Re: WIP: dynahash replacement for buffer table

On 2014-10-14 20:30:45 +0530, Amit Kapila wrote:
> On Tue, Oct 14, 2014 at 7:55 PM, Andres Freund <andres(at)2ndquadrant(dot)com>
> wrote:
> >
> > On 2014-10-14 09:30:58 -0400, Robert Haas wrote:
> > > A few years ago I started working on a concurrent hash table for
> > > PostgreSQL. The hash table part of it worked, but I never did
> > > anything with it, really. Amit mentioned to me earlier this week that
> > > he was seeing contention inside the dynahash machinery, which inspired
> > > me to go back and update the patch.
> >
> > Interestingly I've benchmarked similar loads, even on the same machine
> > as Amit,
>
> There is one catch here, for these profiles I am using Power-8 m/c
> and the load is slightly higher (5000 scale factor).

Ah, right. I don't think the scale factor changes much, but the
different architecture certainly does. As I said elsewhere, I would not
believe these profiles much until they're actually done with optimized
code...

I also think we need to be a bit careful about optimizing too much for
stock pgbench with working set >> s_b. The uniform readonly access
pattern you're profiling here isn't something super realistic. Still
valuable, but we should take it with a grain of salt.

Greetings,

Andres Freund

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