 0.45 MB/sec execute 27 sec latency 90.262 ms 1 2967 0.43 MB/sec execute 28 sec latency 875.331 ms reboot facets: mds1 1 2967 0.42 MB/sec execute 29 sec latency 1875.559 ms 1 2967 0.40 MB/sec execute 30 sec latency 2875.810 ms 1 2967 0.39 MB/sec execute 31 sec latency 3876.019 ms 1 2967 0.38 MB/sec execute 32 sec latency 4876.256 ms 1 2967 0.37 MB/sec execute 33 sec latency 5876.499 ms 1 2967 0.35 MB/sec execute 34 sec latency 6876.694 ms 1 2967 0.34 MB/sec execute 35 sec latency 7876.855 ms 1 2967 0.33 MB/sec execute 36 sec latency 8877.034 ms 1 2967 0.33 MB/sec execute 37 sec latency 9877.206 ms 1 2967 0.32 MB/sec execute 38 sec latency 10877.409 ms Failover mds1 to oleg301-server mount facets: mds1 1 2967 0.31 MB/sec execute 39 sec latency 11877.562 ms Starting mds1: -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 2967 0.30 MB/sec execute 40 sec latency 12877.727 ms 1 2967 0.29 MB/sec execute 41 sec latency 13877.900 ms 1 2967 0.29 MB/sec execute 42 sec latency 14878.023 ms 1 2967 0.28 MB/sec execute 43 sec latency 15878.215 ms oleg301-server: oleg301-server.virtnet: executing set_default_debug -1 all 8 pdsh@oleg301-client: oleg301-server: ssh exited with exit code 1 Started lustre-MDT0000 1 2967 0.27 MB/sec execute 44 sec latency 16878.457 ms 1 2967 0.27 MB/sec execute 45 sec latency 17878.591 ms 1 2967 0.26 MB/sec execute 46 sec latency 18878.764 ms 1 2967 0.26 MB/sec execute 47 sec latency 19878.942 ms 1 2967 0.25 MB/sec execute 48 sec latency 20879.092 ms 1 2967 0.25 MB/sec execute 49 sec latency 21880.117 ms 1 2967 0.24 MB/sec execute 50 sec latency 22880.350 ms 1 2967 0.24 MB/sec execute 51 sec latency 23880.611 ms 1 2967 0.23 MB/sec execute 52 sec latency 24880.871 ms 1 2967 0.23 MB/sec execute 53 sec latency 25881.104 ms 1 2967 0.22 MB/sec execute 54 sec latency 26881.346 ms 1 2967 0.22 MB/sec execute 55 sec latency 27881.562 ms 1 2967 0.22 MB/sec execute 56 sec latency 28881.817 ms 1 2967 0.21 MB/sec execute 57 sec latency 29881.978 ms 1 2968 0.21 MB/sec execute 58 sec latency 30881.149 ms 1 3277 0.24 MB/sec execute 59 sec latency 67.001 ms oleg301-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 3582 0.28 MB/sec execute 60 sec latency 21.105 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 3786 0.30 MB/sec execute 61 sec latency 27.924 ms 1 3958 0.30 MB/sec execute 62 sec latency 26.011 ms 1 4141 0.30 MB/sec execute 63 sec latency 23.880 ms 1 4301 0.30 MB/sec execute 64 sec latency 95.400 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 5504 2203008 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 36864 3703808 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 41984 3696640 2% /mnt/lustre[OST:1] filesystem_summary: 7542784 78848 7400448 2% /mnt/lustre 1 4446 0.30 MB/sec execute 65 sec latency 60.100 ms 1 4564 0.30 MB/sec execute 66 sec latency 55.597 ms 1 4810 0.31 MB/sec execute 67 sec latency 19.851 ms test_26 fail mds1 3 times 1 5078 0.35 MB/sec execute 68 sec latency 71.902 ms Failing mds1 on oleg301-server Stopping /mnt/lustre-mds1 (opts:) on oleg301-server 1 5261 0.35 MB/sec execute 69 sec latency 64.610 ms 1 5288 0.34 MB/sec execute 70 sec latency 855.490 ms 1 5288 0.34 MB/sec execute 71 sec latency 1855.629 ms 1 5288 0.33 MB/sec execute 72 sec latency 2855.757 ms 1 5288 0.33 MB/sec execute 73 sec latency 3855.927 ms 1 5288 0.32 MB/sec execute 74 sec latency 4856.102 ms 1 5288 0.32 MB/sec execute 75 sec latency 5856.241 ms 1 5288 0.31 MB/sec execute 76 sec latency 6856.361 ms reboot facets: mds1 1 5288 0.31 MB/sec execute 77 sec latency 7856.495 ms 1 5288 0.31 MB/sec execute 78 sec latency 8856.636 ms 1 5288 0.30 MB/sec execute 79 sec latency 9856.809 ms 1 5288 0.30 MB/sec execute 80 sec latency 10856.926 ms 1 5288 0.30 MB/sec execute 81 sec latency 11857.053 ms 1 5288 0.29 MB/sec execute 82 sec latency 12857.209 ms 1 5288 0.29 MB/sec execute 83 sec latency 13857.446 ms 1 5288 0.28 MB/sec execute 84 sec latency 14857.695 ms 1 5288 0.28 MB/sec execute 85 sec latency 15857.981 ms 1 5288 0.28 MB/sec execute 86 sec latency 16858.200 ms Failover mds1 to oleg301-server mount facets: mds1 1 5288 0.28 MB/sec execute 87 sec latency 17858.385 ms Starting mds1: -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 5288 0.27 MB/sec execute 88 sec latency 18858.530 ms 1 5288 0.27 MB/sec execute 89 sec latency 19858.679 ms 1 5288 0.27 MB/sec execute 90 sec latency 20858.832 ms 1 5288 0.26 MB/sec execute 91 sec latency 21859.001 ms oleg301-server: oleg301-server.virtnet: executing set_default_debug -1 all 8 pdsh@oleg301-client: oleg301-server: ssh exited with exit code 1 1 5288 0.26 MB/sec execute 92 sec latency 22859.168 ms Started lustre-MDT0000 1 5288 0.26 MB/sec execute 93 sec latency 23859.424 ms 1 5298 0.25 MB/sec execute 94 sec latency 24727.264 ms 1 5499 0.25 MB/sec execute 95 sec latency 58.597 ms oleg301-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 5730 0.25 MB/sec execute 96 sec latency 23.329 ms 1 5959 0.26 MB/sec execute 97 sec latency 74.923 ms 1 6213 0.28 MB/sec execute 98 sec latency 42.463 ms 1 6565 0.32 MB/sec execute 99 sec latency 89.593 ms 1 cleanup 100 sec UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 6656 2201856 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 38912 3705856 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 44032 3697664 2% /mnt/lustre[OST:1] filesystem_summary: 7542784 82944 7403520 2% /mnt/lustre 1 cleanup 101 sec 0 cleanup 101 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 1006 38.215 24727.253 Close 774 42.533 30891.621 Rename 46 18.064 37.625 Unlink 171 6.693 19.915 Qpathinfo 969 35.800 30881.131 Qfileinfo 183 0.693 3.971 Qfsinfo 163 0.436 5.343 Sfileinfo 93 9.364 19.820 Find 386 2.042 17.206 WriteX 544 3.131 15.347 ReadX 1728 0.340 49.206 LockX 4 2.883 4.539 UnlockX 4 2.700 4.417 Flush 74 39.848 95.387 Throughput 0.315134 MB/sec 1 clients 1 procs max_latency=30891.641 ms stopping dbench on /mnt/lustre at Thu Mar 26 09:17:40 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt test_26 fail mds1 4 times '/usr/share/dbench/client.txt' -> 'client.txt' running 'dbench 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100' on /mnt/lustre at Thu Mar 26 09:17:43 EDT 2026 waiting for dbench pid 48378 dbench version 4.00 - Copyright Andrew Tridgell 1999-2004 Running for 100 seconds with load 'client.txt' and minimum warmup 20 secs 0 of 1 processes prepared for launch 0 sec 1 of 1 processes prepared for launch 0 sec releasing clients Failing mds1 on oleg301-server Stopping /mnt/lustre-mds1 (opts:) on oleg301-server 1 147 6.28 MB/sec warmup 1 sec latency 41.799 ms 1 164 3.40 MB/sec warmup 2 sec latency 833.632 ms reboot facets: mds1 1 164 2.27 MB/sec warmup 3 sec latency 1833.803 ms 1 164 1.70 MB/sec warmup 4 sec latency 2833.992 ms 1 164 1.36 MB/sec warmup 5 sec latency 3834.176 ms 1 164 1.13 MB/sec warmup 6 sec latency 4834.372 ms 1 164 0.97 MB/sec warmup 7 sec latency 5834.596 ms 1 164 0.85 MB/sec warmup 8 sec latency 6834.844 ms 1 164 0.76 MB/sec warmup 9 sec latency 7835.084 ms 1 164 0.68 MB/sec warmup 10 sec latency 8835.350 ms 1 164 0.62 MB/sec warmup 11 sec latency 9835.524 ms 1 164 0.57 MB/sec warmup 12 sec latency 10835.718 ms Failover mds1 to oleg301-server mount facets: mds1 1 164 0.52 MB/sec warmup 13 sec latency 11835.831 ms 1 164 0.49 MB/sec warmup 14 sec latency 12836.022 ms Starting mds1: -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 164 0.45 MB/sec warmup 15 sec latency 13836.219 ms 1 164 0.43 MB/sec warmup 16 sec latency 14836.386 ms 1 164 0.40 MB/sec warmup 17 sec latency 15836.544 ms 1 164 0.38 MB/sec warmup 18 sec latency 16836.708 ms 1 164 0.36 MB/sec warmup 19 sec latency 17836.935 ms 1 164 0.00 MB/sec execute 1 sec latency 19837.304 ms oleg301-server: oleg301-server.virtnet: executing set_default_debug -1 all 8 pdsh@oleg301-client: oleg301-server: ssh exited with exit code 1 Started lustre-MDT0000 1 164 0.00 MB/sec execute 2 sec latency 20837.507 ms 1 164 0.00 MB/sec execute 3 sec latency 21837.627 ms 1 164 0.00 MB/sec execute 4 sec latency 22837.773 ms 1 164 0.00 MB/sec execute 5 sec latency 23837.943 ms 1 164 0.00 MB/sec execute 6 sec latency 24838.165 ms 1 164 0.00 MB/sec execute 7 sec latency 25838.329 ms 1 164 0.00 MB/sec execute 8 sec latency 26838.543 ms 1 164 0.00 MB/sec execute 9 sec latency 27838.767 ms 1 164 0.00 MB/sec execute 10 sec latency 28839.000 ms 1 164 0.00 MB/sec execute 11 sec latency 29839.177 ms 1 164 0.00 MB/sec execute 12 sec latency 30839.368 ms 1 173 0.02 MB/sec execute 13 sec latency 31640.150 ms 1 326 0.35 MB/sec execute 14 sec latency 31.908 ms oleg301-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 470 0.64 MB/sec execute 15 sec latency 38.358 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 664 0.90 MB/sec execute 16 sec latency 72.337 ms 1 780 0.86 MB/sec execute 17 sec latency 110.828 ms 1 951 0.83 MB/sec execute 18 sec latency 60.840 ms 1 1149 0.85 MB/sec execute 19 sec latency 65.342 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 4608 2203904 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 28672 3698688 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 35840 3691520 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 