Github user roshannaik commented on the issue:
https://github.com/apache/storm/pull/2270
So the ACKer bolt is usually the bigger bottleneck ...compared to the
groupings. So with ACKing enabled it will hide any bottlenecks in the
groupings. The only thing slower than ACKer bolt is the inter-worker message
transfer code.
Latency is unlikely to take a noticeable hit...unless you have lots of
hops Spot->Bolt->Bolt-Bolt->Bolt->Bolt. Regardless, good you have validated
that there is latency is.
The real observable hit if any will be in the throughput. You should
examine the ConstSpoutNull Bolt with ACKing disabled.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
