== replay-dual test 26: dbench and tar with mds failover ========================================================== 11:32:49 (1787844769) Starting client oleg632-client.virtnet: -o user_xattr,flock 192.168.206.132@tcp:/lustre /mnt/lustre Started clients oleg632-client.virtnet: 192.168.206.132@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 45259 Started dbench loop with 45260 looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt '/usr/share/dbench/client.txt' -> 'client.txt' UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2048 2206464 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 14336 3730432 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3751936 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 16384 7482368 1% /mnt/lustre running 'dbench 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100' on /mnt/lustre at Thu Aug 27 11:32:54 EDT 2026 waiting for dbench pid 45307 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 32 1.04 MB/sec warmup 1 sec latency 147.546 ms 1 111 2.61 MB/sec warmup 2 sec latency 121.738 ms 1 152 2.13 MB/sec warmup 3 sec latency 134.315 ms 1 197 1.96 MB/sec warmup 4 sec latency 112.785 ms test_26 fail mds1 1 times 1 255 1.93 MB/sec warmup 5 sec latency 82.296 ms 1 297 1.82 MB/sec warmup 6 sec latency 88.043 ms Failing mds1 on oleg632-server Stopping /mnt/lustre-mds1 (opts:) on oleg632-server 1 341 1.75 MB/sec warmup 7 sec latency 192.580 ms 1 372 1.66 MB/sec warmup 8 sec latency 190.884 ms 1 372 1.48 MB/sec warmup 9 sec latency 1191.361 ms 11:33:04 (1787844784) shut down facet: mds1 facet_host: oleg632-server facet_failover_host: oleg632-server 1 372 1.33 MB/sec warmup 10 sec latency 2191.731 ms 1 372 1.21 MB/sec warmup 11 sec latency 3192.217 ms 1 372 1.11 MB/sec warmup 12 sec latency 4192.399 ms 1 372 1.02 MB/sec warmup 13 sec latency 5192.621 ms 1 372 0.95 MB/sec warmup 14 sec latency 6192.869 ms 1 372 0.89 MB/sec warmup 15 sec latency 7193.042 ms 1 372 0.83 MB/sec warmup 16 sec latency 8193.308 ms 1 372 0.78 MB/sec warmup 17 sec latency 9193.637 ms 1 372 0.74 MB/sec warmup 18 sec latency 10193.827 ms 1 372 0.70 MB/sec warmup 19 sec latency 11194.008 ms Failover mds1 to oleg632-server mount facets: mds1 1 372 0.00 MB/sec execute 1 sec latency 13194.271 ms 1 372 0.00 MB/sec execute 2 sec latency 14196.737 ms 1 372 0.00 MB/sec execute 3 sec latency 15196.998 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 372 0.00 MB/sec execute 4 sec latency 16198.720 ms 1 372 0.00 MB/sec execute 5 sec latency 17198.924 ms 1 372 0.00 MB/sec execute 6 sec latency 18199.945 ms 1 372 0.00 MB/sec execute 7 sec latency 19200.124 ms 1 372 0.00 MB/sec execute 8 sec latency 20200.374 ms oleg632-server: oleg632-server.virtnet: executing set_default_debug -1 all 1 372 0.00 MB/sec execute 9 sec latency 21200.621 ms pdsh@oleg632-client: oleg632-server: ssh exited with exit code 1 1 372 0.00 MB/sec execute 10 sec latency 22200.841 ms Started lustre-MDT0000 11:33:24 (1787844804) targets are mounted 11:33:24 (1787844804) facet_failover done 1 372 0.00 MB/sec execute 11 sec latency 23201.635 ms 1 373 0.00 MB/sec execute 12 sec latency 24010.646 ms 1 421 0.12 MB/sec execute 13 sec latency 227.327 ms 1 465 0.21 MB/sec execute 14 sec latency 136.390 ms 1 511 0.29 MB/sec execute 15 sec latency 105.309 ms oleg632-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 593 0.45 MB/sec execute 16 sec latency 144.617 ms 1 649 0.46 MB/sec execute 17 sec latency 112.004 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 674 0.44 MB/sec execute 18 sec latency 158.150 ms 1 703 0.42 MB/sec execute 19 sec latency 114.867 ms 1 728 0.40 MB/sec execute 20 sec latency 245.449 ms 1 765 0.38 MB/sec execute 21 sec latency 110.162 ms 1 808 0.37 MB/sec execute 22 sec latency 197.728 ms 1 876 0.36 MB/sec execute 23 sec latency 189.946 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2304 2206208 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 36864 3670016 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 14336 3691520 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 51200 7361536 1% /mnt/lustre 1 905 0.35 MB/sec execute 24 sec latency 120.042 ms 1 924 0.34 MB/sec execute 25 sec latency 261.424 ms 1 967 0.33 MB/sec execute 26 sec latency 80.161 ms 1 987 0.32 MB/sec execute 27 sec latency 211.234 ms 1 1060 0.34 MB/sec execute 28 sec latency 104.533 ms 1 1128 0.33 MB/sec execute 29 sec latency 64.150 ms test_26 fail mds1 2 times 1 1177 0.32 MB/sec execute 30 sec latency 95.902 ms 1 1221 0.31 MB/sec execute 31 sec latency 90.550 ms Failing mds1 on oleg632-server 1 1251 0.31 MB/sec execute 32 sec latency 124.900 ms Stopping /mnt/lustre-mds1 (opts:) on oleg632-server 1 1384 0.38 MB/sec execute 33 sec latency 133.377 ms 1 1403 0.37 MB/sec execute 34 sec latency 536.678 ms 1 1403 0.36 MB/sec execute 35 sec latency 1537.435 ms 1 1403 0.35 MB/sec execute 36 sec latency 2539.105 ms 11:33:50 (1787844830) shut down facet: mds1 facet_host: oleg632-server facet_failover_host: oleg632-server 1 1403 0.34 MB/sec execute 37 sec latency 3540.123 ms 1 1403 0.33 MB/sec execute 38 sec latency 4540.550 ms 1 1403 0.33 MB/sec execute 39 sec latency 5540.813 ms 1 1403 0.32 MB/sec execute 40 sec latency 6541.589 ms 1 1403 0.31 MB/sec execute 41 sec latency 7541.805 ms 1 1403 0.30 MB/sec execute 42 sec latency 8541.983 ms 1 1403 0.30 MB/sec execute 43 sec latency 9542.290 ms 1 1403 0.29 MB/sec execute 44 sec latency 10542.464 ms 1 1403 0.28 MB/sec execute 45 sec latency 11542.807 ms 1 1403 0.28 MB/sec execute 46 sec latency 12545.799 ms Failover mds1 to oleg632-server mount facets: mds1 1 1403 0.27 MB/sec execute 47 sec latency 13547.849 ms 1 1403 0.26 MB/sec execute 48 sec latency 14548.074 ms 1 1403 0.26 MB/sec execute 49 sec latency 15548.520 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 1403 0.25 MB/sec execute 50 sec latency 16548.720 ms 1 1403 0.25 MB/sec execute 51 sec latency 17549.046 ms 1 1403 0.24 MB/sec execute 52 sec latency 18554.442 ms 1 1403 0.24 MB/sec execute 53 sec latency 19554.673 ms 1 1403 0.24 MB/sec execute 54 sec latency 20555.300 ms oleg632-server: oleg632-server.virtnet: executing set_default_debug -1 all 1 1403 0.23 MB/sec execute 55 sec latency 21555.696 ms pdsh@oleg632-client: oleg632-server: ssh exited with exit code 1 1 1403 0.23 MB/sec execute 56 sec latency 22559.312 ms Started lustre-MDT0000 11:34:11 (1787844851) targets are mounted 11:34:11 (1787844851) facet_failover done 1 1403 0.22 MB/sec execute 57 sec latency 23564.719 ms 1 1403 0.22 MB/sec execute 58 sec latency 24570.384 ms 1 1403 0.22 MB/sec execute 59 sec latency 25570.525 ms 1 1403 0.21 MB/sec execute 60 sec latency 26579.656 ms 1 1403 0.21 MB/sec execute 61 sec latency 27580.347 ms 1 1403 0.20 MB/sec execute 62 sec latency 28582.322 ms 1 1403 0.20 MB/sec execute 63 sec latency 29582.780 ms 1 1403 0.20 MB/sec execute 64 sec latency 30582.977 ms 1 1403 0.20 MB/sec execute 65 sec latency 31583.571 ms 1 1403 0.19 MB/sec execute 66 sec latency 32584.610 ms 1 1403 0.19 MB/sec execute 67 sec latency 33587.998 ms 1 1403 0.19 MB/sec execute 68 sec latency 34589.240 ms 1 1403 0.18 MB/sec execute 69 sec latency 35589.397 ms 1 1403 0.18 MB/sec execute 70 sec latency 36592.676 ms 1 1403 0.18 MB/sec execute 71 sec latency 37594.350 ms 1 1403 0.18 MB/sec execute 72 sec latency 38594.667 ms 1 1403 0.17 MB/sec execute 73 sec latency 39594.840 ms 1 1403 0.17 MB/sec execute 74 sec latency 40598.036 ms 1 1434 0.17 MB/sec execute 75 sec latency 40660.846 ms 1 1474 0.17 MB/sec execute 76 sec latency 113.127 ms 1 1502 0.17 MB/sec execute 77 sec latency 305.547 ms 1 1562 0.16 MB/sec execute 78 sec latency 86.340 ms 1 1625 0.16 MB/sec execute 79 sec latency 86.618 ms oleg632-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 1656 0.16 MB/sec execute 80 sec latency 257.280 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 1699 0.16 MB/sec execute 81 sec latency 142.424 ms 1 1773 0.16 MB/sec execute 82 sec latency 87.251 ms 1 1834 0.16 MB/sec execute 83 sec latency 101.828 ms 1 1884 0.16 MB/sec execute 84 sec latency 162.337 ms 1 1976 0.15 MB/sec execute 85 sec latency 171.986 ms 1 2057 0.15 MB/sec execute 86 sec latency 69.934 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2688 2205824 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 48128 3707904 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 24576 3737600 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 72704 7445504 1% /mnt/lustre 1 2137 0.15 MB/sec execute 87 sec latency 76.843 ms 1 2174 0.15 MB/sec execute 88 sec latency 115.716 ms 1 2259 0.15 MB/sec execute 89 sec latency 73.217 ms 1 2345 0.16 MB/sec execute 90 sec latency 60.321 ms 1 2377 0.16 MB/sec execute 91 sec latency 197.655 ms 1 2416 0.16 MB/sec execute 92 sec latency 178.330 ms test_26 fail mds1 3 times 1 2446 0.16 MB/sec execute 93 sec latency 307.538 ms 1 2478 0.16 MB/sec execute 94 sec latency 274.101 ms Failing mds1 on oleg632-server Stopping /mnt/lustre-mds1 (opts:) on oleg632-server 1 2559 0.16 MB/sec execute 95 sec latency 155.128 ms 1 2566 0.16 MB/sec execute 96 sec latency 856.675 ms 1 2567 0.16 MB/sec execute 97 sec latency 1202.372 ms 1 2567 0.16 MB/sec execute 98 sec latency 1654.898 ms 11:34:52 (1787844892) shut down facet: mds1 facet_host: oleg632-server facet_failover_host: oleg632-server 1 2567 0.16 MB/sec execute 99 sec latency 2655.089 ms 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec 1 cleanup 103 sec 1 cleanup 104 sec 1 cleanup 105 sec 1 cleanup 106 sec 1 cleanup 107 sec 1 cleanup 108 sec Failover mds1 to oleg632-server mount facets: mds1 1 cleanup 109 sec 1 cleanup 110 sec 1 cleanup 111 sec 1 cleanup 112 sec Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 cleanup 113 sec 1 cleanup 114 sec 1 cleanup 115 sec 1 cleanup 116 sec 1 cleanup 117 sec oleg632-server: oleg632-server.virtnet: executing set_default_debug -1 all 1 cleanup 118 sec pdsh@oleg632-client: oleg632-server: ssh exited with exit code 1 Started lustre-MDT0000 11:35:13 (1787844913) targets are mounted 11:35:13 (1787844913) facet_failover done 1 cleanup 119 sec 1 cleanup 120 sec 1 cleanup 121 sec 0 cleanup 121 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 369 161.399 40660.834 Close 319 86.739 24010.627 Rename 15 90.939 155.108 Unlink 38 29.145 69.541 Qpathinfo 340 14.852 133.320 Qfileinfo 97 1.591 8.691 Qfsinfo 43 4.410 31.566 Sfileinfo 49 504.500 22162.449 Find 116 5.179 61.997 WriteX 349 10.654 88.474 ReadX 427 1.734 66.157 Flush 34 139.299 307.525 Throughput 0.157399 MB/sec 1 clients 1 procs max_latency=40660.846 ms stopping dbench on /mnt/lustre at Thu Aug 27 11:35:15 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt oleg632-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec '/usr/share/dbench/client.txt' -> 'client.txt' running 'dbench 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100' on /mnt/lustre at Thu Aug 27 11:35:21 EDT 2026 waiting for dbench pid 48191 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 1 58 2.36 MB/sec warmup 1 sec latency 115.939 ms 1 121 2.75 MB/sec warmup 2 sec latency 136.800 ms 1 155 2.18 MB/sec warmup 3 sec latency 154.939 ms 1 197 1.96 MB/sec warmup 4 sec latency 160.597 ms 1 239 1.83 MB/sec warmup 5 sec latency 106.574 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 3200 2205312 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 39936 3685376 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 18432 3710976 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 58368 7396352 1% /mnt/lustre 1 271 1.70 MB/sec warmup 6 sec latency 135.143 ms 1 305 1.60 MB/sec warmup 7 sec latency 142.859 ms 1 339 1.53 MB/sec warmup 8 sec latency 148.265 ms 1 377 1.48 MB/sec warmup 9 sec latency 132.244 ms 1 429 1.51 MB/sec warmup 10 sec latency 113.351 ms 1 485 1.54 MB/sec warmup 11 sec latency 84.351 ms test_26 fail mds1 4 times 1 531 1.54 MB/sec warmup 12 sec latency 115.595 ms Failing mds1 on oleg632-server 1 616 1.61 MB/sec warmup 13 sec latency 135.881 ms Stopping /mnt/lustre-mds1 (opts:) on oleg632-server 1 669 1.51 MB/sec warmup 14 sec latency 163.220 ms 1 692 1.41 MB/sec warmup 15 sec latency 472.173 ms 1 692 1.32 MB/sec warmup 16 sec latency 1472.348 ms 1 692 1.25 MB/sec warmup 17 sec latency 2472.584 ms 1 692 1.18 MB/sec warmup 18 sec latency 3473.387 ms 1 692 1.11 MB/sec warmup 19 sec latency 4473.516 ms 1 692 0.00 MB/sec execute 1 sec latency 6473.874 ms 1 692 0.00 MB/sec execute 2 sec latency 7475.476 ms 11:35:44 (1787844944) shut down 1 692 0.00 MB/sec execute 3 sec latency 8475.943 ms facet: mds1 facet_host: oleg632-server facet_failover_host: oleg632-server 1 692 0.00 MB/sec execute 4 sec latency 9476.107 ms 1 692 0.00 MB/sec execute 5 sec latency 10476.293 ms 1 692 0.00 MB/sec execute 6 sec latency 11476.464 ms 1 692 0.00 MB/sec execute 7 sec latency 12477.107 ms 1 692 0.00 MB/sec execute 8 sec latency 13477.282 ms 1 692 0.00 MB/sec execute 9 sec latency 14477.463 ms 1 692 0.00 MB/sec execute 10 sec latency 15478.075 ms 1 692 0.00 MB/sec execute 11 sec latency 16478.250 ms 1 692 0.00 MB/sec execute 12 sec latency 17478.427 ms 1 692 0.00 MB/sec execute 13 sec latency 18479.089 ms Failover mds1 to oleg632-server mount facets: mds1 1 692 0.00 MB/sec execute 14 sec latency 19479.304 ms 1 692 0.00 MB/sec execute 15 sec latency 20479.474 ms 1 692 0.00 MB/sec execute 16 sec latency 21479.768 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 692 0.00 MB/sec execute 17 sec latency 22482.111 ms 1 692 0.00 MB/sec execute 18 sec latency 23482.293 ms 1 692 0.00 MB/sec execute 19 sec latency 24482.506 ms 1 692 0.00 MB/sec execute 20 sec latency 25482.833 ms 1 692 0.00 MB/sec execute 21 sec latency 26483.829 ms 1 692 0.00 MB/sec execute 22 sec latency 27484.161 ms oleg632-server: oleg632-server.virtnet: executing set_default_debug -1 all 1 692 0.00 MB/sec execute 23 sec latency 28485.307 ms pdsh@oleg632-client: oleg632-server: ssh exited with exit code 1 1 692 0.00 MB/sec execute 24 sec latency 29486.196 ms Started lustre-MDT0000 11:36:06 (1787844966) targets are mounted 11:36:06 (1787844966) facet_failover done 1 692 0.00 MB/sec execute 25 sec latency 30488.769 ms 1 692 0.00 MB/sec execute 26 sec latency 31488.908 ms 1 692 0.00 MB/sec execute 27 sec latency 32489.178 ms 1 692 0.00 MB/sec execute 28 sec latency 33489.714 ms 1 710 0.00 MB/sec execute 29 sec latency 33880.218 ms 1 740 0.00 MB/sec execute 30 sec latency 174.232 ms 1 789 0.01 MB/sec execute 31 sec latency 98.514 ms 1 814 0.01 MB/sec execute 32 sec latency 237.130 ms oleg632-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 873 0.01 MB/sec execute 33 sec latency 229.331 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 903 0.01 MB/sec execute 34 sec latency 249.661 ms 1 929 0.02 MB/sec execute 35 sec latency 265.967 ms 1 980 0.02 MB/sec execute 36 sec latency 137.040 ms 1 1002 0.02 MB/sec execute 37 sec latency 235.194 ms 1 1059 0.04 MB/sec execute 38 sec latency 246.250 ms 1 1127 0.05 MB/sec execute 39 sec latency 62.447 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 1176 0.05 MB/sec execute 40 sec latency 85.570 ms 1 1234 0.05 MB/sec execute 41 sec latency 60.857 ms 1 1382 0.11 MB/sec execute 42 sec latency 99.620 ms 1 1442 0.11 MB/sec execute 43 sec latency 73.470 ms 1 1504 0.11 MB/sec execute 44 sec latency 215.430 ms 1 1568 0.11 MB/sec execute 45 sec latency 76.807 ms 1 1609 0.11 MB/sec execute 46 sec latency 74.719 ms 1 1653 0.11 MB/sec execute 47 sec latency 247.831 ms 1 1711 0.11 MB/sec execute 48 sec latency 142.344 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Thu Aug 27 11:36:30 EDT 2026 with return code 0 48191 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 48191 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished