Re: our buffer replacement strategy is kind of lame

On Sun, Aug 14, 2011 at 7:33 PM, Robert Haas <robertmhaas@gmail.com> wrote:

> Simon is proposing to bound the
> really bad case where you flip through the entire ring multiple times
> before you find a buffer, and that may well be worth doing.  But I
> think even scanning 100 buffers every time you need to bring something
> in is too slow.  What's indisputable is that a SELECT-only workload
> which is larger than shared_buffers can be very easily rate-limited by
> the speed at which BufFreelistLock can be taken and released.  If you
> have a better idea for solving that problem, I'm all ears...

I felt we were on the right track here for a while.

Does anyone dispute that BufFreelistLock is a problem? shared buffer
replacement is *not* O(k) and it definitely needs to be.

Does anyone have a better idea for reducing BufFreelistLock
contention? Something simple that will work for 9.2?

What steps are there between here and committing the freelist_ok.v2.patch?

--
 Simon Riggs                   http://www.2ndQuadrant.com/
 PostgreSQL Development, 24x7 Support, Training & Services