Github user cestella commented on the issue:
    @arunmahadevan Thanks for chiming in Arun.   I would say that most of the 
enrichment work is I/O bound and we try to avoid it whenever possible with a a 
time-evicted LRU cache in front of the enrichments.  We don't always know a 
priori what enrichments users are doing, per se, as their individual 
enrichments may be expressed via stellar.  The threads here are entirely 
managed via the fixed threadpool service in storm and the threadpool is shared 
across all of the executors running in-process on the worker, so we try to 
minimize that.


Reply via email to