Tuesday, May 18, 2010

Re: [BLUG] new big computer for a lab

Hi Ignasi,

Some of the answers to your questions really depend on the
requirements of the end users. For instance, what is the primary area
of research (microarray, sequencing, phylogenetics, web database,
etc...)? Each specialized area can have different requirements. You
also need to take into account the applications that they want to run
and what operating systems they are compatible with. If this is going
to be used for processing high throughput sequencing then you might
want to take a look at cloud computing solutions instead of running it
locally (1).

As others have already said, definitely go with a RAID or ZFS (2)
system with some sort of backup system. I generally prefer hardware
RAID cards because they tend to have better performance, support
advanced RAID levels that you usually don't get with software RAID,
and are less susceptible (not immune) to software bugs in my
experience. I've also run into problems with software RAID where it
complicated the use of traditional system rescue tools. Not something
you want to happen when you are in a pinch.

For linux distros I would suggest anything with a long term patch
cycle such as Ubuntu LTS or Centos. If you care to check out ZFS your
choices are FreeBSD, OpenSolaris, or Nexenta (3). Above all else,
remember to check what software your users will want to run and make
sure that it compiles and runs cleanly on your system. Many
bioinformatics packages can be a bit fickle when it comes to different
platforms or even different versions of platforms.

1. The case for cloud computing in genome informatics - Lincoln Stein
(http://genomebiology.com/2010/11/5/207)
2. ZFS - http://en.wikipedia.org/wiki/ZFS
3. Nexenta - http://www.nexenta.org/

Good luck!

Josh


On Mon, May 17, 2010 at 11:52 AM, Ignasi <ignasilucas@gmail.com> wrote:
> Hello.
>
> A colleague is starting his own biology lab in Spain, and he's planning to
> spend between 10,000 and 15,000 € in a computer. He asked me what features I
> think the computer should have. The fact is that I'd like to provide him
> some useful information, because I expect him to give me a job soon. So, I'd
> really appreciate your advise. Anything from hardware brands to operating
> systems will be welcome. Plus, how to spend money in hardware is a subject
> that also interests me personally. Let me give you some more background
> about what the computer may be used for.
>
> I expect between 4 and 10 people to use it at the same time. Most jobs will
> be CPU intensive, but I can also envision some sporadic jobs to require
> several GB of RAM. He also wants to store quite a bit of data there, and
> maybe host a database. I assume that nobody would use it as a desktop, but
> it would be accessed remotely. In principle, the main concern is to make it
> a fast computer.
>
> I've read a little bit about RAID arrays, but never met anybody who used
> them. I'm interested in those configurations where data is mirrored, so that
> the system can tolerate the failure of one of the disks. And I've been
> warned that if all the disks composing the array are of the same brand and
> design, more than one may fail at the same time. Do you think RAID is worthy
> at all, or not necessary with a good back up system? what is better, an
> operating system RAID controller, or a hardware one?
>
> As a biologist who works with computers, I'd like to learn more about this
> topics. Feel free to recommend books, magazines, web sites... that I can use
> to teach myself. Thanks.
>
> Ignasi.
>
> _______________________________________________
> BLUG mailing list
> BLUG@linuxfan.com
> http://mailman.cs.indiana.edu/mailman/listinfo/blug
>
>

_______________________________________________
BLUG mailing list
BLUG@linuxfan.com
http://mailman.cs.indiana.edu/mailman/listinfo/blug

Re: [BLUG] new big computer for a lab

Thanks a lot for all your replies. I enjoy reading you.


2010/5/18 Thomas Smith <tgs@resc.net>
Hi,
The ridiculous prices usually come when you have them preinstall a
disk on a system.  It's always much cheaper to buy a disk separately
than to have them install it.  The bad part is that, as has been said
before, they only give the system exactly the parts that it needs as
you order it, so forget about getting an extra drive sled in the box,
for instance.  Perverse incentives... it's in their best interest if
the system is as un-expandable as possible.
-Thomas

