Given a fixed amount of memory allocated to your workers, more memory per executor means fewer executors can execute in parallel. This means it takes longer to finish all of the tasks. Set high enough, and your executors can find no worker with enough memory and so they all are stuck waiting for resources. The reason the tasks seem to take longer is really that they spend time waiting for an executor rather than spend more time running. That's my first guess.
If you want Spark to use more memory on your machines, give workers more memory. It sounds like there is no value in increasing executor memory as it only means you are underutilizing the CPU of your cluster by not running as many tasks in parallel as would be optimal. Hi all, I'm doing some testing on a small dataset (HadoopRDD, 2GB, ~10M records), with a cluster of 3 nodes Simple calculations like count take approximately 5s when using the default value of executor.memory (512MB). When I scale this up to 2GB, several Tasks take 1m or more (while most still are <1s), and tasks hang indefinitely if I set it to 4GB or higher. While these worker nodes aren't very powerful, they seem to have enough RAM to handle this: Running 'free –m' shows I have >7GB free on each worker. Any tips on why these jobs would hang when given more available RAM? Thanks Ben ------------------------------ The information contained in this e-mail is confidential and/or proprietary to Capital One and/or its affiliates. The information transmitted herewith is intended only for use by the individual or entity to which it is addressed. If the reader of this message is not the intended recipient, you are hereby notified that any review, retransmission, dissemination, distribution, copying or other use of, or taking of any action in reliance upon this information is strictly prohibited. If you have received this communication in error, please contact the sender and delete the material from your computer.