== replay-dual test 26: dbench and tar with mds failover ========================================================== 03:43:13 (1787384593) Starting client oleg450-client.virtnet: -o user_xattr,flock 192.168.204.150@tcp:/lustre /mnt/lustre Started clients oleg450-client.virtnet: 192.168.204.150@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 65661 Started dbench loop with 65662 striped dir -i0 -c2 -H crush /mnt/lustre2/d26.replay-dual/run_dbench striped dir -i0 -c2 -H crush /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 1944 1269360 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 3580768 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 19492 7186224 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 Aug 22 03:43:18 EDT 2026 waiting for dbench pid 65734 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 11 0.00 MB/sec warmup 1 sec latency 1.563 ms 1 67 1.47 MB/sec warmup 2 sec latency 124.356 ms 1 121 1.83 MB/sec warmup 3 sec latency 135.077 ms 1 147 1.57 MB/sec warmup 4 sec latency 175.203 ms 1 160 1.31 MB/sec warmup 5 sec latency 272.465 ms 1 173 1.18 MB/sec warmup 6 sec latency 708.577 ms 1 184 1.05 MB/sec warmup 7 sec latency 846.388 ms 1 200 0.98 MB/sec warmup 8 sec latency 499.696 ms 1 238 1.01 MB/sec warmup 9 sec latency 105.214 ms test_26 fail mds1 1 times 1 267 1.00 MB/sec warmup 10 sec latency 156.986 ms 1 290 0.97 MB/sec warmup 11 sec latency 167.964 ms 1 309 0.94 MB/sec warmup 12 sec latency 296.753 ms Failing mds1 on oleg450-server 1 337 0.93 MB/sec warmup 13 sec latency 170.709 ms Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 1 357 0.91 MB/sec warmup 14 sec latency 189.165 ms 1 385 0.90 MB/sec warmup 15 sec latency 189.310 ms 1 396 0.88 MB/sec warmup 16 sec latency 605.250 ms 1 396 0.82 MB/sec warmup 17 sec latency 1605.425 ms 03:43:37 (1787384617) shut down 1 396 0.78 MB/sec warmup 18 sec latency 2605.677 ms facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server 1 396 0.74 MB/sec warmup 19 sec latency 3606.281 ms 1 396 0.00 MB/sec execute 1 sec latency 5606.722 ms 1 396 0.00 MB/sec execute 2 sec latency 6607.129 ms 1 396 0.00 MB/sec execute 3 sec latency 7613.003 ms 1 396 0.00 MB/sec execute 4 sec latency 8616.148 ms 1 396 0.00 MB/sec execute 5 sec latency 9617.404 ms 1 396 0.00 MB/sec execute 6 sec latency 10617.895 ms 1 396 0.00 MB/sec execute 7 sec latency 11618.203 ms 1 396 0.00 MB/sec execute 8 sec latency 12618.415 ms Failover mds1 to oleg450-server mount facets: mds1 1 396 0.00 MB/sec execute 9 sec latency 13620.945 ms 1 396 0.00 MB/sec execute 10 sec latency 14621.274 ms 1 396 0.00 MB/sec execute 11 sec latency 15629.475 ms 1 396 0.00 MB/sec execute 12 sec latency 16629.734 ms 1 396 0.00 MB/sec execute 13 sec latency 17630.218 ms 1 396 0.00 MB/sec execute 14 sec latency 18631.105 ms 1 396 0.00 MB/sec execute 15 sec latency 19631.356 ms 1 396 0.00 MB/sec execute 16 sec latency 20631.509 ms 1 396 0.00 MB/sec execute 17 sec latency 21632.582 ms 1 396 0.00 MB/sec execute 18 sec latency 22632.876 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 396 0.00 MB/sec execute 19 sec latency 23633.130 ms 1 396 0.00 MB/sec execute 20 sec latency 24633.415 ms 1 396 0.00 MB/sec execute 21 sec latency 25634.692 ms 1 396 0.00 MB/sec execute 22 sec latency 26635.170 ms 1 396 0.00 MB/sec execute 23 sec latency 27635.625 ms 1 396 0.00 MB/sec execute 24 sec latency 28636.889 ms 1 396 0.00 MB/sec execute 25 sec latency 29637.288 ms 1 396 0.00 MB/sec execute 26 sec latency 30637.551 ms oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all 1 396 0.00 MB/sec execute 27 sec latency 31637.706 ms pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 1 396 0.00 MB/sec execute 28 sec latency 32639.280 ms Started lustre-MDT0000 03:44:07 (1787384647) targets are mounted 03:44:07 (1787384647) facet_failover done 1 396 0.00 MB/sec execute 29 sec latency 33640.082 ms 1 397 0.00 MB/sec execute 30 sec latency 34498.702 ms 1 430 0.03 MB/sec execute 31 sec latency 223.176 ms 1 469 0.07 MB/sec execute 32 sec latency 135.717 ms 1 502 0.10 MB/sec execute 33 sec latency 161.188 ms 1 522 0.12 MB/sec execute 34 sec latency 279.736 ms 1 552 0.14 MB/sec execute 35 sec latency 335.239 ms 1 597 0.19 MB/sec execute 36 sec latency 633.554 ms oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 638 0.19 MB/sec execute 37 sec latency 172.389 ms 1 656 0.18 MB/sec execute 38 sec latency 211.943 ms 1 682 0.18 MB/sec execute 39 sec latency 174.112 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 699 0.18 MB/sec execute 40 sec latency 213.007 ms 1 721 0.18 MB/sec execute 41 sec latency 211.481 ms 1 740 0.17 MB/sec execute 42 sec latency 173.850 ms 1 769 0.17 MB/sec execute 43 sec latency 184.000 ms 1 791 0.17 MB/sec execute 44 sec latency 198.374 ms 1 815 0.16 MB/sec execute 45 sec latency 135.770 ms 1 858 0.16 MB/sec execute 46 sec latency 137.238 ms 1 885 0.16 MB/sec execute 47 sec latency 163.269 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2052 1269252 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1860 1269444 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 12288 3593600 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 46372 3555680 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 58660 7149280 1% /mnt/lustre 1 910 0.16 MB/sec execute 48 sec latency 136.253 ms 1 935 0.16 MB/sec execute 49 sec latency 141.088 ms 1 959 0.15 MB/sec execute 50 sec latency 181.099 ms 1 980 0.15 MB/sec execute 51 sec latency 183.024 ms 1 1020 0.16 MB/sec execute 52 sec latency 144.142 ms 1 1061 0.17 MB/sec execute 53 sec latency 103.564 ms 1 1086 0.16 MB/sec execute 54 sec latency 128.791 ms 1 1132 0.16 MB/sec execute 55 sec latency 77.621 ms 1 1168 0.16 MB/sec execute 56 sec latency 119.213 ms 1 1172 0.16 MB/sec execute 57 sec latency 917.657 ms 1 1182 0.15 MB/sec execute 58 sec latency 1532.393 ms 1 1221 0.15 MB/sec execute 59 sec latency 102.772 ms test_26 fail mds2 2 times 1 1248 0.15 MB/sec execute 60 sec latency 115.990 ms 1 1274 0.15 MB/sec execute 61 sec latency 125.287 ms Failing mds2 on oleg450-server 1 1390 0.19 MB/sec execute 62 sec latency 133.783 ms Stopping /mnt/lustre-mds2 (opts:) on oleg450-server 1 1418 0.19 MB/sec execute 63 sec latency 169.995 ms 1 1448 0.19 MB/sec execute 64 sec latency 149.232 ms 1 1497 0.18 MB/sec execute 65 sec latency 185.201 ms 1 1532 0.18 MB/sec execute 66 sec latency 129.110 ms 1 1605 0.18 MB/sec execute 67 sec latency 72.141 ms 1 1653 0.18 MB/sec execute 68 sec latency 108.892 ms 1 1695 0.18 MB/sec execute 69 sec latency 131.705 ms 1 1762 0.17 MB/sec execute 70 sec latency 92.703 ms 1 1814 0.17 MB/sec execute 71 sec latency 101.114 ms 1 1851 0.17 MB/sec execute 72 sec latency 118.636 ms 03:44:52 (1787384692) shut down 1 1901 0.17 MB/sec execute 73 sec latency 120.529 ms facet: mds2 facet_host: oleg450-server facet_failover_host: oleg450-server 1 1974 0.17 MB/sec execute 74 sec latency 60.107 ms 1 2022 0.17 MB/sec execute 75 sec latency 83.376 ms 1 2095 0.17 MB/sec execute 76 sec latency 92.959 ms 1 2154 0.16 MB/sec execute 77 sec latency 110.679 ms 1 2191 0.16 MB/sec execute 78 sec latency 126.178 ms 1 2258 0.16 MB/sec execute 79 sec latency 105.169 ms 1 2259 0.16 MB/sec execute 80 sec latency 979.229 ms 1 2259 0.16 MB/sec execute 81 sec latency 1979.568 ms 1 2259 0.15 MB/sec execute 82 sec latency 2980.090 ms 1 2259 0.15 MB/sec execute 83 sec latency 3980.493 ms Failover mds2 to oleg450-server mount facets: mds2 1 2259 0.15 MB/sec execute 84 sec latency 4981.357 ms 1 2259 0.15 MB/sec execute 85 sec latency 5981.649 ms 1 2259 0.15 MB/sec execute 86 sec latency 6987.282 ms 1 2259 0.15 MB/sec execute 87 sec latency 7987.540 ms 1 2259 0.14 MB/sec execute 88 sec latency 8987.958 ms 1 2259 0.14 MB/sec execute 89 sec latency 9993.679 ms 1 2259 0.14 MB/sec execute 90 sec latency 10993.828 ms 1 2259 0.14 MB/sec execute 91 sec latency 11994.494 ms 1 2259 0.14 MB/sec execute 92 sec latency 12996.926 ms 1 2259 0.14 MB/sec execute 93 sec latency 14001.459 ms 1 2259 0.13 MB/sec execute 94 sec latency 15007.425 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 2259 0.13 MB/sec execute 95 sec latency 16007.701 ms 1 2259 0.13 MB/sec execute 96 sec latency 17007.963 ms 1 2259 0.13 MB/sec execute 97 sec latency 18008.851 ms 1 2259 0.13 MB/sec execute 98 sec latency 19009.412 ms 1 2259 0.13 MB/sec execute 99 sec latency 20009.669 ms 1 cleanup 100 sec 1 cleanup 101 sec oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all 1 cleanup 102 sec pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 1 cleanup 103 sec Started lustre-MDT0001 03:45:23 (1787384723) targets are mounted 03:45:23 (1787384723) facet_failover done 1 cleanup 104 sec 1 cleanup 105 sec 1 cleanup 106 sec 1 cleanup 107 sec 0 cleanup 108 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 333 143.572 25084.533 Close 290 132.833 34498.668 Rename 11 114.366 211.452 Unlink 30 32.505 76.401 Qpathinfo 295 17.039 137.216 Qfileinfo 82 3.145 17.230 Qfsinfo 33 5.677 26.248 Sfileinfo 34 86.462 174.092 Find 92 15.490 96.115 WriteX 286 16.891 89.665 ReadX 348 3.483 138.310 Flush 30 75.611 144.515 Throughput 0.128057 MB/sec 1 clients 1 procs max_latency=34498.702 ms stopping dbench on /mnt/lustre at Sat Aug 22 03:45:27 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid striped dir -i0 -c2 -H fnv_1a_64 /mnt/lustre2/d26.replay-dual/run_dbench mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 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 Sat Aug 22 03:45:37 EDT 2026 waiting for dbench pid 67871 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 119.725 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2348 1268956 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2120 1269184 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 26528 3579328 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 20700 3581944 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 47228 7161272 1% /mnt/lustre 1 69 1.53 MB/sec warmup 2 sec latency 109.362 ms 1 109 1.72 MB/sec warmup 3 sec latency 183.247 ms 1 137 1.50 MB/sec warmup 4 sec latency 203.944 ms 1 157 1.30 MB/sec warmup 5 sec latency 244.179 ms 1 184 1.23 MB/sec warmup 6 sec latency 249.976 ms 1 199 1.12 MB/sec warmup 7 sec latency 519.265 ms 1 234 1.11 MB/sec warmup 8 sec latency 209.822 ms 1 271 1.13 MB/sec warmup 9 sec latency 154.115 ms 1 298 1.09 MB/sec warmup 10 sec latency 224.065 ms 1 331 1.09 MB/sec warmup 11 sec latency 118.836 ms 1 358 1.06 MB/sec warmup 12 sec latency 193.051 ms test_26 fail mds1 3 times 1 388 1.06 MB/sec warmup 13 sec latency 207.270 ms 1 421 1.06 MB/sec warmup 14 sec latency 115.587 ms 1 451 1.05 MB/sec warmup 15 sec latency 156.031 ms Failing mds1 on oleg450-server 1 477 1.04 MB/sec warmup 16 sec latency 136.446 ms Stopping /mnt/lustre-mds1 (opts:) on oleg450-server 1 503 1.03 MB/sec warmup 17 sec latency 198.115 ms 1 542 1.06 MB/sec warmup 18 sec latency 155.622 ms 1 606 1.10 MB/sec warmup 19 sec latency 227.992 ms 03:45:57 (1787384757) shut down facet: mds1 facet_host: oleg450-server facet_failover_host: oleg450-server 1 606 0.00 MB/sec execute 1 sec latency 2229.882 ms 1 606 0.00 MB/sec execute 2 sec latency 3230.701 ms 1 606 0.00 MB/sec execute 3 sec latency 4230.944 ms 1 606 0.00 MB/sec execute 4 sec latency 5231.281 ms 1 