== replay-dual test 26: dbench and tar with mds failover ========================================================== 22:14:25 (1788920065) Starting client oleg107-client.virtnet: -o user_xattr,flock 192.168.201.107@tcp:/lustre /mnt/lustre Started clients oleg107-client.virtnet: 192.168.201.107@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 65547 Started dbench loop with 65548 striped dir -i0 -c2 -H fnv_1a_64 /mnt/lustre2/d26.replay-dual/run_dbench striped dir -i0 -c2 -H crush2 /mnt/lustre/d26.replay-dual/run_tar 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 1544 3584800 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3108 7190256 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 Sep 8 22:14:31 EDT 2026 waiting for dbench pid 65627 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 26 0.79 MB/sec warmup 1 sec latency 20.572 ms 1 84 1.90 MB/sec warmup 2 sec latency 110.380 ms 1 133 1.94 MB/sec warmup 3 sec latency 156.927 ms 1 166 1.70 MB/sec warmup 4 sec latency 223.666 ms 1 190 1.51 MB/sec warmup 5 sec latency 420.375 ms 1 223 1.44 MB/sec warmup 6 sec latency 153.279 ms 1 272 1.45 MB/sec warmup 7 sec latency 94.559 ms test_26 fail mds1 1 times 1 313 1.43 MB/sec warmup 8 sec latency 134.099 ms 1 341 1.36 MB/sec warmup 9 sec latency 160.295 ms 1 369 1.31 MB/sec warmup 10 sec latency 174.240 ms Failing mds1 on oleg107-server 1 401 1.28 MB/sec warmup 11 sec latency 160.272 ms Stopping /mnt/lustre-mds1 (opts:) on oleg107-server 1 437 1.28 MB/sec warmup 12 sec latency 205.343 ms 1 444 1.20 MB/sec warmup 13 sec latency 783.155 ms 1 444 1.12 MB/sec warmup 14 sec latency 1783.348 ms 22:14:46 (1788920086) shut down facet: mds1 facet_host: oleg107-server facet_failover_host: oleg107-server 1 444 1.04 MB/sec warmup 15 sec latency 2783.813 ms 1 444 0.98 MB/sec warmup 16 sec latency 3784.219 ms 1 444 0.92 MB/sec warmup 17 sec latency 4785.867 ms 1 444 0.87 MB/sec warmup 18 sec latency 5786.495 ms 1 444 0.82 MB/sec warmup 19 sec latency 6787.154 ms 1 444 0.00 MB/sec execute 1 sec latency 8790.963 ms 1 444 0.00 MB/sec execute 2 sec latency 9791.634 ms 1 444 0.00 MB/sec execute 3 sec latency 10791.829 ms 1 444 0.00 MB/sec execute 4 sec latency 11792.139 ms Failover mds1 to oleg107-server mount facets: mds1 1 444 0.00 MB/sec execute 5 sec latency 12797.620 ms 1 444 0.00 MB/sec execute 6 sec latency 13797.941 ms 1 444 0.00 MB/sec execute 7 sec latency 14798.666 ms 1 444 0.00 MB/sec execute 8 sec latency 15798.869 ms 1 444 0.00 MB/sec execute 9 sec latency 16799.116 ms 1 444 0.00 MB/sec execute 10 sec latency 17799.500 ms 1 444 0.00 MB/sec execute 11 sec latency 18799.728 ms 1 444 0.00 MB/sec execute 12 sec latency 19799.944 ms 1 444 0.00 MB/sec execute 13 sec latency 20800.378 ms 1 444 0.00 MB/sec execute 14 sec latency 21800.672 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 444 0.00 MB/sec execute 15 sec latency 22800.872 ms 1 444 0.00 MB/sec execute 16 sec latency 23801.498 ms 1 444 0.00 MB/sec execute 17 sec latency 24801.719 ms 1 444 0.00 MB/sec execute 18 sec latency 25802.961 ms 1 444 0.00 MB/sec execute 19 sec latency 26803.588 ms 1 444 0.00 MB/sec execute 