== replay-dual test 26: dbench and tar with mds failover ========================================================== 13:27:01 (1781285221) Starting client oleg125-client.virtnet: -o user_xattr,flock oleg125-server@tcp:/lustre /mnt/lustre Started clients oleg125-client.virtnet: 192.168.201.125@tcp:/lustre on /mnt/lustre type lustre (rw,checksum,flock,user_xattr,lruresize,lazystatfs,nouser_fid2path,verbose,encrypt) Started tar loop with pid 64837 Started dbench loop with 64838 striped dir -i0 -c2 -H all_char /mnt/lustre/d26.replay-dual/run_tar striped dir -i0 -c2 -H fnv_1a_64 /mnt/lustre2/d26.replay-dual/run_dbench 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 2210560 3584 2204928 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 2210688 3200 2205440 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3771392 3072 3747840 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 3072 3766272 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 6144 7514112 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 Fri Jun 12 13:27:09 EDT 2026 waiting for dbench pid 64920 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 0 5 0.00 MB/sec warmup 1 sec latency 133.785 ms 1 34 0.52 MB/sec warmup 2 sec latency 200.693 ms 1 101 1.55 MB/sec warmup 3 sec latency 161.593 ms test_26 fail mds1 1 times 1 129 1.44 MB/sec warmup 4 sec latency 269.188 ms 1 152 1.28 MB/sec warmup 5 sec latency 202.438 ms Failing mds1 on oleg125-server 1 181 1.22 MB/sec warmup 6 sec latency 192.900 ms Stopping /mnt/lustre-mds1 (opts:) on oleg125-server 1 207 1.16 MB/sec warmup 7 sec latency 236.210 ms 1 232 1.11 MB/sec warmup 8 sec latency 176.861 ms 1 271 1.13 MB/sec warmup 9 sec latency 172.857 ms 1 306 1.12 MB/sec warmup 10 sec latency 141.955 ms reboot facets: mds1 1 339 1.11 MB/sec warmup 11 sec latency 215.272 ms 1 339 1.02 MB/sec warmup 12 sec latency 1222.920 ms 1 339 0.94 MB/sec warmup 13 sec latency 2223.331 ms 1 339 0.87 MB/sec warmup 14 sec latency 3223.794 ms 1 339 0.82 MB/sec warmup 15 sec latency 4225.039 ms 1 339 0.77 MB/sec warmup 16 sec latency 5225.395 ms 1 339 0.72 MB/sec warmup 17 sec latency 6226.895 ms 1 339 0.68 MB/sec warmup 18 sec latency 7229.393 ms 1 339 0.64 MB/sec warmup 19 sec latency 8229.747 ms Failover mds1 to oleg125-server 1 339 0.00 MB/sec execute 1 sec latency 10234.629 ms 1 339 0.00 MB/sec execute 2 sec latency 11235.120 ms mount facets: mds1 1 339 0.00 MB/sec execute 3 sec latency 12235.761 ms 1 339 0.00 MB/sec execute 4 sec latency 13236.190 ms 1 339 0.00 MB/sec execute 5 sec latency 14237.586 ms Starting mds1: -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 339 0.00 MB/sec execute 6 sec latency 15239.306 ms 1 339 0.00 MB/sec execute 7 sec latency 16241.415 ms 1 339 0.00 MB/sec execute 8 sec latency 17242.258 ms 1 339 0.00 MB/sec execute 9 sec latency 18244.207 ms 1 339 0.00 MB/sec execute 10 sec latency 19244.660 ms 1 339 0.00 MB/sec execute 11 sec latency 20244.896 ms 1 339 0.00 MB/sec execute 12 sec latency 21245.263 ms oleg125-server: oleg125-server.virtnet: executing set_default_debug -1 all 8 1 339 0.00 MB/sec execute 13 sec latency 22248.496 ms pdsh@oleg125-client: oleg125-server: ssh exited with exit code 1 1 339 0.00 MB/sec execute 14 sec latency 23254.695 ms Started lustre-MDT0000 1 339 0.00 MB/sec execute 15 sec latency 24256.355 ms 1 373 0.06 MB/sec execute 16 sec latency 24316.923 ms 1 405 