Callum Styan

@href is this still an issue in current release?

so via curl or logcli you always see all the expected log results? could you share more the exact query you're running? we may need to file a grafana issue

Note that some work here will be done via the related LFX project, I believe LFX selection notifications go out next week on the 12th PST. > The Avalanche project...

I see. I had no envisioned using anything like a "remote write directly from avalanche" mode as a way of benchmark testing remote write itself, just using avalanche as a...

> Which looks non-representative of a realistic workload. [test-infra/tools/fake-webserver](https://github.com/prometheus/test-infra/tree/master/tools/fake-webserver) Looks better. And even better was using data from a real source in the string interning PR implementation. I'm not very...

> I think this may lead to higher dropped samples if the redistribution fails? Note, when we attempt redistribution and it fails, we haven't spent any time yet, so retaining...

I'm actually working on this at the moment, based on Nicole's original branch. The main thing is that if the checkpoint file is not present, or if the segment mentioned...

relevant "feature" requirements: https://github.com/prometheus/prometheus/pull/9862#issuecomment-979471947

@codesome We've been calling this feature "remote write checkpointing" so I'll refer to it as that here. Regardless of the mechanism we use for deciding what to write (I still...

Remote write has no ownership over the WAL, that would have to be okay-ed by the TSDB maintainers. If we were to have something like that it would need some...