Raspberry Pi server clusters

Clustering was my plan as well, though I have zero experience in such.　It'll be a fun project for sure!

Yep, that mirrors my thoughts on the topic too, Richard.  Sticking the Pi into a bespoke plugin module is almost mandatory if one is going to use several, as hardwiring them together directly would be very unsatisfactory for a whole pile of reasons.  Designing a module with a little internal loom and replicating it is much more attractive.

And you mentioned LEDs .... No self-respecting project should ever skimp on LEDs, we need loads!!!!!

Morg.

In yesterday's webinar, Eben talks about clusters, at 56:25. 

He recommends that for building a cheap supercomputer,

you would be better off using x86 hardware (which is something

he has mentioned before).

What Eben said is quite right.  ARM isn't the world's fastest architecture, and within the ARM stable, the Pi's 700Mhz ARM1176JZF-S isn't going to win any speed races, so if one's goal is to build a supercomputer then to use a pile of Rpi boards would not be very effective.

But there are many more reasons for building clusters than just supercomputing.

One very common one is to run some types of Internet services which use little computing power per session but require multiple sessions to cater for a useful number of simultaneous Internet users.  For that, a cluster of multiple Rpi boards could be very effective if the application fits the constraints of a single Rpi well.

Also, ARM can beat most other processor families in performance per watt, so a cluster of Pi boards might well be able to hit a particular desired level of performance without requiring as much electrical power as say an Intel system.

Another application of clusters that isn't supercomputing is High Availability or resilient computing.  If your server cluster provides a number of independent hardware nodes and a heartbeat mechanism then graceful degradation can be achieved, reducing the overall system performance only slightly when one board dies.  This can be important even for home sites, allowing you to provide an effective Internet presence without losing sleep through midnight alerts, and being able to relax when on holiday.  Who knew, ARM clusters have social benefits.

And finally, actual applications aside, some people like myself want to work with clusters for the simple reason that, despite this being officially the age of multicore, concurrent software still hasn't really caught up with the multicore hardware that's been appearing for several years now.  Concurrency is still a research area even today some decades after I did my PhD in the subject, so I'd like to continue exploring the topic a bit more, and multiple Rpis would provide a perfectly suitable platform without breaking the bank.

And I'm sure that there are plenty of other good reasons for clustering Rpis as well, outside of supercomputing.

Morgaine.

Hi,

The idea of an ARM-based cluster is very interesting. I see a good applicationfield for for example SIP-based telephone systems. Scalability and high availability are here very important. Just as lower energy consumption.

Had not reflection of a value, a look at Q-Seven standard for example with this solution.

http://www.campro-cctv.com/products/13.Embeded/htm/Camera_01-0001.php

This board with Freescale ARM SoC has for 70 $ , PCI, Ethernet and everything that would be necessary for a cluster (imo).

And is available

And for more power freunds : http://www.iwavesystems.com/?q=node/239

The Q7 architecture has some advantages in my opinion, firstly for the development of the cluster and for the future for the use of other, more powerful modules.

Sorry for my poor English.

Zbig

I don't know the Q7 standard, but I do have some passive backplane PICMG rack units with dual redundant PSUs, and it did occur to me that filling their slots with ARM boards would be quite interesting and very low power.  Four Rpi mounted as daughterboards  on a carrier PCB that just takes power from a PICMG slot seems quite viable, and I have up to 20 slots available.

Hi Morgaine,

The people at the University of Munich have built and tested a cluster with ARM boards :http://www.nm.ifi.lmu.de/projects/ATV2CLUSTER/.

After doing this: http://www.mnm-team.org/projects/ATV2CLUSTER/atvcluster.pdf have read, I do not see a usable  solution for a cluster with 100MB Ethernet on an ARM board. Thereafter is a 1Gb Ethernet necessary for a reasonable load distribution.

BTW: Do you have any documentation about this PICMG backplane that you have ?.

Regards

Zbig

Thanks Zbig, those were interesting links.

I suspect that your comment about gigabit Ethernet is mostly with a view to using ARM nodes for HPC, which is not a very effective thing to do at the present level of ARM technology.  I certainly wouldn't consider using the Rpi for a supercomputing cluster, since its ARM core is rather slow and its GPU is not available for OpenCL tasks.  The result would be very poor.

But as I wrote earlier in this thread in answer to coder27, there are several good reasons for clustering ARM devices other than for performance, and that's my area of interest, not for HPC.

Re PICMG gear, my units are all from Advantech -- http://www.advantech.com/ , and their passive backplanes are here --http://www.advantech.com/products/Passive-Backplanes/sub_1-2JKOGC.aspx .  But there are tons of other players in the industrial computing sector offering similar systems (PICMG is a very long lived standard) -- Portwell, Peak, and Nexcom are other well known names that come to mind.

Morgaine.

Hello sir,

I'm an Undergrad who is interested in cluster computing and parallel computing and i would like to do this as my final year project to analyze signals and do some VLSI based simulations. I would like to know how you are going to deal with raspberry pi's architechture because it has fairly less limitations in terms of horse power when you compare to the A9 processor in Apple TV which LMU Scientists used to construct a cluster.

Thank you,

Kishore Kumar

@freads: Clustering Pi boards for High Performance Computing (HPC) is not an effective use of the Pi.  I wrote about this at more length earlier in this thread, article #14.  What's more, Eben Upton said the same thing in the recent Element 14 webinar.

My clustering requirements are not for HPC (as I explained before), but it sounds like yours are, since signal analysis and VLSI simulation are very demanding applications.  What's more, you will be quite likely to hit your head against the Pi's limited amount of memory in your application.

On the face of it then, I would guess that you may be misapplying the Pi.

Morgaine.