Re: [PERFORM] wal_level=archive gives better performance than minimal - why?

2012-02-04 Thread Cédric Villemain
Le 3 février 2012 19:48, Robert Haas a écrit : > 2012/1/22 Tomas Vondra : >> That's suspiciously similar to the checkpoint timeout (which was set to >> 4 minutes), but why should this matter for minimal WAL level and not for >> archive? > > I went through and looked at all the places where we invo

Re: [PERFORM] wal_level=archive gives better performance than minimal - why?

2012-02-04 Thread Tomas Vondra
On 4.2.2012 17:04, Cédric Villemain wrote: > Le 3 février 2012 19:48, Robert Haas a écrit : >> 2012/1/22 Tomas Vondra : >>> That's suspiciously similar to the checkpoint timeout (which was set to >>> 4 minutes), but why should this matter for minimal WAL level and not for >>> archive? >> >> I went

[PERFORM] how to demonstrate the effect of direct I/O ?

2012-02-04 Thread Tomas Vondra
Hi all, I've been running a lot of benchmarks recently (I'll publish the results once I properly analyze them). One thing I'd like to demonstrate is the effect of direct I/O when the wal_fsync_method is set to open_sync/open_datasync. I.e. I'd like to see cases when this improves/hurts performanc

Re: [PERFORM] how to demonstrate the effect of direct I/O ?

2012-02-04 Thread Tomas Vondra
On 5.2.2012 00:25, Tomas Vondra wrote: > Hi all, > > I've been running a lot of benchmarks recently (I'll publish the results > once I properly analyze them). One thing I'd like to demonstrate is the > effect of direct I/O when the wal_fsync_method is set to > open_sync/open_datasync. > > I.e. I'