Github user ptgoetz commented on the issue:
https://github.com/apache/storm/pull/2203
We really need hardware and environment information. I'd also argue that
tests should be run headless. I've seen some benchmarks vary greatly on a MBP
depending on what you're doing at the time. Something as mundane as checking
email, etc. can affect benchmark results.
sigar might be an easy target (since it's included) to get some of that
info.
---
