Skip to main content

Diigo Home

Tv's cobweb: Incremental mapreduce - The Diigo Meta page

eagain.net/...incremental-mapreduce - Cached - Annotated View

Joel Liu's personal annotations on this page

joel
Joel bookmarked on 2007-12-28 mapreduce
  • The way I imagined building an incremental mapreduce mechanism, without storing
    the intermediate data and just recomputing chunks that are out-of-date (which
    would be lame), is to add one extra concept into the system: call it "demap". It
    will basically create "negative entries" for the old data. This is basically
    what Damien did by providing both the old and new data map calls, all the time,
    just said differently, and I think my way might make the average call a lot
    simpler. And I don't see any reason why my version wouldn't be parallelizable,
    chainable, and generally yummy.

This link has been bookmarked by 3 people . It was first bookmarked on 28 Dec 2007, by Joel Liu.

  • 18 Feb 08
    rampion
    rampion

    interesting idea. not sure how well it'd work with generalized algorithms.

    map.reduce algorithms

  • 28 Dec 07
    • The way I imagined building an incremental mapreduce mechanism, without storing
      the intermediate data and just recomputing chunks that are out-of-date (which
      would be lame), is to add one extra concept into the system: call it "demap". It
      will basically create "negative entries" for the old data. This is basically
      what Damien did by providing both the old and new data map calls, all the time,
      just said differently, and I think my way might make the average call a lot
      simpler. And I don't see any reason why my version wouldn't be parallelizable,
      chainable, and generally yummy.
  • 27 Dec 07