Frederic Branczyk

Thanks for opening this! I replied on the discussion, you're right it's not something we've kept a close look on. Thank you for bringing it to our attention!

Here we control all parts, so I wouldn't be against having some deeper Kubernetes integrations. Sort of as if the Prometheus Operator functionality was built into Prometheus directly. I do...

While parca stores these labels they’re not included in the queries yet. We’ve done all the ground work though it should only be a few lines if you want to...

Looks like we don't aggregate them away when querying from the database: https://github.com/parca-dev/parca/blob/73f3f1d15a50e02fef244b9441b99f4a3d22a40a/pkg/parcacol/querier.go#L918-L938 But in the pprof download, we appear to (incorrectly) not add the labels again: https://github.com/parca-dev/parca/blob/73f3f1d15a50e02fef244b9441b99f4a3d22a40a/pkg/query/pprof.go#L155-L158

hmm yeah this is a difficult one, we should probably store stacktraces in the columnstore directly, and not fail on reading from the metastore, then like you said Alfonso, it...

Makes sense!

Very cool! I'm curious, what do the numbers before the closing curly brackets mean are they parameters? For a 5 seconds profile 1.1k samples seems like _a lot_, what's the...

> {ModuleName, Function, Arity} so its mean for example Erlang.garbage_collect(arg1, arg2) -> {:erlang, :garbage_collect, 2}. Got it! Thanks for the explanation! > actually fprof is not simple call stack sampling,...

Thank you so much for this work, the community needs this type of engagement!

Storing things in pprof is also very inefficient, I don't think this approach would scale either. We're working on something in Polar Signals Cloud that we think will fix all...