Search
Jay Kreps

SE Radio 162: Project Voldemort with Jay Kreps

Recording Venue: QCon
Guest(s): Jay Kreps
Host(s): Robert
Jay Kreps talks about the open source data store Project Voldemort. Voldemort is a distributed key-value store used by LinkedIn and other high-traffic web sites to overcome the inherent scalability limitations of a relational database. The conversation delves into the workings of a Voldemort cluster, the type of consistency guarantees that can be made in a distributed database, and the tradeoff between client and the server.


Show Notes

Links:

Join the discussion
9 comments
  • Hi guys, I think there’s a problem with the download:

    wget http://media.libsyn.com/media/seradio/seradio-episode162-projectVoldemort.mp3
    –2010-05-23 20:36:41– http://media.libsyn.com/media/seradio/seradio-episode162-projectVoldemort.mp3
    Resolving media.libsyn.com… 38.100.193.81, 205.234.249.196
    Connecting to media.libsyn.com|38.100.193.81|:80… connected.
    HTTP request sent, awaiting response… 500 Internal Server Error
    2010-05-23 20:36:41 ERROR 500: Internal Server Error.

  • Very interessting topic since I have to do a seminar on a related topic (cloud databases). The interviewer asked the right questions. If the sound quality would be a bit better, it would much more pleasure to listen.
    What about a flattr button for this page? I would definitly click on it.

  • Is there a reason (I assume it is) why you called it “Project Voldemort”?

  • I have to say that the interviewer did an extraordinary job. The episode was content-dense because the interviewer had really prepared, and kept things going with good, solid questions.

  • The answer is at the end of a blog post by the guest: http://blog.linkedin.com/2009/04/01/project-voldemort-part-ii-how-it-works/

    Picking A Name

    I should probably also mention how it got its name, since that is something I got a lot of questions about. I wanted to come up with a name that was distinctive and a little self-deprecating (projects shouldn’t take themselves too seriously). At the time I was reading the last Harry Potter book, and Voldemort had split himself into many pieces each of which had to be destroyed to kill him. I thought, “that sounds like a distributed system”. I don’t know whether it is nerdier to be reading Harry Potter or to be wondering what kind of consistency protocol Voldemort uses when keeping all his pieces up-to-date, but regardless, the name stuck.

  • I second the praise for Robert Blumen’s interviews. Some of the other SE-Radio stuff can be a bit cringeworthy – the interviewer often seems more interested in expressing his own opinions than those of the interviewees. Robert does a great job of keeping it interesting – both the Voldemort and the Spring AOP interviews I heard so far from him were excellent. Keep up the good work!

  • […] Episode 162: Project Voldemort with Jay Kreps Recording Venue: QCon Guest(s): Jay Kreps Host(s): Robert Jay Kreps talks about the open source data store Project Voldemort. Voldemort is a distributed key-value store used by LinkedIn and other high-traffic web sites to overcome the inherent scalability limitations of a relational database. The conversation delves into the workings of a Voldemort cluster, the type of consistency guarantees that can be made in a distributed database, and the tradeoff between client and the server. – Project Voldemort – Jay Kreps presentation at QCon San Francisco 2009 – Google mailing list for Project Voldemort – Project Voldmort on github – LinkedIn blog entry on Project Voldemort – Amazon’s paper on Dynamo – NoSQL hub – Google mailing list for NoSQL http://www.se-radio.net/2010/05/episode-162-project-voldemort-with-jay-kreps/ […]

More from this show