Project JSMeter: JavaScript Performance Analysis in the Real World

Sign in to queue

The Discussion

  • User profile image
    ShinNoNoir

    I watched this two weeks ago and skimmed the paper. Now I have this question: Have you studied the number of (simultaneous) XmlHttpRequests most web apps make?

  • User profile image
    Charles

    I just FW'd it to the two Bens.

    C

  • User profile image
    BenZorn

    Thanks for the question.  We did not measure the number of simultaneous XmlHttpRequests in our current study, although that's an interesting question.   There are a number of additional measures like that including the ways the typical WebApps interact with the DOM that we are also interesting in knowing.  While we do not have concrete plans right now for collecting such data, if we do get it, we'll make it available from our project website.

  • User profile image
    ShinNoNoir

    Thank you for your time answering my question. Smiley

     

    My question arose when I was reading this proposal to add a priority property to XmlHttpRequests, but I had my doubts whether it would be a useful addition.

  • User profile image
    we

    There's a blog post about the report: www.belshe.com/2010/03/31/how-to-tune-a-porsche/  

     

    I wonder how the authors would respond to that.

  • User profile image
    BenZorn

    Thanks for your question.  We are aware of the related blog post and disagree with the conclusions the author reaches.  Specifically, the analogy with the elephant, while quite visually provacative, is inaccurate.  The implication is that browser users want to drive their browsers on a racetrack all day (e.g., the benchmarks).     Browser users want high performance, but not for small benchmarks that don't correspond to their daily experience.  A better analogy would be to consider driving your browser down a city street in traffic.  In that case, which we argue is the common case, the fact that your browser performs like a Porsche on a racetrack isn't as meaningful.   What the user cares about is how it handles in traffic.  We are presenting this research at the WebApps 2010 conference in Boston, on June 23, 2010 (http://www.usenix.org/events/webapps10/). 

Add Your 2 Cents