|From:||Andres Freund <andres(at)anarazel(dot)de>|
|To:||Nils Goroll <slink(at)schokola(dot)de>|
|Cc:||Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>, Jan Wieck <jan(at)wi3ck(dot)info>, PostgreSQL Development <pgsql-hackers(at)postgresql(dot)org>|
|Subject:||Re: s_lock() seems too aggressive for machines with many sockets|
|Views:||Raw Message | Whole Thread | Download mbox|
On 2015-06-10 16:55:31 +0200, Nils Goroll wrote:
> But still I am convinced that on today's massively parallel NUMAs, spinlocks are
> plain wrong:
Sure. But a large number of installations are not using massive NUMA
systems, so we can't focus on optimizing for NUMA.
We definitely have quite some catchup to do there. Unfortunately most of
the problems are only reproducible on 4, 8 socket machines, and it's
hard to get hand on those for prolonged amounts of time.
> - Even if critical sections are kept minimal, they can still become hot spots
That's why we started to remove several of them...
> - The fact that well behaved mutexes have a higher initial cost could even
> motivate good use of them rather than optimize misuse.
Well. There's many locks in a RDBMS that can't realistically be
avoided. So optimizing for no and moderate contention isn't something
you can simply forgo.
|Next Message||Jan Wieck||2015-06-10 15:03:31||Re: s_lock() seems too aggressive for machines with many sockets|
|Previous Message||Gurjeet Singh||2015-06-10 15:00:28||Re: replication slot restart_lsn initialization|