Looking at flamegraphs for some queries I see quite a bit of copy_user_enhanced_fast_string, which is supposed to be alleviated with io_uring, as far as I understand:

@bobrik copy_user is also eliminated with:

• Linux AIO that is enabled with min_bytes_to_use_direct_io setting;
• mmap that is enabled with min_bytes_to_use_mmap_io setting.

Now we have the notion of read_method to select between various read engines.
And we can start experimenting with io_uring.

CC @azat maybe you will find this interesting?

CC @azat maybe you will find this interesting?

Yep, this idea already visited me (added these to my internal to-do/to-look list)

There was an experiment adding uring by @sauliusvl
Unfortunately, it proves to be unsustainable.

There is only a marginal improvement in performance. But the code becomes way more complicated. It became so complicated that even an experienced C++ engineer (the author of the code) cannot figure out why there are rare hangs of queries (found by our automated testing before the release).

Done.