On Tue, May 18, 2010 at 4:32 PM, Shei, Shing-Shong <shei@cs.indiana.edu> wrote:
> Mark,
>>  Here is an option for a server hard drive  from Dell's website just now:
>>
>>   1TB 7.2K RPM SATA 3Gbps 3.5-in Cabled Hard Drive [$449.00]
>>
>>  From Newegg:
>>
>>   Western Digital RE3 WD1002FBYS 1TB 7200 RPM SATA Drive - $159.99
>
> What's the URL you got from Dell?  Looks like it's more than bare bone drive
> (since it's "cabled hard drive.")  I just went to Dell and here are some
> sample URLs:
>
> 1) 1TB 7200 RPM Hot Swappable Serial ATA II Hard Drive for Dell PowerEdge 2900 Server
>   for $148.99 (with tray).
> http://accessories.us.dell.com/sna/products/System_Drives/productdetail.aspx?c=us&l=en&cs=19&sku=341-5895
>
> 2) 1TB 7200 RPM Serial ATA Hard Drive for Dell Vostro 220/ 430 / Studio XPS 8000 Desktop
>   for $120.99
>
> http://accessories.us.dell.com/sna/products/System_Drives/productdetail.aspx?c=us&l=en&cs=19&sku=341-8259
>
> 3) 1TB Caviar Blue SATA 3 Internal Hard Drive for $83.99
>
> http://accessories.us.dell.com/sna/products/System_Drives/productdetail.aspx?c=us&l=en&cs=19&sku=A3677038
>
> Thanks,
> Shing-Shong
> _______________________________________________
> BLUG mailing list
> BLUG@linuxfan.com
> http://mailman.cs.indiana.edu/mailman/listinfo/blug
>



--
http://resc.smugmug.com/

_______________________________________________
BLUG mailing list
BLUG@linuxfan.com
http://mailman.cs.indiana.edu/mailman/listinfo/blug

Re: [BLUG] new big computer for a lab

Hi,
The ridiculous prices usually come when you have them preinstall a
disk on a system. It's always much cheaper to buy a disk separately
than to have them install it. The bad part is that, as has been said
before, they only give the system exactly the parts that it needs as
you order it, so forget about getting an extra drive sled in the box,
for instance. Perverse incentives... it's in their best interest if
the system is as un-expandable as possible.
-Thomas

On Tue, May 18, 2010 at 4:32 PM, Shei, Shing-Shong <shei@cs.indiana.edu> wrote:
> Mark,
>>  Here is an option for a server hard drive  from Dell's website just now:
>>
>>   1TB 7.2K RPM SATA 3Gbps 3.5-in Cabled Hard Drive [$449.00]
>>
>>  From Newegg:
>>
>>   Western Digital RE3 WD1002FBYS 1TB 7200 RPM SATA Drive - $159.99
>
> What's the URL you got from Dell?  Looks like it's more than bare bone drive
> (since it's "cabled hard drive.")  I just went to Dell and here are some
> sample URLs:
>
> 1) 1TB 7200 RPM Hot Swappable Serial ATA II Hard Drive for Dell PowerEdge 2900 Server
>   for $148.99 (with tray).
> http://accessories.us.dell.com/sna/products/System_Drives/productdetail.aspx?c=us&l=en&cs=19&sku=341-5895
>
> 2) 1TB 7200 RPM Serial ATA Hard Drive for Dell Vostro 220/ 430 / Studio XPS 8000 Desktop
>   for $120.99
>
> http://accessories.us.dell.com/sna/products/System_Drives/productdetail.aspx?c=us&l=en&cs=19&sku=341-8259
>
> 3) 1TB Caviar Blue SATA 3 Internal Hard Drive for $83.99
>
> http://accessories.us.dell.com/sna/products/System_Drives/productdetail.aspx?c=us&l=en&cs=19&sku=A3677038
>
> Thanks,
> Shing-Shong
> _______________________________________________
> BLUG mailing list
> BLUG@linuxfan.com
> http://mailman.cs.indiana.edu/mailman/listinfo/blug
>

--
http://resc.smugmug.com/

_______________________________________________
BLUG mailing list
BLUG@linuxfan.com
http://mailman.cs.indiana.edu/mailman/listinfo/blug

