== replay-dual test 26: dbench and tar with mds failover ========================================================== 00:41:45 (1783140105) 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,nouser_fid2path,user_xattr,verbose) Started tar loop with pid 44953 Started dbench loop with 44954 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 18432 3732480 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 20480 7494656 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 Jul 4 00:41:51 EDT 2026 waiting for dbench pid 45023 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 32 1.03 MB/sec warmup 1 sec latency 130.421 ms 1 60 1.23 MB/sec warmup 2 sec latency 340.403 ms 1 113 1.73 MB/sec warmup 3 sec latency 163.160 ms 1 148 1.56 MB/sec warmup 4 sec latency 164.989 ms test_26 fail mds1 1 times 1 182 1.46 MB/sec warmup 5 sec latency 162.917 ms 1 207 1.34 MB/sec warmup 6 sec latency 175.409 ms Failing mds1 on oleg301-server 1 236 1.28 MB/sec warmup 7 sec latency 188.376 ms Stopping /mnt/lustre-mds1 (opts:) on oleg301-server 1 280 1.30 MB/sec warmup 8 sec latency 100.951 ms 1 296 1.21 MB/sec warmup 9 sec latency 432.122 ms 1 296 1.09 MB/sec warmup 10 sec latency 1432.413 ms 00:42:02 (1783140122) shut down facet: mds1 facet_host: oleg301-server facet_failover_host: oleg301-server 1 296 0.99 MB/sec warmup 11 sec latency 2433.049 ms 1 296 0.91 MB/sec warmup 12 sec latency 3433.311 ms 1 296 0.84 MB/sec warmup 13 sec latency 4437.869 ms 1 296 0.78 MB/sec warmup 14 sec latency 5438.159 ms 1 296 0.73 MB/sec warmup 15 sec latency 6439.673 ms 1 296 0.68 MB/sec warmup 16 sec latency 7443.886 ms 1 296 0.64 MB/sec warmup 17 sec latency 8451.803 ms 1 296 0.61 MB/sec warmup 18 sec latency 9452.105 ms 1 296 0.57 MB/sec warmup 19 sec latency 10456.206 ms 1 296 0.00 MB/sec execute 1 sec latency 12456.543 ms Failover mds1 to oleg301-server mount facets: mds1 1 296 0.00 MB/sec execute 2 sec latency 13457.110 ms 1 296 0.00 MB/sec execute 3 sec latency 14457.368 ms 1 296 0.00 MB/sec execute 4 sec latency 15457.953 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 296 0.00 MB/sec execute 5 sec latency 16458.431 ms 1 296 0.00 MB/sec execute 6 sec latency 17463.838 ms 1 296 0.00 MB/sec execute 7 sec latency 18465.170 ms 1 296 0.00 MB/sec execute 8 sec latency 19465.752 ms 1 296 0.00 MB/sec execute 9 sec latency 20465.883 ms 1 296 0.00 MB/sec execute 10 sec latency 21466.094 ms 1 296 0.00 MB/sec execute 11 sec latency 22467.088 ms 1 310 0.03 MB/sec execute 12 sec latency 22832.985 ms 1 339 0.10 MB/sec execute 13 sec latency 149.744 ms oleg301-server: oleg301-server.virtnet: executing set_default_debug -1 all 1 365 0.15 MB/sec execute 14 sec latency 181.518 ms pdsh@oleg301-client: oleg301-server: ssh exited with exit code 1 1 402 0.22 MB/sec execute 15 sec latency 153.576 ms Started lustre-MDT0000 00:42:27 (1783140147) targets are mounted 00:42:27 (1783140147) facet_failover done 1 445 0.29 MB/sec execute 16 sec latency 111.892 ms 1 478 0.34 MB/sec execute 17 sec latency 173.635 ms 1 511 0.38 MB/sec execute 18 sec latency 228.202 ms 1 561 0.43 MB/sec execute 19 sec latency 197.473 ms 1 638 0.50 MB/sec execute 20 sec latency 90.547 ms 1 664 0.48 MB/sec execute 21 sec latency 274.200 ms 1 691 0.46 MB/sec execute 22 sec latency 320.929 ms oleg301-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 721 0.45 MB/sec execute 23 sec latency 119.523 ms 1 734 0.43 MB/sec execute 24 sec latency 253.489 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 767 0.42 MB/sec execute 25 sec latency 137.222 ms 1 789 0.40 MB/sec execute 26 sec latency 217.762 ms 1 804 0.39 MB/sec execute 27 sec latency 447.366 ms 1 848 0.38 MB/sec execute 28 sec latency 102.194 ms 1 877 0.37 MB/sec execute 29 sec latency 191.288 