606 0.00 MB/sec execute 5 sec latency 6231.549 ms 1 606 0.00 MB/sec execute 6 sec latency 7231.871 ms 1 606 0.00 MB/sec execute 7 sec latency 8233.253 ms 1 606 0.00 MB/sec execute 8 sec latency 9233.522 ms 1 606 0.00 MB/sec execute 9 sec latency 10233.943 ms 1 606 0.00 MB/sec execute 10 sec latency 11234.228 ms 1 606 0.00 MB/sec execute 11 sec latency 12236.183 ms Failover mds1 to oleg450-server mount facets: mds1 1 606 0.00 MB/sec execute 12 sec latency 13236.587 ms 1 606 0.00 MB/sec execute 13 sec latency 14238.214 ms 1 606 0.00 MB/sec execute 14 sec latency 15243.337 ms 1 606 0.00 MB/sec execute 15 sec latency 16243.535 ms 1 606 0.00 MB/sec execute 16 sec latency 17245.021 ms 1 606 0.00 MB/sec execute 17 sec latency 18251.059 ms 1 606 0.00 MB/sec execute 18 sec latency 19251.449 ms 1 606 0.00 MB/sec execute 19 sec latency 20251.886 ms 1 606 0.00 MB/sec execute 20 sec latency 21252.141 ms 1 606 0.00 MB/sec execute 21 sec latency 22253.007 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 606 0.00 MB/sec execute 22 sec latency 23253.213 ms 1 606 0.00 MB/sec execute 23 sec latency 24253.406 ms 1 606 0.00 MB/sec execute 24 sec latency 25253.684 ms 1 606 0.00 MB/sec execute 25 sec latency 26254.056 ms 1 606 0.00 MB/sec execute 26 sec latency 27254.944 ms 1 606 0.00 MB/sec execute 27 sec latency 28258.175 ms 1 606 0.00 MB/sec execute 28 sec latency 29266.937 ms 1 606 0.00 MB/sec execute 29 sec latency 30267.176 ms 1 606 0.00 MB/sec execute 30 sec latency 31267.641 ms 1 606 0.00 MB/sec execute 31 sec latency 32267.893 ms oleg450-server: oleg450-server.virtnet: executing set_default_debug -1 all 1 606 0.00 MB/sec execute 32 sec latency 33271.908 ms pdsh@oleg450-client: oleg450-server: ssh exited with exit code 1 1 606 0.00 MB/sec execute 33 sec latency 34274.738 ms Started lustre-MDT0000 03:46:31 (1787384791) targets are mounted 1 606 0.00 MB/sec execute 34 sec latency 35277.583 ms 03:46:31 (1787384791) facet_failover done 1 642 0.00 MB/sec execute 35 sec latency 35698.902 ms 1 674 0.01 MB/sec execute 36 sec latency 144.721 ms 1 708 0.01 MB/sec execute 37 sec latency 142.131 ms 1 720 0.01 MB/sec execute 38 sec latency 573.281 ms 1 735 0.01 MB/sec execute 39 sec latency 995.612 ms 1 776 0.01 MB/sec execute 40 sec latency 130.568 ms oleg450-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 806 0.01 MB/sec execute 41 sec latency 107.951 ms 1 857 0.01 MB/sec execute 42 sec latency 127.591 ms 1 882 0.02 MB/sec execute 43 sec latency 192.969 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 903 0.02 MB/sec execute 44 sec latency 138.469 ms 1 923 0.02 MB/sec execute 45 sec latency 159.590 ms 1 969 0.02 MB/sec execute 46 sec latency 153.393 ms 1 988 0.02 MB/sec execute 47 sec latency 157.038 ms 1 1050 0.04 MB/sec execute 48 sec latency 120.085 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 1086 0.04 MB/sec execute 49 sec latency 109.091 ms 1 1135 0.04 MB/sec execute 50 sec latency 145.648 ms 1 1177 0.04 MB/sec execute 51 sec latency 148.914 ms 1 1217 0.04 MB/sec execute 52 sec latency 85.618 ms 1 1244 0.04 MB/sec execute 53 sec latency 138.252 ms 1 1276 0.04 MB/sec execute 54 sec latency 149.694 ms 1 1360 0.08 MB/sec execute 55 sec latency 755.246 ms 1 1396 0.09 MB/sec execute 56 sec latency 173.867 ms 1 1425 0.09 MB/sec execute 57 sec latency 165.095 ms 1 1464 0.09 MB/sec execute 58 sec latency 104.119 ms 1 1502 0.09 MB/sec execute 59 sec latency 117.280 ms tar: Error is not recoverable: exiting now 1 1547 0.09 MB/sec execute 60 sec latency 94.596 ms dbench killed by signal 15 stopping dbench on /mnt/lustre at Sat Aug 22 03:46:57 EDT 2026 with return code 0 67871 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 67871 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished