== replay-dual test 26: dbench and tar with mds failover ========================================================== 16:50:23 (1778619023) Starting client oleg342-client.virtnet: -o user_xattr,flock 192.168.203.142@tcp:/lustre /mnt/lustre Started clients oleg342-client.virtnet: 192.168.203.142@tcp:/lustre on /mnt/lustre type lustre (rw,checksum,encrypt,flock,lazystatfs,lruresize,nolock,statfs_project,nouser_fid2path,user_xattr,verbose) Started tar loop with pid 44538 Started dbench loop with 44539 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 3762176 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 6144 3741696 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 8192 7503872 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 Tue May 12 16:50:29 EDT 2026 waiting for dbench pid 44607 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 34 1.05 MB/sec warmup 1 sec latency 140.896 ms 1 80 1.77 MB/sec warmup 2 sec latency 163.488 ms 1 128 1.92 MB/sec warmup 3 sec latency 179.184 ms 1 160 1.63 MB/sec warmup 4 sec latency 137.181 ms test_26 fail mds1 1 times 1 197 1.57 MB/sec warmup 5 sec latency 118.518 ms 1 226 1.44 MB/sec warmup 6 sec latency 144.168 ms Failing mds1 on oleg342-server 1 255 1.38 MB/sec warmup 7 sec latency 172.946 ms 1 294 1.35 MB/sec warmup 8 sec latency 144.596 ms Stopping /mnt/lustre-mds1 (opts:) on oleg342-server 1 322 1.30 MB/sec warmup 9 sec latency 166.588 ms 1 331 1.20 MB/sec warmup 10 sec latency 774.020 ms 1 331 1.09 MB/sec warmup 11 sec latency 1777.551 ms 1 331 1.00 MB/sec warmup 12 sec latency 2779.759 ms 1 331 0.92 MB/sec warmup 13 sec latency 3779.993 ms 1 331 0.86 MB/sec warmup 14 sec latency 4782.499 ms 16:50:43 (1778619043) shut down facet: mds1 facet_host: oleg342-server facet_failover_host: oleg342-server 1 331 0.80 MB/sec warmup 15 sec latency 5782.714 ms 1 331 0.75 MB/sec warmup 16 sec latency 6784.760 ms 1 331 0.71 MB/sec warmup 17 sec latency 7785.021 ms 1 331 0.67 MB/sec warmup 18 sec latency 8785.296 ms 1 331 0.63 MB/sec warmup 19 sec latency 9788.586 ms 1 331 0.00 MB/sec execute 1 sec latency 11790.035 ms 1 331 0.00 MB/sec execute 2 sec latency 12790.256 ms 1 331 0.00 MB/sec execute 3 sec latency 13791.983 ms 1 331 0.00 MB/sec execute 4 sec latency 14795.439 ms Failover mds1 to oleg342-server mount facets: mds1 1 331 0.00 MB/sec execute 5 sec latency 15798.622 ms 1 331 0.00 MB/sec execute 6 sec latency 16798.882 ms 1 331 0.00 MB/sec execute 7 sec latency 17799.068 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 331 0.00 MB/sec execute 8 sec latency 18801.435 ms 1 331 0.00 MB/sec execute 9 sec latency 19802.092 ms 1 331 0.00 MB/sec execute 10 sec latency 20802.616 ms 1 331 0.00 MB/sec execute 11 sec latency 21808.429 ms 1 331 0.00 MB/sec execute 12 sec latency 22809.531 ms 1 331 0.00 MB/sec execute 13 sec latency 23809.770 ms 1 331 0.00 MB/sec execute 14 sec latency 24810.190 ms oleg342-server: oleg342-server.virtnet: executing set_default_debug -1 all 1 331 0.00 MB/sec execute 15 sec latency 25811.059 ms pdsh@oleg342-client: oleg342-server: ssh exited with exit code 1 1 331 0.00 MB/sec execute 16 sec latency 26811.282 ms Started lustre-MDT0000 16:51:06 (1778619066) targets are mounted 16:51:06 (1778619066) facet_failover done 1 331 0.00 MB/sec execute 17 sec latency 27811.521 ms 1 331 0.00 MB/sec execute 18 sec latency 28816.489 ms 1 331 0.00 MB/sec execute 19 sec latency 29818.053 ms 1 331 0.00 MB/sec execute 20 sec latency 30818.295 ms 1 350 0.02 MB/sec execute 21 sec latency 31137.869 ms 1 394 0.09 MB/sec execute 22 sec latency 123.819 ms oleg342-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 437 0.15 MB/sec execute 23 sec latency 133.014 ms 1 477 0.19 MB/sec execute 24 sec latency 118.834 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 504 0.22 MB/sec execute 25 sec latency 188.765 ms 1 541 0.27 MB/sec execute 26 sec latency 169.014 ms 1 616 0.33 MB/sec execute 27 sec latency 161.581 ms 1 664 0.33 MB/sec execute 28 sec latency 219.266 ms 1 695 0.32 MB/sec execute 29 sec latency 227.969 ms 1 721 0.31 MB/sec execute 30 sec latency 217.998 ms 1 736 0.30 MB/sec execute 31 sec latency 231.721 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2304 2206208 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 8192 3740672 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 36864 3702784 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 45056 7443456 1% /mnt/lustre 1 765 0.29 MB/sec execute 32 sec latency 147.304 ms 1 789 0.29 MB/sec execute 33 sec latency 239.339 ms 1 808 0.28 MB/sec execute 34 sec latency 311.012 ms 1 849 0.27 MB/sec execute 35 sec latency 165.429 ms 1 882 0.27 MB/sec execute 36 sec latency 193.184 ms 1 913 0.26 MB/sec execute 37 sec latency 158.395 ms test_26 fail mds1 2 times 1 943 0.26 MB/sec execute 38 sec latency 169.716 ms Failing mds1 on oleg342-server 1 971 0.25 MB/sec execute 39 sec latency 139.112 ms Stopping /mnt/lustre-mds1 (opts:) on oleg342-server 1 992 0.25 MB/sec execute 40 sec latency 297.964 ms 1 1062 0.27 MB/sec execute 41 sec latency 85.804 ms 1 1064 0.26 MB/sec execute 42 sec latency 931.412 ms 1 1064 0.25 MB/sec execute 43 sec latency 1931.631 ms 16:51:33 (1778619093) shut down 1 1064 0.25 MB/sec execute 44 sec latency 2931.776 ms facet: mds1 facet_host: oleg342-server facet_failover_host: oleg342-server 1 1064 0.24 MB/sec execute 45 sec latency 3932.352 ms 1 1064 0.24 MB/sec execute 46 sec latency 4933.303 ms 1 1064 0.23 MB/sec execute 47 sec latency 5933.535 ms 1 1064 0.23 MB/sec execute 48 sec latency 6935.008 ms 1 1064 0.22 MB/sec execute 49 sec latency 7935.306 ms 1 1064 0.22 MB/sec execute 50 sec latency 8936.366 ms 1 1064 0.21 MB/sec execute 51 sec latency 9936.677 ms 1 1064 0.21 MB/sec execute 52 sec latency 10937.275 ms 1 1064 0.21 MB/sec execute 53 sec latency 11937.567 ms 1 1064 0.20 MB/sec execute 54 sec latency 12937.874 ms Failover mds1 to oleg342-server mount facets: mds1 1 1064 0.20 MB/sec execute 55 sec latency 13940.079 ms 1 1064 0.19 MB/sec execute 56 sec latency 14941.459 ms 1 1064 0.19 MB/sec execute 57 sec latency 15942.091 ms 1 1064 0.19 MB/sec execute 58 sec latency 16943.948 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 1064 0.18 MB/sec execute 59 sec latency 17944.201 ms 1 1064 0.18 MB/sec execute 60 sec latency 18944.467 ms 1 1064 0.18 MB/sec execute 61 sec latency 19946.438 ms 1 1064 0.18 MB/sec execute 62 sec latency 20947.337 ms 1 1064 0.17 MB/sec execute 63 sec