Anton Firszov

I managed to capture events with `dotnet-trace`, but I don't have any nice output, beacuse EventID-s do not translate to method names unlike when laumching with PerfView on windows: ...

@brianrob opened dotnet/diagnostics#884 and shared details. > Then you can control exactly which events are emitted via an environment variable. It's really not ideal. What environment variables should we set...

> I think it may be `COMPlus_EventPipeConfig` `perfcollect` is based on `LTTng` and does not use EventPipe AFAIK, so I think this won't help collecting traces on `aspnet-pef-lin` > If...

> I'm not sure if we should include a=false. I assume it can only be better, but better to not assume? I think the point is to have a proper...

@tmds @adamsitnik you can check the results here: https://microsoft-my.sharepoint.com/:x:/p/anfirszo/ETUPVQ8QN9BGmysfL5uDJswBpZsSrKZtuFaMtaoU7ifGUQ?e=s1H2gY The grouping should be straightforward, but if it's not I'm happy to answer questions. On several places, there are multiple versions...

@tmds as we discussed, I extended the ThreadPool scheduling benchmarks with `t=1,2,3`, and also added graphs comparing the impact of `COMPlus_ThreadPool_UnfairSemaphoreSpinLimit`. It's only measurable for small `t` values. 

Also sharing the doc here: https://microsoft.sharepoint.com/:x:/r/teams/SocketsPerfWG/Shared%20Documents/General/ContinuationsComparison-Full-0407.xlsx?d=w4e6c85d2c7c54431b8b77793d894e6d0&csf=1&web=1&e=hg3T2q @tmds added the 2 graphs you requested

@tmds @halter73: I did a comparison between the configurations discussed here.  Explanation of labels: Optimal | c=inline | c=threadpool -- | -- | -- `c=inline i=inline a=true o=iothread` |...

This is next on my list after the benchmark reports.

@tmds I guess it will be: ``` c = inline,threadpool t = 1,2,3,4,6,8,10,12,13,14,15,16,17,18,20,22,24,26,28,30 ``` Or do we need anything else?