FW:

-----Original Message-----
From: Orhan Aglagul
Sent: Tuesday, May 08, 2007 5:37 PM
To: 'Scott Marlowe'
Subject: RE: [PERFORM]

But 10,000 records in 65 sec comes to ~153 records per second. On a dual
3.06 Xeon....
What range is acceptable?

-----Original Message-----
From: Scott Marlowe [mailto:smarlowe(at)g2switchworks(dot)com]
Sent: Tuesday, May 08, 2007 5:31 PM
To: Orhan Aglagul
Cc: pgsql-performance(at)postgresql(dot)org
Subject: Re: [PERFORM]

On Tue, 2007-05-08 at 17:59, Orhan Aglagul wrote:
> Hi Everybody,
>
> I was trying to see how many inserts per seconds my application could
> handle on various machines.

>
> Here is the data:
>
>
>
> Time for 10000 inserts
>
> Fsync=on
>
> Fsync=off
>
> Pentium M 1.7
>
> ~17 sec
>
> ~6 sec
>
> Pentium 4 2.4
>
> ~13 sec
>
> ~11 sec
>
> Dual Xeon
>
> ~65 sec
>
> ~1.9 sec
>
>
>

In addition to my previous post, if you see that big a change between
fsync on and off, you likely have a drive subsystem that is actually
reporting fsync properly.

The other two machines are lying. Or they have a battery backed caching
raid controller