0

I'm running CDH4 MR1 and looking at performance metrics in preparation for migrating to a new hadoop environment.

Total time spent by all maps in occupied slots (ms) 0 0 3,801,573,232

Total time spent by all reduces in occupied slots (ms) 0 0 30,152,549

CPU time spent (ms) 0 0 5,151,794,220

Shouldn't CPU time be smaller than map millis+reduce millis because the map/reduce millis includes time when the CPU is both running and idle?

Community
  • 1
  • 1
Alvin C
  • 47
  • 1
  • 6
  • Your answer is here [enter link description here](http://stackoverflow.com/questions/11726388/what-does-cpu-time-for-a-hadoop-job-signify) – Self Jan 08 '17 at 18:11
  • Does the time spent by all maps in occupied slots only include a subset of record reader, map, combiner, and partitioner? I didn't think so. If CPU time includes all phases of map/reduce, and the "total time spent by all maps/reduces" also includes all phases, then I still don't know why cpu time spent can be higher. I thought it would be lower if there's times when the CPU is idle during the map/reduce phases. – Alvin C Jan 11 '17 at 16:45

0 Answers0