On this note - the ganglia web front end that runs on the master (assuming you're launching with the ec2 scripts) is great for this. 

Also, a common technique for diagnosing "which step is slow" is to run a '.cache' and a '.count' on the RDD after each step. This forces the RDD to be materialized, which subverts the lazy evaluation that causes such diagnosis to be hard sometimes. 

- Evan

On Jan 8, 2014, at 2:57 PM, Andrew Ash <andrew@andrewash.com> wrote:

My first thought on hearing that you're calling collect is that taking all the data back to the driver is intensive on the network.  Try checking the basic systems stuff on the machines to get a sense of what's being heavily used:

disk IO

Any kind of distributed system monitoring framework should be able to handle these sorts of things.


On Wed, Jan 8, 2014 at 1:49 PM, Yann Luppo <YannLuppo@livenation.com> wrote:

I have what I hope is a simple question. What's a typical approach to diagnostic performance issues on a Spark cluster?
We've followed all the pertinent parts of the following document already: http://spark.incubator.apache.org/docs/latest/tuning.html
But we seem to still have issues. More specifically we have a leftouterjoin followed by a flatmap and then a collect running a bit long.

How would I go about determining the bottleneck operation(s) ? 
Is our leftouterjoin taking a long time? 
Is the function we send to the flatmap not optimized?