ms 1 903 0.36 MB/sec execute 30 sec latency 135.576 ms 1 923 0.35 MB/sec execute 31 sec latency 360.107 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2304 2206208 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 17408 3712000 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 35840 3696640 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 53248 7408640 1% /mnt/lustre 1 957 0.34 MB/sec execute 32 sec latency 107.280 ms 1 981 0.33 MB/sec execute 33 sec latency 301.658 ms 1 1037 0.35 MB/sec execute 34 sec latency 132.775 ms 1 1084 0.34 MB/sec execute 35 sec latency 89.978 ms 1 1147 0.33 MB/sec execute 36 sec latency 84.503 ms 1 1193 0.33 MB/sec execute 37 sec latency 100.364 ms test_26 fail mds1 2 times 1 1231 0.32 MB/sec execute 38 sec latency 94.798 ms Failing mds1 on oleg301-server 1 1262 0.31 MB/sec execute 39 sec latency 114.815 ms Stopping /mnt/lustre-mds1 (opts:) on oleg301-server 1 1391 0.38 MB/sec execute 40 sec latency 118.643 ms 1 1420 0.37 MB/sec execute 41 sec latency 261.502 ms 1 1420 0.36 MB/sec execute 42 sec latency 1261.699 ms 1 1420 0.35 MB/sec execute 43 sec latency 2264.428 ms 00:42:54 (1783140174) shut down facet: mds1 facet_host: oleg301-server facet_failover_host: oleg301-server 1 1420 0.34 MB/sec execute 44 sec latency 3265.484 ms 1 1420 0.33 MB/sec execute 45 sec latency 4266.421 ms 1 1420 0.33 MB/sec execute 46 sec latency 5266.612 ms 1 1420 0.32 MB/sec execute 47 sec latency 6267.843 ms 1 1420 0.31 MB/sec execute 48 sec latency 7268.245 ms 1 1420 0.31 MB/sec execute 49 sec latency 8269.044 ms 1 1420 0.30 MB/sec execute 50 sec latency 9271.077 ms 1 1420 0.29 MB/sec execute 51 sec latency 10271.265 ms 1 1420 0.29 MB/sec execute 52 sec latency 11272.547 ms 1 1420 0.28 MB/sec execute 53 sec latency 12272.858 ms Failover mds1 to oleg301-server mount facets: mds1 1 1420 0.28 MB/sec execute 54 sec latency 13273.723 ms 1 1420 0.27 MB/sec execute 55 sec latency 14273.942 ms 1 1420 0.27 MB/sec execute 56 sec latency 15274.161 ms 1 1420 0.26 MB/sec execute 57 sec latency 16274.642 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 1420 0.26 MB/sec execute 58 sec latency 17274.892 ms 1 1420 0.25 MB/sec execute 59 sec latency 18275.081 ms 1 1420 0.25 MB/sec execute 60 sec latency 19275.511 ms 1 1420 0.25 MB/sec execute 61 sec latency 20277.135 ms 1 1420 0.24 MB/sec execute 62 sec latency 21277.293 ms 1 1420 0.24 MB/sec execute 63 sec latency 22277.841 ms 1 1420 0.23 MB/sec execute 64 sec latency 23278.051 ms 1 1420 0.23 MB/sec execute 65 sec latency 24278.612 ms 1 1420 0.23 MB/sec execute 66 sec latency 25278.842 ms 1 1420 0.22 MB/sec execute 67 sec latency 26280.889 ms 1 1420 0.22 MB/sec execute 68 sec latency 27281.076 ms 1 1420 0.22 MB/sec execute 69 sec latency 28281.307 ms 1 1420 0.21 MB/sec execute 70 sec latency 29281.478 ms 1 1420 0.21 MB/sec execute 71 sec latency 30291.151 ms 1 1420 0.21 MB/sec execute 72 sec latency 31293.747 ms 1 1420 0.21 MB/sec execute 73 sec latency 32293.974 ms 1 1420 0.20 MB/sec execute 74 sec latency 33294.267 ms oleg301-server: oleg301-server.virtnet: executing set_default_debug -1 all 1 1420 0.20 MB/sec execute 75 sec latency 34297.178 ms pdsh@oleg301-client: oleg301-server: ssh exited with exit code 1 1 1420 0.20 MB/sec execute 76 sec latency 35298.364 ms Started lustre-MDT0000 00:43:28 (1783140208) targets are mounted 00:43:28 (1783140208) facet_failover done 1 1420 0.20 MB/sec execute 77 sec latency 36298.876 ms 1 1420 0.19 MB/sec execute 78 sec latency 37300.208 ms 1 1420 0.19 MB/sec execute 79 sec latency 38300.543 ms 1 1420 0.19 MB/sec execute 80 sec latency 39303.058 ms 1 1420 0.19 MB/sec execute 81 sec latency 40303.691 ms 1 1451 0.18 MB/sec execute 82 sec latency 40343.261 ms 1 1489 0.18 MB/sec