== replay-dual test 26: dbench and tar with mds failover ========================================================== 04:26:33 (1785399993) Starting client oleg405-client.virtnet: -o user_xattr,flock 192.168.204.105@tcp:/lustre /mnt/lustre Started clients oleg405-client.virtnet: 192.168.204.105@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 44989 Started dbench loop with 44990 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 2048 2206464 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 2048 3739648 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3762176 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 4096 7501824 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 Thu Jul 30 04:26:40 EDT 2026 waiting for dbench pid 45058 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 11 0.00 MB/sec warmup 1 sec latency 20.098 ms 1 46 0.92 MB/sec warmup 2 sec latency 145.156 ms 1 78 1.14 MB/sec warmup 3 sec latency 229.289 ms 1 108 1.28 MB/sec warmup 4 sec latency 320.315 ms 1 126 1.13 MB/sec warmup 5 sec latency 442.631 ms 1 142 1.00 MB/sec warmup 6 sec latency 259.140 ms test_26 fail mds1 1 times 1 160 0.93 MB/sec warmup 7 sec latency 246.237 ms 1 184 0.91 MB/sec warmup 8 sec latency 166.629 ms Failing mds1 on oleg405-server 1 208 0.90 MB/sec warmup 9 sec latency 351.798 ms Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 1 255 0.96 MB/sec warmup 10 sec latency 149.645 ms 1 279 0.95 MB/sec warmup 11 sec latency 474.173 ms 1 279 0.87 MB/sec warmup 12 sec latency 1474.656 ms 1 279 0.80 MB/sec warmup 13 sec latency 2482.223 ms 1 279 0.74 MB/sec warmup 14 sec latency 3482.491 ms 04:26:55 (1785400015) shut down 1 279 0.69 MB/sec warmup 15 sec latency 4485.751 ms facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server 1 279 0.65 MB/sec warmup 16 sec latency 5486.031 ms 1 279 0.61 MB/sec warmup 17 sec latency 6487.015 ms 1 279 0.58 MB/sec warmup 18 sec latency 7488.774 ms 1 279 0.55 MB/sec warmup 19 sec latency 8489.122 ms 1 279 0.00 MB/sec execute 1 sec latency 10492.578 ms 1 279 0.00 MB/sec execute 2 sec latency 11494.054 ms 1 279 0.00 MB/sec execute 3 sec latency 12494.256 ms 1 279 0.00 MB/sec execute 4 sec latency 13494.481 ms 1 279 0.00 MB/sec execute 5 sec latency 14494.993 ms Failover mds1 to oleg405-server mount facets: mds1 1 279 0.00 MB/sec execute 6 sec latency 15496.094 ms 1 279 0.00 MB/sec execute 7 sec latency 16498.127 ms 1 279 0.00 MB/sec execute 8 sec latency 17498.321 ms 1 279 0.00 MB/sec execute 9 sec latency 18498.641 ms 1 279 0.00 MB/sec execute 10 sec latency 19499.027 ms 1 279 0.00 MB/sec execute 11 sec latency 20502.562 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 279 0.00 MB/sec execute 12 sec latency 21502.828 ms 1 279 0.00 MB/sec execute 13 sec latency 22503.869 ms 1 279 0.00 MB/sec execute 14 sec latency 23504.258 ms 1 279 0.00 MB/sec execute 15 sec latency 24506.007 ms 1 279 0.00 MB/sec execute 16 sec latency 25506.181 ms 1 279 0.00 MB/sec execute 17 sec latency 26506.849 ms 1 279 0.00 MB/sec execute 18 sec latency 27507.113 ms 1 279 0.00 MB/sec execute 19 sec latency 28507.360 ms 1 279 0.00 MB/sec execute 20 sec latency 29509.266 ms 1 279 0.00 MB/sec execute 21 