== replay-dual test 26: dbench and tar with mds failover ========================================================== 04:42:56 (1789548176) Starting client oleg310-client.virtnet: -o user_xattr,flock 192.168.203.110@tcp:/lustre /mnt/lustre Started clients oleg310-client.virtnet: 192.168.203.110@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 65479 Started dbench loop with 65480 striped dir -i0 -c2 -H fnv_1a_64 /mnt/lustre/d26.replay-dual/run_tar 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 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1980 1269324 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1792 1269512 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1564 3605456 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 9736 3593088 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 11300 7198544 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 Wed Sep 16 04:43:04 EDT 2026 waiting for dbench pid 65562 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 8 0.00 MB/sec warmup 1 sec latency 117.724 ms 1 52 1.05 MB/sec warmup 2 sec latency 119.582 ms 1 108 1.70 MB/sec warmup 3 sec latency 117.831 ms 1 133 1.45 MB/sec warmup 4 sec latency 188.295 ms 1 147 1.25 MB/sec warmup 5 sec latency 278.767 ms 1 155 1.09 MB/sec warmup 6 sec latency 663.955 ms 1 166 0.97 MB/sec warmup 7 sec latency 1165.742 ms 1 190 0.95 MB/sec warmup 8 sec latency 264.559 ms 1 221 0.95 MB/sec warmup 9 sec latency 192.880 ms test_26 fail mds1 1 times 1 263 0.99 MB/sec warmup 10 sec latency 112.651 ms 1 289 0.97 MB/sec warmup 11 sec latency 254.587 ms 1 313 0.95 MB/sec warmup 12 sec latency 260.375 ms Failing mds1 on oleg310-server 1 342 0.94 MB/sec warmup 13 sec latency 182.970 ms Stopping /mnt/lustre-mds1 (opts:) on oleg310-server 1 366 0.93 MB/sec warmup 14 sec latency 241.951 ms 1 396 0.94 MB/sec warmup 15 sec latency 131.006 ms 1 396 0.88 MB/sec warmup 16 sec latency 1128.085 ms 04:43:21 (1789548201) shut down facet: mds1 facet_host: oleg310-server facet_failover_host: oleg310-server 1 396 0.83 MB/sec warmup 17 sec latency 2136.194 ms 1 396 0.78 MB/sec warmup 18 sec latency 3136.303 ms 1 396 0.74 MB/sec warmup 19 sec latency 4136.601 ms 1 396 0.00 MB/sec execute 1 sec latency 6137.245 ms 1 396 0.00 MB/sec execute 2 sec latency 7140.398 ms 1 396 0.00 MB/sec execute 3 sec latency 8142.608 ms 1 396 0.00 MB/sec execute 4 sec latency 9145.398 ms 1 396 0.00 MB/sec execute 5 sec latency 10146.083 ms 1 396 0.00 MB/sec execute 6 sec latency 11147.262 ms 1 396 0.00 MB/sec execute 7 sec latency 12147.634 ms Failover mds1 to oleg310-server mount facets: mds1 1 396 0.00 MB/sec execute 8 sec latency 13147.842 ms 1 396 0.00 MB/sec execute 9 sec latency 14163.944 ms 1 396 0.00 MB/sec execute 10 sec latency 15164.393 ms 1 396 0.00 MB/sec execute 11 sec latency 16167.139 ms 1 396 0.00 MB/sec execute 12 sec latency 17168.614 ms 1 396 0.00 MB/sec execute 13 sec latency 18169.030 ms 1 396 0.00 MB/sec execute 14 sec latency 19181.066 ms 1 396 0.00 MB/sec execute 15 sec latency 20181.410 ms 1 396 0.00 MB/sec execute 16 sec latency 21181.990 ms 1 396 0.00 MB/sec execute 17 sec latency 22182.980 ms 1 396 0.00 MB/sec execute 18 sec latency 23183.170 ms 1 396 0.00 MB/sec execute 19 sec latency 24188.499 ms 1 396 0.00 MB/sec execute 20 sec latency 25188.693 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 396 0.00 MB/sec execute 21 sec latency 26189.071 ms 1 396 0.00 MB/sec execute 22 sec latency 27189.258 ms 1 396 0.00 MB/sec execute 23 sec latency 28189.478 ms 1 396 0.00 MB/sec execute 24 sec latency 29190.389 ms 1 396 0.00 MB/sec execute 25 sec latency 30190.847 ms 1 396 0.00 MB/sec execute 26 sec latency 31193.413 ms 1 396 0.00 MB/sec execute 27 sec latency 32193.630 ms 1 396 0.00 MB/sec execute 28 sec latency 33193.796 ms 1 396 0.00 MB/sec execute 29 sec latency 34194.006 ms oleg310-server: oleg310-server.virtnet: executing set_default_debug -1 all 1 396 0.00 MB/sec execute 30 sec latency 35194.187 ms pdsh@oleg310-client: oleg310-server: ssh exited with exit code 1 1 396 0.00 MB/sec execute 31 sec latency 36196.479 ms Started lustre-MDT0000 04:43:56 (1789548236) targets are mounted 04:43:56 (1789548236) facet_failover done 1 396 0.00 MB/sec execute 32 sec latency 37199.316 ms 1 438 0.04 MB/sec execute 33 sec latency 37266.973 ms 1 477 0.08 MB/sec execute 34 sec latency 123.484 ms 1 514 0.10 MB/sec execute 35 sec latency 121.948 ms 1 577 0.15 MB/sec execute 36 sec latency 447.902 ms oleg310-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 651 0.19 MB/sec execute 37 sec latency 84.459 ms 1 697 0.19 MB/sec execute 38 sec latency 83.097 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 735 0.19 MB/sec execute 39 sec latency 100.492 ms 1 776 0.18 MB/sec execute 40 sec latency 98.654 ms 1 813 0.18 MB/sec execute 41 sec latency 89.293 ms 1 874 0.18 MB/sec execute 42 sec latency 75.149 ms 1 918 0.18 MB/sec execute 43 sec latency 83.730 ms 1 967 0.18 MB/sec execute 44 sec latency 104.354 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2140 1269164 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1904 1269400 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 13396 3581080 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 34408 3568444 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 47804 7149524 1% /mnt/lustre 1 990 0.17 MB/sec execute 45 sec latency 140.985 ms 1 1064 0.19 MB/sec execute 46 sec latency 100.141 ms 1 1132 0.19 MB/sec execute 47 sec latency 73.069 ms 1 1172 0.19 MB/sec execute 48 sec latency 202.397 ms 1 1182 0.18 MB/sec execute 49 sec latency 775.476 ms 1 1235 0.18 MB/sec execute 50 sec latency 64.413 ms 1 1378 0.23 MB/sec execute 51 sec latency 131.358 ms 1 1440 0.23 MB/sec execute 52 sec latency 70.156 ms test_26 fail mds2 2 times 1 1504 0.23 MB/sec execute 53 sec latency 76.991 ms 1 1558 0.22 MB/sec execute 54 sec latency 134.190 ms Failing mds2 on oleg310-server 1 1625 0.22 MB/sec execute 55 sec latency 83.396 ms Stopping /mnt/lustre-mds2 (opts:) on oleg310-server 1 1686 0.22 MB/sec execute 56 sec latency 91.207 ms 1 1764 0.21 MB/sec execute 57 sec latency 86.076 ms 04:44:22 (1789548262) shut down facet: mds2 facet_host: oleg310-server facet_failover_host: oleg310-server 1 1843 0.21 MB/sec execute 58 sec latency 66.705 ms 1 1953 0.21 MB/sec execute 59 sec latency 54.016 ms 1 2042 0.21 MB/sec execute 60 sec latency 46.334 ms 1 2156 0.21 MB/sec execute 61 sec latency 53.881 ms 1 2228 0.20 MB/sec execute 62 sec latency 79.029 