Interpreting the Data: Parallel Analysis with Sawzall (Draft)
While MapReduce and GFS allow Google to use their massive computer clusters effectively, the use of C++ can make programming for such a systems more difficult than it needs to be. Cue Sawzall, a new language that Google use to write distributed, parallel data-processing programs for use on their clusters. While the language isn’t particularly attractive (I’ve never liked C-style syntax’s), the approach is very interesting and the implementation issues they describe are enlightening.