JobTracker metrics do not match job counters
--------------------------------------------
Key: HADOOP-5499
URL: https://issues.apache.org/jira/browse/HADOOP-5499
Project: Hadoop Core
Issue Type: Bug
Components: mapred, metrics
Affects Versions: 0.20.0
Reporter: Chris Douglas
After one run of a 10 map, 3 reduce sort job, the mapred metrics report:
{noformat}
mapred.tasktracker: hostName=snip, sessionId=, mapTaskSlots=3, maps_running=0, \
reduceTaskSlots=3, reduces_running=0, tasks_completed=15,
tasks_failed_ping=0, tasks_failed_timeout=0
mapred.jobtracker: hostName=snip, sessionId=, jobs_completed=1,
jobs_submitted=1, \
maps_completed=10, maps_launched=12, reduces_completed=3, reduces_launched=3
{noformat}
After the second (w/ one manually killed reduce)
{noformat}
mapred.tasktracker: hostName=pineapple-lm, sessionId=, mapTaskSlots=3,
maps_running=0, \
reduceTaskSlots=3, reduces_running=0, tasks_completed=32,
tasks_failed_ping=0, tasks_failed_timeout=0
mapred.jobtracker: hostName=pineapple-lm, sessionId=, jobs_completed=2,
jobs_submitted=2, \
maps_completed=20, maps_launched=24, reduces_completed=6, reduces_launched=8
{noformat}
The counters report the expected 10/3 map/reduce completions, the second job
reporting a single failure.
# The {{maps_launched}} and {{reduces_launched}} counts are likely recording
setup and cleanup tasks as well
# After being recorded among launched tasks, it looks like setup and cleanup
are _not_ included among completed tasks
# {{tasks_completed}} on the TaskTracker should include only user tasks
# The {{reduces_launched}} count makes little sense to me. With three reduces
launched per job and one failed, what's the other launched reduce counting?
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
