== replay-dual test 26: dbench and tar with mds failover ========================================================== 18:10:33 (1787436633) Starting client oleg301-client.virtnet: -o user_xattr,flock 192.168.203.101@tcp:/lustre /mnt/lustre Started clients oleg301-client.virtnet: 192.168.203.101@tcp:/lustre on /mnt/lustre type lustre (rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose) Started tar loop with pid 65709 Started dbench loop with 65711 striped dir -i0 -c2 -H crush /mnt/lustre2/d26.replay-dual/run_dbench striped dir -i0 -c2 -H all_char /mnt/lustre/d26.replay-dual/run_tar looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1936 1269368 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1756 1269548 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 17948 3584868 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 19492 7190344 1% /mnt/lustre '/usr/share/dbench/client.txt' -> 'client.txt' running 'dbench 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100' on /mnt/lustre at Sat Aug 22 18:10:39 EDT 2026 waiting for dbench pid 65789 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 1 16 0.13 MB/sec warmup 1 sec latency 8.463 ms 1 70 1.56 MB/sec warmup 2 sec latency 204.562 ms 1 111 1.74 MB/sec warmup 3 sec latency 217.856 ms 1 145 1.55 MB/sec warmup 4 sec latency 225.283 ms 1 181 1.46 MB/sec warmup 5 sec latency 132.243 ms 1 199 1.30 MB/sec warmup 6 sec latency 468.896 ms 1 243 1.31 MB/sec warmup 7 sec latency 134.744 ms 1 279 1.30 MB/sec warmup 8 sec latency 158.269 ms test_26 fail mds1 1 times 1 305 1.24 MB/sec warmup 9 sec latency 158.507 ms 1 339 1.22 MB/sec warmup 10 sec latency 171.025 ms Failing mds1 on oleg301-server 1 365 1.18 MB/sec warmup 11 sec latency 164.564 ms Stopping /mnt/lustre-mds1 (opts:) on oleg301-server 1 402 1.18 MB/sec warmup 12 sec latency 124.220 ms 1 429 1.16 MB/sec warmup 13 sec latency 189.528 ms 1 429 1.08 MB/sec warmup 14 sec latency 1189.752 ms 1 429 1.00 MB/sec warmup 15 sec latency 2190.416 ms 18:10:55 (1787436655) shut down facet: mds1 facet_host: oleg301-server facet_failover_host: oleg301-server 1 429 0.94 MB/sec warmup 16 sec latency 3198.648 ms 1 429 0.89 MB/sec warmup 17 sec latency 4200.174 ms 1 429 0.84 MB/sec warmup 18 sec latency 5200.416 ms 1 429 0.79 MB/sec warmup 19 sec latency 6201.243 ms 1 429 0.00 MB/sec execute 1 sec latency 8202.459 ms 1 429 0.00 MB/sec execute 2 sec latency 9202.774 ms 1 429 0.00 MB/sec execute 3 sec latency 10202.916 ms 1 429 0.00 MB/sec execute 4 sec latency 11203.143 ms 1 429 0.00 MB/sec execute 5 sec latency 12204.189 ms 1 429 0.00 MB/sec execute 6 sec latency 13204.490 ms Failover mds1 to oleg301-server mount facets: mds1 1 429 0.00 MB/sec execute 7 sec latency 14204.690 ms 1 429 0.00 MB/sec execute 8 sec latency 15204.888 ms 1 429 0.00 MB/sec execute 9 sec latency 16206.102 ms 1 429 0.00 MB/sec execute 10 sec latency 17208.438 ms 1 429 0.00 MB/sec execute 11 sec latency 18208.879 ms 1 429 0.00 MB/sec execute 12 sec latency 19209.036 ms 1 429 0.00 MB/sec execute 13 sec latency 20210.384 ms 1 429 0.00 MB/sec execute 14 sec latency 21210.636 ms 1 429 0.00 MB/sec execute 15 sec latency 22210.866 ms 1 429 0.00 MB/sec execute 16 sec latency 23211.282 ms 1 429 0.00 MB/sec execute 17 sec latency 24213.280 ms 1 429 0.00 MB/sec execute 