Github user revans2 commented on the pull request:
https://github.com/apache/storm/pull/765#issuecomment-144059813
@mjsax The difference is not that huge yet. It is 2x in a number of use
cases. But we have a lot of slowness in the metrics processing code, which, at
least in the case of word count, is dominating the performance, which is
probably why you were not seeing a 6x performance improvement in your pull like
you were seeing before. I am going to be doing some follow on optimization
work on that. The big thing right now is that the System CPU utilization went
from 15-30% depending on the OS, etc. to 2-6%. This frees up a huge amount of
CPU for other processing, so the overall throughput capability of a node
increased significantly.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