sec latency 30509.909 ms 1 279 0.00 MB/sec execute 22 sec latency 31512.727 ms 1 279 0.00 MB/sec execute 23 sec latency 32513.040 ms 1 279 0.00 MB/sec execute 24 sec latency 33513.486 ms 1 279 0.00 MB/sec execute 25 sec latency 34518.428 ms 1 279 0.00 MB/sec execute 26 sec latency 35518.671 ms oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all 1 279 0.00 MB/sec execute 27 sec latency 36518.936 ms pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 1 279 0.00 MB/sec execute 28 sec latency 37519.449 ms Started lustre-MDT0000 04:27:29 (1785400049) targets are mounted 04:27:29 (1785400049) facet_failover done 1 279 0.00 MB/sec execute 29 sec latency 38519.697 ms 1 279 0.00 MB/sec execute 30 sec latency 39521.478 ms 1 279 0.00 MB/sec execute 31 sec latency 40521.824 ms 1 279 0.00 MB/sec execute 32 sec latency 41522.046 ms 1 279 0.00 MB/sec execute 33 sec latency 42522.360 ms 1 288 0.01 MB/sec execute 34 sec latency 43023.383 ms 1 314 0.03 MB/sec execute 35 sec latency 173.016 ms 1 339 0.05 MB/sec execute 36 sec latency 202.062 ms 1 357 0.06 MB/sec execute 37 sec latency 213.711 ms 1 381 0.08 MB/sec execute 38 sec latency 193.715 ms 1 406 0.10 MB/sec execute 39 sec latency 185.308 ms 1 429 0.12 MB/sec execute 40 sec latency 176.015 ms oleg405-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 453 0.13 MB/sec execute 41 sec latency 192.427 ms 1 477 0.15 MB/sec execute 42 sec latency 238.283 ms 1 501 0.16 MB/sec execute 43 sec latency 181.966 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 519 0.17 MB/sec execute 44 sec latency 214.300 ms 1 575 0.20 MB/sec execute 45 sec latency 179.978 ms 1 616 0.23 MB/sec execute 46 sec latency 116.270 ms 1 652 0.23 MB/sec execute 47 sec latency 187.410 ms 1 666 0.22 MB/sec execute 48 sec latency 467.711 ms 1 678 0.22 MB/sec execute 49 sec latency 202.099 ms 1 699 0.21 MB/sec execute 50 sec latency 168.363 ms 1 721 0.21 MB/sec execute 51 sec latency 151.922 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2304 2206208 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 39936 3698688 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 6144 3737600 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 46080 7436288 1% /mnt/lustre 1 728 0.21 MB/sec execute 52 sec latency 402.108 ms 1 738 0.20 MB/sec execute 53 sec latency 237.053 ms 1 767 0.20 MB/sec execute 54 sec latency 195.407 ms 1 789 0.20 MB/sec execute 55 sec latency 150.202 ms 1 801 0.20 MB/sec execute 56 sec latency 360.107 ms 1 827 0.19 MB/sec execute 57 sec latency 187.363 ms 1 873 0.19 MB/sec execute 58 sec latency 109.381 ms 1 885 0.19 MB/sec execute 59 sec latency 499.321 ms test_26 fail mds1 2 times 1 910 0.19 MB/sec execute 60 sec latency 176.613 ms 1 921 0.19 MB/sec execute 61 sec latency 352.574 ms 1 949 0.18 MB/sec execute 62 sec latency 143.957 ms Failing mds1 on oleg405-server 1 970 0.18 MB/sec execute 63 sec latency 166.381 ms Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 1 981 0.18 MB/sec execute 64 sec latency 324.897 ms 1 998 0.18 MB/sec execute 65 sec latency 334.476 ms 1 1038 0.19 MB/sec execute 66 sec latency 332.442 ms 1 1038 0.19 MB/sec execute 67 sec latency 1332.614 ms 1 1038 0.18 MB/sec