Jacob Kaplan-Moss
Activity tagged “mapreduce”
Bookmarks
Writing An Hadoop MapReduce Program In Python - Michael G. Noll
Neat. I hadn't realized that Hadoop map/reduce jobs could be a bog-standard shell script. It's especially cute that testing the job comes down to “cat data | map | reduce”.
Google Scalability Conference Trip Report: MapReduce, BigTable, and Other Distributed System Abstractions for Handling Large Datasets
More details (than I've seen so far) on the Google architecture. If I'm doing my math right, the data given here tells us that Google has around 25 exa(10^18)bytes.