- Add methods to select random nodes in the graph
- Add statistical analysis of values
- Add single edge access benchmark
Details
Details
Diff Detail
Diff Detail
- Repository
- rDGRPH Compressed graph representation
- Lint
Automatic diff as part of commit; lint not applicable. - Unit
Automatic diff as part of commit; unit tests not applicable.
Event Timeline
Comment Actions
I rebooted the azure VM and did the benchmark, here is the result for 1M edges:
Command being timed: "java -Xmx220G -Xss10M -server -XX:PretenureSizeThreshold=512M -XX:MaxNewSize=4G -XX:+UseLargePages -XX:+UseTransparentHugePages -XX:+UseNUMA -XX:+UseTLAB -XX:+Re
sizeTLAB -cp swh-graph-0.0.1.jar org.softwareheritage.graph.benchmark.AccessEdge graph/compressed/all"
User time (seconds): 316.50
System time (seconds): 97.80
Percent of CPU this job got: 16%
Elapsed (wall clock) time (h:mm:ss or m:ss): 41:58.50
Average shared text size (kbytes): 0
Average unshared data size (kbytes): 0
Average stack size (kbytes): 0
Average total size (kbytes): 0
Maximum resident set size (kbytes): 124274776
Average resident set size (kbytes): 0
Major (requiring I/O) page faults: 151
Minor (reclaiming a frame) page faults: 314267
Voluntary context switches: 902158
Involuntary context switches: 5357
Swaps: 0
File system inputs: 223611496
File system outputs: 2376
Socket messages sent: 0
Socket messages received: 0
Signals delivered: 0
Page size (bytes): 4096
Exit status: 0
Used 1000000 random edges (results are in seconds):
min value: 2.0000000233721948E-7
max value: 0.001727816998027265
average: 1.0490578032659385E-6
standard deviation: 3.779805627909352E-6