latency 21947.541 ms 1 1064 0.17 MB/sec execute 64 sec latency 22949.190 ms 1 1064 0.17 MB/sec execute 65 sec latency 23949.451 ms 1 1064 0.16 MB/sec execute 66 sec latency 24957.568 ms 1 1064 0.16 MB/sec execute 67 sec latency 25957.863 ms 1 1064 0.16 MB/sec execute 68 sec latency 26958.550 ms 1 1064 0.16 MB/sec execute 69 sec latency 27959.366 ms 1 1064 0.16 MB/sec execute 70 sec latency 28962.056 ms 1 1064 0.15 MB/sec execute 71 sec latency 29962.977 ms 1 1064 0.15 MB/sec execute 72 sec latency 30963.512 ms 1 1064 0.15 MB/sec execute 73 sec latency 31964.554 ms 1 1064 0.15 MB/sec execute 74 sec latency 32964.888 ms oleg342-server: oleg342-server.virtnet: executing set_default_debug -1 all 1 1064 0.14 MB/sec execute 75 sec latency 33966.182 ms pdsh@oleg342-client: oleg342-server: ssh exited with exit code 1 1 1064 0.14 MB/sec execute 76 sec latency 34966.516 ms Started lustre-MDT0000 16:52:06 (1778619126) targets are mounted 16:52:06 (1778619126) facet_failover done 1 1064 0.14 MB/sec execute 77 sec latency 35966.711 ms 1 1064 0.14 MB/sec execute 78 sec latency 36966.882 ms 1 1064 0.14 MB/sec execute 79 sec latency 37967.102 ms 1 1073 0.14 MB/sec execute 80 sec latency 38721.923 ms 1 1122 0.14 MB/sec execute 81 sec latency 93.914 ms 1 1147 0.13 MB/sec execute 82 sec latency 125.919 ms oleg342-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 1185 0.13 MB/sec execute 83 sec latency 168.503 ms 1 1223 0.13 MB/sec execute 84 sec latency 109.950 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 1244 0.13 MB/sec execute 85 sec latency 153.486 ms 1 1267 0.13 MB/sec execute 86 sec latency 202.561 ms 1 1387 0.16 MB/sec execute 87 sec latency 115.614 ms 1 1421 0.16 MB/sec execute 88 sec latency 129.458 ms 1 1451 0.16 MB/sec execute 89 sec latency 150.623 ms 1 1481 0.16 MB/sec execute 90 sec latency 273.094 ms 1 1512 0.15 MB/sec execute 91 sec latency 333.843 ms 1 1554 0.15 MB/sec execute 92 sec latency 105.701 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2688 2205824 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 22528 3737600 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 41984 3723264 2% /mnt/lustre[OST:1] filesystem_summary: 7542784 64512 7460864 1% /mnt/lustre 1 1585 0.15 MB/sec execute 93 sec latency 91.710 ms 1 1619 0.15 MB/sec execute 94 sec latency 130.452 ms 1 1643 0.15 MB/sec execute 95 sec latency 356.533 ms 1 1675 0.15 MB/sec execute 96 sec latency 179.184 ms 1 1713 0.15 MB/sec execute 97 sec latency 135.973 ms 1 1775 0.15 MB/sec execute 98 sec latency 95.194 ms 1 1825 0.14 MB/sec execute 99 sec latency 88.118 ms test_26 fail mds1 3 times 1 cleanup 100 sec 1 cleanup 101 sec Failing mds1 on oleg342-server 1 cleanup 102 sec Stopping /mnt/lustre-mds1 (opts:) on oleg342-server 1 cleanup 103 sec 0 cleanup 104 sec 0 cleanup 105 sec 0 cleanup 106 sec 16:52:36 (1778619156) shut down facet: mds1 facet_host: oleg342-server facet_failover_host: oleg342-server 0 cleanup 107 sec 0 cleanup 108 sec 0 cleanup 109 sec 0 cleanup 110 sec 0 cleanup 111 sec 0 cleanup 112 sec 0 cleanup 113 sec 0 cleanup 114 sec 0 cleanup 115 sec 0 cleanup 116 sec Failover mds1 to oleg342-server mount facets: mds1 0 cleanup 117 sec 0 cleanup 118 sec 0 cleanup 119 sec 0 cleanup 120 sec Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 0 cleanup 121 sec 0 cleanup 122 sec 0 cleanup 123 sec 0 cleanup 124 sec 0 cleanup 125 sec 0 cleanup 126 sec 0 cleanup 127 sec 0 cleanup 128 sec 0 cleanup 129 sec 0 cleanup 130 sec 0 cleanup 131 sec 0 cleanup 132 sec 0 cleanup 133 sec 0 cleanup 134 sec 0 cleanup 135 sec oleg342-server: oleg342-server.virtnet: executing set_default_debug -1 all 0 cleanup 136 sec pdsh@oleg342-client: oleg342-server: ssh exited with exit code 1 0 cleanup 137 sec Started lustre-MDT0000 16:53:07 (1778619187) targets are mounted 16:53:07 (1778619187) facet_failover done 0 cleanup 138 sec 0 cleanup 139 sec 0 cleanup 140 sec 0 cleanup 141 sec 0 cleanup 142 sec 0 cleanup 143 sec 0 cleanup 144 sec 0 cleanup 145 sec 0 cleanup 146 sec 0 cleanup 147 sec 0 cleanup 148 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 273 182.549 31137.845 Close 219 14.896 45.502 Rename 11 113.254 202.521 Unlink 24 37.768 84.014 Qpathinfo 188 227.740 38721.900 Qfileinfo 78 3.360 53.864 Qfsinfo 33 5.346 24.952 Sfileinfo 34 68.245 145.346 Find 71 7.369 54.175 WriteX 296 14.373 106.900 ReadX 292 2.811 112.751 Flush 27 163.829 356.508 Throughput 0.144583 MB/sec 1 clients 1 procs max_latency=38721.923 ms stopping dbench on /mnt/lustre at Tue May 12 16:53:17 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished oleg342-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 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 Tue May 12 16:53:24 EDT 2026 waiting for dbench pid 47404 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 31 1.05 MB/sec warmup 1 sec latency 20.332 ms 1 91 2.09 MB/sec warmup 2 sec latency 114.567 ms 1 132 1.91 MB/sec warmup 3 sec latency 159.500 ms 1 174 1.76 MB/sec warmup 4 sec latency 132.135 ms 1 207 1.62 MB/sec warmup 5 sec latency 145.073 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2816 2205696 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 55296 3688448 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 3072 3745792 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 58368 7434240 1% /mnt/lustre 1 260 1.63 MB/sec warmup 6 sec latency 107.380 ms 1 297 1.56 MB/sec warmup 7 sec latency 134.343 ms 1 332 1.50 MB/sec warmup 8 sec latency 134.365 ms 1 372 1.48 MB/sec warmup 9 sec latency 118.385 ms 1 418 1.47 MB/sec warmup 10 sec latency 101.634 ms test_26 fail mds1 4 times 1 469 1.49 MB/sec warmup 11 sec latency 89.028 ms 1 506 1.45 MB/sec warmup 12 sec latency 174.970 ms Failing mds1 on oleg342-server 1 548 1.47 MB/sec warmup 13 sec latency 157.254 ms 1 642 1.50 MB/sec warmup 14 sec latency 95.603 ms Stopping /mnt/lustre-mds1 (opts:) on oleg342-server 1 669 1.41 MB/sec warmup 15 sec latency 322.553 ms 1 677 1.32 MB/sec warmup 16 sec latency 449.877 ms 1 677 1.24 MB/sec warmup 17 sec latency 1450.231 ms 1 677 1.17 MB/sec warmup 18 sec latency 2450.464 ms 16:53:42 (1778619222) shut down facet: mds1 facet_host: oleg342-server facet_failover_host: oleg342-server 1 677 1.11 MB/sec warmup 19 sec latency 3450.893 ms 1 677 0.00 MB/sec execute 1 sec latency 5451.784 ms 1 677 0.00 MB/sec execute 2 sec latency 6452.439 ms 1 677 0.00 MB/sec execute 3 sec latency 7452.637 ms 1 677 0.00 MB/sec execute 4 sec latency 8452.862 ms 1 677 0.00 MB/sec execute 5 sec latency 9453.138 ms 1 677 0.00 MB/sec execute 6 sec latency 10455.540 ms 1 677 0.00 MB/sec execute 7 sec latency 11456.377 ms 1 677 0.00 MB/sec execute 8 sec latency 12456.678 ms Failover mds1 to oleg342-server mount facets: mds1 1 677 0.00 MB/sec execute 9 sec latency 13466.583 ms 1 677 0.00 MB/sec execute 10 sec latency 14467.942 ms 1 677 0.00 MB/sec execute 11 sec latency 15468.211 ms 1 677 0.00 MB/sec execute 12 sec latency 16471.372 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 677 0.00 MB/sec execute 13 sec latency 17475.960 ms 1 677 0.00 MB/sec execute 14 sec latency 18476.213 ms 1 677 0.00 MB/sec execute 15 sec latency 19478.463 ms 1 677 0.00 MB/sec execute 16 sec latency 20478.684 ms 1 677 0.00 MB/sec execute 17 sec latency 21478.918 ms 1 677 0.00 MB/sec execute 18 sec latency 22479.661 ms oleg342-server: oleg342-server.virtnet: executing set_default_debug -1 all 1 677 0.00 MB/sec execute 19 sec latency 23491.602 ms 1 677 0.00 MB/sec execute 20 sec latency 24494.184 ms pdsh@oleg342-client: oleg342-server: ssh exited with exit code 1 1 699 0.00 MB/sec execute 21 sec latency 24839.564 ms Started lustre-MDT0000 16:54:06 (1778619246) targets are mounted 16:54:06 (1778619246) facet_failover done 1 721 0.01 MB/sec execute 22 sec latency 283.437 ms 1 735 0.01 MB/sec execute 23 sec latency 454.327 ms 1 767 0.01 MB/sec execute 24 sec latency 140.805 ms 1 791 0.01 MB/sec execute 25 sec latency 280.240 ms oleg342-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 810 0.01 MB/sec execute 26 sec latency 121.283 ms 1 863 0.01 MB/sec execute 27 sec latency 135.036 ms 1 876 0.02 MB/sec execute 28 sec latency 460.848 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 903 0.02 MB/sec execute 29 sec latency 157.086 ms 1 919 0.02 MB/sec execute 30 sec latency 306.129 ms 1 955 0.02 MB/sec execute 31 sec latency 109.573 ms 1 980 0.02 MB/sec execute 32 sec latency 188.093 ms 1 1000 0.03 MB/sec execute 33 sec latency 205.977 ms 1 1028 0.05 MB/sec execute 34 sec latency 305.918 ms 1 1077 0.05 MB/sec execute 35 sec latency 109.318 ms 1 1131 0.05 MB/sec execute 36 sec latency 122.844 ms 1 1163 0.05 MB/sec execute 37 sec latency 137.897 ms 1 1204 0.05 MB/sec execute 38 sec latency 109.912 ms 1 1244 0.05 MB/sec execute 39 sec latency 85.864 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 1378 0.12 MB/sec execute 40 sec latency 96.192 ms 1 1403 0.12 MB/sec execute 41 sec latency 155.477 ms 1 1455 0.12 MB/sec execute 42 sec latency 105.327 ms 1 1499 0.11 MB/sec execute 43 sec latency 119.582 ms 1 1547 0.11 MB/sec execute 44 sec latency 117.644 ms 1 1582 0.11 MB/sec execute 45 sec latency 61.675 ms 1 1632 0.11 MB/sec execute 46 sec latency 92.160 ms 1 1656 0.11 MB/sec execute 47 sec latency 207.963 ms 1 1698 0.10 MB/sec execute 48 sec latency 95.283 ms 1 1751 0.10 MB/sec execute 49 sec latency 113.134 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 1 1801 0.10 MB/sec execute 50 sec latency 101.934 ms stopping dbench on /mnt/lustre at Tue May 12 16:54:34 EDT 2026 with return code 0 47404 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 47404 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished