Details
-
Improvement
-
Status: Closed
-
Major
-
Resolution: Fixed
-
0.21.0
-
None
-
None
-
Expert level config properties mapred.shuffle.connect.timeout and mapred.shuffle.read.timeout that are to be used at cluster level are added by this patch.
Description
It would be good for latency-sensitive applications to tune the shuffle read/connection timeouts... in fact this made a huge difference to terasort since we were seeing individual shuffles stuck for upwards of 60s and had to have a very small read timeout.
Attachments
Attachments
Issue Links
- relates to
-
MAPREDUCE-1249 mapreduce.reduce.shuffle.read.timeout's default value should be 3 minutes, in mapred-default.xml
-
- Closed
-