I am personally very excited to see that work on direct IO has started. It is a huge undertaking so I do not expect any production ready thing any time soon but nice to see that some code landed.
Yeah- we've been working on that for quite a while, and it'll take a few more years to finish it. I hope we can get some important parts into 17 though.
FWIW, there have been smaller prerequisites merged into 15 already, and 16 has a number of improvements that are part of that work. E.g. the more scalable relation extension (making COPY scale much better), and the related buffer mapping changes, come from the AIO effort.
Personally I think the feature is using asynchronous IO and direct IO support is part of that :)
FWIW, there have been smaller prerequisites merged into 15 already, and 16 has a number of improvements that are part of that work. E.g. the more scalable relation extension (making COPY scale much better), and the related buffer mapping changes, come from the AIO effort.
Personally I think the feature is using asynchronous IO and direct IO support is part of that :)