Re: [Beowulf] Docker in HPC

-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 On 27/11/13 23:01, Peter Clapham wrote: > In the bio-informatics arena the local software half life is > approximately 6-12 months. I feel your pain.. > This, along with the wide range of applications in use rapidly > creates an environment where u

Re: [Beowulf] Admin action request

-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 On 28/11/13 07:04, Prentice Bisbal wrote: > On 11/27/2013 12:48 AM, Christopher Samuel wrote: > >> On 26/11/13 07:53, Andrew Holway wrote: >> >>> Its been awfully quiet around here since Vincent Diepeveen was >>> kicked >> >> To clarify: he w

Re: [Beowulf] raspberri pi or similar hard ware cluster

-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 On 27/11/13 11:53, Adam DeConinck wrote: > SDSC also had a 12-node cluster at SC13, running a display wall where > they had a Tron Lightcycles tournament going. Very fun if you got to > check it out. :) I think it was at least 15 nodes (at least that

Re: [Beowulf] Admin action request

-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 On 28/11/13 01:52, Peter St. John wrote: > Well I'm sorry but Christopher I think just "unacceptable" is > facile. This list is about HPC and Beowulf systems, it's not for arguing and attacks. I have no problem with vigorous discussion and disagreem

[Beowulf] last week of Scientific Computing Course (free Coursera course)

Last week of the course. https://class.coursera.org/scientificcomp-005/lecture/index Video Lectures Help Scientific Computing Course Overview (expanded, click to collapse) Course Overview (2:03) Subtitles (text) for Course Overview (2:03) Subtitles (srt) for Course Overview (2:03) Video (M

Re: [Beowulf] Docker in HPC

Jim, You're either an evil genius, or someone with too much free time on your hands today. I suspect it's probably a little bit of both! On 11/27/2013 08:23 AM, Lux, Jim (337C) wrote: From: John Hearns mailto:hear...@googlemail.com>> Date: Wednesday, November 27, 2013 4:35 AM To: "beowulf@be

Re: [Beowulf] SC13 wrapup, please post your own

From: "prentice.bis...@rutgers.edu" mailto:prentice.bis...@rutgers.edu>> Reply-To: "prentice.bis...@rutgers.edu" mailto:prentice.bis...@rutgers.edu>> Date: Wednesday, November 27, 2013 11:58 AM To: "beowulf@beowulf.org

Re: [Beowulf] Admin action request

On 11/27/2013 12:48 AM, Christopher Samuel wrote: > -BEGIN PGP SIGNED MESSAGE- > Hash: SHA1 > > On 26/11/13 07:53, Andrew Holway wrote: > >> Its been awfully quiet around here since Vincent Diepeveen was >> kicked > To clarify: he wasn't kicked, he unsubscribed himself. > > Thanks for

Re: [Beowulf] SC13 wrapup, please post your own

John, Since you work in F1... The guys from Intelligent Light (http://www.ilight.com/) gave a presentation at SC13 on how they helped both Red Bull F1 and Zipp wheels (http://www.zipp.com) with HPC. I think both of these examples show how easily quantifiable ROI can be in certain scenarios. I

Re: [Beowulf] immersion cooling for ASIC Bitcoin miners

On 11/26/2013 10:28 AM, Eugen Leitl wrote: > On Tue, Nov 26, 2013 at 10:22:16AM -0500, Ellis H. Wilson III wrote: > >> I have heard (a long time ago, admittedly) from little overclocking >> birdies that in poorly-designed or tightly-packed arrangements, putting >> an aquarium bubbler or some such

Re: [Beowulf] immersion cooling for ASIC Bitcoin miners

On 11/26/2013 10:22 AM, Ellis H. Wilson III wrote: > On 11/26/2013 07:22 AM, Bogdan Costescu wrote: >> One of the pics shows a bubbling liquid surface, we've seen recently >> similar pics. From what I remember from past discussions on this very >> list, the bubbles are bad for heat transfer - it's

Re: [Beowulf] Docker in HPC

Furthermore, the latest incarnation of OpenStack (Havana) has support for docker. The rate of development and industry adoption has been very impressive. Definitely something that could make an impact in HPC as well. I've been playing around with it a bit under Vagrant but no interesting result

Re: [Beowulf] SC13 wrapup, please post your own

The problem with that measuring citations is that it can take several years (sometimes decades) for a research paper to gain traction, which might be a longer time horizon that we have to show the ROI on an HPC investment. While we're at it, we could through in someone's Erdos number in see h

Re: [Beowulf] SC13 wrapup, please post your own

On 11/26/2013 09:15 AM, Lux, Jim (337C) wrote: > On 11/25/13 4:11 PM, "Adam DeConinck" wrote: > >> -BEGIN PGP SIGNED MESSAGE- >> Hash: SHA512 >> >>> 4. I went to a BoF on ROI on HPC investment. All the presentations in >>> the BoF frustrated me. Not because they were poorly done, but becau

Re: [Beowulf] immersion cooling for ASIC Bitcoin miners

On 11/26/2013 07:22 AM, Bogdan Costescu wrote: > On Tue, Nov 26, 2013 at 12:05 PM, Eugen Leitl wrote: > >> In fact, this cooling technique is of the planet most advanced. > Thanks for limiting to a snippet ! I found the article a little too > light on tech details... inexperienced reporter :) > >

Re: [Beowulf] Docker in HPC

On 27 November 2013 15:49, Peter Clapham wrote: > The enforcement of the memory limit has to date either been via wrapping > jobs on startup by the scheduler with ulimit or via a local daemon sending > a kill command when it notices that the job or job component exceeded the > initial set limits.

Re: [Beowulf] SC13 wrapup, please post your own

On 11/25/2013 07:11 PM, Adam DeConinck wrote: -BEGIN PGP SIGNED MESSAGE- Hash: SHA512 4. I went to a BoF on ROI on HPC investment. All the presentations in the BoF frustrated me. Not because they were poorly done, but because they tried to measure the value of a cluster by number of pa

Re: [Beowulf] Docker in HPC

Not at all. The restriction / affinity of jobs / process to a given core or core subset is very much in mind. Memory management is also potentially rather useful. In the case of most schedulers the memory used is obtained via a poll report. The enforcement of the memory limit has to date eithe

Re: [Beowulf] Docker in HPC

I use cpusets very successfully. I rather idly wonder if on a cluster with manycore nodes (such as we have these days) if cgroups should be used to keep the OS processes on the first core, and as Igor says let the scheduler run the applications in separate cgroups. The aim being to reduce 'OS ji

Re: [Beowulf] Docker in HPC

Hello Igor, We're on the same release stream and initially ran into some interesting memory resolution issues. The good news is that we have a pre-release patch in hand that is in testing (as we speak) if this proves to resolve the issues we ran into then I'm hopeful that the roll out will take

Re: [Beowulf] Docker in HPC

Hi Peter, we are running LSF 9.1.1.1 on one of our new clusters here at ICR. We allowed jobs sharing nodes but enabled cgroups support in LSF to perform job isolation using core and memory control. So far so good. SGE supports cgroups too but I don't know how well. Compartmentalisation is interest

Re: [Beowulf] Admin action request

Well I'm sorry but Christopher I think just "unacceptable" is facile. Are spam and copyright infringement acceptable (hypothetically)? Presumably not. Do we have an option besides unsubscribing? Do we want the rule "spam is unacceptable but talking about it is also unacceptable"? Flamewars are bad,

Re: [Beowulf] Docker in HPC

On 27/11/13 13:23, Lux, Jim (337C) wrote: From: John Hearns mailto:hear...@googlemail.com>> Date: Wednesday, November 27, 2013 4:35 AM To: "beowulf@beowulf.org " mailto:beowulf@beowulf.org>> Subject: Re: [Beowulf] Docker in HPC On 27 November 2013 12:29, Tim Cutt

Re: [Beowulf] raspberri pi or similar hard ware cluster

On 11/26/2013 07:53 PM, Adam DeConinck wrote: > -BEGIN PGP SIGNED MESSAGE- > Hash: SHA512 > >> Has anyone tried or is working on setting up a cluster using raspberri >> pi's or similar types of hardware? > > This has been done a bunch of times, and seems to be an increasingly > popular way

Re: [Beowulf] Docker in HPC

From: John Hearns mailto:hear...@googlemail.com>> Date: Wednesday, November 27, 2013 4:35 AM To: "beowulf@beowulf.org" mailto:beowulf@beowulf.org>> Subject: Re: [Beowulf] Docker in HPC On 27 November 2013 12:29, Tim Cutts mailto:t...@sanger.ac.uk>> wrote: Yes, Pete,

Re: [Beowulf] Docker in HPC

On 27 November 2013 12:29, Tim Cutts wrote: > Yes, Pete, Guy and I have been debating this stuff for some time, together > with some of our informatics coders. > Should virtualisation ever also be necessary (for example to ship ... to another site to analyse some of their data) Well why not jus

Re: [Beowulf] Docker in HPC

Yes, Pete, Guy and I have been debating this stuff for some time, together with some of our informatics coders. Should virtualisation ever also be necessary (for example to ship a software stack to another site to analyse some of their data), it's also a very small step further from Docker to t

Re: [Beowulf] Docker in HPC

On 27 November 2013 12:01, Peter Clapham wrote: > > In the bio-informatics arena the local software half life is > approximately 6-12 months. This, along with the wide range of > applications in use rapidly creates an environment where users can cross > link or pick up binaries or libraries that

Re: [Beowulf] Docker in HPC

On 27/11/13 11:45, John Hearns wrote: > Here is a Register article, which covers the same ground as Joe's post: > http://www.theregister.co.uk/2013/11/26/docker_spreads_to_more_linux_distros/ > " For instance, Docker could be used to run a database in one > container and an app server in another,

Re: [Beowulf] Docker in HPC

Here is a Register article, which covers the same ground as Joe's post: http://www.theregister.co.uk/2013/11/26/docker_spreads_to_more_linux_distros/ " For instance, Docker could be used to run a database in one container and an app server in another, and the configurable isolation properties" S

Re: [Beowulf] immersion cooling for ASIC Bitcoin miners

On Tue, Nov 26, 2013 at 4:28 PM, Eugen Leitl wrote: > This is one of 3M Fluorinerts (not at all cheap), so there is phase change > enthalpy as the liquid boils -- I presume there is a heat exchanger at the > top where it condenses, and drips down again. Indeed, this is how it should work at a mac

Re: [Beowulf] raspberri pi or similar hard ware cluster

And the Glasgow cluster uses Lego! http://raspberrypicloud.wordpress.com/blog/ ___ Beowulf mailing list, Beowulf@beowulf.org sponsored by Penguin Computing To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/lis