I am having some issues with processes running out of memory and I'm wondering 
if I'm setting things up incorrectly. 

I am running a job on two nodes with 24 cores and 256Gb of memory each. I start 
the pyspark shell with SPARK_EXECUTOR_MEMORY=210gb. When I run the job with 
anything more than 8 cores, the processes start dying off with out of memory 
errors. But when I watch the memory consumption using top on the two execute 
nodes, the individual processes never seem to exceed the per-core memory and 
the nodes themselves are far from running out of memory. So I'm wondering if 
Spark is setting the per-core memory limit somewhere? 

Thanks,

Rok




---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to