0.12 MB/sec execute 17 sec latency 187.725 ms 1 440 0.17 MB/sec execute 18 sec latency 185.017 ms 1 501 0.27 MB/sec execute 19 sec latency 146.612 ms 1 523 0.29 MB/sec execute 20 sec latency 198.612 ms 1 612 0.41 MB/sec execute 21 sec latency 90.919 ms oleg125-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 664 0.40 MB/sec execute 22 sec latency 103.347 ms 1 680 0.39 MB/sec execute 23 sec latency 314.973 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 711 0.37 MB/sec execute 24 sec latency 143.505 ms 1 733 0.36 MB/sec execute 25 sec latency 171.554 ms 1 765 0.35 MB/sec execute 26 sec latency 211.457 ms 1 796 0.34 MB/sec execute 27 sec latency 181.708 ms 1 857 0.33 MB/sec execute 28 sec latency 81.804 ms 1 909 0.33 MB/sec execute 29 sec latency 97.695 ms 1 949 0.32 MB/sec execute 30 sec latency 158.356 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 3968 2204544 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 2210688 3712 2204928 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3771392 39936 3677184 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 10240 3699712 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 50176 7376896 1% /mnt/lustre 1 980 0.31 MB/sec execute 31 sec latency 124.439 ms 1 1040 0.33 MB/sec execute 32 sec latency 221.629 ms 1 1086 0.32 MB/sec execute 33 sec latency 83.550 ms 1 1134 0.31 MB/sec execute 34 sec latency 121.583 ms 1 1181 0.31 MB/sec execute 35 sec latency 80.878 ms 1 1239 0.30 MB/sec execute 36 sec latency 70.791 ms test_26 fail mds2 2 times 1 1273 0.29 MB/sec execute 37 sec latency 114.892 ms 1 1396 0.36 MB/sec execute 38 sec latency 133.969 ms Failing mds2 on oleg125-server 1 1426 0.35 MB/sec execute 39 sec latency 146.964 ms Stopping /mnt/lustre-mds2 (opts:) on oleg125-server 1 1481 0.34 MB/sec execute 40 sec latency 89.996 ms 1 1512 0.34 MB/sec execute 41 sec latency 158.210 ms 1 1564 0.33 MB/sec execute 42 sec latency 100.191 ms 1 1610 0.32 MB/sec execute 43 sec latency 106.958 ms 1 1643 0.32 MB/sec execute 44 sec latency 296.872 ms reboot facets: mds2 1 1684 0.31 MB/sec execute 45 sec latency 218.396 ms 1 1748 0.30 MB/sec execute 46 sec latency 116.490 ms 1 1810 0.30 MB/sec execute 47 sec latency 77.471 ms 1 1873 0.29 MB/sec execute 48 sec latency 82.421 ms 1 1924 0.29 MB/sec execute 49 sec latency 298.446 ms 1 2010 0.28 MB/sec execute 50 sec latency 51.596 ms 1 2098 0.28 MB/sec execute 51 sec latency 72.352 ms 1 2166 0.28 MB/sec execute 52 sec latency 193.376 ms 1 2239 0.27 MB/sec execute 53 sec latency 119.519 ms 1 2259 0.27 MB/sec execute 54 sec latency 859.930 ms Failover mds2 to oleg125-server 1 2259 0.26 MB/sec execute 55 sec latency 1860.414 ms 1 2259 0.26 MB/sec execute 56 sec latency 2861.091 ms 1 2259 0.25 MB/sec execute 57 sec latency 3880.413 ms mount facets: mds2 1 2259 0.25 MB/sec execute 58 sec latency 4884.589 ms 1 2259 0.25 MB/sec execute 59 sec latency 5886.541 ms 1 2259 0.24 MB/sec execute 60 sec latency 6886.907 ms 1 2259 0.24 MB/sec execute 61 sec latency 7888.285 ms Starting mds2: -o localrecov lustre-mdt2/mdt2 /mnt/lustre-mds2 1 2259 0.23 MB/sec execute 62 sec latency 8895.719 ms 1 2259 0.23 MB/sec execute 63 sec latency 9896.640 ms 1 2259 0.23 MB/sec execute 64 sec latency 10896.846 ms 1 2259 0.22 MB/sec execute 65 sec latency 11908.347 ms 1 2259 0.22 MB/sec execute 66 sec latency 12908.544 ms 1 2259 0.22 MB/sec execute 67 sec latency 13908.995 ms 1 2259 0.21 MB/sec execute 68 sec latency 14909.874 ms 1 2259 0.21 MB/sec execute 69 sec latency 15910.794 ms oleg125-server: oleg125-server.virtnet: executing set_default_debug -1 all 8 1 2292 0.22 MB/sec execute 70 sec latency 16376.954 ms 1 2337 0.22 MB/sec execute 71 sec latency 108.739 ms pdsh@oleg125-client: oleg125-server: ssh exited with exit code 1 1 2359 0.22 MB/sec execute 72 sec latency 241.909 ms 1 2377 0.21 MB/sec execute 73 sec latency 455.135 ms Started lustre-MDT0001 1 2406 0.21 MB/sec execute 74 sec latency 205.388 ms 1 2428 0.21 MB/sec execute 75 sec latency 361.438 ms 1 2453 0.21 MB/sec execute 76 sec latency 153.693 ms 1 2478 0.21 MB/sec execute 77 sec latency 283.896 ms 1 2506 0.21 MB/sec execute 78 sec latency 155.933 ms 1 2577 0.21 MB/sec execute 79 sec latency 173.298 ms 1 2604 0.21 MB/sec execute 80 sec latency 160.896 ms 1 2753 0.24 MB/sec execute 81 sec latency 125.768 ms 1 2776 0.24 MB/sec execute 82 sec latency 295.721 ms 1 2897 0.25 MB/sec execute 83 sec latency 107.114 ms oleg125-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1 2929 0.25 MB/sec execute 84 sec latency 133.629 ms 1 2982 0.25 MB/sec execute 85 sec latency 167.060 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 3010 0.25 MB/sec execute 86 sec latency 241.101 ms 1 3172 0.25 MB/sec execute 87 sec latency 145.638 ms 1 3204 0.25 MB/sec execute 88 sec latency 279.815 ms 1 3275 0.26 MB/sec execute 89 sec latency 132.106 ms 1 3325 0.26 MB/sec execute 90 sec latency 147.517 ms 1 3359 0.25 MB/sec execute 91 sec latency 151.747 ms 1 3410 0.26 MB/sec execute 92 sec latency 120.055 ms 1 3533 0.28 MB/sec execute 93 sec latency 102.407 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 4480 2204032 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 2210688 4352 2204288 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3771392 55296 3712000 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 15360 3733504 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 70656 7445504 1% /mnt/lustre 1 3584 0.28 MB/sec execute 94 sec latency 81.241 ms 1 3636 0.28 MB/sec execute 95 sec latency 105.060 ms 1 3682 0.28 MB/sec execute 96 sec latency 148.194 ms 1 3724 0.27 MB/sec execute 97 sec latency 89.456 ms 1 3780 0.28 MB/sec execute 98 sec latency 148.298 ms 1 3802 0.28 MB/sec execute 99 sec latency 172.443 ms test_26 fail mds1 3 times 1 cleanup 100 sec 1 cleanup 101 sec Failing mds1 on oleg125-server 1 cleanup 102 sec 1 cleanup 103 sec Stopping /mnt/lustre-mds1 (opts:) on oleg125-server 1 cleanup 104 sec 1 cleanup 105 sec 1 cleanup 106 sec 1 cleanup 107 sec reboot facets: mds1 1 cleanup 108 sec 1 cleanup 109 sec 1 cleanup 110 sec 1 cleanup 111 sec 1 cleanup 112 sec 1 cleanup 113 sec 1 cleanup 114 sec 1 cleanup 115 sec 1 cleanup 116 sec 1 cleanup 117 sec Failover mds1 to oleg125-server 1 cleanup 118 sec 1 cleanup 119 sec mount facets: mds1 1 cleanup 120 sec 1 cleanup 121 sec 1 cleanup 122 sec 1 cleanup 123 sec Starting mds1: -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 cleanup 124 sec 1 cleanup 125 sec 1 cleanup 126 sec 1 cleanup 127 sec 1 cleanup 128 sec 1 cleanup 129 sec 1 cleanup 130 sec 1 cleanup 131 sec 1 cleanup 132 sec 1 cleanup 133 sec 1 cleanup 134 sec 1 cleanup 135 sec 1 cleanup 136 sec 1 cleanup 137 sec 1 cleanup 138 sec 1 cleanup 139 sec 1 cleanup 140 sec oleg125-server: oleg125-server.virtnet: executing set_default_debug -1 all 8 1 cleanup 141 sec 0 cleanup 142 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 534 134.036 24316.889 Close 438 13.238 71.939 Rename 26 78.912 205.353 Unlink 72 28.566 74.786 Qpathinfo 490 17.226 121.567 Qfileinfo 133 2.517 21.436 Qfsinfo 94 3.763 39.161 Sfileinfo 50 47.023 114.868 Find 193 13.521 90.897 WriteX 468 12.440 99.244 ReadX 953 0.737 93.896 LockX 2 13.319 15.614 UnlockX 2 6.117 6.209 Flush 43 166.998 455.107 Throughput 0.277159 MB/sec 1 clients 1 procs max_latency=24316.923 ms stopping dbench on /mnt/lustre at Fri Jun 12 13:29:51 EDT 2026 with return code 0 pdsh@oleg125-client: oleg125-server: ssh exited with exit code 1 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre Started lustre-MDT0000 removed 'client.txt' /mnt/lustre dbench successfully finished striped dir -i0 -c2 -H all_char /mnt/lustre2/d26.replay-dual/run_dbench looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt oleg125-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid '/usr/share/dbench/client.txt' -> 'client.txt' running 'dbench 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100' on /mnt/lustre at Fri Jun 12 13:30:03 EDT 2026 waiting for dbench pid 67806 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 0 3 0.00 MB/sec warmup 1 sec latency 791.967 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 0 12 0.00 MB/sec warmup 2 sec latency 44.748 ms 1 71 1.05 MB/sec warmup 3 sec latency 153.419 ms 1 113 1.31 MB/sec warmup 4 sec latency 188.277 ms 1 157 1.31 MB/sec warmup 5 sec latency 144.194 ms 1 186 1.24 MB/sec warmup 6 sec latency 202.973 ms 1 210 1.16 MB/sec warmup 7 sec latency 195.661 ms 1 243 1.15 MB/sec warmup 8 sec latency 174.626 ms 1 271 1.13 MB/sec warmup 9 sec latency 238.459 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210432 4864 2203520 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 2210560 4736 2203776 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3771392 20480 3735552 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 40960 3709952 2% /mnt/lustre[OST:1] filesystem_summary: 7542784 61440 7445504 1% /mnt/lustre 1 290 1.07 MB/sec warmup 10 sec latency 260.279 ms 1 318 1.04 MB/sec warmup 11 sec latency 182.138 ms 1 341 1.02 MB/sec warmup 12 sec latency 188.811 ms 1 374 1.02 MB/sec warmup 13 sec latency 184.161 ms 1 406 1.02 MB/sec warmup 14 sec latency 177.829 ms 1 445 1.04 MB/sec warmup 15 sec latency 178.839 ms 1 485 1.06 MB/sec warmup 16 sec latency 134.653 ms test_26 fail mds2 4 times 1 513 1.04 MB/sec warmup 17 sec latency 212.585 ms 1 573 1.07 MB/sec warmup 18 sec latency 227.668 ms 1 636 1.11 MB/sec warmup 19 sec latency 138.482 ms Failing mds2 on oleg125-server Stopping /mnt/lustre-mds2 (opts:) on oleg125-server 1 678 0.03 MB/sec execute 1 sec latency 262.419 ms 1 711 0.03 MB/sec execute 2 sec latency 278.879 ms 1 711 0.02 MB/sec execute 3 sec latency 1279.265 ms 1 711 0.01 MB/sec execute 4 sec latency 2279.609 ms reboot facets: mds2 1 711 0.01 MB/sec execute 5 sec latency 3280.652 ms 1 711 0.01 MB/sec execute 6 sec latency 4281.070 ms 1 711 0.01 MB/sec execute 7 sec latency 5281.522 ms 1 711 0.01 MB/sec execute 8 sec latency 6282.189 ms 1 711 0.01 MB/sec execute 9 sec latency 7285.069 ms 1 711 0.01 MB/sec execute 10 sec latency 8285.689 ms 1 711 0.00 MB/sec execute 11 sec latency 9286.735 ms 1 711 0.00 MB/sec execute 12 sec latency 10288.415 ms 1 711 0.00 MB/sec execute 13 sec latency 11294.770 ms 1 711 0.00 MB/sec execute 14 sec latency 12297.019 ms Failover mds2 to oleg125-server 1 711 0.00 MB/sec execute 15 sec latency 13297.309 ms 1 711 0.00 MB/sec execute 16 sec latency 14298.077 ms mount facets: mds2 1 711 0.00 MB/sec execute 17 sec latency 15300.423 ms 1 711 0.00 MB/sec execute 18 sec latency 16300.752 ms 1 711 0.00 MB/sec execute 19 sec latency 17301.134 ms Starting mds2: -o localrecov lustre-mdt2/mdt2 /mnt/lustre-mds2 1 711 0.00 MB/sec execute 20 sec latency 18301.548 ms 1 711 0.00 MB/sec execute 21 sec latency 19302.280 ms 1 711 0.00 MB/sec execute 22 sec latency 20302.434 ms 1 711 0.00 MB/sec execute 23 sec latency 21303.448 ms 1 711 0.00 MB/sec execute 24 sec latency 22303.664 ms 1 711 0.00 MB/sec execute 25 sec latency 23303.984 ms 1 711 0.00 MB/sec execute 26 sec latency 24306.020 ms 1 711 0.00 MB/sec execute 27 sec latency 25306.706 ms oleg125-server: oleg125-server.virtnet: executing set_default_debug -1 all 8 1 711 0.00 MB/sec execute 28 sec latency 26307.628 ms 1 711 0.00 MB/sec execute 29 sec latency 27307.995 ms 1 711 0.00 MB/sec execute 30 sec latency 28308.261 ms pdsh@oleg125-client: oleg125-server: ssh exited with exit code 1 1 723 0.00 MB/sec execute 31 sec latency 28745.156 ms Started lustre-MDT0001 1 735 0.01 MB/sec execute 32 sec latency 204.162 ms 1 774 0.01 MB/sec execute 33 sec latency 147.589 ms 1 791 0.01 MB/sec execute 34 sec latency 253.542 ms 1 812 0.01 MB/sec execute 35 sec latency 196.252 ms 1 860 0.01 MB/sec execute 36 sec latency 164.408 ms 1 881 0.01 MB/sec execute 37 sec latency 288.416 ms 1 910 0.02 MB/sec execute 38 sec latency 119.604 ms 1 939 0.02 MB/sec execute 39 sec latency 195.558 ms oleg125-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1 971 0.02 MB/sec execute 40 sec latency 121.007 ms 1 993 0.02 MB/sec execute 41 sec latency 236.447 ms 1 1060 0.04 MB/sec execute 42 sec latency 111.779 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 1128 0.04 MB/sec execute 43 sec latency 69.623 ms 1 1185 0.04 MB/sec execute 44 sec latency 101.689 ms 1 1257 0.04 MB/sec execute 45 sec latency 82.356 ms 1 1384 0.11 MB/sec execute 46 sec latency 98.731 ms 1 1421 0.10 MB/sec execute 47 sec latency 137.822 ms 1 1481 0.10 MB/sec execute 48 sec latency 75.229 ms 1 1523 0.10 MB/sec execute 49 sec latency 132.510 ms 1 1573 0.10 MB/sec execute 50 sec latency 85.827 ms 1 1632 0.10 MB/sec execute 51 sec latency 68.474 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 1667 0.10 MB/sec execute 52 sec latency 138.543 ms 1 1721 0.10 MB/sec execute 53 sec latency 192.058 ms 1 1801 0.10 MB/sec execute 54 sec latency 96.594 ms 1 1848 0.09 MB/sec execute 55 sec latency 93.644 ms 1 1888 0.09 MB/sec execute 56 sec latency 269.858 ms 1 1958 0.09 MB/sec execute 57 sec latency 189.849 ms 1 2006 0.09 MB/sec execute 58 sec latency 76.134 ms 1 2056 0.09 MB/sec execute 59 sec latency 78.480 ms 1 2117 0.09 MB/sec execute 60 sec latency 89.561 ms 1 2168 0.09 MB/sec execute 61 sec latency 103.513 ms 1 2235 0.09 MB/sec execute 62 sec latency 95.723 ms 1 2305 0.10 MB/sec execute 63 sec latency 86.661 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Fri Jun 12 13:31:26 EDT 2026 with return code 0 67806 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 67806 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished