Re: There's random access and then there's random access

On 12/2/07, Gregory Stark <stark(at)enterprisedb(dot)com> wrote:
>
> The two interfaces I'm aware of for this are posix_fadvise() and libaio. I've
> run tests with a synthetic benchmark which generates a large file then reads a
> random selection of blocks from within it using either synchronous reads like
> we do now or either of those interfaces. I saw impressive speed gains on a
> machine with only three drives in a raid array. I did this a while ago so I
> don't have the results handy. I'll rerun the tests again and post them.

The issue I've always seen raised with asynchronous I/O is
portability--apparently some platforms PG runs on don't support it (or
not well). AIUI Linux actually still has a fairly crappy
implementation of AIO--glibc starts threads to do the I/O and then
tracks when they finish. Not absolutely horrible, but a nice way to
suddenly have a threaded backend when you're not expecting one.

-Doug