== replay-dual test 26: dbench and tar with mds failover ========================================================== 00:56:24 (1790744184) Starting client oleg309-client.virtnet: -o user_xattr,flock 192.168.203.109@tcp:/lustre /mnt/lustre Started clients oleg309-client.virtnet: 192.168.203.109@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 65667 Started dbench loop with 65669 striped dir -i0 -c2 -H crush /mnt/lustre/d26.replay-dual/run_tar striped dir -i0 -c2 -H crush /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 1414116 1980 1269324 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1788 1269516 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1564 3605456 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 9736 3593088 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 11300 7198544 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 Wed Sep 30 00:56:31 EDT 2026 waiting for dbench pid 65747 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 8 0.00 MB/sec warmup 1 sec latency 129.929 ms 1 51 1.05 MB/sec warmup 2 sec latency 135.754 ms 1 94 1.39 MB/sec warmup 3 sec latency 184.314 ms 1 129 1.44 MB/sec warmup 4 sec latency 232.380 ms 1 155 1.31 MB/sec warmup 5 sec latency 199.494 ms 1 174 1.18 MB/sec warmup 6 sec latency 384.134 ms 1 197 1.12 MB/sec warmup 7 sec latency 503.954 ms 1 231 1.11 MB/sec warmup 8 sec latency 166.779 ms 1 271 1.13 MB/sec warmup 9 sec latency 133.316 ms test_26 fail mds1 1 times 1 300 1.09 MB/sec warmup 10 sec latency 161.273 ms 1 324 1.07 MB/sec warmup 11 sec latency 220.802 ms Failing mds1 on oleg309-server 1 354 1.05 MB/sec warmup 12 sec latency 161.940 ms Stopping /mnt/lustre-mds1 (opts:) on oleg309-server 1 396 1.08 MB/sec warmup 13 sec latency 135.888 ms 1 412 1.04 MB/sec warmup 14 sec latency 537.096 ms 1 412 0.97 MB/sec warmup 15 sec latency 1538.041 ms 1 412 0.91 MB/sec warmup 16 sec latency 2538.696 ms 00:56:47 (1790744207) shut down facet: mds1 facet_host: oleg309-server facet_failover_host: oleg309-server 1 412 0.86 MB/sec warmup 17 sec latency 3539.963 ms 1 412 0.81 MB/sec warmup 18 sec latency 4543.035 ms 1 412 0.77 MB/sec warmup 19 sec latency 5543.290 ms 1 412 0.00 MB/sec execute 1 sec latency 7543.717 ms 1 412 0.00 MB/sec execute 2 sec latency 8544.857 ms 1 412 0.00 MB/sec execute 3 sec latency 9545.128 ms 1 412 0.00 MB/sec execute 4 sec latency 10548.487 ms 1 412 0.00 MB/sec execute 5 sec latency 11548.724 ms 1 412 0.00 MB/sec execute 6 sec latency 12548.961 ms Failover mds1 to oleg309-server mount facets: mds1 1 412 0.00 MB/sec execute 7 sec latency 13549.145 ms 1 412 0.00 MB/sec execute 8 sec latency 14551.452 ms 1 412 0.00 MB/sec execute 9 sec latency 15551.703 ms 1 412 0.00 MB/sec execute 10 sec latency 16552.591 ms 1 412 0.00 MB/sec execute 11 sec latency 17552.989 ms 1 412 0.00 MB/sec execute 12 sec latency 18553.174 ms 1 412 0.00 MB/sec execute 13 sec latency 19553.711 ms 1 412 0.00 MB/sec execute 14 sec latency 20554.139 ms 1 412 0.00 MB/sec execute 15 sec latency 21554.420 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 412 0.00 MB/sec execute 16 sec latency 22554.805 ms 1 412 0.00 MB/sec execute 17 sec latency 23557.611 ms 1 412 0.00 MB/sec execute 18 sec latency 24557.970 ms 1 412 0.00 MB/sec execute 19 sec latency 25558.215 ms 1 