Throughput graphs are generated by multiple executions of the same performance tests across physical testbeds hosted LF FD.io labs: 2n-skx, 3n-skx, 2n-clx. Box-and-Whisker plots are used to display variations in measured throughput values, without making any assumptions of the underlying statistical distribution.
For each test case, Box-and-Whisker plots show the quartiles (Min, 1st quartile / 25th percentile, 2nd quartile / 50th percentile / mean, 3rd quartile / 75th percentile, Max) across collected data set. Outliers are plotted as individual points.
Additional information about graph data:
Graph Title: describes tested packet path, testbed topology, processor model, NIC model, packet size, number of cores and threads used by data plane workers and indication of DPDK DUT configuration.
X-axis Labels: indices of individual test suites as listed in Graph Legend.
Y-axis Labels: measured Packets Per Second [pps] throughput values.
Graph Legend: lists X-axis indices with associated CSIT test suites executed to generate graphed test results.
Hover Information: lists minimum, first quartile, median, third quartile, and maximum. If either type of outlier is present the whisker on the appropriate side is taken to 1.5×IQR from the quartile (the “inner fence”) rather than the max or min, and individual outlying data points are displayed as unfilled circles (for suspected outliers) or filled circles (for outliers). (The “outer fence” is 3×IQR from the quartile.)
Test results are stored in build logs from FD.io dpdk performance job 2n-skx, build logs from FD.io dpdk performance job 3n-skx, build logs from FD.io dpdk performance job 2n-clx, build logs from FD.io dpdk performance job 2n-zn2, build logs from FD.io dpdk performance job 3n-tsh, build logs from FD.io dpdk performance job 2n-tx2, build logs from FD.io dpdk performance job 2n-dnv and build logs from FD.io dpdk performance job 3n-dnv with RF result files csit-dpdk-perf-2106-*.zip archived here. Required per test case data set size is 10 and for DPDK tests this is the actual size, as all scheduled test executions completed successfully.