== replay-dual test 26: dbench and tar with mds failover ========================================================== 11:04:33 (1783955073) Starting client oleg235-client.virtnet: -o user_xattr,flock 192.168.202.135@tcp:/lustre /mnt/lustre Started clients oleg235-client.virtnet: 192.168.202.135@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 65647 Started dbench loop with 65648 striped dir -i0 -c2 -H crush2 /mnt/lustre/d26.replay-dual/run_tar striped dir -i0 -c2 -H crush /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 1940 1269364 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1756 1269548 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 17948 3580756 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 19492 7186232 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 Mon Jul 13 11:04:38 EDT 2026 waiting for dbench pid 65718 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 15.476 ms 1 72 1.57 MB/sec warmup 2 sec latency 141.190 ms 1 116 1.74 MB/sec warmup 3 sec latency 186.936 ms 1 155 1.63 MB/sec warmup 4 sec latency 144.708 ms 1 184 1.47 MB/sec warmup 5 sec latency 119.220 ms 1 192 1.26 MB/sec warmup 6 sec latency 514.917 ms 1 223 1.23 MB/sec warmup 7 sec latency 138.518 ms 1 256 1.21 MB/sec warmup 8 sec latency 175.479 ms 1 308 1.24 MB/sec warmup 9 sec latency 92.961 ms test_26 fail mds1 1 times 1 341 1.22 MB/sec warmup 10 sec latency 124.125 ms 1 369 1.19 MB/sec warmup 11 sec latency 196.602 ms Failing mds1 on oleg235-server 1 400 1.17 MB/sec warmup 12 sec latency 172.203 ms Stopping /mnt/lustre-mds1 (opts:) on oleg235-server 1 440 1.18 MB/sec warmup 13 sec latency 128.947 ms 1 468 1.17 MB/sec warmup 14 sec latency 331.332 ms 1 468 1.09 MB/sec warmup 15 sec latency 1331.735 ms 1 468 1.02 MB/sec warmup 16 sec latency 2332.125 ms 11:04:54 (1783955094) shut down facet: mds1 facet_host: oleg235-server facet_failover_host: oleg235-server 1 468 0.96 MB/sec warmup 17 sec latency 3332.314 ms 1 468 0.91 MB/sec warmup 18 sec latency 4332.518 ms 1 468 0.86 MB/sec warmup 19 sec latency 5333.116 ms 1 468 0.00 MB/sec execute 1 sec latency 7334.916 ms 1 468 0.00 MB/sec execute 2 sec latency 8336.544 ms 1 468 0.00 MB/sec execute 3 sec latency 9337.082 ms 1 468 0.00 MB/sec execute 4 sec latency 10337.330 ms 1 468 0.00 MB/sec execute 5 sec latency 11337.905 ms 1 468 0.00 MB/sec execute 6 sec latency 12347.150 ms Failover mds1 to oleg235-server mount facets: mds1 1 468 0.00 MB/sec execute 7 sec latency 13347.432 ms 1 468 0.00 MB/sec execute 8 sec latency 14347.641 ms 1 468 0.00 MB/sec execute 9 sec latency 15352.674 ms 1 468 0.00 MB/sec execute 10 sec latency 16354.004 ms 1 468 0.00 MB/sec execute 11 sec latency 17354.155 ms 1 468 0.00 MB/sec execute 12 sec latency 18354.348 ms 1 468 0.00 MB/sec execute 13 sec latency 19360.931 ms 1 468 0.00 MB/sec execute 14 sec latency 20361.193 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 468 0.00 MB/sec execute 15 sec latency 21361.543 ms 1 468 0.00 MB/sec execute 16 sec latency 22364.989 ms 1 468 0.00 MB/sec execute 17 sec latency 23366.093 ms 1 468 0.00 MB/sec execute 18 sec latency 24366.365 ms 1 468 0.00 MB/sec execute 19 sec latency 25366.626 ms 1 468 0.00 MB/sec execute 20 sec latency 26366.857 ms 1 468 0.00 MB/sec execute 21 sec latency 27367.064 ms 1 468 0.00 MB/sec execute 22 sec latency 28367.397 ms 1 468 0.00 MB/sec execute 23 sec latency 29367.610 ms 1 468 0.00 MB/sec execute 24 sec latency 30367.886 ms 1 468 0.00 MB/sec execute 25 sec latency 31368.068 ms 1 468 0.00 MB/sec execute 26 sec latency 32368.670 ms 1 468 0.00 MB/sec execute 27 sec latency 33369.599 ms 1 468 0.00 MB/sec execute 28 sec latency 34370.975 ms 1 468 0.00 MB/sec execute 29 sec latency 35371.951 ms 1 468 0.00 MB/sec execute 30 sec latency 36372.239 ms oleg235-server: oleg235-server.virtnet: executing set_default_debug -1 all 1 468 0.00 MB/sec execute 31 sec latency 37372.379 ms 1 468 0.00 MB/sec execute 32 sec latency 38372.634 ms pdsh@oleg235-client: oleg235-server: ssh exited with exit code 1 1 468 0.00 MB/sec execute 33 sec latency 39374.781 ms Started lustre-MDT0000 11:05:32 (1783955132) targets are mounted 11:05:32 (1783955132) facet_failover done 1 485 0.02 MB/sec execute 34 sec latency 39993.311 ms 1 522 0.05 MB/sec execute 35 sec latency 131.508 ms 1 552 0.07 MB/sec execute 36 sec latency 422.388 ms 1 608 0.12 MB/sec execute 37 sec latency 678.977 ms 1 654 0.12 MB/sec execute 38 sec latency 128.594 ms 1 692 0.12 MB/sec execute 39 sec latency 141.068 ms oleg235-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 718 0.12 MB/sec execute 40 sec latency 133.850 ms 1 749 0.12 MB/sec execute 41 sec latency 150.368 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 779 0.12 MB/sec execute 42 sec latency 149.054 ms 1 810 0.12 MB/sec execute 43 sec latency 116.830 ms 1 851 0.12 MB/sec execute 44 sec latency 226.892 ms 1 890 0.12 MB/sec execute 45 sec latency 149.644 ms 1 919 0.12 MB/sec execute 46 sec latency 110.639 ms 1 959 0.11 MB/sec execute 47 sec latency 134.182 ms 1 990 0.11 MB/sec execute 48 sec latency 102.022 ms 1 1057 0.13 MB/sec execute 49 sec latency 92.900 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2100 1269204 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1920 1269384 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 35332 3571092 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 23420 3578484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 58752 7149576 1% /mnt/lustre 1 1089 0.13 MB/sec execute 50 sec latency 131.986 ms 1 1132 0.13 MB/sec execute 51 sec latency 103.752 ms 1 1167 0.13 MB/sec execute 52 sec latency 149.013 ms 1 1172 0.12 MB/sec execute 53 sec latency 958.319 ms 1 1193 0.12 MB/sec execute 54 sec latency 1322.128 ms 1 1233 0.12 MB/sec execute 55 sec latency 87.834 ms 1 1268 0.12 MB/sec execute 56 sec latency 85.024 ms 1 1385 0.17 MB/sec execute 57 sec latency 219.169 ms 1 1418 0.17 MB/sec execute 58 sec latency 134.054 ms 1 1467 0.16 MB/sec execute 59 sec latency 134.307 ms test_26 fail mds2 2 times 1 1514 0.16 MB/sec execute 60 sec latency 75.650 ms 1 1568 0.16 MB/sec execute 61 sec latency 61.859 ms Failing mds2 on oleg235-server 1 1609 0.16 MB/sec execute 62 sec latency 71.491 ms Stopping /mnt/lustre-mds2 (opts:) on oleg235-server 1 1646 0.15 MB/sec execute 63 sec latency 142.165 ms 1 1682 0.15 MB/sec execute 64 sec latency 100.955 ms 1 1721 0.15 MB/sec execute 65 sec latency 104.798 ms 1 1781 0.15 MB/sec execute 66 sec latency 133.857 ms 11:06:05 (1783955165) shut down facet: mds2 facet_host: oleg235-server facet_failover_host: oleg235-server 1 1828 0.15 MB/sec execute 67 sec latency 153.347 ms 1 1884 0.15 MB/sec execute 68 sec latency 82.556 ms 1 1954 0.15 MB/sec execute 69 sec latency 64.349 ms 1 2006 0.14 MB/sec execute 70 sec latency 106.804 ms 1 2088 0.14 MB/sec execute 71 sec latency 126.939 ms 1 2160 0.14 MB/sec execute 72 sec latency 63.906 ms 1 2236 0.14 MB/sec execute 73 sec latency 89.002 ms 1 2259 0.14 MB/sec execute 74 sec latency 812.917 ms 1 2259 0.14 MB/sec execute 75 sec latency 1815.437 ms 1 2259 0.14 MB/sec execute 76 sec latency 2816.508 ms 1 2259 0.13 MB/sec execute 77 sec latency 3816.781 ms Failover mds2 to oleg235-server mount facets: mds2 1 2259 0.13 MB/sec execute 78 sec latency 4816.988 ms 1 2259 0.13 MB/sec execute 79 sec latency 5827.811 ms 1 2259 0.13 MB/sec execute 80 sec latency 6828.179 ms 1 2259 0.13 MB/sec execute 81 sec latency 7831.209 ms 1 2259 0.13 MB/sec execute 82 sec latency 8831.701 ms 1 2259 0.12 MB/sec execute 83 sec latency 9831.910 ms 1 2259 0.12 MB/sec execute 84 sec latency 10832.109 ms 1 2259 0.12 MB/sec execute 85 sec latency 11832.360 ms 1 2259 0.12 MB/sec execute 86 sec latency 12832.727 ms 1 2259 0.12 MB/sec execute 87 sec latency 13832.957 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 2259 0.12 MB/sec execute 88 sec latency 14834.254 ms 1 2259 0.12 MB/sec execute 89 sec latency 15834.919 ms 1 2259 0.11 MB/sec execute 90 sec latency 16835.600 ms 1 2259 0.11 MB/sec execute 91 sec latency 17835.833 ms 1 2259 0.11 MB/sec execute 92 sec latency 18836.059 ms 1 2259 0.11 MB/sec execute 93 sec latency 19837.126 ms 1 2259 0.11 MB/sec execute 94 sec latency 20837.645 ms oleg235-server: oleg235-server.virtnet: executing set_default_debug -1 all 1 2259 0.11 MB/sec execute 95 sec latency 21838.753 ms 1 2259 0.11 MB/sec execute 96 sec latency 22842.113 ms pdsh@oleg235-client: oleg235-server: ssh exited with exit code 1 1 2259 0.11 MB/sec execute 97 sec latency 23842.314 ms 1 2326 0.12 MB/sec execute 98 sec latency 23965.954 ms Started lustre-MDT0001 11:06:37 (1783955197) targets are mounted 11:06:37 (1783955197) facet_failover done 1 2366 0.12 MB/sec execute 99 sec latency 109.668 ms 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec 1 cleanup 103 sec 1 cleanup 104 sec 0 cleanup 105 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 338 126.242 23965.938 Close 293 148.706 39993.286 Rename 13 85.960 127.110 Unlink 33 31.826 86.525 Qpathinfo 316 16.929 112.562 Qfileinfo 77 2.089 8.395 Qfsinfo 39 4.239 26.843 Sfileinfo 41 66.140 149.627 Find 106 12.706 47.691 WriteX 264 13.748 87.417 ReadX 381 3.184 134.603 Flush 32 49.227 116.808 Throughput 0.115741 MB/sec 1 clients 1 procs max_latency=39993.311 ms stopping dbench on /mnt/lustre at Mon Jul 13 11:06:44 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished oleg235-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 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 '/usr/share/dbench/client.txt' -> 'client.txt' running 'dbench 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100' on /mnt/lustre at Mon Jul 13 11:06:54 EDT 2026 waiting for dbench pid 67856 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 8 0.00 MB/sec warmup 1 sec latency 251.679 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2352 1268952 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2132 1269172 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 34880 3569212 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 12332 3594116 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 47212 7163328 1% /mnt/lustre 1 51 1.04 MB/sec warmup 2 sec latency 161.874 ms 1 97 1.45 MB/sec warmup 3 sec latency 190.078 ms 1 116 1.30 MB/sec warmup 4 sec latency 329.354 ms 1 139 1.20 MB/sec warmup 5 sec latency 266.918 ms 1 165 1.13 MB/sec warmup 6 sec latency 231.222 ms 1 184 1.05 MB/sec warmup 7 sec latency 247.642 ms 1 196 0.98 MB/sec warmup 8 sec latency 637.641 ms 1 196 0.87 MB/sec warmup 9 sec latency 1256.005 ms 1 207 0.81 MB/sec warmup 10 sec latency 1786.844 ms 1 247 0.85 MB/sec warmup 11 sec latency 120.193 ms 1 289 0.89 MB/sec warmup 12 sec latency 119.918 ms test_26 fail mds1 3 times 1 315 0.88 MB/sec warmup 13 sec latency 193.611 ms 1 349 0.89 MB/sec warmup 14 sec latency 216.852 ms Failing mds1 on oleg235-server 1 389 0.92 MB/sec warmup 15 sec latency 121.787 ms Stopping /mnt/lustre-mds1 (opts:) on oleg235-server 1 445 0.98 MB/sec warmup 16 sec latency 185.359 ms 1 460 0.95 MB/sec warmup 17 sec latency 668.919 ms 11:07:12 (1783955232) shut down 1 460 0.90 MB/sec warmup 18 sec latency 1669.052 ms facet: mds1 facet_host: oleg235-server facet_failover_host: oleg235-server 1 460 0.85 MB/sec warmup 19 sec latency 2669.271 ms 1 460 0.00 MB/sec execute 1 sec latency 4670.634 ms 1 460 0.00 MB/sec execute 2 sec latency 5670.899 ms 1 460 0.00 MB/sec execute 3 sec latency 6671.100 ms 1 460 0.00 MB/sec execute 4 sec latency 7671.645 ms 1 460 0.00 MB/sec execute 5 sec latency 8671.933 ms 1 460 0.00 MB/sec execute 6 sec latency 9672.253 ms 1 460 0.00 MB/sec execute 7 sec latency 10672.480 ms 1 460 0.00 MB/sec execute 8 sec latency 11672.707 ms Failover mds1 to oleg235-server mount facets: mds1 1 460 0.00 MB/sec execute 9 sec latency 12680.771 ms 1 460 0.00 MB/sec execute 10 sec latency 13685.593 ms 1 460 0.00 MB/sec execute 11 sec latency 14687.744 ms 1 460 0.00 MB/sec execute 12 sec latency 15689.971 ms 1 460 0.00 MB/sec execute 13 sec latency 16690.163 ms 1 460 0.00 MB/sec execute 14 sec latency 17692.275 ms 1 460 0.00 MB/sec execute 15 sec latency 18692.644 ms 1 460 0.00 MB/sec execute 16 sec latency 19693.825 ms 1 460 0.00 MB/sec execute 17 sec latency 20694.045 ms 1 460 0.00 MB/sec execute 18 sec latency 21694.311 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 460 0.00 MB/sec execute 19 sec latency 22695.002 ms 1 460 0.00 MB/sec execute 20 sec latency 23695.202 ms 1 460 0.00 MB/sec execute 21 sec latency 24695.468 ms 1 460 0.00 MB/sec execute 22 sec latency 25695.721 ms 1 460 0.00 MB/sec execute 23 sec latency 26696.341 ms 1 460 0.00 MB/sec execute 24 sec latency 27700.853 ms 1 460 0.00 MB/sec execute 25 sec latency 28701.100 ms 1 460 0.00 MB/sec execute 26 sec latency 29701.308 ms 1 460 0.00 MB/sec execute 27 sec latency 30701.570 ms 1 460 0.00 MB/sec execute 28 sec latency 31701.763 ms 1 460 0.00 MB/sec execute 29 sec latency 32702.111 ms 1 460 0.00 MB/sec execute 30 sec latency 33702.438 ms 1 460 0.00 MB/sec execute 31 sec latency 34702.653 ms oleg235-server: oleg235-server.virtnet: executing set_default_debug -1 all 1 460 0.00 MB/sec execute 32 sec latency 35702.783 ms pdsh@oleg235-client: oleg235-server: ssh exited with exit code 1 1 477 0.02 MB/sec execute 33 sec latency 35858.781 ms Started lustre-MDT0000 11:07:48 (1783955268) targets are mounted 11:07:48 (1783955268) facet_failover done 1 504 0.04 MB/sec execute 34 sec latency 174.024 ms 1 582 0.10 MB/sec execute 35 sec latency 82.129 ms 1 642 0.14 MB/sec execute 36 sec latency 132.713 ms 1 674 0.14 MB/sec execute 37 sec latency 131.855 ms 1 699 0.13 MB/sec execute 38 sec latency 151.695 ms 1 731 0.13 MB/sec execute 39 sec latency 154.362 ms 1 769 0.13 MB/sec execute 40 sec latency 116.322 ms 1 799 0.13 MB/sec execute 41 sec latency 121.060 ms oleg235-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 845 0.13 MB/sec execute 42 sec latency 136.130 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 878 0.13 MB/sec execute 43 sec latency 155.403 ms 1 884 0.12 MB/sec execute 44 sec latency 849.839 ms 1 885 0.12 MB/sec execute 45 sec latency 1635.206 ms 1 916 0.12 MB/sec execute 46 sec latency 252.571 ms 1 964 0.12 MB/sec execute 47 sec latency 89.076 ms 1 1008 0.13 MB/sec execute 48 sec latency 115.709 ms 1 1079 0.14 MB/sec execute 49 sec latency 105.661 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 1132 0.14 MB/sec execute 50 sec latency 95.440 ms 1 1181 0.13 MB/sec execute 51 sec latency 91.792 ms 1 1229 0.13 MB/sec execute 52 sec latency 80.985 ms 1 1268 0.13 MB/sec execute 53 sec latency 129.608 ms 1 1405 0.18 MB/sec execute 54 sec latency 103.201 ms 1 1447 0.18 MB/sec execute 55 sec latency 116.445 ms 1 1474 0.18 MB/sec execute 56 sec latency 448.415 ms 1 1509 0.17 MB/sec execute 57 sec latency 98.639 ms 1 1558 0.17 MB/sec execute 58 sec latency 140.981 ms 1 1603 0.17 MB/sec execute 59 sec latency 74.403 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Mon Jul 13 11:08:14 EDT 2026 with return code 0 1 1651 0.17 MB/sec execute 60 sec latency 126.633 ms 67856 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 67856 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished