[
https://issues.apache.org/jira/browse/FLINK-1967?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14611965#comment-14611965
]
ASF GitHub Bot commented on FLINK-1967:
---------------------------------------
Github user aljoscha commented on the pull request:
https://github.com/apache/flink/pull/879#issuecomment-118037363
Ok, the test results I posted earlier seem correct. I also ran the tests on
my machine with two TaskManagers, There the result is the same for
master/event-time/event-time-marks-every-500. The overhead seems to not be from
the additional object creation/joda.time.Instant but from the additional
network traffic or from other effects that happen with the network and
watermarks.
> Introduce (Event)time in Streaming
> ----------------------------------
>
> Key: FLINK-1967
> URL: https://issues.apache.org/jira/browse/FLINK-1967
> Project: Flink
> Issue Type: Improvement
> Reporter: Aljoscha Krettek
> Assignee: Aljoscha Krettek
>
> This requires introducing a timestamp in streaming record and a change in the
> sources to add timestamps to records. This will also introduce punctuations
> (or low watermarks) to allow windows to work correctly on unordered,
> timestamped input data. In the process of this, the windowing subsystem also
> needs to be adapted to use the punctuations. Furthermore, all operators need
> to be made aware of punctuations and correctly forward them. Then, a new
> operator must be introduced to to allow modification of timestamps.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
