I wonder if the issues you are seeing are related to
This shouldn't happen.
On 5/1/12 7:29 AM, Benjamin Heitmann wrote:
under which circumstances is it possible that a Giraph job, will report that he
is 100% finished will his mappers,
but the job is still running ?
I can see that it is still running from:
* debugging messages,
* list of running threads (in top)
* the hadoop jobtracker web site (it reports 100% completion of mappers, but
also that all mappers are running, and none is complete)
I am currently running some benchmarks to get a handle on the scalability of
giraph and of my algorithm implementation.
And the results up to now are very confusing...
Looking forward to any answers, cheers, Benjamin.