execute 68 sec latency 2336.483 ms 1 1038 0.18 MB/sec execute 69 sec latency 3336.678 ms 1 1038 0.18 MB/sec execute 70 sec latency 4336.880 ms 04:28:10 (1785400090) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server 1 1038 0.17 MB/sec execute 71 sec latency 5338.647 ms 1 1038 0.17 MB/sec execute 72 sec latency 6339.010 ms 1 1038 0.17 MB/sec execute 73 sec latency 7340.673 ms 1 1038 0.17 MB/sec execute 74 sec latency 8341.203 ms 1 1038 0.17 MB/sec execute 75 sec latency 9341.929 ms 1 1038 0.16 MB/sec execute 76 sec latency 10344.870 ms 1 1038 0.16 MB/sec execute 77 sec latency 11345.104 ms 1 1038 0.16 MB/sec execute 78 sec latency 12347.339 ms 1 1038 0.16 MB/sec execute 79 sec latency 13347.789 ms 1 1038 0.16 MB/sec execute 80 sec latency 14348.827 ms Failover mds1 to oleg405-server 1 1038 0.15 MB/sec execute 81 sec latency 15355.532 ms mount facets: mds1 1 1038 0.15 MB/sec execute 82 sec latency 16356.208 ms 1 1038 0.15 MB/sec execute 83 sec latency 17356.455 ms 1 1038 0.15 MB/sec execute 84 sec latency 18357.045 ms 1 1038 0.15 MB/sec execute 85 sec latency 19358.007 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 1038 0.14 MB/sec execute 86 sec latency 20360.634 ms 1 1038 0.14 MB/sec execute 87 sec latency 21361.091 ms 1 1038 0.14 MB/sec execute 88 sec latency 22361.330 ms 1 1038 0.14 MB/sec execute 89 sec latency 23361.764 ms 1 1038 0.14 MB/sec execute 90 sec latency 24363.330 ms 1 1038 0.14 MB/sec execute 91 sec latency 25364.437 ms 1 1038 0.13 MB/sec execute 92 sec latency 26364.704 ms 1 1038 0.13 MB/sec execute 93 sec latency 27364.972 ms 1 1038 0.13 MB/sec execute 94 sec latency 28365.224 ms 1 1038 0.13 MB/sec execute 95 sec latency 29366.411 ms 1 1038 0.13 MB/sec execute 96 sec latency 30367.254 ms 1 1038 0.13 MB/sec execute 97 sec latency 31367.415 ms 1 1038 0.13 MB/sec execute 98 sec latency 32368.430 ms 1 1038 0.13 MB/sec execute 99 sec latency 33369.093 ms 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec 1 cleanup 103 sec oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all 1 cleanup 104 sec 1 cleanup 105 sec pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 1 cleanup 106 sec 1 cleanup 107 sec Started lustre-MDT0000 04:28:48 (1785400128) targets are mounted 04:28:48 (1785400128) facet_failover done 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 0 cleanup 116 sec 0 cleanup 116 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 109 920.550 44051.897 Close 96 19.467 67.026 Rename 4 148.530 176.581 Unlink 10 48.873 84.843 Qpathinfo 34 36.757 116.249 Qfileinfo 53 3.954 22.697 Qfsinfo 22 7.468 36.991 Sfileinfo 18 105.274 334.445 Find 26 12.789 62.492 WriteX 268 22.318 170.484 ReadX 96 6.312 116.274 Flush 24 232.758 499.301 Throughput 0.125411 MB/sec 1 clients 1 procs max_latency=43023.383 ms stopping dbench on /mnt/lustre at Thu Jul 30 04:28:57 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished oleg405-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec '/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 Jul 30 04:29:07 EDT 2026 waiting for dbench pid 46969 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 10 0.00 MB/sec warmup 1 sec latency 63.462 ms 1 51 1.05 MB/sec warmup 2 sec latency 151.079 ms 1 71 1.04 MB/sec warmup 3 sec latency 254.567 ms 1 98 1.11 MB/sec warmup 4 sec latency 230.913 ms 1 121 1.10 MB/sec warmup 5 sec latency 238.003 ms 1 140 1.00 MB/sec warmup 6 sec latency 248.938 ms 1 165 0.97 MB/sec warmup 7 sec latency 205.967 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2560 2205952 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 31744 3714048 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 15360 3753984 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 47104 7468032 1% /mnt/lustre 1 181 0.91 MB/sec warmup 8 sec latency 275.640 ms 1 194 0.85 MB/sec warmup 9 sec latency 348.371 ms 1 207 0.81 MB/sec warmup 10 sec latency 376.785 ms 1 223 0.78 MB/sec warmup 11 sec latency 291.155 ms 1 244 0.77 MB/sec warmup 12 sec latency 193.130 ms 1 264 0.76 MB/sec warmup 13 sec latency 183.153 ms 1 287 0.76 MB/sec warmup 14 sec latency 198.161 ms 1 313 0.76 MB/sec warmup 15 sec latency 210.515 ms 1 338 0.76 MB/sec warmup 16 sec latency 195.310 ms test_26 fail mds1 3 times 1 357 0.75 MB/sec warmup 17 sec latency 172.618 ms 1 389 0.76 MB/sec warmup 18 sec latency 185.124 ms 1 413 0.76 MB/sec warmup 19 sec latency 177.872 ms Failing mds1 on oleg405-server Stopping /mnt/lustre-mds1 (opts:) on oleg405-server 1 459 0.85 MB/sec execute 1 sec latency 212.377 ms 1 491 0.94 MB/sec execute 2 sec latency 141.496 ms 1 492 0.65 MB/sec execute 3 sec latency 997.483 ms 1 492 0.49 MB/sec execute 4 sec latency 1997.709 ms 04:29:32 (1785400172) shut down facet: mds1 facet_host: oleg405-server facet_failover_host: oleg405-server 1 492 0.39 MB/sec execute 5 sec latency 2998.601 ms 1 492 0.32 MB/sec execute 6 sec latency 3998.913 ms 1 492 0.28 MB/sec execute 7 sec latency 4999.179 ms 1 492 0.24 MB/sec execute 8 sec latency 5999.712 ms 1 492 0.22 MB/sec execute 9 sec latency 7000.722 ms 1 492 0.19 MB/sec execute 10 sec latency 8001.746 ms 1 492 0.18 MB/sec execute 11 sec latency 9002.403 ms 1 492 0.16 MB/sec execute 12 sec latency 10002.723 ms 1 492 0.15 MB/sec execute 13 sec latency 11003.121 ms 1 492 0.14 MB/sec execute 14 sec latency 12003.964 ms 1 492 0.13 MB/sec execute 15 sec latency 13004.164 ms Failover mds1 to oleg405-server mount facets: mds1 1 492 0.12 MB/sec execute 16 sec latency 14004.360 ms 1 492 0.11 MB/sec execute 17 sec latency 15004.528 ms 1 492 0.11 MB/sec execute 18 sec latency 16005.359 ms 1 492 0.10 MB/sec execute 19 sec latency 17005.981 ms 1 492 0.10 MB/sec execute 20 sec latency 18007.108 ms 1 492 0.09 MB/sec execute 21 sec latency 19007.667 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 492 0.09 MB/sec execute 22 sec latency 20009.005 ms 1 492 0.08 MB/sec execute 23 sec latency 21010.486 ms 1 492 0.08 MB/sec execute 24 sec latency 22010.932 ms 1 492 0.08 MB/sec execute 25 sec latency 23012.337 ms 1 492 0.07 MB/sec execute 26 sec latency 24012.579 ms 1 492 0.07 MB/sec execute 27 sec latency 25016.501 ms 1 492 0.07 MB/sec execute 28 sec latency 26016.734 ms 1 492 0.07 MB/sec execute 29 sec latency 27016.993 ms 1 492 0.06 MB/sec execute 30 sec latency 28017.328 ms 1 492 0.06 MB/sec execute 31 sec latency 29017.626 ms 1 492 0.06 MB/sec execute 32 sec