Re: [BLUG] new big computer for a lab

Mark,
> Here is an option for a server hard drive from Dell's website just now:
>
> 1TB 7.2K RPM SATA 3Gbps 3.5-in Cabled Hard Drive [$449.00]
>
> From Newegg:
>
> Western Digital RE3 WD1002FBYS 1TB 7200 RPM SATA Drive - $159.99

What's the URL you got from Dell? Looks like it's more than bare bone drive
(since it's "cabled hard drive.") I just went to Dell and here are some
sample URLs:

1) 1TB 7200 RPM Hot Swappable Serial ATA II Hard Drive for Dell PowerEdge 2900 Server
for $148.99 (with tray).
http://accessories.us.dell.com/sna/products/System_Drives/productdetail.aspx?c=us&l=en&cs=19&sku=341-5895

2) 1TB 7200 RPM Serial ATA Hard Drive for Dell Vostro 220/ 430 / Studio XPS 8000 Desktop
for $120.99

http://accessories.us.dell.com/sna/products/System_Drives/productdetail.aspx?c=us&l=en&cs=19&sku=341-8259

3) 1TB Caviar Blue SATA 3 Internal Hard Drive for $83.99

http://accessories.us.dell.com/sna/products/System_Drives/productdetail.aspx?c=us&l=en&cs=19&sku=A3677038

Thanks,
Shing-Shong
_______________________________________________
BLUG mailing list
BLUG@linuxfan.com
http://mailman.cs.indiana.edu/mailman/listinfo/blug

Re: [BLUG] new big computer for a lab

There is one important aspect to buying drives off of newegg for a
server: if the replacement drives have fewer sectors than the original
drives in the array they won't work. Since hard drive vendors play it
pretty loose with how they define capacity, its kind of a crap shoot.

Apple bit me on that one -- the replacement 80G drive for the system
disk mirror was about 2M smaller than the original drive so I had to
rebuild the mirror by hand. One drive was a Maxtor and the other was a
Seagate. I wouldn't be surprised if different models of 80G drives from
the same manufacturer would have different sector counts.

All of our servers are IBM (except for that stupid Mac) and when you get
a replacement drive from them its the exact same drive. We had some
older pSeries machines (one was 9 years old) and the replacement drives
were IBM refurbs of the original drives.

Brian

On Tue, 2010-05-18 at 16:14 -0400, Simón Ruiz wrote:
> On Tue, May 18, 2010 at 10:13 AM, Mark Krenz <mark@slugbug.org> wrote:
> > Here is an option for a server hard drive from Dell's website just now:
> >
> > 1TB 7.2K RPM SATA 3Gbps 3.5-in Cabled Hard Drive [$449.00]
> >
> > From Newegg:
> >
> > Western Digital RE3 WD1002FBYS 1TB 7200 RPM SATA Drive - $159.99
> >
> > So with 12 drives that's $3480 overpaid.
> >
> >
> >
> > --
> > Mark Krenz
> > Bloomington Linux Users Group
> > http://www.bloomingtonlinux.org/
> > _______________________________________________
> > BLUG mailing list
> > BLUG@linuxfan.com
> > http://mailman.cs.indiana.edu/mailman/listinfo/blug
> >
>
> You hit the biggest problem/easiest fix on the nose.
>
> We got a great deal from Dell on some file servers and RAID enclosures.
>
> It was the end of the quarter, and the salesperson seemed to be
> working towards a quota or something, because we got an awesome price
> on the whole shebang.
>
> When we went *back* (when the time pressure was off) to ask them for
> an extra couple of SATA hard disks for it (we also needed these
> caddies/sleds to slide the disks in right;they only give you exactly
> enough, which I think is their form of "DRM" to get you to go buy
> everything from them). They pointed to prices like those and I just
> laughed. I pointed out that I could easily buy the equipment I wanted
> from elsewhere for more than 75% off their price, and the salesperson
> observed that such hard disks would not be covered by Dell tech
> support.
>
> I pointed out that I've never asked for tech support on "Dell hard
> drives", and that if I bought twice the number of hard drives so I had
> an entire set of drives on hand to swap out I'd still be paying less
> than half what Dell wanted; that the economics of the situation
> demanded Dell lower their price if they expected us to take them
> seriously.
>
> There was absolutely no reply to that, so I went on eBay for the right
> caddies, and bought the SATA drives from NewEgg.
>
> I've yet to regret it.
>
> Simón
>
> _______________________________________________
> BLUG mailing list
> BLUG@linuxfan.com
> http://mailman.cs.indiana.edu/mailman/listinfo/blug


_______________________________________________
BLUG mailing list
BLUG@linuxfan.com
http://mailman.cs.indiana.edu/mailman/listinfo/blug

Re: [BLUG] new big computer for a lab

On Tue, May 18, 2010 at 10:13 AM, Mark Krenz <mark@slugbug.org> wrote:
>  Here is an option for a server hard drive  from Dell's website just now:
>
>  1TB 7.2K RPM SATA 3Gbps 3.5-in Cabled Hard Drive [$449.00]
>
>  From Newegg:
>
>  Western Digital RE3 WD1002FBYS 1TB 7200 RPM SATA Drive - $159.99
>
> So with 12 drives that's $3480 overpaid.
>
>
>
> --
> Mark Krenz
> Bloomington Linux Users Group
> http://www.bloomingtonlinux.org/
> _______________________________________________
> BLUG mailing list
> BLUG@linuxfan.com
> http://mailman.cs.indiana.edu/mailman/listinfo/blug
>

You hit the biggest problem/easiest fix on the nose.

We got a great deal from Dell on some file servers and RAID enclosures.

It was the end of the quarter, and the salesperson seemed to be
working towards a quota or something, because we got an awesome price
on the whole shebang.

When we went *back* (when the time pressure was off) to ask them for
an extra couple of SATA hard disks for it (we also needed these
caddies/sleds to slide the disks in right;they only give you exactly
enough, which I think is their form of "DRM" to get you to go buy
everything from them). They pointed to prices like those and I just
laughed. I pointed out that I could easily buy the equipment I wanted
from elsewhere for more than 75% off their price, and the salesperson
observed that such hard disks would not be covered by Dell tech
support.

I pointed out that I've never asked for tech support on "Dell hard
drives", and that if I bought twice the number of hard drives so I had
an entire set of drives on hand to swap out I'd still be paying less
than half what Dell wanted; that the economics of the situation
demanded Dell lower their price if they expected us to take them
seriously.

There was absolutely no reply to that, so I went on eBay for the right
caddies, and bought the SATA drives from NewEgg.

I've yet to regret it.

Simón

_______________________________________________
BLUG mailing list
BLUG@linuxfan.com
http://mailman.cs.indiana.edu/mailman/listinfo/blug

Re: [BLUG] new big computer for a lab

Hiya,

I run the computer infrastructure for a psychology lab at IU, and am
actually struggling with related questions right now. But anyway, my
observations are:

Having as many processors/cores available as possible is great. If 4
to 10 people are going to use the server at the same time, this lets
more of them get their work done at once. Right before a paper
deadline, I've seen 3 or 4 people running several MATLAB processes
each, at the same time, and it's great to have the capacity for this.
Of course, our system is really underutilized when that's not
happening, which I guess is an attraction of cloud computing...

We're just starting to run into some difficulties with getting enough
storage space available. If your dataset is going to expand, and of
course it is, it probably makes sense to have some sort of external
disk drive chassis, which connects to your server through iSCSI, SAS,
or something. Many of these systems will allow you to add storage to
your server without any downtime---just stick another terabyte into a
free drive bay. Unfortunately, there are a multitude of ways to do
this, and it seems to be very difficult to figure out using only the
internet. I think I need to consult with an actual expert before I'll
be able to recommend something to my boss.

Are all your users going to be collaborating on the same dataset? If
so, I'd recommend that you keep incremental backups, or better yet use
some kind of version control (svn or git would be best, hg doesn't
handle large files well). We've had a lot of problems with the
granularity of our permissions being too gross, and not being able to
track changes, on account of lacking a real version control system.

> Agreed as well, RAID is not a substitute for backups.  Although a
> question for the group: how to people do backups these days on large
> (multi-TB) data sets?  I assume to hard drive somehow, but when you're
> talking about 10-20TB, that's not necessarily very easy, especially if
> you want to take those backups off-site.
This is not very useful for most people, but I've been using IU's MDSS
--- http://uits.iu.edu/page/aiyi --- for backup storage. It has 4.2
petabytes of storage, on a tape robot system with a hard-drive-based
cache. It has 2 nodes, located in Bloomington and Indy, so it seems
very secure. And it's free for IU researchers. Yay!

I think that other people are using cloud-based storage. For
instance, Amazon S3 charges something like $0.10 / GB to transfer
data, then $0.10/GB/month for storage. So that's about $100/tb per
month for storage and another $100 for transfer. Hmm. That's sort of
expensive, but there are services that will manage this for you (Mozy,
ZManda).

Maybe you could find someone who will swap a few rack units of
colocation space with you, and back up to disk servers on each other's
networks?

Um, I guess I've talked a lot. Good luck, Ignasi! Do you have a set
date that you're leaving for Spain? Have you gone already?
-Thomas


>
> At a former job, I once had the pleasure of being able to buy a server
> from these folks:
>
> http://www.asaservers.com
>
> Very nice machine, at am impressive price.  I didn't stay at the job
> long enough to play with it all that much, but I wish I had...  I
> doubt that you'll want to buy from them if the machine is going to
> Spain, but it could give you an idea of what you can get for the
> money.  Of course, you could check Dell, etc., too.
>
> How do people feel about multi-processor machines?  I know little
> about them, but if you've got a big budget to buy a fast machine, I'd
> think that it'd be something you'd consider.
>
> David
>
>
> On Mon, May 17, 2010 at 07:13:57PM -0400, Jeremy L. Gaddis wrote:
>>On Mon, May 17, 2010 at 11:52 AM, Ignasi <ignasilucas@gmail.com> wrote:
>>> I expect between 4 and 10 people to use it at the same time. Most jobs will
>>> be CPU intensive, but I can also envision some sporadic jobs to require
>>> several GB of RAM. He also wants to store quite a bit of data there, and
>>> maybe host a database. I assume that nobody would use it as a desktop, but
>>> it would be accessed remotely. In principle, the main concern is to make it
>>> a fast computer.
>>
>>Have you considered the potential benefits of a number of smaller servers
>>instead of a single large server?  I'm not familiar with exactly what you're
>>doing, but it be worth investigating.
>>
>>> I've read a little bit about RAID arrays, but never met anybody who used
>>> them. I'm interested in those configurations where data is mirrored, so that
>>> the system can tolerate the failure of one of the disks. And I've been
>>> warned that if all the disks composing the array are of the same brand and
>>> design, more than one may fail at the same time. Do you think RAID is worthy
>>> at all, or not necessary with a good back up system? what is better, an
>>> operating system RAID controller, or a hardware one?
>>
>>If the data is considered important, RAID is a must.  The data on my home
>>servers isn't critical and no financial meltdown will occur if I lose
>>it, but it's
>>important enough to me that I use RAID at home.
>>
>>Steven mentioned hot spares.  I'm also a big fan of hot spares, as the
>>failed drive
>>is automatically replaced by another (hopefully good!) drive and
>>rebuilding begins
>>(almost) immediately.  Without a hot spare, someone must physically
>>pull the failed
>>drive and replace it before rebuilding of the array will begin.
>>During that time, if
>>another drive happens to fails, you will (typically) lose data -- this
>>is dependent on
>>what type of RAID you're using, however.
>>
>>Also, and I can't stress this enough:  RAID IS NOT A SUBSTITUTE FOR BACKUPS.
>>
>>As I said, if a drive in a RAID array fails, you can pull the dead
>>drive and replace it
>>without (online) losing any data.  Heck, I've done just that less than
>>an hour ago.
>>If, however, your data becomes corrupted/accidentally deleted/etc., RAID is not
>>going to help you out a bit, and you're going to wish you had those backups.
>>
>>--
>>Jeremy L. Gaddis
>>http://evilrouters.net/
>>_______________________________________________
>>BLUG mailing list
>>BLUG@linuxfan.com
>>http://mailman.cs.indiana.edu/mailman/listinfo/blug
> _______________________________________________
> BLUG mailing list
> BLUG@linuxfan.com
> http://mailman.cs.indiana.edu/mailman/listinfo/blug
>

--
http://resc.smugmug.com/

_______________________________________________
BLUG mailing list
BLUG@linuxfan.com
http://mailman.cs.indiana.edu/mailman/listinfo/blug

Re: [BLUG] new big computer for a lab

On Tue, May 18, 2010 at 01:54:04PM GMT, Josh Goodman [jogoodman@gmail.com] said the following:
>
> My experience with Dell has been the opposite. Yes, Dell does sometimes overcharge but it depends
> entirely on what systems you are spec'ing, the entity doing the purchasing (company, university,
> self, etc...), and any contracts your company or university already has with them. I just completed
> a bid process a couple of weeks ago for a 12 TB 16 core server and Dell was very competitive with
> Supermicro. I've heard the same thing about Dell's competitive pricing from colleagues at other
> institutions as well. I'm not trying to push Dell over other options, but I think it is a mistake
> to exclude them from the start.

You probably got good pricing being in a large enterprise situation,
but someone who is just starting out is not likely to get good pricing.
I work at a large company during the day that gets large discounts from
Dell because they buy a lot of equipment from them, but at Suso I barely
got a discount at all from them and they were always much more expensive
than the equivilent Supermicro system. Especially higher end systems
with more redundancy, more RAM, more drives, etc. And for something
like a 12TB 16 core server you are likely to get really ripped off.

Here is an option for a server hard drive from Dell's website just now:

1TB 7.2K RPM SATA 3Gbps 3.5-in Cabled Hard Drive [$449.00]

From Newegg:

Western Digital RE3 WD1002FBYS 1TB 7200 RPM SATA Drive - $159.99

So with 12 drives that's $3480 overpaid.

--
Mark Krenz
Bloomington Linux Users Group
http://www.bloomingtonlinux.org/
_______________________________________________
BLUG mailing list
BLUG@linuxfan.com
http://mailman.cs.indiana.edu/mailman/listinfo/blug

Re: [BLUG] new big computer for a lab

My experience with Dell has been the opposite. Yes, Dell does sometimes overcharge but it depends
entirely on what systems you are spec'ing, the entity doing the purchasing (company, university,
self, etc...), and any contracts your company or university already has with them. I just completed
a bid process a couple of weeks ago for a 12 TB 16 core server and Dell was very competitive with
Supermicro. I've heard the same thing about Dell's competitive pricing from colleagues at other
institutions as well. I'm not trying to push Dell over other options, but I think it is a mistake
to exclude them from the start.

In short, get lots of bids (including ones you think might be too expensive), look them all over,
and go with the best bang for your buck (euro).

Josh

On 05/18/2010 08:46 AM, Mark Krenz wrote:
> On Tue, May 18, 2010 at 12:24:30PM GMT, David Ernst [david.ernst@davidernst.net] said the following:
>>
>> At a former job, I once had the pleasure of being able to buy a server
>> from these folks:
>>
>> http://www.asaservers.com
>>
>> Very nice machine, at am impressive price. I didn't stay at the job
>
>
> Yes, those are decent prices for them putting it together for you.
> Definate a lot better than Dell. What ASA is doing here is taking
> Supermicro barebones servers (which is a brand I highly recommend) and
> helping you add in the parts to complete the whole server.
>
> At Suso I buy the parts seperately and put it together myself, which
> is cheaper, but requires that I do my research and make sure I have the
> right parts. So its time vs. money.
>
> But ASA seems to be much more competitive pricewise than other
> companies I've seen who do the same thing.
>
> I can't recommend enough to stay away from Dell. They have nice
> servers, but they grossly overcharge.
>
_______________________________________________
BLUG mailing list
BLUG@linuxfan.com
http://mailman.cs.indiana.edu/mailman/listinfo/blug

Re: [BLUG] new big computer for a lab

On Tue, May 18, 2010 at 12:24:30PM GMT, David Ernst [david.ernst@davidernst.net] said the following:
>
> At a former job, I once had the pleasure of being able to buy a server
> from these folks:
>
> http://www.asaservers.com
>
> Very nice machine, at am impressive price. I didn't stay at the job


Yes, those are decent prices for them putting it together for you.
Definate a lot better than Dell. What ASA is doing here is taking
Supermicro barebones servers (which is a brand I highly recommend) and
helping you add in the parts to complete the whole server.

At Suso I buy the parts seperately and put it together myself, which
is cheaper, but requires that I do my research and make sure I have the
right parts. So its time vs. money.

But ASA seems to be much more competitive pricewise than other
companies I've seen who do the same thing.

I can't recommend enough to stay away from Dell. They have nice
servers, but they grossly overcharge.

--
Mark Krenz
Bloomington Linux Users Group
http://www.bloomingtonlinux.org/
_______________________________________________
BLUG mailing list
BLUG@linuxfan.com
http://mailman.cs.indiana.edu/mailman/listinfo/blug

Re: [BLUG] new big computer for a lab

Just to chime in here...

Agreed, RAID is awesome. If your budget can support it -- and,
Ignasi, yours certainly can -- you should totally do it, unless your
machine is basically a thin client, which obviously isn't the case
here.

Agreed as well, RAID is not a substitute for backups. Although a
question for the group: how to people do backups these days on large
(multi-TB) data sets? I assume to hard drive somehow, but when you're
talking about 10-20TB, that's not necessarily very easy, especially if
you want to take those backups off-site.

At a former job, I once had the pleasure of being able to buy a server
from these folks:

http://www.asaservers.com

Very nice machine, at am impressive price. I didn't stay at the job
long enough to play with it all that much, but I wish I had... I
doubt that you'll want to buy from them if the machine is going to
Spain, but it could give you an idea of what you can get for the
money. Of course, you could check Dell, etc., too.

How do people feel about multi-processor machines? I know little
about them, but if you've got a big budget to buy a fast machine, I'd
think that it'd be something you'd consider.

David


On Mon, May 17, 2010 at 07:13:57PM -0400, Jeremy L. Gaddis wrote:
>On Mon, May 17, 2010 at 11:52 AM, Ignasi <ignasilucas@gmail.com> wrote:
>> I expect between 4 and 10 people to use it at the same time. Most jobs will
>> be CPU intensive, but I can also envision some sporadic jobs to require
>> several GB of RAM. He also wants to store quite a bit of data there, and
>> maybe host a database. I assume that nobody would use it as a desktop, but
>> it would be accessed remotely. In principle, the main concern is to make it
>> a fast computer.
>
>Have you considered the potential benefits of a number of smaller servers
>instead of a single large server? I'm not familiar with exactly what you're
>doing, but it be worth investigating.
>
>> I've read a little bit about RAID arrays, but never met anybody who used
>> them. I'm interested in those configurations where data is mirrored, so that
>> the system can tolerate the failure of one of the disks. And I've been
>> warned that if all the disks composing the array are of the same brand and
>> design, more than one may fail at the same time. Do you think RAID is worthy
>> at all, or not necessary with a good back up system? what is better, an
>> operating system RAID controller, or a hardware one?
>
>If the data is considered important, RAID is a must. The data on my home
>servers isn't critical and no financial meltdown will occur if I lose
>it, but it's
>important enough to me that I use RAID at home.
>
>Steven mentioned hot spares. I'm also a big fan of hot spares, as the
>failed drive
>is automatically replaced by another (hopefully good!) drive and
>rebuilding begins
>(almost) immediately. Without a hot spare, someone must physically
>pull the failed
>drive and replace it before rebuilding of the array will begin.
>During that time, if
>another drive happens to fails, you will (typically) lose data -- this
>is dependent on
>what type of RAID you're using, however.
>
>Also, and I can't stress this enough: RAID IS NOT A SUBSTITUTE FOR BACKUPS.
>
>As I said, if a drive in a RAID array fails, you can pull the dead
>drive and replace it
>without (online) losing any data. Heck, I've done just that less than
>an hour ago.
>If, however, your data becomes corrupted/accidentally deleted/etc., RAID is not
>going to help you out a bit, and you're going to wish you had those backups.
>
>--
>Jeremy L. Gaddis
>http://evilrouters.net/
>_______________________________________________
>BLUG mailing list
>BLUG@linuxfan.com
>http://mailman.cs.indiana.edu/mailman/listinfo/blug
_______________________________________________
BLUG mailing list
BLUG@linuxfan.com
http://mailman.cs.indiana.edu/mailman/listinfo/blug