Github user StephanEwen commented on the pull request:
https://github.com/apache/flink/pull/879#issuecomment-117986440
We may also try and think about how we assign timestamps. We have measured
in some experiments that it decreases peak throughput if you call
`System.currentTimeMillis()` for every record. Tricky thing is trying to figure
out when to call it. There is no way to determine that based on number of
records, but to measure delay since the last record, well, you need to call it
as well ;-)
---
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.
---
