Ah, nevermind, I don't know anything about scheduling tasks in YARN.

On Thu, Aug 13, 2015 at 11:03 PM, Ara Vartanian <[email protected]> wrote:

> I’m running on Yarn.
>
> On Aug 13, 2015, at 10:58 PM, Philip Weaver <[email protected]>
> wrote:
>
> Are you running on mesos, yarn or standalone? If you're on mesos, are you
> using coarse grain or fine grained mode?
>
> On Thu, Aug 13, 2015 at 10:13 PM, Ara Vartanian <[email protected]>
> wrote:
>
>> I’m observing an unusual situation where my step duration increases as I
>> add further executors to my cluster. My algorithm is fully data
>> parallelizable into a map phase, followed by a reduce step at the end that
>> amounts to matrix addition. So I’ve kicked a cluster of, say, 100 executors
>> with 4 cores per executor and before running the algorithm I’ve
>> repartitioned the RDD into 400 partitions. I can see in the Spark UI that
>> each of the 400 (map) tasks takes about 2 seconds. However, the entire step
>> is taking over a minute, and this is because the launch times of the tasks
>> as reported in the Spark UI are staggered. For example, the first 100 might
>> be launched in the same second, then another group 3 seconds later, and so
>> forth (with the durations slowly expanding). With a task time of 2 seconds,
>> this “launch lag” is dominating the computation time and only gets worse as
>> I add nodes.
>>
>> Any insight on how I could go about diagnosing this would be greatly
>> appreciated.
>>
>>
>>
>> ---------------------------------------------------------------------
>> To unsubscribe, e-mail: [email protected]
>> For additional commands, e-mail: [email protected]
>>
>>
>
>

Reply via email to