Skip to content

Instantly share code, notes, and snippets.

@ottomata
Created June 7, 2012 20:31
Show Gist options
  • Save ottomata/2891370 to your computer and use it in GitHub Desktop.
Save ottomata/2891370 to your computer and use it in GitHub Desktop.
http://www.cloudera.com/blog/2009/03/configuration-parameters-what-can-you-just-ignore/
- block size
- open files limit
- epoll limit
- io.sort.mb (io.sort.factor?)
- io.file.buffer.size (65536?)
- dfs.namenode.handler, mapred.job.tracker.handler.count
- dfs.datanode.handler.count
- mapred.child.ulimit, mapred.child.java.opts
http://www.cloudera.com/blog/2009/12/7-tips-for-improving-mapreduce-performance/
- mapred.compress.map.output
- LZO compression: http://www.cloudera.com/blog/2009/11/hadoop-at-twitter-part-1-splittable-lzo-compression/
This will only work if the input is already LZO compressed - annoying for benchmarking
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment