Giedrius Statkevičius

Trying to add a test for this here https://github.com/thanos-io/thanos/issues/4549 but cannot reproduce it. Does this error still happen if you _only_ query (using the selection UI) Thanos Store?

Seems like we need to add a test case for switching to vertical compaction from regular compaction. Help wanted.

So, something like galaxycache but for gRPC calls? Did I understand you correctly?

I agree, this would be great. Perhaps this could be a LFX project? In the mean time I have been using a local version of this functionality: https://github.com/thanos-io/thanos/commit/310df0c5c982551d3412ce578cab52cf1e120ca6. It already...

It can work the other way too: if someone is asking for a metric `foo{}` then we can reuse the results of that request for all queries that use the...

https://github.com/thanos-io/thanos/pull/4290 has been running in prod here for the past couple of months but I suppose it is worth investing time looking into whether it is possible to pushdown this...

> Hey, can I work on this issue? :) Sure, feel free. The `embed` package looks great, we should try it.

This is _not_ a retryable error since we don't have enough data on disk when compaction runs and this occurs. We have been running into this the past month or...

> We are seeing the same issue. We have 200+ compactors and this is happening in all of them. Restarting pod fixes the issue temporarily. Are you using S3 as...

Should be fixed with https://github.com/thanos-io/thanos/pull/3795.