[MAPREDUCE-4087] [Gridmix] GenerateDistCacheData job of Gridmix can become slow in some cases

• Type: Bug
• Status: Closed
• Priority: Major
• Resolution: Fixed
• Fix Version/s: 1.1.0
• Hadoop Flags: Reviewed
• Release Note: Fixes the issue of GenerateDistCacheData job slowness.
• Assignee: Ravi Gummadi
• Reporter: Ravi Gummadi
• Created: 30/Mar/12 10:39
• Updated: 03/Sep/14 22:47
• Resolved: 31/Mar/12 08:29

Description

In map() method of GenerateDistCacheData job of Gridmix, val.setSize() is done every time based on the bytes to be written to a distributed cache file. When we try to write data to next distributed cache file in the same map task, the size of random data generated in each iteration can become small based on the particular case. This can make this dist cache data generation slow.