20 sec latency 27803.845 ms 1 444 0.00 MB/sec execute 21 sec latency 28807.500 ms 1 444 0.00 MB/sec execute 22 sec latency 29808.188 ms 1 444 0.00 MB/sec execute 23 sec latency 30808.570 ms 1 444 0.00 MB/sec execute 24 sec latency 31808.902 ms 1 444 0.00 MB/sec execute 25 sec latency 32809.046 ms 1 444 0.00 MB/sec execute 26 sec latency 33809.242 ms 1 444 0.00 MB/sec execute 27 sec latency 34809.479 ms 1 444 0.00 MB/sec execute 28 sec latency 35809.696 ms 1 444 0.00 MB/sec execute 29 sec latency 36809.940 ms oleg107-server: oleg107-server.virtnet: executing set_default_debug -1 all 1 444 0.00 MB/sec execute 30 sec latency 37811.336 ms 1 444 0.00 MB/sec execute 31 sec latency 38811.728 ms pdsh@oleg107-client: oleg107-server: ssh exited with exit code 1 1 444 0.00 MB/sec execute 32 sec latency 39811.947 ms Started lustre-MDT0000 22:15:24 (1788920124) targets are mounted 22:15:24 (1788920124) facet_failover done 1 446 0.00 MB/sec execute 33 sec latency 40557.979 ms 1 478 0.03 MB/sec execute 34 sec latency 167.065 ms 1 503 0.05 MB/sec execute 35 sec latency 175.752 ms 1 540 0.09 MB/sec execute 36 sec latency 185.146 ms 1 582 0.11 MB/sec execute 37 sec latency 508.684 ms 1 640 0.14 MB/sec execute 38 sec latency 99.238 ms 1 674 0.14 MB/sec execute 39 sec latency 215.110 ms 1 710 0.14 MB/sec execute 40 sec latency 115.024 ms oleg107-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 736 0.14 MB/sec execute 41 sec latency 136.157 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 767 0.14 MB/sec execute 42 sec latency 190.181 ms 1 799 0.14 MB/sec execute 43 sec latency 114.940 ms 1 827 0.13 MB/sec execute 44 sec latency 115.541 ms 1 882 0.13 MB/sec execute 45 sec latency 90.877 ms 1 910 0.13 MB/sec execute 46 sec latency 123.621 ms 1 949 0.13 MB/sec execute 47 sec latency 92.202 ms 1 973 0.13 MB/sec execute 48 sec latency 118.317 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2116 1269188 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1896 1269408 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 17956 3584504 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 36964 3568152 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 54920 7152656 1% /mnt/lustre 1 995 0.13 MB/sec execute 49 sec latency 136.143 ms 1 1059 0.14 MB/sec execute 50 sec latency 64.449 ms 1 1099 0.14 MB/sec execute 51 sec latency 84.293 ms 1 1136 0.14 MB/sec execute 52 sec latency 102.167 ms 1 1172 0.14 MB/sec execute 53 sec latency 219.290 ms 1 1173 0.14 MB/sec execute 54 sec latency 1104.744 ms 1 1201 0.13 MB/sec execute 55 sec latency 134.110 ms 1 1231 0.13 MB/sec execute 56 sec latency 130.263 ms 1 1263 0.13 MB/sec execute 57 sec latency 146.250 ms 1 1403 0.18 MB/sec execute 58 sec latency 89.160 ms test_26 fail mds2 2 times 1 1446 0.18 MB/sec execute 59 sec latency 98.138 ms 1 1486 0.17 MB/sec execute 60 sec latency 132.808 ms Failing mds2 on oleg107-server 1 1509 0.17 MB/sec execute 61 sec latency 128.795 ms Stopping /mnt/lustre-mds2 (opts:) on oleg107-server 1 1556 0.17 MB/sec execute 62 sec latency 88.990 ms 1 1593 0.17 MB/sec execute 63 sec latency 73.417 ms 1 1632 0.16 MB/sec execute 64 sec latency 124.269 ms 1 1669 0.16 MB/sec execute 65 sec latency 91.227 ms 22:15:57 (1788920157) shut down facet: mds2 facet_host: oleg107-server facet_failover_host: oleg107-server 1 1738 0.16 MB/sec execute 66 sec latency 63.536 ms 1 1816 0.16 MB/sec execute 67 sec latency 119.165 ms 1 1877 0.16 MB/sec execute 68 sec latency 86.314 ms 1 1976 0.16 MB/sec execute 69 sec latency 94.507 ms 1 2063 0.16 MB/sec execute 70 sec latency 82.618 ms 1 2139 0.16 MB/sec execute 71 sec latency 73.196 ms 1 2198 0.15 MB/sec execute 72 sec latency 78.935 ms 1 2259 0.15 MB/sec execute 73 sec latency 331.613 ms 1 2259 0.15 MB/sec execute 74 sec latency 1335.039 ms 1 2259 0.15 MB/sec execute 75 sec latency 2335.329 ms Failover mds2 to oleg107-server 1 2259 0.15 MB/sec execute 76 sec latency 3337.568 ms mount facets: mds2 1 2259 0.14 MB/sec execute 77 sec latency 4337.846 ms 1 2259 0.14 MB/sec execute 78 sec latency 5338.132 ms 1 2259 0.14 MB/sec execute 79 sec latency 6339.224 ms 1 2259 0.14 MB/sec execute 80 sec latency 7341.178 ms 1 2259 0.14 MB/sec execute 81 sec latency 8341.402 ms 1 2259 0.14 MB/sec execute 82 sec latency 9343.330 ms 1 2259 0.13 MB/sec execute 83 sec latency 10344.100 ms 1 2259 0.13 MB/sec execute 84 sec latency 11344.411 ms 1 2259 0.13 MB/sec execute 85 sec latency 12345.602 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 2259 0.13 MB/sec execute 86 sec latency 13345.956 ms 1 2259 0.13 MB/sec execute 87 sec latency 14346.278 ms 1 2259 0.13 MB/sec execute 88 sec latency 15352.188 ms 1 2259 0.13 MB/sec execute 89 sec latency 16353.793 ms 1 2259 0.12 MB/sec execute 90 sec latency 17354.002 ms 1 2259 0.12 MB/sec execute 91 sec latency 18354.292 ms oleg107-server: oleg107-server.virtnet: executing set_default_debug -1 all 1 2259 0.12 MB/sec execute 92 sec latency 19354.566 ms pdsh@oleg107-client: oleg107-server: ssh exited with exit code 1 1 2259 0.12 MB/sec execute 93 sec latency 20354.724 ms 1 2259 0.12 MB/sec execute 94 sec latency 21358.137 ms Started lustre-MDT0001 22:16:25 (1788920185) targets are mounted 22:16:25 (1788920185) facet_failover done 1 2272 0.12 MB/sec execute 95 sec latency 22190.644 ms 1 2343 0.13 MB/sec execute 96 sec latency 61.985 ms 1 2371 0.13 MB/sec execute 97 sec latency 131.314 ms 1 2400 0.13 MB/sec execute 98 sec latency 125.716 ms 1 2429 0.13 MB/sec execute 99 sec latency 97.599 ms 1 cleanup 100 sec 1 cleanup 101 sec oleg107-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 1 cleanup 102 sec 1 cleanup 103 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 cleanup 104 sec 0 cleanup 104 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 354 118.858 22190.624 Close 304 145.710 40557.944 Rename 14 96.136 146.214 Unlink 36 28.288 52.271 Qpathinfo 325 15.824 91.145 Qfileinfo 85 2.812 25.317 Qfsinfo 41 5.048 24.153 Sfileinfo 44 69.789 130.226 Find 109 10.810 41.696 WriteX 297 15.718 124.248 ReadX 382 2.709 90.203 Flush 33 59.959 136.142 Throughput 0.125635 MB/sec 1 clients 1 procs max_latency=40557.979 ms stopping dbench on /mnt/lustre at Tue Sep 8 22:16:36 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished 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 2352 1268952 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2092 1269212 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 21092 3585272 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 27804 3565360 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 48896 7150632 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 Sep 8 22:16:44 EDT 2026 waiting for dbench pid 67791 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 40.416 ms 1 51 1.05 MB/sec warmup 2 sec latency 124.140 ms 1 101 1.55 MB/sec warmup 3 sec latency 110.163 ms 1 128 1.44 MB/sec warmup 4 sec latency 201.914 ms 1 128 1.15 MB/sec warmup 5 sec latency 1093.020 ms 1 128 0.96 MB/sec warmup 6 sec latency 2093.946 ms 1 155 0.93 MB/sec warmup 7 sec latency 2107.894 ms 1 182 0.91 MB/sec warmup 8 sec latency 198.587 ms 1 207 0.90 MB/sec warmup 9 sec latency 448.834 ms test_26 fail mds1 3 times 1 245 0.93 MB/sec warmup 10 sec latency 137.180 ms 1 279 0.95 MB/sec warmup 11 sec latency 144.379 ms Failing mds1 on oleg107-server 1 301 0.92 MB/sec warmup 12 sec latency 224.196 ms Stopping /mnt/lustre-mds1 (opts:) on oleg107-server 1 339 0.94 MB/sec warmup 13 sec latency 153.421 ms 1 364 0.93 MB/sec warmup 14 sec latency 243.901 ms 1 364 0.87 MB/sec warmup 15 sec latency 1244.144 ms 1 364 0.81 MB/sec warmup 16 sec latency 2244.422 ms 1 364 0.77 MB/sec warmup 17 sec latency 3244.805 ms 1 364 0.72 MB/sec warmup 18 sec latency 4245.056 ms 1 364 0.69 MB/sec warmup 19 sec latency 5245.322 ms 1 364 0.00 MB/sec execute 1 sec latency 7245.922 ms 22:17:06 (1788920226) shut down 1 364 0.00 MB/sec execute 2 sec latency 8248.354 ms facet: mds1 facet_host: oleg107-server facet_failover_host: oleg107-server 1 364 0.00 MB/sec execute 3 sec latency 9248.587 ms 1 364 0.00 MB/sec execute 4 sec latency 10248.879 ms 1 364 0.00 MB/sec execute 5 sec latency 11249.136 ms 1 364 0.00 MB/sec execute 6 sec latency 12249.394 ms 1 364 0.00 MB/sec execute 7 sec latency 13249.976 ms 1 364 0.00 MB/sec execute 8 sec latency 14255.434 ms 1 364 0.00 MB/sec execute 9 sec latency 15255.664 ms 1 364 0.00 MB/sec execute 10 sec latency 16256.631 ms 1 364 0.00 MB/sec execute 11 sec latency 17256.955 ms 1 364 0.00 MB/sec execute 12 sec latency 18257.823 ms Failover mds1 to oleg107-server mount facets: mds1 1 364 0.00 MB/sec execute 13 sec latency 19259.339 ms 1 364 0.00 MB/sec execute 14 sec latency 20259.887 ms 1 364 0.00 MB/sec execute 15 sec latency 21260.113 ms 1 364 0.00 MB/sec execute 16 sec latency 22260.910 ms 1 364 0.00 MB/sec execute 17 sec latency 23261.366 ms 1 364 0.00 MB/sec execute 18 sec latency 24263.198 ms 1 364 0.00 MB/sec execute 19 sec latency 25263.369 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 364 0.00 MB/sec execute 20 sec latency 26265.443 ms 1 364 0.00 MB/sec execute 21 sec latency 27265.664 ms 1 364 0.00 MB/sec execute 22 sec latency 28270.723 ms 1 364 0.00 MB/sec execute 23 sec latency 29272.723 ms 1 364 0.00 MB/sec execute 24 sec latency 30273.020 ms 1 364 0.00 MB/sec execute 25 sec latency 31273.564 ms 1 364 0.00 MB/sec execute 26 sec latency 32273.942 ms 1 364 0.00 MB/sec