Tony Solomonik

Wouldn't this be a big step for libuv? I don't get why it's on hold for so long...

Scan needs to go to the threads that contain the keys you want to scan. The iterator should live in the client, rust has an AsyncIter only in nightly, so...

Oh I missed this issue, only now noticed it, thanks for the kind words :) When using gossip to relay messages, I thought, why should I simply rely on gossip...

> Thanks for your PR. The way the logic is split here between `optimize_split_order` and `optimize` makes it very hard to proof read. Currently it's already a bit confusing because...

> before i review further, i have a major concern to express. for mostly historic reasons, start/end_timestamps are only precise up to the second, but the ast can express sub-second...

> i think `Bounds` would be a tad annoying because SearchRequest must be protobuf-serializable, but an `Option` that happens to contain ns is likely good enough Cool I'll work on...

@fulmicoton-dd @trinity-1686a The optimizations I talk about are stuff like `is_metadata_count_request_with_ast` checking that the query is a MatchAll query. I thought of this PR after making [this PR](https://github.com/quickwit-oss/quickwit/pull/5758). > this...

> Nice optimization. I think it deserves a unit test. E.g the following test scenario: > > * The mock metastore returns 4 splits (1 outside the range, 1 overlapping...

> Thanks for adding a test. Unfortunately I think it is flawed (so was my example of test earlier, I should have written "the mock search service expects to be...

https://github.com/UlakCommunications/ulak-presto-connectors/tree/master I'll try it out soon and update!