Re: Dream Server? - Mailing list pgsql-general

From Steve Wolfe
Subject Re: Dream Server?
Date
Msg-id 02e101c1af72$f8114b20$d281f6cc@iboats.com
Whole thread Raw
In response to Dream Server?  ("Gavin M. Roy" <gmr@justsportsusa.com>)
Responses Re: Dream Server?  (Andrew Sullivan <andrew@libertyrms.info>)
List pgsql-general
----- Original Message -----

> Perhaps we should think wide not tall. As the pontiac commercial says,
wider
> is
> better. Build a distributed database. Increasing height of a box does
not
> scale.
> Amdahl proved it.
>
> Perhaps someone can help with some links, it have seen references to it
on
> ha-linux groups.

  That's something that I've dreamed about for some time.  My rack of
load-balanced web servers scales efficiently, easily, and cheaply.   I
need double the capacity?  I buy more machines, and plug them in.  If
there were a way of replicating PG data from one master to many slaves in
near-real-time, I could have a rack full of load-balanced database servers
right next to it - cheap, easy, and effective.

  Even though I've kept my mouth shut, I've wondered why more effort isn't
devoted to that.  There are a LOT of companies out there that fork money
over hand-over-fist trying to buy a single machine that can handle all of
their database usage, and as the size of the machine increases, the cost
per transaction seems to increase exponentially.  Sure, a million dollars
would get you an entry-level Starfire, with 16 processors, upgradeably to
64, with a couple of gigabytes/second throughput, or for a lot less money,
you could buy a number of smaller systems that, through copious amounts of
RAM, CPU cycles, and combined bandwidth, could spin circles around the
Starfire.

  Don't get the impression that I'm bad-mouthing the developpers - I'm
sure that they're taking care of priorities as best they can.

steve



pgsql-general by date:

Previous
From: Patrick Dunford
Date:
Subject: Re: Server does not reply to Alter Table
Next
From: Josh Rovero
Date:
Subject: Re: Request for Benchmarks...