Home | About | Sematext search-lucene.com search-hadoop.com
 Search Hadoop and all its subprojects:

Switch to Threaded View
Avro >> mail # user >> improve performance of avro map reduce jobs


Copy link to this message
-
improve performance of avro map reduce jobs

Our Map/Reduce jobs are all based on avro.  We would like to enhance their performance.  The objects collected in our mappers and reducers are mainly of the type GenericData.Record.  Currently, most of jobs are CPU, rather than IO, bound.  Can anybody suggest ways to improve the performance of the jobs?  Thanks a lot.
Ey-Chih Chow