Description of problem: [RFE] rados bench : add cleanup message with time it has taken to delete the objects when cleanup start for written objects # rados -p rbd bench 20 write -b 8192 -t 256 Maintaining 256 concurrent writes of 8192 bytes for up to 20 seconds or 0 objects Object prefix: benchmark_data_dell-per630-8.gsslab.pnq2.red_59618 sec Cur ops started finished avg MB/s cur MB/s last lat avg lat 0 0 0 0 0 0 - 0 1 255 11275 11020 85.9967 86.0938 0.0209201 0.022394 2 255 21299 21044 82.1255 78.3125 0.0160036 0.0240254 3 256 33494 33238 86.5002 95.2656 0.0176813 0.0229041 4 255 44851 44596 87.0498 88.7344 0.0204237 0.0228027 ................................ ................................. 2016-05-03 16:45:28.715926min lat: 0.00156224 max lat: 7.1998 avg lat: 0.0559234 sec Cur ops started finished avg MB/s cur MB/s last lat avg lat 20 254 85867 85613 33.4264 6.195310.00497779 0.0559234 21 254 85867 85613 31.8353 0 - 0.0559234 22 254 85867 85613 30.3887 0 - 0.0559234 Total time run: 22.334877 Total writes made: 85867 Write size: 8192 Bandwidth (MB/sec): 30.035 Stddev Bandwidth: 34.5402 Max bandwidth (MB/sec): 95.2656 Min bandwidth (MB/sec): 0 Average Latency: 0.0664779 Stddev Latency: 0.456263 Max latency: 7.1998 Min latency: 0.00156224 - After benchmark is completed, there is a long pause as it start deleting the written objects (clean up). - Add cleanup message with time it has taken to delete the objects when cleanup start for written objects Version-Release number of selected component (if applicable): Red Hat Ceph Storage 1.3.2
Upstream Patch : https://github.com/ceph/ceph/pull/8913
Upstream Jewel Backport Tracker : http://tracker.ceph.com/issues/16338 Upstream Jewel Backport PR : https://github.com/ceph/ceph/pull/9740
Working as required $sudo rados -p 1332513 bench 10 write -b 10240 Maintaining 16 concurrent writes of 10240 bytes to objects of size 10240 for up to 10 seconds or 0 objects Object prefix: benchmark_data_magna111_26595 sec Cur ops started finished avg MB/s cur MB/s last lat(s) avg lat(s) 0 0 0 0 0 0 - 0 1 16 372 356 3.47637 3.47656 0.00966636 0.0445187 2 16 610 594 2.90006 2.32422 0.00239654 0.0464271 3 16 687 671 2.18397 0.751953 0.13433 0.0692285 4 16 1178 1162 2.83655 4.79492 0.0292036 0.0532861 5 16 1699 1683 3.28669 5.08789 0.0465653 0.0472847 6 16 1999 1983 3.22715 2.92969 0.00958194 0.0475815 7 16 2311 2295 3.20134 3.04688 0.0293496 0.0479501 8 16 2680 2664 3.25157 3.60352 0.0235217 0.0475715 9 16 2936 2920 3.16804 2.5 0.0399677 0.0491101 10 16 3211 3195 3.11976 2.68555 0.00850986 0.0499317 Total time run: 10.080578 Total writes made: 3211 Write size: 10240 Object size: 10240 Bandwidth (MB/sec): 3.11068 Stddev Bandwidth: 1.24251 Max bandwidth (MB/sec): 5.08789 Min bandwidth (MB/sec): 0.751953 Average IOPS: 318 Stddev IOPS: 127 Max IOPS: 521 Min IOPS: 77 Average Latency(s): 0.0502264 Stddev Latency(s): 0.0713263 Max latency(s): 0.980568 Min latency(s): 0.00174271 Cleaning up (deleting benchmark objects) Clean up completed and total clean up time :8.492848 ---------
Since the problem described in this bug report should be resolved in a recent advisory, it has been closed with a resolution of ERRATA. For information on the advisory, and where to find the updated files, follow the link below. If the solution does not work for you, open a new bug report. https://rhn.redhat.com/errata/RHSA-2016-2815.html