Re: Advice on RAID card - Mailing list pgsql-performance

While I understand being economical, at some point one crosses the line
to being penny wise and pound foolish.

How much is the data on this server going to be worth?
How much much will it cost you to recover or restore it (assuming that
is even possible if you lose it)?

If your data is worth nothing or the cost to recover or restore it is
negligible, then you don't need (nor should want) a DB server.  You'll
get higher performance at less cost via a number of other methods.

OTOH, if you data _does_ have value by any of the above metrics,
then it is worth it to pay attention to reliable, safe, fast, physical IO.

Battery backed HD caches of appropriate size are usually well worth
the $, as they pay for themselves (and then some) with the first data
loss they prevent.

RAID 5 means you are _always_ only 2 HDs from data loss, and 1 HD
from a serious performance hit.  Part of the trade-off with using SATA
HDs that cost 1/3-1/4 their U320 15Krpm brethren is that such
circumstances are +FAR+ more likely with SATA HDs.

If you are not going to use RAID 10 because of cost issues, then
spend the $ to get the biggest battery backed cache you can afford
and justify as being cheaper than what the proper RAID 6 or RAID 10
setup would cost you.  Even if you are going to use SW RAID and the
controller will just be a JBOD controller.

On the general subject of costs...

At this writing, SODIMM RAM costs ~$100 (US) per GB.  Standard
DIMMs cost ~$75 per GB unless you buy 4GB ones, in which case
they cost ~$100 per GB.

The "sweet spot" in SATA HD pricing is ~$160 for 320GB at 7200rpm
(don't buy the 36GB or 74GB WD Raptors, they are no longer worth
it).  If you are careful you can get SATA HD's with 16MB rather than
8MB buffers for that price.  Each such HD will give you ~50MB/s of
raw Average Sustained Transfer Rate.

Decent x86 compatible CPUs are available for ~$200-$400 apiece.
Rarely will a commodity HW DB server need a more high end CPU.

Some of the above numbers rate to either fall to 1/2 cost or 2x in value
for the dollar within the next 6-9 months, and all of them will within the
next 18 months.  And so will RAID controller costs.

Your salary will hopefully not degrade at that rate, and it is unlikely that
your value for the dollar will increase at that rate.  Nor is it likely that
data worth putting on a DB server will do so.

Figure out what your required performance and reliability for the next 18
months is going to be, and buy the stuff from the above list that will
sustain that.  No matter what.

Anything less rates _highly_ to end up costing you and your organization
more money within the next 18months than you will "save" in initial
acquisition cost.

Ron





-----Original Message-----
From: PFC <lists@boutiquenumerique.com>
Sent: Sep 24, 2005 12:27 PM
Subject: Re: [PERFORM] Advice on RAID card


> It looks like a rebranded low end Adaptec 64MB PCI-X <-> SATA RAID card.
> Looks like the 64MB buffer is not upgradable.
> Looks like it's SATA, not SATA II

    Yeah, that's exactly what it is. I can get one for 150 Euro, the Areca is
at least 600. This is for a budget server so while it would be nice to
have all the high-tech stuff, it's not the point. My question was raher,
is it one of the crap RAID5 cards which are actually SLOWER than plain IDE
disks, or is it decent, even though low-end (and cheap), and worth it
compared to software RAID5 ?

> Assuming you are not building 1U boxes, get one of the full height
> cards and order it with the maximum size buffer you can afford.
> The cards take 1 SODIMM, so that will be a max of 1GB or 2GB
> depending on whether 2GB SODIMMs are available to you yet.

    It's for a budget dev server which should have RAID5 for reliability, but
not necessarily stellar performance (and price). I asked about this card
because I can get one at a good price.

    Thanks for taking the time to answer.