execute 27 sec latency 33274.221 ms 1 364 0.00 MB/sec execute 28 sec latency 34274.439 ms 1 364 0.00 MB/sec execute 29 sec latency 35275.899 ms 1 364 0.00 MB/sec execute 30 sec latency 36276.173 ms 1 364 0.00 MB/sec execute 31 sec latency 37277.285 ms oleg107-server: oleg107-server.virtnet: executing set_default_debug -1 all 1 364 0.00 MB/sec execute 32 sec latency 38279.469 ms pdsh@oleg107-client: oleg107-server: ssh exited with exit code 1 1 364 0.00 MB/sec execute 33 sec latency 39280.273 ms Started lustre-MDT0000 22:17:38 (1788920258) targets are mounted 22:17:38 (1788920258) facet_failover done 1 382 0.02 MB/sec execute 34 sec latency 39551.424 ms 1 405 0.04 MB/sec execute 35 sec latency 245.908 ms 1 422 0.05 MB/sec execute 36 sec latency 208.942 ms 1 446 0.07 MB/sec execute 37 sec latency 197.611 ms 1 477 0.10 MB/sec execute 38 sec latency 175.205 ms 1 497 0.11 MB/sec execute 39 sec latency 195.139 ms 1 514 0.12 MB/sec execute 40 sec latency 268.827 ms 1 554 0.15 MB/sec execute 41 sec latency 247.690 ms 1 618 0.19 MB/sec execute 42 sec latency 157.646 ms 1 654 0.19 MB/sec execute 43 sec latency 194.349 ms oleg107-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 674 0.18 MB/sec execute 44 sec latency 243.343 ms 1 691 0.18 MB/sec execute 45 sec latency 209.292 ms 1 699 0.18 MB/sec execute 46 sec latency 394.541 ms 1 704 0.17 MB/sec execute 47 sec latency 1064.510 ms 1 712 0.17 MB/sec execute 48 sec latency 544.882 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 730 0.17 MB/sec execute 49 sec latency 167.600 ms 1 738 0.17 MB/sec execute 50 sec latency 418.756 ms 1 767 0.16 MB/sec execute 51 sec latency 148.353 ms 1 789 0.16 MB/sec execute 52 sec latency 195.573 ms 1 821 0.16 MB/sec execute 53 sec latency 153.989 ms 1 864 0.16 MB/sec execute 54 sec latency 134.147 ms 1 884 0.16 MB/sec execute 55 sec latency 343.481 ms 1 885 0.15 MB/sec execute 56 sec latency 1106.902 ms 1 914 0.15 MB/sec execute 57 sec latency 256.271 ms 1 952 0.15 MB/sec execute 58 sec latency 137.188 ms 1 971 0.15 MB/sec execute 59 sec latency 151.893 ms 1 1020 0.16 MB/sec execute 60 sec latency 142.530 ms 1 1074 0.16 MB/sec execute 61 sec latency 115.884 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 1124 0.16 MB/sec execute 62 sec latency 97.958 ms 1 1147 0.16 MB/sec execute 63 sec latency 131.650 ms 1 1182 0.16 MB/sec execute 64 sec latency 154.555 ms 1 1214 0.15 MB/sec execute 65 sec latency 184.570 ms 1 1239 0.15 MB/sec execute 66 sec latency 154.803 ms 1 1263 0.15 MB/sec execute 67 sec latency 162.122 ms 1 1340 0.17 MB/sec execute 68 sec latency 204.021 ms 1 1418 0.19 MB/sec execute 69 sec latency 76.606 ms 1 1447 0.18 MB/sec execute 70 sec latency 226.249 ms 1 1470 0.18 MB/sec execute 71 sec latency 418.431 ms 1 1511 0.18 MB/sec execute 72 sec latency 113.764 ms 1 1558 0.18 MB/sec execute 73 sec latency 79.464 ms 1 1619 0.18 MB/sec execute 74 sec latency 136.902 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Tue Sep 8 22:18:19 EDT 2026 with return code 0 67791 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 67791 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished