Princeton S* Network Systems

The CS community recently discussed extending the Q&A session that occurs after each talk at a conference into a more formal written Q&A.  More specifically, this was raised during the business meeting at SOSP and the proposal was to publish the results in SIGOPS OSR.  The idea was this written extension to Q&A could really get to the bottom of the issues raised, and it wouldn’t let speakers avoid questions by saying, “Let’s take that offline.”  There was some push back against this with arguments like “most questions are just misunderstandings” and “that will add a lot of pointless work … Continue Reading

I recently attended OSDI 2010 where I sat through about 30 presentations on systems-related topics. I was surprised that there were so many occurrences of things that I think should be avoided when giving a presentation.

In this post, I’m going to outline several things that, in my opinion, you should avoid when giving a talk at a conference. Keep in mind that this is just my opinion and you’re welcome to disagree, but I think you’re wrong and I’ll explain why.

Note that the examples below are all taken from the OSDI slides that were posted after the conference. If … Continue Reading

I’m back in Princeton after spending the week in Indianapolis, Indiana for the first ACM Symposium on Cloud Computing (SOCC 2010). I’m posting here with a brief summary of each talk from Day 2 of the conference as well as some of my thoughts. These are my reactions to the presentations only, as I haven’t read most of the papers.

[See my previous post for Day 1]

Keynote 2

Building Facebook: Performance at Massive Scale
Jason Sobel (Facebook)

Jason gave a great presentation about the architecture at Facebook and some of the lessons their engineering team has learned in the last several … Continue Reading

I’m currently in Indianapolis, Indiana for the first ACM Symposium on Cloud Computing (SOCC 2010). I’m posting here with a brief summary of each talk at the conference as well as some of my thoughts. These are my reactions to the presentations only, as I haven’t read most of the papers.

[See my next post for Day 2

Keynote 1

[Note: My SIGMOD paper was being presented opposite the first keynote, so Steve Ko who is also at the conference wrote this first summary.]

Evolution and Future Directions of Large-Scale Storage and Computation Systems at Google
Jeffrey Dean (Google)

Jeff … Continue Reading

Oct 2009 issue of the SIGCOMM CCR has an editorial by Kentaro Toyama and me where we ask the question if technologies for developing regions be considered a core area of computer science research? It is relatively easy to argue that technology can help improve the lives of the poorest billion people on the planet. But, is it research? More specifically, is it computer science research? This editorial stems out of our discussions at the CCC Workshop on Global Development. Keshav asked us to merge our, somewhat opposing, views into an editorial. You can read it here. … Continue Reading

Together with Arvind Krishnamurthy, I’ll be chairing this year’s International Workshop on Peer-to-Peer Systems (IPTPS).  The workshop was started in 2002, which coincided both with the popularization of P2P file sharing (Napster, KaZaA) and the introduction of distributed hash tables (DHTs) from several different research groups.

Eight years later, P2P file sharing is still going strong (now through BitTorrent), while the previously-academic DHTs have found their way into real use.  DHTs now form the decentralized lookup structures for file sharing services—in the form of so-called “trackerless” BitTorrent—with the DHT in the Vuze service comprising more than a million concurrent users.  (As an aside, I’m proud to note that Vuze’s DHT is based on Kademlia, which was proposed by one of my officemates in grad school, Petar Maymounkov.)

These self-organizing systems have also found their way into the datacenter.  One notable example is the storage system, Dynamo, that forms the basis for Amazon’s shopping cart and other back-end  applications.  Or Facebook’s Cassandra, used for its Inbox search.  Or the rest of the key-value stores that do automated partitioning.  And we are starting to see these techniques being proposed for scaling enterprise networks as well.  With that in mind, we wanted to broaden the scope of this year’s IPTPS to include topics relating to self-organizing and self-managing distributed systems, even those running in single administrative domains.

We also plan to have a demo session at this year’s IPTPS to highlight developed and deployed systems.  The workshop will be collocated with NSDI in San Jose, so will be especially convenient for those in the Bay Area.  We welcome submissions (both paper and demos) from researchers, developers, and hackers.  If you don’t want to write a paper, come show off your running P2P system.

Paper submissions are due Friday, December 18, 2009.  More information can be found at http://www.usenix.org/event/iptps10/cfp/.

Continue Reading

We’ve recently been working hard on Firecoral – a browser-based, peer-to-peer content distribution network for web caching. I’ll be presenting a short talk on Firecoral at the 8th International Workshop on Peer-to-Peer Systems (IPTPS) on April 21st in Boston, MA.

Peer-to-peer content distribution has been inarguably successful for large file distribution (e.g. BitTorrent), but P2P services have been restricted to stand-alone applications, not transparently incorporated into Web browsing and seamlessly running over HTTP. CoralCDN has served as a web content distribution network for the past five years, but its deployment has been limited to PlanetLab and demand quickly … Continue Reading

The call for papers for the 3rd Workshop on Networked Systems for Developing Regions (NSDR) was announced today. NSDR 2009 will be held with ACM SOSP this year at Big Sky, Montana. Direct all whining about the location to the SOSP organizers please!

I thought I’d share a little history of NSDR on this blog. Research in technologies for developing regions has been going on for a while. For example, the TIER group at Berkeley started in 2003. However, this area (often dubbed as ICTD) lacked a sense of community with no specialized workshops/conferences.

In 2006, I was attending SenSys at … Continue Reading