412 0.00 MB/sec execute 20 sec latency 26558.710 ms 1 412 0.00 MB/sec execute 21 sec latency 27560.349 ms 1 412 0.00 MB/sec execute 22 sec latency 28561.221 ms 1 412 0.00 MB/sec execute 23 sec latency 29562.479 ms 1 412 0.00 MB/sec execute 24 sec latency 30564.037 ms 1 412 0.00 MB/sec execute 25 sec latency 31564.619 ms 1 412 0.00 MB/sec execute 26 sec latency 32564.876 ms oleg309-server: oleg309-server.virtnet: executing set_default_debug -1 all 1 412 0.00 MB/sec execute 27 sec latency 33565.115 ms 1 412 0.00 MB/sec execute 28 sec latency 34565.349 ms pdsh@oleg309-client: oleg309-server: ssh exited with exit code 1 1 412 0.00 MB/sec execute 29 sec latency 35565.830 ms Started lustre-MDT0000 00:57:20 (1790744240) targets are mounted 00:57:20 (1790744240) facet_failover done 1 429 0.02 MB/sec execute 30 sec latency 36026.827 ms 1 461 0.05 MB/sec execute 31 sec latency 181.689 ms 1 493 0.08 MB/sec execute 32 sec latency 140.303 ms 1 513 0.09 MB/sec execute 33 sec latency 227.558 ms 1 552 0.13 MB/sec execute 34 sec latency 306.505 ms 1 606 0.18 MB/sec execute 35 sec latency 681.393 ms 1 649 0.18 MB/sec execute 36 sec latency 130.207 ms oleg309-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 685 0.18 MB/sec execute 37 sec latency 110.589 ms 1 711 0.17 MB/sec execute 38 sec latency 127.606 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 738 0.17 MB/sec execute 39 sec latency 127.838 ms 1 769 0.17 MB/sec execute 40 sec latency 133.993 ms 1 798 0.17 MB/sec execute 41 sec latency 196.309 ms 1 849 0.17 MB/sec execute 42 sec latency 87.770 ms 1 885 0.16 MB/sec execute 43 sec latency 130.270 ms 1 916 0.16 MB/sec execute 44 sec latency 134.286 ms 1 955 0.16 MB/sec execute 45 sec latency 111.626 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2140 1269164 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1908 1269396 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 6928 3597128 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 45484 3552804 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 52412 7149932 1% /mnt/lustre 1 983 0.16 MB/sec execute 46 sec latency 156.543 ms 1 1031 0.18 MB/sec execute 47 sec latency 144.988 ms 1 1076 0.17 MB/sec execute 48 sec latency 102.649 ms 1 1118 0.17 MB/sec execute 49 sec latency 120.302 ms 1 1147 0.17 MB/sec execute 50 sec latency 113.505 ms 1 1172 0.16 MB/sec execute 51 sec latency 499.355 ms 1 1177 0.16 MB/sec execute 52 sec latency 1237.440 ms 1 1214 0.16 MB/sec execute 53 sec latency 120.409 ms 1 1244 0.16 MB/sec execute 54 sec latency 115.929 ms 1 1382 0.21 MB/sec execute 55 sec latency 100.715 ms test_26 fail mds2 2 times 1 1418 0.20 MB/sec execute 56 sec latency 105.640 ms 1 1447 0.20 MB/sec execute 57 sec latency 123.451 ms 1 1481 0.20 MB/sec execute 58 sec latency 157.986 ms Failing mds2 on oleg309-server 1 1505 0.19 MB/sec execute 59 sec latency 123.588 ms Stopping /mnt/lustre-mds2 (opts:) on oleg309-server 1 1538 0.19 MB/sec execute 60 sec latency 111.604 ms 1 1576 0.19 MB/sec execute 61 sec latency 106.614 ms 1 1613 0.19 MB/sec execute 62 sec latency 122.723 ms 1 1651 0.18 MB/sec execute 63 sec latency 144.360 ms 1 1675 0.18 MB/sec execute 64 sec latency 169.275 ms 00:57:56 (1790744276) shut down facet: mds2 facet_host: oleg309-server facet_failover_host: oleg309-server 1 1709 0.18 MB/sec execute 65 sec latency 131.609 ms 1 1814 0.18 MB/sec execute 66 sec latency 54.892 ms 1 1861 0.18 MB/sec execute 67 sec latency 124.140 ms 1 1916 0.17 MB/sec execute 68 sec latency 102.957 ms 1 1999 0.17 MB/sec execute 69 sec latency 73.570 ms 1 2034 0.17 MB/sec execute 70 sec latency 173.243 ms 1 2108 0.17 MB/sec execute 71 sec latency 83.803 ms 1 2175 0.17 MB/sec execute 72 sec latency 75.664 ms 1 2259 0.17 MB/sec execute 73 sec latency 81.332 ms 1 2259 0.16 MB/sec execute 74 sec latency 1083.563 ms Failover mds2 to oleg309-server 1 2259 0.16 MB/sec execute 75 sec latency 2084.011 ms mount facets: mds2 1 2259 0.16 MB/sec execute 76 sec latency 3084.378 ms 1 2259 0.16 MB/sec execute 77 sec latency 4084.784 ms 1 2259 0.16 MB/sec execute 78 sec latency 5085.069 ms 1 2259 0.15 MB/sec execute 79 sec latency 6085.374 ms 1 2259 0.15 MB/sec execute 80 sec latency 7087.626 ms 1 2259 0.15 MB/sec execute 81 sec latency 8090.343 ms 1 2259 0.15 MB/sec execute 82 sec latency 9090.699 ms 1 2259 0.15 MB/sec execute 83 sec latency 10091.014 ms 1 2259 0.14 MB/sec execute 84 sec latency 11091.247 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 2259 0.14 MB/sec execute 85 sec latency 12091.619 ms 1 2259 0.14 MB/sec execute 86 sec latency 13093.808 ms 1 2259 0.14 MB/sec execute 87 sec latency 14096.612 ms 1 2259 0.14 MB/sec execute 88 sec latency 15100.938 ms 1 2259 0.14 MB/sec execute 89 sec latency 16101.561 ms 1 2259 0.14 MB/sec execute 90 sec latency 17101.831 ms 1 2259 0.13 MB/sec execute 91 sec latency 18104.194 ms 1 2259 0.13 MB/sec execute 92 sec latency 19104.499 ms oleg309-server: oleg309-server.virtnet: executing set_default_debug -1 all 1 2259 0.13 MB/sec execute 93 sec latency 20106.561 ms pdsh@oleg309-client: oleg309-server: ssh exited with exit code 1 1 2259 0.13 MB/sec execute 94 sec latency 21106.756 ms Started lustre-MDT0001 00:58:26 (1790744306) targets are mounted 00:58:26 (1790744306) facet_failover done 1 2259 0.13 MB/sec execute 95 sec latency 22107.476 ms 1 2334 0.14 MB/sec execute 96 sec latency 22274.797 ms 1 2367 0.14 MB/sec execute 97 sec latency 122.081 ms 1 2396 0.14 MB/sec execute 98 sec latency 163.908 ms 1 2418 0.14 MB/sec execute 99 sec latency 182.680 ms 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec 1 cleanup 103 sec oleg309-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 1 cleanup 104 sec 0 cleanup 105 sec 0 cleanup 105 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 352 124.953 22274.776 Close 305 131.547 36026.797 Rename 14 109.862 169.825 Unlink 35 28.249 106.851 Qpathinfo 322 16.685 116.740 Qfileinfo 87 2.255 11.831 Qfsinfo 40 4.907 26.168 Sfileinfo 44 68.036 133.951 Find 109 13.213 85.555 WriteX 306 14.418 87.682 ReadX 382 2.885 102.926 Flush 33 73.080 182.660 Throughput 0.136017 MB/sec 1 clients 1 procs max_latency=36026.827 ms stopping dbench on /mnt/lustre at Wed Sep 30 00:58:36 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec removed 'client.txt' /mnt/lustre dbench successfully finished striped dir -i0 -c2 -H crush /mnt/lustre2/d26.replay-dual/run_dbench looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt '/usr/share/dbench/client.txt' -> 'client.txt' UUID 1K-blocks Used Available Use% Mounted on running 'dbench 