latency 30019.207 ms 1 492 0.06 MB/sec execute 33 sec latency 31020.327 ms 1 492 0.06 MB/sec execute 34 sec latency 32020.900 ms 1 492 0.06 MB/sec execute 35 sec latency 33021.144 ms 1 492 0.05 MB/sec execute 36 sec latency 34021.737 ms 1 492 0.05 MB/sec execute 37 sec latency 35023.062 ms 1 492 0.05 MB/sec execute 38 sec latency 36023.858 ms 1 492 0.05 MB/sec execute 39 sec latency 37024.040 ms 1 492 0.05 MB/sec execute 40 sec latency 38024.907 ms oleg405-server: oleg405-server.virtnet: executing set_default_debug -1 all 1 492 0.05 MB/sec execute 41 sec latency 39026.588 ms 1 492 0.05 MB/sec execute 42 sec latency 40027.735 ms pdsh@oleg405-client: oleg405-server: ssh exited with exit code 1 1 492 0.05 MB/sec execute 43 sec latency 41028.573 ms 1 501 0.05 MB/sec execute 44 sec latency 41258.700 ms Started lustre-MDT0000 04:30:12 (1785400212) targets are mounted 04:30:12 (1785400212) facet_failover done 1 522 0.06 MB/sec execute 45 sec latency 269.886 ms 1 580 0.10 MB/sec execute 46 sec latency 287.187 ms 1 612 0.12 MB/sec execute 47 sec latency 159.974 ms 1 654 0.12 MB/sec execute 48 sec latency 216.411 ms 1 669 0.12 MB/sec execute 49 sec latency 281.847 ms 1 689 0.12 MB/sec execute 50 sec latency 207.349 ms 1 708 0.12 MB/sec execute 51 sec latency 170.396 ms 1 721 0.12 MB/sec execute 52 sec latency 230.063 ms 1 731 0.11 MB/sec execute 53 sec latency 421.831 ms 1 758 0.11 MB/sec execute 54 sec latency 182.741 ms oleg405-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 786 0.11 MB/sec execute 55 sec latency 162.866 ms 1 801 0.11 MB/sec execute 56 sec latency 209.919 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 821 0.11 MB/sec execute 57 sec latency 136.454 ms 1 863 0.11 MB/sec execute 58 sec latency 167.536 ms 1 876 0.11 MB/sec execute 59 sec latency 442.367 ms 1 897 0.11 MB/sec execute 60 sec latency 175.692 ms 1 913 0.11 MB/sec execute 61 sec latency 190.987 ms 1 925 0.10 MB/sec execute 62 sec latency 393.586 ms 1 967 0.10 MB/sec execute 63 sec latency 108.036 ms 1 983 0.10 MB/sec execute 64 sec latency 396.918 ms 1 1028 0.12 MB/sec execute 65 sec latency 130.810 ms 1 1071 0.12 MB/sec execute 66 sec latency 108.654 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 1119 0.11 MB/sec execute 67 sec latency 96.814 ms 1 1145 0.11 MB/sec execute 68 sec latency 137.197 ms 1 1164 0.11 MB/sec execute 69 sec latency 216.627 ms 1 1193 0.11 MB/sec execute 70 sec latency 122.140 ms 1 1225 0.11 MB/sec execute 71 sec latency 96.249 ms 1 1263 0.11 MB/sec execute 72 sec latency 94.022 ms 1 1385 0.15 MB/sec execute 73 sec latency 133.770 ms 1 1403 0.15 MB/sec execute 74 sec latency 270.439 ms 1 1413 0.14 MB/sec execute 75 sec latency 488.712 ms 1 1441 0.14 MB/sec execute 76 sec latency 173.760 ms 1 1474 0.14 MB/sec execute 77 sec latency 123.514 ms 1 1508 0.14 MB/sec execute 78 sec latency 213.544 ms 1 1552 0.14 MB/sec execute 79 sec latency 99.493 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Thu Jul 30 04:30:47 EDT 2026 with return code 0 1 1572 0.14 MB/sec execute 80 sec latency 150.250 ms 46969 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 46969 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished