Filip Petkovski

Hm hard to explain with a diagram, but let me try with code links. From what I see, we start a gorouting for each store that we query, and that...

Regarding consequences, one thing that comes to mind is hashes being different depending on how labels are sorted: https://github.com/prometheus/prometheus/blob/main/model/labels/labels.go#L137

> How would you like to get insight when this limit is hit? I think this could potentially be solved by emitting a metric when the limit is hit and...

One question, do you think it makes sense to have separate sharding number for query range and query instant? It would mean we change `--query-frontend.vertical-shards` to ``` --query-range.vertical-shards --query-instant.vertical-shards ```...

Got it. Let's start with a single flag and we can revisit if a use case comes up.

Could you share the command that fails for you currently?

Amazing stuff, one of our instant queries went from 36s to 8s.

I tested this in our infra and can confirm improved performance for queries across lots of series. Some queries went down from 40s to 30s. Dashboards also seem to be...

I am also happy to see this shipped in its current incarnation.

I deployed this in one of our environments, and I saw a drop in the p90 for gRPC stream duration. However, I also noticed a drop in series selects per...