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100' on /mnt/lustre at Wed Sep 30 00:58:45 EDT 2026 waiting for dbench pid 67886 lustre-MDT0000_UUID 1414116 2356 1268948 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2096 1269208 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 11532 3595068 1% /mnt/lustre[OST:0] dbench version 4.00 - Copyright Andrew Tridgell 1999-2004 Running for 100 seconds with load 'client.txt' and minimum warmup 20 secs lustre-OST0001_UUID 3833116 31620 3569692 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 43152 7164760 1% /mnt/lustre 0 of 1 processes prepared for launch 0 sec 1 of 1 processes prepared for launch 0 sec releasing clients 0 9 0.00 MB/sec warmup 1 sec latency 8.945 ms 1 65 1.41 MB/sec warmup 2 sec latency 127.902 ms 1 113 1.73 MB/sec warmup 3 sec latency 140.050 ms 1 140 1.50 MB/sec warmup 4 sec latency 204.186 ms 1 172 1.41 MB/sec warmup 5 sec latency 199.052 ms 1 172 1.17 MB/sec warmup 6 sec latency 1136.751 ms 1 180 1.04 MB/sec warmup 7 sec latency 1933.086 ms 1 197 0.98 MB/sec warmup 8 sec latency 492.201 ms 1 223 0.95 MB/sec warmup 9 sec latency 241.522 ms 1 263 0.99 MB/sec warmup 10 sec latency 104.649 ms test_26 fail mds1 3 times 1 289 0.97 MB/sec warmup 11 sec latency 182.494 ms 1 314 0.95 MB/sec warmup 12 sec latency 268.076 ms Failing mds1 on oleg309-server 1 339 0.94 MB/sec warmup 13 sec latency 149.234 ms 1 365 0.93 MB/sec warmup 14 sec latency 186.681 ms Stopping /mnt/lustre-mds1 (opts:) on oleg309-server 1 397 0.94 MB/sec warmup 15 sec latency 135.955 ms 1 405 0.89 MB/sec warmup 16 sec latency 855.600 ms 1 405 0.84 MB/sec warmup 17 sec latency 1855.930 ms 1 405 0.80 MB/sec warmup 18 sec latency 2856.439 ms 1 405 0.75 MB/sec warmup 19 sec latency 3857.198 ms 1 405 0.00 MB/sec execute 1 sec latency 5861.119 ms 1 405 0.00 MB/sec execute 2 sec latency 6862.784 ms 1 405 0.00 MB/sec execute 3 sec latency 7863.032 ms 00:59:09 (1790744349) shut down facet: mds1 facet_host: oleg309-server facet_failover_host: oleg309-server 1 405 0.00 MB/sec execute 4 sec latency 8864.832 ms 1 405 0.00 MB/sec execute 5 sec latency 9865.065 ms 1 405 0.00 MB/sec execute 6 sec latency 10865.262 ms 1 405 0.00 MB/sec execute 7 sec latency 11865.448 ms 1 405 0.00 MB/sec execute 8 sec latency 12865.685 ms 1 405 0.00 MB/sec execute 9 sec latency 13865.936 ms 1 405 0.00 MB/sec execute 10 sec latency 14866.901 ms 1 405 0.00 MB/sec execute 11 sec latency 15867.232 ms 1 405 0.00 MB/sec execute 12 sec latency 16868.907 ms 1 405 0.00 MB/sec execute 13 sec latency 17869.097 ms 1 405 0.00 MB/sec execute 14 sec latency 18869.263 ms Failover mds1 to oleg309-server mount facets: mds1 1 405 0.00 MB/sec execute 15 sec latency 19877.692 ms 1 405 0.00 MB/sec execute 16 sec latency 20879.749 ms 1 405 0.00 MB/sec execute 17 sec latency 21880.134 ms 1 405 0.00 MB/sec execute 18 sec latency 22885.723 ms 1 405 0.00 MB/sec execute 19 sec latency 23889.122 ms 1 405 0.00 MB/sec execute 20 sec latency 24891.658 ms 1 405 0.00 MB/sec execute 21 sec latency 25894.915 ms 1 405 0.00 MB/sec execute 22 sec latency 26901.221 ms 1 405 0.00 MB/sec execute 23 sec latency 27901.970 ms 1 405 0.00 MB/sec execute 24 sec latency 28904.931 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 405 0.00 MB/sec execute 25 sec latency 