Comments on: Over There Vs. Over Here http://www.linux-mag.com/id/7456/ Open Source, Open Standards Sat, 05 Oct 2013 13:48:18 +0000 hourly 1 http://wordpress.org/?v=3.1 By: laytonjb http://www.linux-mag.com/id/7456/#comment-6813 laytonjb Wed, 30 Nov -0001 00:00:00 +0000 http://www.linux-mag.com/id/7456/#comment-6813 <p>Love the article! Once again a good timely insight.</p> <p>The virtualization in HPC jihad seems to be gaining steam lately. It must be grant proposal time for NSF so researchers are trying to capture all the buzz words and new concepts together for their grants :) (hey - don\'t kill me - I did the same thing for a little, but I refused to seduced by proposal writing by buzzwords). There are still a great many problems that need to be solved with virtualization before it becomes an attractive scenario for HPC. For example, in my day job, our engineering team tried to migrate a single process from a single node to a second node. It was done over GigE while the first node was performing local IO. It took about 30 minutes to migrate the process. It worked and there was no data loss, but 30 minutes? Since one of the desires of process migration is the ability to move off a node that appears to be having trouble, 30 minutes is probably too long (BTW - Garth Gibson has a great article that talks about the time between interruptions as systems get larger and larger. To reach Petscale or a larger we need so many processors that we are getting very close to the 30 minute time before we have an interruption which means the code dies).</p> <p>But to help any one looking for cool new buzz words or phrases to sling into a proposal here are some that might help:</p> <ul> <li>Cloud</li> <li>Virtual or Virtualization or Virtualized</li> <li>Accelerated</li> <li>Heterogeneous</li> <li>GPU</li> <li>Intelligent (as in Business Intelligence)</li> <li>Data-Intensive</li> <li>Cohesive (always a favorite)</li> <li>Grid (a bit overused but in combination with Cloud it\'s very powerful)</li> <li>Resilient</li> <li>\"As a Service\"</li> <li> </li> </ul> <p>Now if you use these words or phrases in conjunction with the following:</p> <ul> <li>Processors or processing</li> <li>Network (including the plural \"Network fabrics\" reall punches it up)</li> <li>Storage and/or file system</li> <li>Pick your favorite application area (e.g. chemistry, gene sequencing)</li> </ul> <p>And you have yourself a potentially heavily funded research project courtesy of NSF. My favorite story was the guy who wrote a proposal or an article that described the wheel - it either got funded or published (can\'t remember which).</p> <p>Sorry for being so cynical on a Sunday but lately I\'ve just seen too much of this and when I\'m reminded to be honest on Sundays, it\'s sometimes hard for me not to become cynical :)</p> <p>However, there are some worthwhile goals in virtualization in HPC (I think). I just think they may are really hard problems and may be even be impossible to adequately solve.</p> <p>Enjoy!</p> <p>Jeff </p> Love the article! Once again a good timely insight.

The virtualization in HPC jihad seems to be gaining steam lately. It must be grant proposal time for NSF so researchers are trying to capture all the buzz words and new concepts together for their grants :) (hey – don\’t kill me – I did the same thing for a little, but I refused to seduced by proposal writing by buzzwords). There are still a great many problems that need to be solved with virtualization before it becomes an attractive scenario for HPC. For example, in my day job, our engineering team tried to migrate a single process from a single node to a second node. It was done over GigE while the first node was performing local IO. It took about 30 minutes to migrate the process. It worked and there was no data loss, but 30 minutes? Since one of the desires of process migration is the ability to move off a node that appears to be having trouble, 30 minutes is probably too long (BTW – Garth Gibson has a great article that talks about the time between interruptions as systems get larger and larger. To reach Petscale or a larger we need so many processors that we are getting very close to the 30 minute time before we have an interruption which means the code dies).

But to help any one looking for cool new buzz words or phrases to sling into a proposal here are some that might help:

  • Cloud
  • Virtual or Virtualization or Virtualized
  • Accelerated
  • Heterogeneous
  • GPU
  • Intelligent (as in Business Intelligence)
  • Data-Intensive
  • Cohesive (always a favorite)
  • Grid (a bit overused but in combination with Cloud it\’s very powerful)
  • Resilient
  • \”As a Service\”

Now if you use these words or phrases in conjunction with the following:

  • Processors or processing
  • Network (including the plural \”Network fabrics\” reall punches it up)
  • Storage and/or file system
  • Pick your favorite application area (e.g. chemistry, gene sequencing)

And you have yourself a potentially heavily funded research project courtesy of NSF. My favorite story was the guy who wrote a proposal or an article that described the wheel – it either got funded or published (can\’t remember which).

Sorry for being so cynical on a Sunday but lately I\’ve just seen too much of this and when I\’m reminded to be honest on Sundays, it\’s sometimes hard for me not to become cynical :)

However, there are some worthwhile goals in virtualization in HPC (I think). I just think they may are really hard problems and may be even be impossible to adequately solve.

Enjoy!

Jeff

]]>