Frederic Branczyk
Frederic Branczyk
This makes a ton of sense, and is super easy to add. (we already add thread ID and thread name, which in the meantime might already be useful, but I...
This is not quite correct. Stripped debuginfo does not necessarily have the right offsets anymore (split/objdump remove them because the `.text` section is not there anymore). The binary that was...
Also, the agent already doesn't send it anymore, because it already performs normalization locally.
I think we have yet to instrument the proxy store type (used with the query component) to validate whether and how much this is happening. I do suspect that it...
With #2030 merged we should be able to at least identify the potential for this.
Looking at the metrics in our prod environment, the metrics seem to show that we do _a lot_ of requests that return empty responses.
As mentioned in the previous comment, there is definitely room for improvement still.
I think we have yet to measure how often were unnecessarily hitting stores to validate further work.
@daanx with jemalloc being archived, it might start to be more important to make mimalloc more observable. Any chance this is something you'd be interested in accepting?
At first sight I would say that should work. A cherry on top would be if mimalloc sampled allocations every X bytes allocated and only fired the trace probes then...