18 sec latency 25213.566 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 429 0.00 MB/sec execute 19 sec latency 26214.042 ms 1 429 0.00 MB/sec execute 20 sec latency 27214.314 ms 1 429 0.00 MB/sec execute 21 sec latency 28215.929 ms 1 429 0.00 MB/sec execute 22 sec latency 29216.206 ms 1 429 0.00 MB/sec execute 23 sec latency 30216.432 ms 1 429 0.00 MB/sec execute 24 sec latency 31216.685 ms 1 429 0.00 MB/sec execute 25 sec latency 32216.901 ms 1 429 0.00 MB/sec execute 26 sec latency 33217.274 ms 1 429 0.00 MB/sec execute 27 sec latency 34219.813 ms 1 429 0.00 MB/sec execute 28 sec latency 35220.016 ms oleg301-server: oleg301-server.virtnet: executing set_default_debug -1 all 1 429 0.00 MB/sec execute 29 sec latency 36220.522 ms 1 429 0.00 MB/sec execute 30 sec latency 37223.255 ms 1 429 0.00 MB/sec execute 31 sec latency 38223.781 ms pdsh@oleg301-client: oleg301-server: ssh exited with exit code 1 1 429 0.00 MB/sec execute 32 sec latency 39223.975 ms 1 429 0.00 MB/sec execute 33 sec latency 40230.004 ms Started lustre-MDT0000 18:11:32 (1787436692) targets are mounted 18:11:32 (1787436692) facet_failover done 1 429 0.00 MB/sec execute 34 sec latency 41230.286 ms 1 465 0.03 MB/sec execute 35 sec latency 41436.760 ms 1 504 0.06 MB/sec execute 36 sec latency 146.945 ms 1 542 0.11 MB/sec execute 37 sec latency 164.008 ms 1 601 0.15 MB/sec execute 38 sec latency 610.640 ms 1 654 0.15 MB/sec execute 39 sec latency 114.757 ms 1 678 0.15 MB/sec execute 40 sec latency 162.039 ms oleg301-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 710 0.15 MB/sec execute 41 sec latency 143.914 ms 1 734 0.15 MB/sec execute 42 sec latency 203.076 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 767 0.14 MB/sec execute 43 sec latency 166.536 ms 1 796 0.14 MB/sec execute 44 sec latency 161.423 ms 1 815 0.14 MB/sec execute 45 sec latency 169.427 ms 1 860 0.14 MB/sec execute 46 sec latency 134.992 ms 1 888 0.14 MB/sec execute 47 sec latency 126.104 ms 1 921 0.14 MB/sec execute 48 sec latency 118.158 ms 1 957 0.14 MB/sec execute 49 sec latency 114.806 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2068 1269236 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1904 1269400 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 37488 3568320 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 11692 3585648 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 49180 7153968 1% /mnt/lustre 1 981 0.14 MB/sec execute 50 sec latency 151.810 ms 1 1027 0.15 MB/sec execute 51 sec latency 155.164 ms 1 1067 0.15 MB/sec execute 52 sec latency 121.543 ms 1 1116 0.15 MB/sec execute 53 sec latency 109.122 ms 1 1145 0.15 MB/sec execute 54 sec latency 133.908 ms 1 1172 0.14 MB/sec execute 55 sec latency 247.790 ms 1 1172 0.14 MB/sec execute 56 sec latency 1250.963 ms 1 1198 0.14 MB/sec execute 57 sec latency 1323.014 ms 1 1233 0.14 MB/sec execute 58 sec latency 129.489 ms 1 1268 0.14 MB/sec execute 59 sec latency 167.634 ms 1 1389 0.18 MB/sec execute 60 sec latency 83.100 ms test_26 fail mds2 2 times 1 1410 0.18 MB/sec execute 61 sec latency 150.936 ms 1 1437 0.18 MB/sec execute 62 sec latency 150.487 ms Failing mds2 on oleg301-server 1 1474 0.17 MB/sec execute 63 sec latency 99.904 ms 1 1505 0.17 MB/sec execute 64 sec latency 118.148 ms Stopping /mnt/lustre-mds2 (opts:) on oleg301-server 1 1532 0.17 MB/sec execute 65 sec latency 149.551 ms 1 1557 0.17 MB/sec execute 66 sec latency 185.529 ms 1 1604 0.16 MB/sec execute 67 sec latency 107.361 ms 1 1655 0.16 MB/sec execute 68 sec latency 97.504 ms 1 1692 0.16 MB/sec execute 69 sec latency 121.117 ms 1 1746 0.16 MB/sec execute 70 sec latency 124.707 ms 1 1805 0.16 MB/sec execute 71 sec latency 156.836 ms 1 1857 0.16 MB/sec execute 72 sec latency 116.854 ms 1 1905 0.15 MB/sec execute 73 sec latency 165.373 ms 1 1970 0.15 MB/sec execute 74 sec latency 103.946 ms 1 2010 0.15 MB/sec execute 75 sec latency 124.824 ms 18:12:14 (1787436734) shut down facet: mds2 facet_host: oleg301-server facet_failover_host: oleg301-server 1 2059 0.15 MB/sec execute 76 sec latency 135.003 ms 1 2138 0.15 MB/sec execute 77 sec latency 65.969 ms 1 2166 0.15 MB/sec execute 78 sec latency 126.174 ms 1 2226 0.15 MB/sec execute 79 sec latency 104.488 ms 1 2259 0.15 MB/sec execute 80 sec latency 495.280 ms 1 2259 0.14 MB/sec execute 81 sec latency 1495.743 ms 1 2259 0.14 MB/sec execute 82 sec latency 2497.126 ms 1 2259 0.14 MB/sec execute 83 sec latency 3497.965 ms 1 2259 0.14 MB/sec execute 84 sec latency 4498.127 ms 1 2259 0.14 MB/sec execute 85 sec latency 5498.878 ms Failover mds2 to oleg301-server mount facets: mds2 1 2259 0.14 MB/sec execute 86 sec latency 6499.087 ms 1 2259 0.13 MB/sec execute 87 sec latency 7500.530 ms 1 2259 0.13 MB/sec execute 88 sec latency 8501.231 ms 1 2259 0.13 MB/sec execute 89 sec latency 9502.004 ms 1 2259 0.13 MB/sec execute 90 sec latency 10509.877 ms 1 2259 0.13 MB/sec execute 91 sec latency 11510.162 ms 1 2259 0.13 MB/sec execute 92 sec latency 12511.184 ms 1 2259 0.13 MB/sec execute 93 sec latency 13511.467 ms 1 2259 0.12 MB/sec execute 94 sec latency 14527.446 ms 1 2259 0.12 MB/sec execute 95 sec latency 15528.753 ms 1 2259 0.12 MB/sec execute 96 sec latency 16530.725 ms 1 2259 0.12 MB/sec execute 97 sec latency 17535.893 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 2259 0.12 MB/sec execute 98 sec latency 18536.184 ms 1 2259 0.12 MB/sec execute 99 sec latency 19536.592 ms 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec 1 cleanup 103 sec oleg301-server: oleg301-server.virtnet: executing set_default_debug -1 all 1 cleanup 104 sec 1 cleanup 105 sec pdsh@oleg301-client: oleg301-server: ssh exited with exit code 1 1 cleanup 106 sec Started lustre-MDT0001 18:12:46 (1787436766) targets are mounted 18:12:46 (1787436766) facet_failover done 1 cleanup 107 sec 1 cleanup 108 sec 1 cleanup 109 sec 0 cleanup 110 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 329 268.099 41436.745 Close 285 14.952 78.924 Rename 11 122.348 203.059 Unlink 30 32.291 62.004 Qpathinfo 295 17.810 123.716 Qfileinfo 78 2.340 20.769 Qfsinfo 33 5.565 35.033 Sfileinfo 34 75.042 169.412 Find 92 14.494 46.374 WriteX 266 13.265 99.891 ReadX 348 3.310 135.306 Flush 30 67.026 146.020 Throughput 0.117572 MB/sec 1 clients 1 procs max_latency=41436.760 ms stopping dbench on /mnt/lustre at Sat Aug 22 18:12:49 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished striped dir -i0 -c2 -H crush /mnt/lustre2/d26.replay-dual/run_dbench oleg301-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 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 Sat Aug 22 18:12:57 EDT 2026 waiting for dbench pid 67867 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 1 25 0.72 MB/sec warmup 1 sec latency 20.706 ms 1 82 1.83 MB/sec warmup 2 sec latency 103.833 ms 1 121 1.83 MB/sec warmup 3 sec latency 124.613 ms 1 147 1.56 MB/sec warmup 4 sec latency 203.334 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2268 1269036 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2180 1269124 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 27092 3578396 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 19508 3586592 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 46600 7164988 1% /mnt/lustre 1 161 1.32 MB/sec warmup 5 sec latency 272.898 ms 1 181 1.22 MB/sec warmup 6 sec latency 250.805 ms 1 197 1.12 MB/sec warmup 7 sec latency 424.658 ms 1 221 1.07 MB/sec warmup 8 sec latency 234.569 ms 1 247 1.04 MB/sec warmup 9 sec latency 190.145 ms 1 272 1.02 MB/sec warmup 10 sec latency 169.757 ms 1 297 0.99 MB/sec warmup 11 sec latency 169.446 ms 1 321 0.97 MB/sec warmup 12 sec latency 190.296 ms 1 341 0.94 MB/sec warmup 13 sec latency 224.842 ms 1 358 0.91 MB/sec warmup 14 sec latency 241.738 ms 1 397 0.94 MB/sec warmup 15 sec latency 160.796 ms 1 437 0.96 MB/sec warmup 16 sec latency 110.714 ms test_26 fail mds1 3 times 1 462 0.95 MB/sec warmup 17 sec latency 231.600 ms 1 486 0.94 MB/sec warmup 18 sec latency 191.485 ms 1 504 0.92 MB/sec warmup 19 sec latency 231.736 ms Failing mds1 on oleg301-server 1 636 1.95 MB/sec execute 1 sec latency 192.136 ms Stopping /mnt/lustre-mds1 (opts:) on oleg301-server 1 656 0.98 MB/sec execute 2 sec latency 200.287 ms 1 674 0.69 MB/sec execute 3 sec latency 319.726 ms 1 674 0.52 MB/sec execute 4 sec latency 1321.049 ms 1 674 0.41 MB/sec execute 5 sec latency 2321.280 ms 1 674 0.35 MB/sec execute 6 sec latency 3321.542 ms 1 674 0.30 MB/sec execute 7 sec latency 4321.937 ms 18:13:24 (1787436804) shut down facet: mds1 facet_host: oleg301-server facet_failover_host: oleg301-server 1 674 0.26 MB/sec execute 8 sec latency 5322.196 ms 1 674 0.23 MB/sec execute 9 sec latency 6331.128 ms 1 674 0.21 MB/sec execute 10 sec latency 7331.358 ms 1 674 0.19 MB/sec execute 11 sec latency 8331.635 ms 1 674 0.17 MB/sec execute 12 sec latency 9331.887 ms 1 674 0.16 MB/sec execute 13 sec latency 10332.798 ms 1 674 0.15 MB/sec execute 14 sec latency 11333.692 ms 1 674 0.14 MB/sec execute 15 sec latency 12333.887 ms 1 674 0.13 MB/sec execute 16 sec latency 13334.181 ms 1 674 0.12 MB/sec execute 17 sec latency 14336.965 ms Failover mds1 to oleg301-server mount facets: mds1 1 674 0.11 MB/sec execute 18 sec latency 15349.640 ms 1 674 0.11 MB/sec execute 19 sec latency 16349.885 ms 1 674 0.10 MB/sec execute 20 sec latency 17352.164 ms 1 674 0.10 MB/sec execute 21 sec latency 18352.912 ms 1 674 0.09 MB/sec execute 22 sec latency 19354.247 ms 1 674 0.09 MB/sec execute 23 sec latency 20365.941 ms 1 674 0.09 MB/sec execute 24 sec latency 21370.912 ms 1 674 0.08 MB/sec execute 25 sec latency 22371.112 ms 1 674 0.08 MB/sec execute 26 sec latency 23371.811 ms 1 674 0.08 MB/sec execute 27 sec latency 24380.465 ms 1 674 0.07 MB/sec execute 28 sec latency 25387.351 ms 1 674 0.07 MB/sec execute 29 sec latency 26388.724 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 674 0.07 MB/sec execute 30 sec latency 27388.955 ms 1 674 0.07 MB/sec execute 31 sec latency 28390.452 ms 1 674 0.06 MB/sec execute 32 sec latency 29391.489 ms 1 674 0.06 MB/sec execute 33 sec latency 30392.540 ms 1 674 0.06 MB/sec execute 34 sec latency 31392.942 ms 1 674 0.06 MB/sec execute 35 sec latency 32393.888 ms 1 674 0.06 MB/sec execute 36 sec latency 33394.186 ms 1 674 0.06 MB/sec execute 37 sec latency 34394.495 ms 1 674 0.05 MB/sec execute 38 sec latency 35394.696 ms 1 674 0.05 MB/sec execute 39 sec latency 36395.502 ms 1 674 0.05 MB/sec execute 40 sec latency 37395.999 ms oleg301-server: oleg301-server.virtnet: executing set_default_debug -1 all 1 674 0.05 MB/sec execute 41 sec latency 38397.624 ms 1 674 0.05 MB/sec execute 42 sec latency 39397.909 ms pdsh@oleg301-client: oleg301-server: ssh exited with exit code 1 1 695 0.05 MB/sec execute 43 sec latency 39670.201 ms Started lustre-MDT0000 1 712 0.05 MB/sec execute 44 sec latency 176.551 ms 18:14:02 (1787436842) targets are mounted 18:14:02 (1787436842) facet_failover done 1 720 0.05 MB/sec execute 45 sec latency 720.741 ms 1 747 0.05 MB/sec execute 46 sec latency 794.186 ms 1 786 0.05 MB/sec execute 47 sec latency 128.989 ms 1 806 0.05 MB/sec execute 48 sec latency 153.481 ms 1 845 0.05 MB/sec execute 49 sec latency 243.581 ms 1 874 0.05 MB/sec execute 50 sec latency 131.051 ms 1 895 0.05 MB/sec execute 51 sec latency 167.665 ms 1 914 0.05 MB/sec execute 52 sec latency 188.076 ms oleg301-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 949 0.05 MB/sec execute 53 sec latency 134.119 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 977 0.05 MB/sec execute 54 sec latency 131.303 ms 1 990 0.05 MB/sec execute 55 sec latency 169.642 ms 1 1041 0.07 MB/sec execute 56 sec latency 128.220 ms 1 1076 0.07 MB/sec execute 57 sec latency 123.769 ms 1 1124 0.07 MB/sec execute 58 sec latency 105.879 ms 1 1147 0.07 MB/sec execute 59 sec latency 165.291 ms 1 1192 0.07 MB/sec execute 60 sec latency 171.773 ms 1 1231 0.06 MB/sec execute 61 sec latency 87.333 ms 1 1266 0.06 MB/sec execute 62 sec latency 119.156 ms 1 1378 0.11 MB/sec execute 63 sec latency 322.641 ms 1 1412 0.11 MB/sec execute 64 sec latency 188.143 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 1457 0.11 MB/sec execute 65 sec latency 123.929 ms 1 1497 0.11 MB/sec execute 66 sec latency 101.816 ms 1 1538 0.10 MB/sec execute 67 sec latency 133.326 ms 1 1568 0.10 MB/sec execute 68 sec latency 106.845 ms 1 1588 0.10 MB/sec execute 69 sec latency 113.619 ms 1 1619 0.10 MB/sec execute 70 sec latency 187.781 ms 1 1650 0.10 MB/sec execute 71 sec latency 213.213 ms 1 1677 0.10 MB/sec execute 72 sec latency 144.165 ms 1 1700 0.10 MB/sec execute 73 sec latency 134.288 ms 1 1764 0.10 MB/sec execute 74 sec latency 130.294 ms 1 1797 0.10 MB/sec execute 75 sec latency 147.918 ms 1 1825 0.09 MB/sec execute 76 sec latency 151.247 ms 1 1857 0.09 MB/sec execute 77 sec latency 154.871 ms 1 1909 0.09 MB/sec execute 78 sec latency 124.839 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 1 1978 0.09 MB/sec execute 79 sec latency 93.025 ms stopping dbench on /mnt/lustre at Sat Aug 22 18:14:37 EDT 2026 with return code 0 67867 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 67867 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished