== replay-dual test 26: dbench and tar with mds failover ========================================================== 21:32:10 (1789781530) Starting client oleg615-client.virtnet: -o user_xattr,flock 192.168.206.115@tcp:/lustre /mnt/lustre Started clients oleg615-client.virtnet: 192.168.206.115@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 65638 Started dbench loop with 65639 striped dir -i0 -c2 -H fnv_1a_64 /mnt/lustre/d26.replay-dual/run_tar striped dir -i0 -c2 -H crush2 /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 1968 1269336 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1756 1269548 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1564 3605456 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 17928 3580748 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 19492 7186204 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 Sep 18 21:32:15 EDT 2026 waiting for dbench pid 65709 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 17 0.20 MB/sec warmup 1 sec latency 16.339 ms 1 91 2.09 MB/sec warmup 2 sec latency 107.899 ms 1 137 2.01 MB/sec warmup 3 sec latency 201.439 ms 1 173 1.76 MB/sec warmup 4 sec latency 127.061 ms 1 199 1.57 MB/sec warmup 5 sec latency 343.759 ms 1 239 1.52 MB/sec warmup 6 sec latency 119.856 ms 1 287 1.53 MB/sec warmup 7 sec latency 100.133 ms 1 331 1.50 MB/sec warmup 8 sec latency 134.334 ms test_26 fail mds1 1 times 1 372 1.48 MB/sec warmup 9 sec latency 101.805 ms Failing mds1 on oleg615-server 1 414 1.46 MB/sec warmup 10 sec latency 135.461 ms Stopping /mnt/lustre-mds1 (opts:) on oleg615-server 1 456 1.44 MB/sec warmup 11 sec latency 111.803 ms 1 484 1.41 MB/sec warmup 12 sec latency 402.853 ms 1 484 1.30 MB/sec warmup 13 sec latency 1403.054 ms 1 484 1.21 MB/sec warmup 14 sec latency 2406.052 ms 1 484 1.13 MB/sec warmup 15 sec latency 3406.323 ms 1 484 1.06 MB/sec warmup 16 sec latency 4407.494 ms 1 484 1.00 MB/sec warmup 17 sec latency 5411.676 ms 1 484 0.94 MB/sec warmup 18 sec latency 6421.858 ms 1 484 0.89 MB/sec warmup 19 sec latency 7422.406 ms 21:32:34 (1789781554) shut down facet: mds1 facet_host: oleg615-server facet_failover_host: oleg615-server 1 484 0.00 MB/sec execute 1 sec latency 9422.840 ms 1 484 0.00 MB/sec execute 2 sec latency 10423.050 ms 1 484 0.00 MB/sec execute 3 sec latency 11423.242 ms 1 484 0.00 MB/sec execute 4 sec latency 12425.788 ms 1 484 0.00 MB/sec execute 5 sec latency 13428.577 ms 1 484 0.00 MB/sec execute 6 sec latency 14432.715 ms 1 484 0.00 MB/sec execute 7 sec latency 15432.917 ms 1 484 0.00 MB/sec execute 8 sec latency 16433.124 ms 1 484 0.00 MB/sec execute 9 sec latency 17434.036 ms 1 484 0.00 MB/sec execute 10 sec latency 18436.301 ms Failover mds1 to oleg615-server mount facets: mds1 1 484 0.00 MB/sec execute 11 sec latency 19436.618 ms 1 484 0.00 MB/sec execute 12 sec latency 20436.814 ms 1 484 0.00 MB/sec execute 13 sec latency 21437.778 ms 1 484 0.00 MB/sec execute 14 sec latency 22437.935 ms 1 484 0.00 MB/sec execute 15 sec latency 23438.461 ms 1 484 0.00 MB/sec execute 16 sec latency 24438.638 ms 1 484 0.00 MB/sec execute 17 sec latency 25438.968 ms 1 484 0.00 MB/sec execute 18 sec latency 26439.136 ms 1 484 0.00 MB/sec execute 19 sec latency 27442.004 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 484 0.00 MB/sec execute 20 sec latency 28449.687 ms 1 484 0.00 MB/sec execute 21 sec latency 29449.866 ms 1 484 0.00 MB/sec execute 22 sec latency 30450.055 ms 1 484 0.00 MB/sec execute 23 sec latency 31450.568 ms 1 484 0.00 MB/sec execute 24 sec latency 32450.764 ms 1 484 0.00 MB/sec execute 25 sec latency 33451.577 ms 1 484 0.00 MB/sec execute 26 sec latency 34451.995 ms 1 484 0.00 MB/sec execute 27 sec latency 