Josh Berkus wrote:
>>It might be worth considering Apple if you want a 64-bit chip that has a
>>clock speed comparable to Intel's - the Xserv is similarly priced to Sun
>>V210 (both dual cpu 1U's).
>Personally I'd stay *far* away from the XServs until Apple learns to build
>some real server harware. The current XServs have internal parts more
>appropriate to a Dell desktop (promise controller, low-speed commodity IDE
>drives), than a server.
>If Apple has prices these IU desktop machines similar to Sun, then I sense
>doom ahead for the Apple Server Division.
(thinks...) Point taken - the Xserv is pretty "entry level"...
However, having recently benchmarked a 280R vs a PIII Dell using a
Promise ide raid controller - and finding the Dell comparable (with
write cache *disabled*), I suspect that the Xserv has a pretty good
chance of outperforming a V210 (certainly would be interesting to try
What I think has happened is that over the last few years then "cheap /
slow" ide stuff has gotten pretty fast - even when you make "write mean
In response to
pgsql-performance by date
|Next:||From: Mark Kirkwood||Date: 2004-03-24 09:09:02|
|Subject: Re: Fwd: FreeBSD, PostgreSQL, semwait and sbwait!|
|Previous:||From: Greg Stark||Date: 2004-03-24 03:42:20|
|Subject: Re: SLOW query with aggregates|
pgsql-admin by date
|Next:||From: Oleg Bartunov||Date: 2004-03-24 11:11:33|
|Subject: Re: Cache loolup failed problems with tsearch following|
|Previous:||From: Adam Ruth||Date: 2004-03-24 03:31:46|
|Subject: Re: Databases Vs. Schemas|