On 3/23/13 7:41 AM, Ants Aasma wrote:
On Sat, Mar 23, 2013 at 6:04 AM, Jim Nasby <j...@nasby.net> wrote:
Partitioned clock sweep strikes me as a bad idea... you could certainly get
unlucky and end up with a lot of hot stuff in one partition.
Surely that is not worse than having everything in a single partition.
Given a decent partitioning function it's very highly unlikely to have
more than a few of the hottest buffers end up in a single partition.
One could argue that it is worse because you've added another layer of
unpredictability to performance. If something happens to suddenly put two
heavily hit sets in the same partition your previously good performance
suddenly tanks.
Maybe that issue isn't real enough to be worth worrying about, but I still
think it'd be easier and cleaner to try keeping stuff on the free list first...
Another idea that'sbeen broughht up inthe past is to have something in the
background keep a minimum number of buffers on the free list. That's how OS
VM systems I'm familiar with work, so there's precedent for it.
I recall there were at least some theoretical concerns about this, but I
don't remember if anyone actually tested the idea.
Yes, having bgwriter do the actual cleaning up seems like a good idea.
The whole bgwriter infrastructure will need some serious tuning. There
are many things that could be shifted to background if we knew it
could keep up, like hint bit setting on dirty buffers being flushed
out. But again, we have the issue of having good tests to see where
the changes hurt.
I think at some point we need to stop depending on just bgwriter for all this
stuff. I believe it would be much cleaner if we had separate procs for
everything we needed (although some synergies might exist; if we wanted to set
hint bits during write then bgwriter *is* the logical place to put that).
In this case, I don't think keeping stuff on the free list is close enough to
checkpoints that we'd want bgwriter to handle both. At most we might want them
to pass some metrics back in forth.
--
--
Jim C. Nasby, Data Architect j...@nasby.net
512.569.9461 (cell) http://jim.nasby.net
--
Sent via pgsql-hackers mailing list (pgsql-hackers@postgresql.org)
To make changes to your subscription:
http://www.postgresql.org/mailpref/pgsql-hackers