ms 1 2259 0.20 MB/sec execute 63 sec latency 773.047 ms 1 2259 0.20 MB/sec execute 64 sec latency 1774.696 ms 1 2259 0.20 MB/sec execute 65 sec latency 2774.867 ms 1 2259 0.19 MB/sec execute 66 sec latency 3775.200 ms 1 2259 0.19 MB/sec execute 67 sec latency 4775.553 ms Failover mds2 to oleg310-server mount facets: mds2 1 2259 0.19 MB/sec execute 68 sec latency 5780.499 ms 1 2259 0.18 MB/sec execute 69 sec latency 6782.020 ms 1 2259 0.18 MB/sec execute 70 sec latency 7782.314 ms 1 2259 0.18 MB/sec execute 71 sec latency 8782.556 ms 1 2259 0.18 MB/sec execute 72 sec latency 9782.986 ms 1 2259 0.17 MB/sec execute 73 sec latency 10783.505 ms 1 2259 0.17 MB/sec execute 74 sec latency 11783.723 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 2259 0.17 MB/sec execute 75 sec latency 12784.221 ms 1 2259 0.17 MB/sec execute 76 sec latency 13784.410 ms 1 2259 0.16 MB/sec execute 77 sec latency 14784.613 ms 1 2259 0.16 MB/sec execute 78 sec latency 15785.202 ms oleg310-server: oleg310-server.virtnet: executing set_default_debug -1 all 1 2259 0.16 MB/sec execute 79 sec latency 16785.498 ms pdsh@oleg310-client: oleg310-server: ssh exited with exit code 1 1 2259 0.16 MB/sec execute 80 sec latency 17785.655 ms Started lustre-MDT0001 04:44:45 (1789548285) targets are mounted 04:44:45 (1789548285) facet_failover done 1 2259 0.16 MB/sec execute 81 sec latency 18786.072 ms 1 2259 0.15 MB/sec execute 82 sec latency 19786.896 ms 1 2345 0.17 MB/sec execute 83 sec latency 19864.187 ms 1 2380 0.16 MB/sec execute 84 sec latency 90.218 ms 1 2426 0.16 MB/sec execute 85 sec latency 79.836 ms oleg310-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 1 2477 0.17 MB/sec execute 86 sec latency 76.074 ms 1 2574 0.17 MB/sec execute 87 sec latency 74.937 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 2622 0.17 MB/sec execute 88 sec latency 78.200 ms 1 2880 0.20 MB/sec execute 89 sec latency 61.961 ms 1 2934 0.22 MB/sec execute 90 sec latency 104.562 ms 1 3011 0.21 MB/sec execute 91 sec latency 72.199 ms 1 3207 0.22 MB/sec execute 92 sec latency 91.462 ms 1 3298 0.23 MB/sec execute 93 sec latency 116.965 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2384 1268920 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2144 1269160 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 22156 3582036 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 47016 3558932 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 69172 7140968 1% /mnt/lustre 1 3379 0.23 MB/sec execute 94 sec latency 49.531 ms 1 3539 0.26 MB/sec execute 95 sec latency 99.782 ms 1 3592 0.25 MB/sec execute 96 sec latency 80.905 ms 1 3672 0.25 MB/sec execute 97 sec latency 84.840 ms 1 3729 0.25 MB/sec execute 98 sec latency 90.039 ms 1 3800 0.26 MB/sec execute 99 sec latency 98.326 ms 1 cleanup 100 sec 1 cleanup 101 sec test_26 fail mds1 3 times 1 cleanup 102 sec 1 cleanup 103 sec Failing mds1 on oleg310-server 0 cleanup 103 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 533 77.799 19864.175 Close 432 95.314 37266.951 Rename 26 65.409 140.962 Unlink 73 18.963 65.478 Qpathinfo 493 13.171 85.367 Qfileinfo 126 1.709 9.460 Qfsinfo 94 2.155 26.571 Sfileinfo 50 47.118 95.082 Find 193 8.926 65.777 WriteX 433 10.696 58.809 ReadX 