Graph consensus and vote information from Rob's experiment (May/June 2021)
Rob did recently a similar flooding experiment to the one behind #33076 (closed). We should do a respective analysis for the new experiment, too.
There is a thread on tor-relays@ and an entry on our status page with more details.
According to the older ticket here is what we should look into (copied over verbatim):
Basically, we want to have a standard way to graph results from key metrics from before, during, and after the experiment.
In this case, we want CDF-TTFB, CDF-DL from onionperf results.
We also want CDF-Relay-Stream-Capacity and CDF-Relay-Utilization for the consensus, as well as from the votes, to see if the votes from TorFlow drastically differ from sbws during the experiment.
https://trac.torproject.org/projects/tor/wiki/org/roadmaps/CoreTor/PerformanceMetrics
Here are additional things we should/could have on our radar:
- Did the 5/10/15 sec overload issue appear in onionperf again?
- Check if anything else happened in the long tail
- How did the bytes written/read in extra-info descs look like during the experiment?
- Why does measuring some relays break due to reaching the 15 sec circuit build timeout (reported by Rob during the experiment)?
- How did overload lines develop during the experiment?