Re: Stuck spins in current - Mailing list pgsql-hackers

From Bruce Momjian
Subject Re: Stuck spins in current
Date
Msg-id 200103211325.IAA14765@candle.pha.pa.us
Whole thread Raw
In response to Re: Stuck spins in current  ("Vadim Mikheev" <vmikheev@sectorbase.com>)
List pgsql-hackers
> > > BTW, I've got ~320tps with 50 clients inserting (int4, text[1-256])
> > > records into 50 tables (-B 16384, wal_buffers = 256) on Ultra10
> > > with 512Mb RAM, IDE (clients run on the same host as server).
> > 
> > Not bad.  What were you getting before these recent changes?
> 
> As I already reported - with O_DSYNC this test shows 30% better
> performance than with fsync.
> 
> (BTW, seems in all my tests I was using -O0 flag...)

Good data point.  I could never understand why we would ever use the
normal sync if we had a data-only sync option available.  I can imagine
the data-only being the same, but never slower.

--  Bruce Momjian                        |  http://candle.pha.pa.us pgman@candle.pha.pa.us               |  (610)
853-3000+  If your life is a hard drive,     |  830 Blythe Avenue +  Christ can be your backup.        |  Drexel Hill,
Pennsylvania19026
 


pgsql-hackers by date:

Previous
From: Adriaan Joubert
Date:
Subject: Re: int8 bug on Alpha
Next
From: Tatsuo Ishii
Date:
Subject: Re: Call for platforms