953 0.738 85.867 LockX 2 7.787 8.183 UnlockX 2 12.437 16.493 Flush 43 44.785 96.317 Throughput 0.259018 MB/sec 1 clients 1 procs max_latency=37266.973 ms stopping dbench on /mnt/lustre at Wed Sep 16 04:45:08 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre Stopping /mnt/lustre-mds1 (opts:) on oleg310-server removed 'client.txt' /mnt/lustre dbench successfully finished 04:45:11 (1789548311) shut down facet: mds1 facet_host: oleg310-server facet_failover_host: oleg310-server Failover mds1 to oleg310-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg310-server: oleg310-server.virtnet: executing set_default_debug -1 all pdsh@oleg310-client: oleg310-server: ssh exited with exit code 1 Started lustre-MDT0000 04:45:42 (1789548342) targets are mounted 04:45:42 (1789548342) facet_failover done 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 oleg310-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 '/usr/share/dbench/client.txt' -> 'client.txt' running 'dbench 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100' on /mnt/lustre at Wed Sep 16 04:45:48 EDT 2026 waiting for dbench pid 68496 dbench version 4.00 - Copyright Andrew Tridgell 1999-2004 Running for 100 seconds with load 'client.txt' and minimum warmup 20 secs 1 of 1 processes prepared for launch 0 sec releasing clients mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 25 0.72 MB/sec warmup 1 sec latency 18.084 ms 1 108 2.55 MB/sec warmup 2 sec latency 79.513 ms 1 155 2.18 MB/sec warmup 3 sec latency 115.391 ms 1 189 1.89 MB/sec warmup 4 sec latency 331.943 ms 1 246 1.88 MB/sec warmup 5 sec latency 72.844 ms 1 297 1.83 MB/sec warmup 6 sec latency 116.740 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2904 1268400 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2628 1268676 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 13528 3589260 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 39520 3563096 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 53048 7152356 1% /mnt/lustre 1 345 1.76 MB/sec warmup 7 sec latency 102.989 ms 1 401 1.77 MB/sec warmup 8 sec latency 95.049 ms 1 453 1.76 MB/sec warmup 9 sec latency 97.202 ms 1 507 1.75 MB/sec warmup 10 sec latency 104.476 ms 1 616 1.90 MB/sec warmup 11 sec latency 85.313 ms 1 676 1.76 MB/sec warmup 12 sec latency 95.375 ms 1 731 1.64 MB/sec warmup 13 sec latency 77.319 ms 1 780 1.52 MB/sec warmup 14 sec latency 99.666 ms test_26 fail mds2 4 times 1 845 1.44 MB/sec warmup 15 sec latency 102.156 ms Failing mds2 on oleg310-server 1 884 1.35 MB/sec warmup 16 sec latency 92.247 ms Stopping /mnt/lustre-mds2 (opts:) on oleg310-server 1 896 1.27 MB/sec warmup 17 sec latency 748.815 ms 1 933 1.21 MB/sec warmup 18 sec latency 102.101 ms 1 985 1.15 MB/sec warmup 19 sec latency 75.158 ms 1 995 0.00 MB/sec execute 1 sec latency 1761.888 ms 1 995 0.00 MB/sec execute 2 sec latency 2763.206 ms 1 995 0.00 MB/sec execute 3 sec latency 3763.393 ms 1 995 0.00 MB/sec execute 4 sec latency 4763.800 ms 04:46:12 (1789548372) shut down facet: mds2 facet_host: oleg310-server facet_failover_host: oleg310-server 1 995 0.00 MB/sec execute 5 sec latency 5764.064 ms 1 995 0.00 MB/sec execute 6 sec latency 6764.348 ms 1 995 0.00 MB/sec execute 7 sec latency 7764.572 ms 1 995 0.00 MB/sec execute 8 sec latency 8764.817 ms 1 995 0.00 MB/sec execute 9 sec latency 9765.077 ms 1 995 0.00 MB/sec execute 10 sec latency 10765.199 ms 1 995 0.00 MB/sec execute 11 sec latency 11765.425 ms 1 995 0.00 MB/sec execute 12 sec latency 12765.754 ms 1 995 0.00 MB/sec execute 13 sec latency 13765.949 ms 1 995 0.00 MB/sec execute 14 sec latency 14766.132 ms Failover mds2 to oleg310-server mount facets: mds2 1 995 0.00 MB/sec execute 15 sec latency 15766.375 ms 1 995 0.00 MB/sec execute 16 sec latency 16766.562 ms 1 995 0.00 MB/sec execute 17 sec latency 17779.293 ms 1 995 0.00 MB/sec execute 18 sec latency 18779.934 ms 1 995 0.00 MB/sec execute 19 sec latency 19780.109 ms 1 995 0.00 MB/sec execute 20 sec latency 20781.607 ms 1 995 0.00 MB/sec execute 21 sec latency 21781.896 ms 1 995 0.00 MB/sec execute 22 sec latency 22782.511 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 995 0.00 MB/sec execute 23 sec latency 23783.339 ms 1 995 0.00 MB/sec execute 24 sec latency 24784.160 ms 1 995 0.00 MB/sec execute 25 sec latency 25784.339 ms 1 995 0.00 MB/sec execute 26 sec latency 26784.521 ms 1 995 0.00 MB/sec execute 27 sec latency 27787.201 ms oleg310-server: oleg310-server.virtnet: executing set_default_debug -1 all 1 995 0.00 MB/sec execute 28 sec latency 28787.762 ms pdsh@oleg310-client: oleg310-server: ssh exited with exit code 1 1 995 0.00 MB/sec execute 29 sec latency 29788.107 ms Started lustre-MDT0001 04:46:37 (1789548397) targets are mounted 04:46:37 (1789548397) facet_failover done 1 995 0.00 MB/sec execute 30 sec latency 30789.301 ms 1 1002 0.00 MB/sec execute 31 sec latency 31546.030 ms 1 1062 0.03 MB/sec execute 32 sec latency 179.632 ms 1 1126 0.03 MB/sec execute 33 sec latency 104.151 ms 1 1169 0.03 MB/sec execute 34 sec latency 102.606 ms 1 1215 0.03 MB/sec execute 35 sec latency 77.766 ms oleg310-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 1 1251 0.03 MB/sec execute 36 sec latency 105.941 ms 1 1318 0.06 MB/sec execute 37 sec latency 114.715 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 1410 0.11 MB/sec execute 38 sec latency 141.913 ms 1 1448 0.11 MB/sec execute 39 sec latency 106.687 ms 1 1487 0.10 MB/sec execute 40 sec latency 298.224 ms 1 1524 0.10 MB/sec execute 41 sec latency 90.451 ms 1 1599 0.10 MB/sec execute 42 sec latency 119.238 ms 1 1651 0.10 MB/sec execute 43 sec latency 88.220 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 1696 0.10 MB/sec execute 44 sec latency 101.148 ms 1 1775 0.10 MB/sec execute 45 sec latency 65.441 ms 1 1843 0.10 MB/sec execute 46 sec latency 76.210 ms 1 1884 0.09 MB/sec execute 47 sec latency 101.825 ms 1 1974 0.09 MB/sec execute 48 sec latency 110.495 ms 1 2020 0.09 MB/sec execute 49 sec latency 69.842 ms 1 2088 0.09 MB/sec execute 50 sec latency 95.240 ms 1 2148 0.09 MB/sec execute 51 sec latency 92.420 ms 1 2198 0.09 MB/sec execute 52 sec latency 73.056 ms 1 2294 0.11 MB/sec execute 53 sec latency 91.413 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Wed Sep 16 04:47:02 EDT 2026 with return code 0 1 2359 0.11 MB/sec execute 54 sec latency 63.484 ms 68496 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 68496 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished