may because of snappy-java,
https://issues.apache.org/jira/browse/SPARK-5081


On May 23, 2015, at 1:23 AM, Josh Rosen <[email protected]> wrote:

> I don't think that 0.9.3 has been released, so I'm assuming that you're 
> running on branch-0.9.
> 
> There's been over 4000 commits between 0.9.3 and 1.3.1, so I'm afraid that 
> this question doesn't have a concise answer: 
> https://github.com/apache/spark/compare/branch-0.9...v1.3.1
> 
> To narrow down the potential causes, have you tried comparing 0.9.3 to, say, 
> 1.0.2 or branch-1.0, or some other version that's closer to 0.9?
> 
> On Fri, May 22, 2015 at 9:43 AM, Shay Seng <[email protected]> wrote:
> Hi. 
> I have a job that takes 
> ~50min with Spark 0.9.3 and 
> ~1.8hrs on Spark 1.3.1 on the same cluster.
> 
> The only code difference between the two code bases is to fix the Seq -> Iter 
> changes that happened in the Spark 1.x series.
> 
> Are there any other changes in the defaults from spark 0.9.3 -> 1.3.1 that 
> would cause such a large degradation in performance? Changes in partitioning 
> algorithms, scheduling etc?
> 
> shay
> 
> 

Reply via email to