Bartlomiej Plotka

I have some ideas that are slowly unblocked with the work on https://github.com/bwplotka/gobin (: Otherwise no movement, but would be nice to have.

Still valid, and a big chunk of work to make it happen. Some idea presented already in the past to Prometheus and Cortex teams: Start second, separate WAL just for...

Still valid!

I think it would be nicer if you would propose a PR with proposal to Thanos as flow https://thanos.io/tip/contributing/proposal-process.md/. This will allow us to start discussion on each separate part...

cc @GiedriusS @yeya24 @wiardvanrij, our SLO expert @metalmatze, @kakkoyun @brancz for more opinions (:

I assume you are not on it right? (: Just making sure, so others can help as well (:

1. Does not matter 120 / 140. If there is check I might miss it and all good (: Let's double check. 2. > What's the benefit of Chunks are...

Hey @jacksontj, thanks for all of these! I think for Thanos querier, we have some minor advantage. We exactly know what "types" of underlying leafs we have. It will be...

> Presumably the same issue happens for wherever the long-term storage exists? Good to know that thanos mitigates the prom issues, but I'd definitely suggest looking into marhasling performance (and...

Ah I missed you actually push down only some sub-queries.. hm