[lohmag]

With MYSQLI_CLIENT_COMPRESS, mysqlnd runs compress() on every packet it sends, however small. Each call sets up a new deflate stream, and below a few hundred bytes the packet barely shrinks, so the client pays the full setup cost for almost nothing.

This sends packets smaller than 512 bytes uncompressed inside the compressed envelope (uncompressed length 0), which the protocol already allows and which mysqlnd already does for packets that do not shrink. libmysqlclient uses the same mechanism with a 50 byte threshold.

Client CPU per query, release build, one pinned core, MySQL 8.0.46 on the same host, SELECT '<n bytes>' over a compressed connection, median of 5 runs of 50000 queries:

Query size	Before	After
100 B	7.72 µs	4.76 µs
300 B	8.20 µs	4.86 µs
600 B	8.97 µs	8.96 µs
2000 B	11.31 µs	11.39 µs

The new test sends payloads on both sides of the threshold, including random data that does not compress, and checks that each one comes back intact.

[Sjord]

Looks good to me.

MySQL 8.0.46 on the same host

I think it would be interesting to get performance information when the connection goes over the internet. Compression would be more benificial on slow links, but I guess it would not make much of a difference as long as the query fits in one packet.