64512 7390208 1% /mnt/lustre 1 1396 0.96 MB/sec execute 20 sec latency 29.133 ms 1 1574 0.92 MB/sec execute 21 sec latency 48.752 ms 1 1753 0.89 MB/sec execute 22 sec latency 128.884 ms test_26 fail mds1 5 times 1 1965 0.85 MB/sec execute 23 sec latency 73.049 ms Failing mds1 on oleg301-server Stopping /mnt/lustre-mds1 (opts:) on oleg301-server 1 2160 0.83 MB/sec execute 24 sec latency 28.790 ms 1 2200 0.80 MB/sec execute 25 sec latency 823.691 ms reboot facets: mds1 1 2200 0.77 MB/sec execute 26 sec latency 1823.922 ms 1 2200 0.74 MB/sec execute 27 sec latency 2824.118 ms 1 2200 0.71 MB/sec execute 28 sec latency 3824.376 ms 1 2200 0.69 MB/sec execute 29 sec latency 4824.598 ms 1 2200 0.67 MB/sec execute 30 sec latency 5824.778 ms 1 2200 0.64 MB/sec execute 31 sec latency 6824.944 ms 1 2200 0.62 MB/sec execute 32 sec latency 7825.098 ms 1 2200 0.60 MB/sec execute 33 sec latency 8825.271 ms 1 2200 0.59 MB/sec execute 34 sec latency 9825.451 ms 1 2200 0.57 MB/sec execute 35 sec latency 10825.630 ms Failover mds1 to oleg301-server mount facets: mds1 1 2200 0.55 MB/sec execute 36 sec latency 11826.319 ms 1 2200 0.54 MB/sec execute 37 sec latency 12826.499 ms Starting mds1: -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 2200 0.53 MB/sec execute 38 sec latency 13826.692 ms 1 2200 0.51 MB/sec execute 39 sec latency 14826.911 ms 1 2200 0.50 MB/sec execute 40 sec latency 15827.085 ms oleg301-server: oleg301-server.virtnet: executing set_default_debug -1 all 8 pdsh@oleg301-client: oleg301-server: ssh exited with exit code 1 1 2200 0.49 MB/sec execute 41 sec latency 16827.214 ms Started lustre-MDT0000 1 2200 0.48 MB/sec execute 42 sec latency 17827.424 ms 1 2200 0.46 MB/sec execute 43 sec latency 18827.615 ms 1 2200 0.45 MB/sec execute 44 sec latency 19827.786 ms 1 2200 0.44 MB/sec execute 45 sec latency 20827.967 ms 1 2200 0.43 MB/sec execute 46 sec latency 21828.130 ms 1 2200 0.42 MB/sec execute 47 sec latency 22828.262 ms 1 2200 0.42 MB/sec execute 48 sec latency 23828.436 ms 1 2200 0.41 MB/sec execute 49 sec latency 24828.599 ms 1 2200 0.40 MB/sec execute 50 sec latency 25828.768 ms 1 2200 0.39 MB/sec execute 51 sec latency 26828.911 ms 1 2200 0.38 MB/sec execute 52 sec latency 27829.133 ms 1 2200 0.38 MB/sec execute 53 sec latency 28829.351 ms 1 2200 0.37 MB/sec execute 54 sec latency 29829.583 ms 1 2200 0.36 MB/sec execute 55 sec latency 30829.751 ms 1 2259 0.36 MB/sec execute 56 sec latency 31585.006 ms 1 2416 0.37 MB/sec execute 57 sec latency 153.816 ms oleg301-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 2583 0.38 MB/sec execute 58 sec latency 71.973 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 2931 0.45 MB/sec execute 59 sec latency 58.299 ms 1 3263 0.48 MB/sec execute 60 sec latency 56.856 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Thu Mar 26 09:19:04 EDT 2026 with return code 0 1 3548 0.52 MB/sec execute 61 sec latency 28.198 ms 48378 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 48378 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished