Heikki Linnakangas

> > I want to bring up this topic that I also wrote in a comment on my branch: > > Another type of query which can suffer from order...

> > That happens to work, though. > > Sorry, but why `UNION ALL` and not `UNION`? `UNION ALL` doesn't remove duplicates so for it order is not important. The...

@ankane do you have any thoughts on this? In particular, what do you think of returning rows in "wrong" order vs omitting rows that would be in wrong order?

> Hi @knizhnik, thanks for the PR. It's an interesting approach, but want to explore potentially more efficient methods like [HQANN](https://arxiv.org/abs/2207.07940) for filtered search. HQANN is interesting. [Filtered-DiskANN](https://harsha-simhadri.org/pubs/Filtered-DiskANN23.pdf) is a...

This approach seems pretty inflexible to me. Off the top of my head, some scenarios where this can go wrong: 1. There might be a LIMIT at the top of...

Rebased this

I was reminded of this by https://www.postgresql.org/message-id/CA%2BhUKGJ_7NKd46nx1wbyXWriuZSNzsTfm%2BrhEuvU6nxZi3-KVw%40mail.gmail.com. Rebased.

It's not significant, the pairingheap operations don't really show up in profiling.

See https://www.postgresql.org/message-id/[email protected] for discussion on pgsql-hackers mailing list

Hmm, why is it quadratic at basebackup? AFAICS you need to reconstruct the aux-files key-value pair only once, which is O(n) where n is the number of delta records since...