Github user cestella commented on the issue:
https://github.com/apache/metron/pull/940
Just FYI, as part of the performance experimentation in the lab here, we
found that one major impediment to scale was the guava cache in this topology
when the size of the cache becomes non-trivial in size (e.g. 10k+). Swapping
out [Caffeine](https://github.com/ben-manes/caffeine) immediately had a
substantial affect. I created #947 to migrate the split/join infrastructure to
use caffeine as well and will look at the performance impact of that change. I
wanted to separate that work from here as it may be that guava performance is
fine outside of an explicit threadpool like we have here.
---