execute 83 sec latency 232.996 ms 1 1534 0.18 MB/sec execute 84 sec latency 82.700 ms 1 1590 0.18 MB/sec execute 85 sec latency 59.321 ms oleg301-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 1632 0.18 MB/sec execute 86 sec latency 98.527 ms 1 1669 0.18 MB/sec execute 87 sec latency 183.087 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 1715 0.17 MB/sec execute 88 sec latency 92.844 ms 1 1787 0.17 MB/sec execute 89 sec latency 120.832 ms 1 1855 0.17 MB/sec execute 90 sec latency 87.618 ms 1 1907 0.17 MB/sec execute 91 sec latency 158.665 ms 1 1980 0.17 MB/sec execute 92 sec latency 73.622 ms 1 2053 0.17 MB/sec execute 93 sec latency 79.828 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2688 2205824 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 33792 3722240 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 39936 3716096 2% /mnt/lustre[OST:1] filesystem_summary: 7542784 73728 7438336 1% /mnt/lustre 1 2108 0.17 MB/sec execute 94 sec latency 96.075 ms 1 2162 0.17 MB/sec execute 95 sec latency 98.115 ms 1 2209 0.16 MB/sec execute 96 sec latency 140.321 ms 1 2290 0.17 MB/sec execute 97 sec latency 96.217 ms 1 2350 0.17 MB/sec execute 98 sec latency 188.610 ms 1 2383 0.17 MB/sec execute 99 sec latency 222.882 ms test_26 fail mds1 3 times 1 cleanup 100 sec 1 cleanup 101 sec Failing mds1 on oleg301-server 1 cleanup 102 sec Stopping /mnt/lustre-mds1 (opts:) on oleg301-server 1 cleanup 103 sec 1 cleanup 104 sec 1 cleanup 105 sec 00:43:57 (1783140237) shut down facet: mds1 facet_host: oleg301-server facet_failover_host: oleg301-server 1 cleanup 106 sec 1 cleanup 107 sec 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 Failover mds1 to oleg301-server mount facets: mds1 1 cleanup 117 sec 1 cleanup 118 sec 1 cleanup 119 sec Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 cleanup 120 sec 1 cleanup 121 sec 1 cleanup 122 sec 1 cleanup 123 sec 1 cleanup 124 sec 1 cleanup 125 sec oleg301-server: oleg301-server.virtnet: executing set_default_debug -1 all 1 cleanup 126 sec pdsh@oleg301-client: oleg301-server: ssh exited with exit code 1 1 cleanup 127 sec Started lustre-MDT0000 00:44:19 (1783140259) targets are mounted 00:44:19 (1783140259) facet_failover done 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 1 cleanup 141 sec 1 cleanup 142 sec 0 cleanup 143 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 363 60.297 271.677 Close 317 211.712 40343.233 Rename 13 91.766 149.752 Unlink 33 31.618 60.303 Qpathinfo 317 16.162 104.198 Qfileinfo 101 2.474 20.152 Qfsinfo 39 3.940 34.157 Sfileinfo 42 65.940 144.851 Find 107 6.714 84.995 WriteX 375 13.628 158.831 ReadX 381 1.960 90.530 Flush 33 170.710 447.352 Throughput 0.17144 MB/sec 1 clients 1 procs max_latency=40343.261 ms stopping dbench on /mnt/lustre at Sat Jul 4 00:44:34 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt oleg301-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 Sat Jul 4 00:44:40 EDT 2026 waiting for dbench pid 47782 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 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 of 1 processes prepared for launch 0 sec releasing clients 1 37 1.24 MB/sec warmup 1 sec latency 105.994 ms 1 99 2.26 MB/sec warmup 2 sec latency 165.023 ms 1 139 2.01 MB/sec warmup 3 sec latency 135.365 ms 1 173 1.76 MB/sec warmup 4 sec latency 171.147 ms 1 215 1.67 MB/sec warmup 5 sec latency 120.128 ms 1 263 1.65 MB/sec warmup 6 sec latency 88.096 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2944 2205568 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 52224 3685376 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 6144 3759104 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 58368 7444480 1% /mnt/lustre 1 298 1.56 MB/sec warmup 7 sec latency 181.835 ms 1 339 1.53 MB/sec warmup 8 sec latency 111.837 ms 1 381 1.51 MB/sec warmup 9 sec latency 134.263 ms 1 430 1.51 MB/sec warmup 10 sec latency 134.210 ms 1 487 1.54 MB/sec warmup 11 sec latency 97.698 ms test_26 fail mds1 4 times 1 533 1.55 MB/sec warmup 12 sec latency 131.565 ms 1 642 1.62 MB/sec warmup 13 sec latency 101.622 ms Failing mds1 on oleg301-server 1 673 1.51 MB/sec warmup 14 sec latency 229.455 ms Stopping /mnt/lustre-mds1 (opts:) on oleg301-server 1 708 1.41 MB/sec warmup 15 sec latency 124.201 ms 1 717 1.33 MB/sec warmup 16 sec latency 756.440 ms 1 717 1.25 MB/sec warmup 17 sec latency 1757.139 ms 00:44:58 (1783140298) shut down facet: mds1 facet_host: oleg301-server facet_failover_host: oleg301-server 1 717 1.18 MB/sec warmup 18 sec latency 2757.290 ms 1 717 1.12 MB/sec warmup 19 sec latency 3757.505 ms 1 717 0.00 MB/sec execute 1 sec latency 5758.073 ms 1 717 0.00 MB/sec execute 2 sec latency 6758.256 ms 1 717 0.00 MB/sec execute 3 sec latency 7758.560 ms 1 717 0.00 MB/sec execute 4 sec latency 8759.025 ms 1 717 0.00 MB/sec execute 5 sec latency 9759.223 ms 1 717 0.00 MB/sec execute 6 sec latency 10759.431 ms 1 717 0.00 MB/sec execute 7 sec latency 11759.588 ms 1 717 0.00 MB/sec execute 8 sec latency 12759.770 ms Failover mds1 to oleg301-server mount facets: mds1 1 717 0.00 MB/sec execute 9 sec latency 13761.454 ms 1 717 0.00 MB/sec execute 10 sec latency 14761.658 ms 1 717 0.00 MB/sec execute 11 sec latency 15761.790 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 717 0.00 MB/sec execute 12 sec latency 16762.409 ms 1 717 0.00 MB/sec execute 13 sec latency 17763.596 ms 1 717 0.00 MB/sec execute 14 sec latency 18765.093 ms 1 717 0.00 MB/sec execute 15 sec latency 19765.592 ms 1 717 0.00 MB/sec execute 16 sec latency 20769.359 ms oleg301-server: oleg301-server.virtnet: executing set_default_debug -1 all 1 717 0.00 MB/sec execute 17 sec latency 21770.111 ms pdsh@oleg301-client: oleg301-server: ssh exited with exit code 1 1 717 0.00 MB/sec execute 18 sec latency 22779.248 ms Started lustre-MDT0000 00:45:19 (1783140319) targets are mounted 00:45:19 (1783140319) facet_failover done 1 717 0.00 MB/sec execute 19 sec latency 23780.043 ms 1 733 0.00 MB/sec execute 20 sec latency 24087.984 ms 1 773 0.00 MB/sec execute 21 sec latency 127.297 ms 1 798 0.01 MB/sec execute 22 sec latency 242.805 ms 1 845 0.01 MB/sec execute 23 sec latency 159.548 ms 1 874 0.02 MB/sec execute 24 sec latency 308.610 ms oleg301-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 902 0.02 MB/sec execute 25 sec latency 124.644 ms 1 921 0.02 MB/sec execute 26 sec latency 230.132 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 965 0.02 MB/sec execute 27 sec latency 111.379 ms 1 985 0.02 MB/sec execute 28 sec latency 248.786 ms 1 1011 0.04 MB/sec execute 29 sec latency 172.061 ms 1 1067 0.05 MB/sec execute 30 sec latency 195.831 ms 1 1128 0.05 MB/sec execute 31 sec latency 99.178 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 1173 0.05 MB/sec execute 32 sec latency 136.403 ms 1 1224 0.05 MB/sec execute 33 sec latency 76.278 ms 1 1272 0.05 MB/sec execute 34 sec latency 70.013 ms 1 1410 0.13 MB/sec execute 35 sec latency 84.582 ms 1 1473 0.13 MB/sec execute 36 sec latency 71.062 ms 1 1509 0.13 MB/sec execute 37 sec latency 313.073 ms 1 1566 0.13 MB/sec execute 38 sec latency 84.250 ms 1 1603 0.12 MB/sec execute 39 sec latency 81.399 ms 1 1643 0.12 MB/sec execute 40 sec latency 200.882 ms 1 1689 0.12 MB/sec execute 41 sec latency 85.641 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Sat Jul 4 00:45:41 EDT 2026 with return code 0 47782 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 47782 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished