Evaluator(s)
Alastair Duncan
Evaluation points
| Metric | Description | Metric baseline | Metric goal | 19/06/2014 Maps per node 4 Split 1 |
20/06/2014 Maps per node 8 Split 1 |
23/24/06/2014 Maps per Node 1 split 1 |
25/06/2014 Maps per Node 1 split 33 |
26/06/2014 Maps per Node 4 split 33 |
27/06/2014 Maps per Node 8 split 33 |
|---|---|---|---|---|---|---|---|---|---|
| NumberOfObjectsPerHour | Number of objects processed in one hour | 1667.09 | 1789.48 | 874.16 |
1518.95 | 1746.88 |
2820.24 |
||
| MaxObjectSizeHandledInGbytes | Max size of raw files | 0.16689453 | 0.16689453 | 0.16689453 | 0.16689453 | 0.16689453 | 0.16689453 | ||
| MinObjectSizeHandledInGbytes | Min size of raw files | 2.24113e-5 | 2.24113e-5 | 2.24113e-5 | 2.24113e-5 | 2.24113e-5 | 2.24113e-5 | ||
| ThroughputGbytesPerMinute | The throughput of data measured in Gybtes per minute | 0.856 |
0.919 | 0.449 | 0.780 | 0.897 |
1.45 |
||
| ThroughputGbytesPerHour | The throughput of data measured in Gybtes per hour | 51.379 | 55.151 | 26.94 | 46.81 | 53.84 |
86.91 |
||
| ReliableAndStableAssessment | Manual assessment on if the experiment performed reliable and stable | true | true | true | true | true |
true |
||
| NumberOfFailedFiles | Number of files that failed in the workflow | 1000 | 1000 | 1000 | 1000 | 1000 | 1000 | ||
| AverageRuntimePerItemInSeconds | The average processing time in seconds per item | 2.16 | 2.01 | 4.12 | 2.37 | 2.06 |
1.28 |
||
| throughput in bytes per second | The throughput of data measured in bytes per second | 15324467.037 | 16449541.634 | 8035585.716 | 13962718.892 | 16057937.712 |
25924702.545 |
||
| number of objects per second | Number of objects that can be processed per second | 0.46 |
0.49 |
0.24 |
0.42 | 0.48 |
0.78 |
||
| max object size handled in bytes | Max size of raw files | 160312320 | 160312320 | 160312320 | 160312320 | 160312320 | 160312320 | ||
| min object size handled in bytes | Min size of raw files | 24064 | 24064 | 24064 | 24064 | 24064 | 24064 |
WebDAV logs and configuration
http://fue.onb.ac.at/scape-tb-evaluation/stfc/raw2nexus/largedatasetmap8split1/
http://fue.onb.ac.at/scape-tb-evaluation/stfc/raw2nexus/largedatasetmap4split1/
http://fue.onb.ac.at/scape-tb-evaluation/stfc/raw2nexus/largedatasetmap1split1/
http://fue.onb.ac.at/scape-tb-evaluation/stfc/raw2nexus/largedatasetmap1split33/
http://fue.onb.ac.at/scape-tb-evaluation/stfc/raw2nexus/largedatasetmap4split33/
http://fue.onb.ac.at/scape-tb-evaluation/stfc/raw2nexus/largedatasetmap8split33/
Evaluation notes
Timings for creating the copied dataset and generating the input files for ToMaR are not included in the results above.
There are 1000 failed executions because one of the test set(33 files) of files has a metadata file missing. The data set is 1000 copies of the 33 files.