35452.316 ms 1 484 0.00 MB/sec execute 28 sec latency 36455.740 ms 1 484 0.00 MB/sec execute 29 sec latency 37456.002 ms 1 484 0.00 MB/sec execute 30 sec latency 38456.413 ms 1 484 0.00 MB/sec execute 31 sec latency 39456.781 ms oleg615-server: oleg615-server.virtnet: executing set_default_debug -1 all 1 484 0.00 MB/sec execute 32 sec latency 40456.964 ms pdsh@oleg615-client: oleg615-server: ssh exited with exit code 1 1 484 0.00 MB/sec execute 33 sec latency 41463.192 ms Started lustre-MDT0000 21:33:09 (1789781589) targets are mounted 21:33:09 (1789781589) facet_failover done 1 484 0.00 MB/sec execute 34 sec latency 42467.844 ms 1 488 0.00 MB/sec execute 35 sec latency 43276.767 ms 1 518 0.03 MB/sec execute 36 sec latency 199.678 ms 1 552 0.06 MB/sec execute 37 sec latency 293.580 ms 1 607 0.11 MB/sec execute 38 sec latency 700.033 ms 1 664 0.11 MB/sec execute 39 sec latency 119.397 ms 1 708 0.11 MB/sec execute 40 sec latency 108.531 ms oleg615-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 735 0.11 MB/sec execute 41 sec latency 146.804 ms 1 774 0.11 MB/sec execute 42 sec latency 127.886 ms 1 799 0.11 MB/sec execute 43 sec latency 143.295 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 825 0.10 MB/sec execute 44 sec latency 165.683 ms 1 870 0.10 MB/sec execute 45 sec latency 107.112 ms 1 893 0.10 MB/sec execute 46 sec latency 149.256 ms 1 914 0.10 MB/sec execute 47 sec latency 224.618 ms 1 952 0.10 MB/sec execute 48 sec latency 153.668 ms 1 985 0.10 MB/sec execute 49 sec latency 92.331 ms 1 1040 0.12 MB/sec execute 50 sec latency 125.827 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2220 1269084 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1972 1269332 1% /mnt/lustre[MDT:1] 1 1076 0.12 MB/sec execute 51 sec latency 120.462 ms lustre-OST0000_UUID 3833116 20160 3585012 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 35452 3569264 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 55612 7154276 1% /mnt/lustre 1 1126 0.12 MB/sec execute 52 sec latency 84.567 ms 1 1155 0.11 MB/sec execute 53 sec latency 119.143 ms 1 1172 0.11 MB/sec execute 54 sec latency 497.007 ms 1 1198 0.11 MB/sec execute 55 sec latency 607.099 ms 1 1239 0.11 MB/sec execute 56 sec latency 97.701 ms 1 1278 0.11 MB/sec execute 57 sec latency 115.685 ms 1 1403 0.16 MB/sec execute 58 sec latency 188.580 ms 1 1428 0.15 MB/sec execute 59 sec latency 228.506 ms 1 1474 0.15 MB/sec execute 60 sec latency 97.714 ms 1 1523 0.15 MB/sec execute 61 sec latency 101.131 ms test_26 fail mds2 2 times 1 1570 0.15 MB/sec execute 62 sec latency 100.380 ms 1 1591 0.15 MB/sec execute 63 sec latency 121.242 ms Failing mds2 on oleg615-server 1 1621 0.14 MB/sec execute 64 sec latency 140.743 ms Stopping /mnt/lustre-mds2 (opts:) on oleg615-server 1 1655 0.14 MB/sec execute 65 sec latency 150.421 ms 1 1706 0.14 MB/sec execute 66 sec latency 96.536 ms 1 1775 0.14 MB/sec execute 67 sec latency 85.519 ms 1 1825 0.14 MB/sec execute 68 sec latency 121.260 ms 1 1877 0.14 MB/sec execute 69 sec latency 100.336 ms 21:33:45 (1789781625) shut down facet: mds2 facet_host: oleg615-server facet_failover_host: oleg615-server 1 1967 0.14 MB/sec execute 70 sec latency 115.569 ms 1 2030 0.14 MB/sec execute 71 sec latency 120.647 ms 1 2095 0.13 MB/sec execute 72 sec latency 128.562 ms 1 2160 0.13 MB/sec execute 73 sec latency 96.425 ms 1 2249 0.13 MB/sec execute 74 sec latency 72.948 ms 1 2259 0.13 MB/sec execute 75 sec latency 907.063 ms 1 2259 0.13 MB/sec execute 76 sec latency 1907.391 ms 1 2259 0.13 MB/sec execute 77 sec latency 2913.860 ms 1 2259 0.13 MB/sec execute 78 sec latency 3914.890 ms 1 2259 0.12 MB/sec execute 79 sec latency 4916.620 ms 1 2259 0.12 MB/sec execute 80 sec latency 5917.913 ms Failover mds2 to oleg615-server mount facets: mds2 1 2259 0.12 MB/sec execute 81 sec latency 6919.288 ms 1 2259 0.12 MB/sec execute 82 sec latency 7919.480 ms 1 2259 0.12 MB/sec execute 83 sec latency 8919.671 ms 1 2259 0.12 MB/sec execute 84 sec latency 9922.837 ms 1 2259 0.12 MB/sec execute 85 sec latency 10923.527 ms 1 2259 0.11 MB/sec execute 86 sec latency 11924.027 ms 1 2259 0.11 MB/sec execute 87 sec latency 12924.197 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 2259 0.11 MB/sec execute 88 sec latency 13924.491 ms 1 2259 0.11 MB/sec execute 89 sec latency 14924.748 ms 1 2259 0.11 MB/sec execute 90 sec latency 15925.014 ms 1 2259 0.11 MB/sec execute 91 sec latency 16926.022 ms 1 2259 0.11 MB/sec execute 92 sec latency 17926.660 ms 1 2259 0.11 MB/sec execute 93 sec latency 18926.847 ms 1 2259 0.10 MB/sec execute 94 sec latency 19927.036 ms oleg615-server: oleg615-server.virtnet: executing set_default_debug -1 all 1 2259 0.10 MB/sec execute 95 sec latency 20927.499 ms pdsh@oleg615-client: oleg615-server: ssh exited with exit code 1 1 2259 0.10 MB/sec execute 96 sec latency 21930.953 ms Started lustre-MDT0001 21:34:12 (1789781652) targets are mounted 21:34:12 (1789781652) facet_failover done 1 2301 0.11 MB/sec execute 97 sec latency 22408.998 ms 1 2359 0.11 MB/sec execute 98 sec latency 64.192 ms 1 2400 0.11 MB/sec execute 99 sec latency 101.196 ms 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec 1 cleanup 103 sec 0 cleanup 104 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 343 120.848 22408.980 Close 296 157.974 43276.746 Rename 14 100.408 224.586 Unlink 35 25.531 61.803 Qpathinfo 322 16.389 103.850 Qfileinfo 78 2.025 19.463 Qfsinfo 40 3.559 22.457 Sfileinfo 44 65.206 165.669 Find 109 13.564 36.399 WriteX 261 13.586 105.872 ReadX 382 3.282 119.384 Flush 33 63.597 149.216 Throughput 0.111176 MB/sec 1 clients 1 procs max_latency=43276.767 ms oleg615-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 stopping dbench on /mnt/lustre at Fri Sep 18 21:34:19 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 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 '/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 Sep 18 21:34:27 EDT 2026 waiting for dbench pid 67855 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 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2540 1268764 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2252 1269052 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 20564 3585592 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 14760 3576980 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 35324 7162572 1% /mnt/lustre 1 26 0.79 MB/sec warmup 1 sec latency 17.112 ms 1 96 2.16 MB/sec warmup 2 sec latency 110.402 ms 1 137 2.01 MB/sec warmup 3 sec latency 135.506 ms 1 165 1.70 MB/sec warmup 4 sec latency 174.475 ms 1 188 1.52 MB/sec warmup 5 sec latency 346.003 ms 1 188 1.26 MB/sec warmup 6 sec latency 1202.211 ms 1 213 1.18 MB/sec warmup 7 sec latency 1460.566 ms 1 262 1.24 MB/sec warmup 8 sec latency 134.694 ms 1 305 1.25 MB/sec warmup 9 sec latency 131.885 ms test_26 fail mds1 3 times 1 341 1.23 MB/sec warmup 10 sec latency 140.270 ms 1 381 1.23 MB/sec warmup 11 sec latency 181.087 ms Failing mds1 on oleg615-server 1 425 1.24 MB/sec warmup 12 sec latency 171.555 ms Stopping /mnt/lustre-mds1 (opts:) on oleg615-server 1 472 1.26 MB/sec warmup 13 sec latency 115.862 ms 1 477 1.19 MB/sec warmup 14 sec latency 908.968 ms 1 477 1.11 MB/sec warmup 15 sec latency 1915.716 ms 21:34:43 (1789781683) shut down facet: mds1 facet_host: oleg615-server facet_failover_host: oleg615-server 1 477 1.04 MB/sec warmup 16 sec latency 2916.304 ms 1 477 0.98 MB/sec warmup 17 sec latency 3916.533 ms 1 477 0.93 MB/sec warmup 18 sec latency 4918.644 ms 1 477 0.88 MB/sec warmup 19 sec latency 5919.335 ms 1 477 0.00 MB/sec execute 1 sec latency 7919.700 ms 1 477 0.00 MB/sec execute 2 sec latency 8919.916 ms 1 477 0.00 MB/sec execute 3 sec latency 9920.220 ms 1 477 0.00 MB/sec execute 4 sec latency 10920.406 ms 1 477 0.00 MB/sec execute 5 sec latency 11923.053 ms Failover mds1 to oleg615-server 1 477 0.00 MB/sec execute 6 sec latency 12923.497 ms mount facets: mds1 1 477 0.00 MB/sec execute 7 sec latency 13923.711 ms 1 477 0.00 MB/sec execute 8 sec latency 14923.896 ms 1 477 0.00 MB/sec execute 9 sec latency 15928.439 ms 1 477 0.00 MB/sec execute 10 sec latency 16928.611 ms 1 477 0.00 MB/sec execute 11 sec latency 17929.396 ms 1 477 0.00 MB/sec execute 12 sec latency 18930.880 ms 1 477 0.00 MB/sec execute 13 sec latency 19931.072 ms 1 477 0.00 MB/sec execute 14 sec latency 20931.682 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 477 0.00 MB/sec execute 15 sec latency 21931.858 ms 1 477 0.00 MB/sec execute 16 sec latency 22932.858 ms 1 477 0.00 MB/sec execute 17 sec latency 23933.136 ms 1 477 0.00 MB/sec execute 18 sec latency 24937.670 ms 1 477 0.00 MB/sec execute 19 sec latency 25938.182 ms 1 477 0.00 MB/sec execute 20 sec latency 26941.509 ms 1 477 0.00 MB/sec execute 21 sec latency 27941.707 ms 1 477 0.00 MB/sec execute 22 sec latency 28942.249 ms 1 477 0.00 MB/sec execute 23 sec latency 29943.535 ms 1 477 0.00 MB/sec execute 24 sec latency 30943.759 ms 1 477 0.00 MB/sec execute 25 sec latency 31944.797 ms 1 477 0.00 MB/sec execute 26 sec latency 32945.431 ms 1 477 0.00 MB/sec execute 27 sec latency 33947.133 ms 1 477 0.00 MB/sec execute 28 sec latency 34948.158 ms 1 477 0.00 MB/sec execute 29 sec latency 35948.576 ms oleg615-server: oleg615-server.virtnet: executing set_default_debug -1 all 1 477 0.00 MB/sec execute 30 sec latency 36948.781 ms pdsh@oleg615-client: oleg615-server: ssh exited with exit code 1 1 477 0.00 MB/sec execute 31 sec latency 37949.218 ms Started lustre-MDT0000 21:35:19 (1789781719) targets are mounted 21:35:19 (1789781719) facet_failover done 1 477 0.00 MB/sec execute 32 sec latency 38950.897 ms 1 485 0.01 MB/sec execute 33 sec latency 39793.359 ms 1 517 0.03 MB/sec execute 34 sec latency 139.057 ms 1 603 0.12 MB/sec execute 35 sec latency 127.181 ms 1 654 0.12 MB/sec execute 36 sec latency 113.106 ms 1 689 0.12 MB/sec execute 37 sec latency 128.912 ms 1 712 0.12 MB/sec execute 38 sec latency 160.408 ms oleg615-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 741 0.12 MB/sec execute 39 sec latency 110.744 ms 1 778 0.12 MB/sec execute 40 sec latency 138.823 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 808 0.12 MB/sec execute 41 sec latency 142.483 ms 1 856 0.12 MB/sec execute 42 sec latency 109.399 ms 1 884 0.12 MB/sec execute 43 sec latency 237.369 ms 1 887 0.11 MB/sec execute 44 sec latency 1063.432 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 914 0.11 MB/sec execute 45 sec latency 145.494 ms 1 969 0.11 MB/sec execute 46 sec latency 76.382 ms 1 1023 0.13 MB/sec execute 47 sec latency 106.722 ms 1 1086 0.13 MB/sec execute 48 sec latency 70.815 ms 1 1149 0.13 MB/sec execute 49 sec latency 122.184 ms 1 1208 0.13 MB/sec execute 50 sec latency 65.385 ms 1 1248 0.13 MB/sec execute 51 sec latency 119.151 ms 1 1383 0.18 MB/sec execute 52 sec latency 85.272 ms 1 1428 0.18 MB/sec execute 53 sec latency 108.101 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Fri Sep 18 21:35:41 EDT 2026 with return code 0 67855 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 67855 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished