Github user cestella commented on the issue:
https://github.com/apache/metron/pull/940
@mraliagha It's definitely a tradeoff. This is why this is as a complement
to the original split/join topology. Keep in mind, also, that this
architecture enables use-cases that the other would prevent or make extremely
difficult and/or network intensive, such as multi-level stellar statements
rather than the 2 levels we have now. We are undergoing some preliminary
testing in-lab right now, which @nickwallen alluded to, to compare the two
approaches under at least synthetic load and will report back.
Ultimately this boils down to efficiencies gained by avoiding network hops
and whether that's going to provide an outsized impact, I think.
---
