John Spray

Different but related: #272 may help folks affected by this issue by enabling larger write sizes than the default 16kb. I haven't tested performance on spinning disk, but one would...

Implementing a lazy-flush persistenct mode is probably worthwhile both for slow HDDs, and for people running on cheap virtualized block storage (e.g. cheaper EBS tiers) for people processing ephemeral data...

> @jcsp how does this differ from in-memory acks Different names for the same logical result of acking before persistent: we can implement it at different levels -- the "in...

@senior7515 @ivotron is this something we want to promote to a docs ticket? Or shall we close this?

Saw this relatively issue again today (it's pretty rare): https://github.com/neondatabase/neon/actions/runs/7400306977/job/20133914202?pr=6123

No instances of this on docker CI on dev in last 30 days. Vlad saw it in a PR run 15 days ago. We closed https://github.com/redpanda-data/redpanda/issues/7231 for a similar consumer...

Since we haven't seen this since updating franz-go/kgo-verifier, I'm closing this. The update has slightly better diagnosability (doesn't leave extra consumers running in background until they'd GC'd), so if this...

`sev/low` because it's believed to be a client bug.

@andijcr this has been stalled for a while -- it's not our top priority, but it would be good to know if there were issues blocking this

I've merged this into https://github.com/redpanda-data/redpanda/pull/5315