29905.266 ms 1 405 0.00 MB/sec execute 26 sec latency 30905.733 ms 1 405 0.00 MB/sec execute 27 sec latency 31906.068 ms 1 405 0.00 MB/sec execute 28 sec latency 32906.455 ms 1 405 0.00 MB/sec execute 29 sec latency 33907.452 ms 1 405 0.00 MB/sec execute 30 sec latency 34907.682 ms 1 405 0.00 MB/sec execute 31 sec latency 35909.452 ms 1 405 0.00 MB/sec execute 32 sec latency 36909.737 ms 1 405 0.00 MB/sec execute 33 sec latency 37910.925 ms 1 405 0.00 MB/sec execute 34 sec latency 38911.179 ms oleg309-server: oleg309-server.virtnet: executing set_default_debug -1 all 1 405 0.00 MB/sec execute 35 sec latency 39911.503 ms 1 405 0.00 MB/sec execute 36 sec latency 40911.876 ms pdsh@oleg309-client: oleg309-server: ssh exited with exit code 1 1 413 0.01 MB/sec execute 37 sec latency 41753.267 ms Started lustre-MDT0000 00:59:44 (1790744384) targets are mounted 00:59:44 (1790744384) facet_failover done 1 445 0.03 MB/sec execute 38 sec latency 133.356 ms 1 485 0.07 MB/sec execute 39 sec latency 165.040 ms 1 513 0.08 MB/sec execute 40 sec latency 177.889 ms 1 542 0.12 MB/sec execute 41 sec latency 257.227 ms 1 606 0.16 MB/sec execute 42 sec latency 178.711 ms 1 639 0.16 MB/sec execute 43 sec latency 153.456 ms 1 661 0.15 MB/sec execute 44 sec latency 181.965 ms 1 685 0.15 MB/sec execute 45 sec latency 242.498 ms 1 710 0.15 MB/sec execute 46 sec latency 166.641 ms oleg309-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 733 0.15 MB/sec execute 47 sec latency 162.041 ms 1 762 0.15 MB/sec execute 48 sec latency 136.109 ms 1 779 0.14 MB/sec execute 49 sec latency 205.710 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 799 0.14 MB/sec execute 50 sec latency 189.412 ms 1 827 0.14 MB/sec execute 51 sec latency 153.811 ms 1 874 0.14 MB/sec execute 52 sec latency 111.863 ms 1 884 0.14 MB/sec execute 53 sec latency 640.005 ms 1 885 0.14 MB/sec execute 54 sec latency 1482.039 ms 1 907 0.13 MB/sec execute 55 sec latency 248.384 ms 1 923 0.13 MB/sec execute 56 sec latency 207.650 ms 1 951 0.13 MB/sec execute 57 sec latency 141.603 ms 1 980 0.13 MB/sec execute 58 sec latency 133.971 ms 1 1009 0.13 MB/sec execute 59 sec latency 172.688 ms 1 1074 0.14 MB/sec execute 60 sec latency 94.263 ms 1 1099 0.14 MB/sec execute 61 sec latency 222.131 ms 1 1132 0.14 MB/sec execute 62 sec latency 134.120 ms 1 1176 0.14 MB/sec execute 63 sec latency 114.476 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 1215 0.14 MB/sec execute 64 sec latency 101.429 ms 1 1242 0.13 MB/sec execute 65 sec latency 133.079 ms 1 1285 0.13 MB/sec execute 66 sec latency 155.167 ms 1 1403 0.17 MB/sec execute 67 sec latency 88.333 ms 1 1443 0.17 MB/sec execute 68 sec latency 108.143 ms 1 1468 0.17 MB/sec execute 69 sec latency 364.896 ms 1 1500 0.17 MB/sec execute 70 sec latency 166.112 ms 1 1551 0.17 MB/sec execute 71 sec latency 89.997 ms 1 1591 0.16 MB/sec execute 72 sec latency 96.624 ms 1 1634 0.16 MB/sec execute 73 sec latency 117.790 ms 1 1665 0.16 MB/sec execute 74 sec latency 125.518 ms 1 1700 0.16 MB/sec execute 75 sec latency 158.563 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Wed Sep 30 01:00:21 EDT 2026 with return code 0 67886 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 67886 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished