Message-ID: <1132175017.437b9ea9e33e2@webmail.rawbw.com>
Date: Wed, 16 Nov 2005 13:03:37 -0800
From: mudfoot@rawbw.com
To: pgsql-performance@postgresql.org
Subject: Re: Hardware/OS recommendations for large databases (
References: <3E37B936B592014B978C4415F90D662D01995F7B@MI8NYCMAIL06.Mi8.com>
	<33c6269f0511152115v1a34ab81j30f1f5df5a6c6956@mail.gmail.com>
	<437B3B18.1040509@commandprompt.com> <437B4773.1040404@boreham.org>
	<1132160785.3582.60.camel@state.g2switchworks.com>
	<20051116185138.GA22831@uio.no>
	<1132171683.3582.85.camel@state.g2switchworks.com>
In-Reply-To: <1132171683.3582.85.camel@state.g2switchworks.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 8bit
User-Agent: Internet Messaging Program (IMP) 3.2.1

Yeah those big disks arrays are real sweet.

One day last week I was in a data center in Arizona when the big LSI/Storagetek
array in the cage next to mine had a hard drive failure.  So the alarm shrieked
at like 13225535 decibles continuously for hours.  BEEEP BEEEEP BEEEEP BEEEEP. 
Of course since this was a colo facility it wasn't staffed on site by the idiots
who own the array.  BEEEEP BEEEEEEEP BEEEEEEEP for hours.  So I had to stand
next to this thing--only separated by a few feet and a little wire mesh--while
it shrieked for hours until a knuckle-dragger arrived on site to swap the drive.

Yay.

So if you're going to get a fancy array (they're worth it if somebody else is
paying) then make sure to *turn off the @#%@#SF'ing audible alarm* if you deploy
it in a colo facility.

Quoting Scott Marlowe <smarlowe@g2switchworks.com>:

> On Wed, 2005-11-16 at 12:51, Steinar H. Gunderson wrote:
> > On Wed, Nov 16, 2005 at 11:06:25AM -0600, Scott Marlowe wrote:
> > > There was a big commercial EMC style array in the hosting center at the
> > > same place that had something like a 16 wide by 16 tall array of IDE
> > > drives for storing pdf / tiff stuff on it, and we had at least one
> > > failure a month in it.  Of course, that's 256 drives, so you're gonna
> > > have failures, and it was configured with a spare on every other row or
> > > some such.  We just had a big box of hard drives and it was smart
> enough
> > > to rebuild automagically when you put a new one in, so the maintenance
> > > wasn't really that bad.  The performance was quite impressive too.
> > 
> > If you have a cool SAN, it alerts you and removes all data off a disk
> > _before_ it starts giving hard failures :-)
> 
> Yeah, I forget who made the unit we used, but it was pretty much fully
> automated.  IT was something like a large RAID 5+0 (0+5???) and would
> send an alert when a drive died or started getting errors, and the bad
> drive's caddy would be flashing read instead of steady green.
> 
> I just remember thinking that I'd never used a drive array that was
> taller than I was before that.
> 
> ---------------------------(end of broadcast)---------------------------
> TIP 6: explain analyze is your friend
>