[nylug-talk] Slim home server for samba and subversion ( and possibly IMAP)
Chris Knadle
Chris.Knadle at coredump.us
Thu May 8 15:57:31 EDT 2008
On Wednesday 07 May 2008, Bryan J. Smith wrote:
> On Tue, 2008-05-06 at 17:46 -0400, Ajai Khattri wrote:
> > Also the Drobo device (Google for it) comes in two pieces: a dumb drive
> > box which you can use alone or with an add-on device that plugs into your
> > network.
>
> I have real issues with external storage, unless it's SAS (which is not
> commodity, so a non-consideration here). USB and FireWire have time-out
> issues to the point even Apple had to admit shortcomings of FireWire.
> eSATA is a ball of mechanical non-standards (don't get me started).
> Most cheap NAS' just have piss-poor performance (especially when you try
> to use a GbE MAC on a slow microcontroller with an embedded NPE/SPE).
I had half written a post back concerning the poor GigE NAS device
performance. [In practice I see limits of 14 MB/sec on an embedded GigE NAS
vs 40+MB/sec GigE transfer between a laptop + desktop.] I hadn't even been
aware about the USB + FireWire timeout issues until you mentioned those here.
Ugh.
> On Tue, 2008-05-06 at 17:46 -0400, Ajai Khattri wrote:
> > In your case, could you not use a mini ITX machine to serve as file
> > server and authenticator in front of your drives?
>
> Consider Intel's $60-70 Yonah Mini-ITX solutions:
> http://www.intel.com/products/motherboard/D201GLY2/index.htm
>
> They say "MicroATX compatible" but are Mini-ITX mechanical (6.7" x
> 6.7"). They are much better than anything ViA offers and beat AMD's
> aging Geode NX (embedded Athlon, not to be confused with the older Geode
> GX or LX, which are Cyrix/NS licensed designs).
Yeah the Yonah Celeron core seems to have 512k L2 cache (or so says
Wikipedia) whereas the AMD Geode NX doesn't have any L2 cache at all, and L2
cache makes a huge performance improvement.
The Geode NX runs at lower power at 6W compared to about 19W, but I'm
guessing that the power savings likely isn't worth the performance hit.
Seems like you've done plenty of research into this already, certainly more
so than I have on this particular niche. I've focused more on Geode LX based
products, i.e. more embedded x86-compatible hardware, for use as low-powered
Linux boxes as firewalls or other uses, and that kind of hardware doesn't
cover 500 GB storage that performs well.
> In the future, the 2-issue "Atom" design (IA-32e aka x86 EM64T) from
> Intel will prove even more interesting, especially as Intel has dropped
> its IXP (X-Scale ARM) line that dominates those "cheap" SOHO devices.
> Of course not everyone agrees, and even Apple snatched up an IBM Power 5
> licensee recently, showing that not everyone believes in Atom yet. ;)
Is the Atom licensing restrictive or something? WTH? I wonder why it's
not getting more widespread adoption.
> Alexander L. Belikoff wrote:
> > Old laptops - well, same reason as above. I doubt, there are
> > affordable 500+Gb 2.5" drives. I also don't think they are as
> > reliable as their 3.5" cousins.
>
> First off, the largest commodity disk in 2.5" right now is 320GB.
>
> Secondly, what do you mean "don't think they are as reliable"?
It also seems to me I've experimentally gotten more reliability out of 3.5"
hard disks than 2.5" hard disks -- however this statement is completely
subjective, only has a tiny sample set (less than 5 2.5" drives) and I
haven't (yet) read any hard data comparing 3.5" to 2.5" disk reliability.
> Commodity 2.5" disks can take a crapload more of vibration and off-line
> than commodity 3.5" disks. Have you ever used (and abused) an external
> 3.5" disk like you have a laptop? The MTBF is an order of magnitude
> difference.
I don't even know how to compare these, beacause practially speaking it's
just not possible to use a 3.5" disk exactly like a 2.5" disk. Yes I've
moved around 3.5" disks in external drive bays, but IMHO that's just not the
same thing.
> The 2.5" disk is overtaking the data center. It's more reliable, cooler
> and -- at 10-15Krpm -- can almost be just as high performing.
> Correspondingly, this has pushed down the price of more commodity
> 5400-7200rpm 2.5" disk to almost $0.30/GB.
That's interesting and I hadn't heard about it. I'll put that on the list
of things to look into.
-- Chris
--
Chris Knadle
Chris.Knadle at coredump.us
More information about the nylug-talk
mailing list