You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@flink.apache.org by "zhuhaifeng (JIRA)" <ji...@apache.org> on 2016/10/20 03:26:59 UTC

[jira] [Commented] (FLINK-4840) Measure latency/delay of record processing and expose it as a metric

    [ https://issues.apache.org/jira/browse/FLINK-4840?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15590636#comment-15590636 ] 

zhuhaifeng commented on FLINK-4840:
-----------------------------------

It measure the time cost of record processing from the beginning time to the completion time(eg. from System.nanoTime() ). It's a histogram metric and a  update interface will be called to save the processing time when a record processing completion, it's just store the processing time. The calculate will be invloved when MetricFetcher to fetcher a snapshot. so it will not introduce a non-trivial overhead.

> Measure latency/delay of record processing and expose it as a metric
> --------------------------------------------------------------------
>
>                 Key: FLINK-4840
>                 URL: https://issues.apache.org/jira/browse/FLINK-4840
>             Project: Flink
>          Issue Type: Improvement
>          Components: Metrics
>            Reporter: zhuhaifeng
>            Assignee: zhuhaifeng
>            Priority: Minor
>             Fix For: 1.2.0
>
>
> We should expose the following Metrics on the OperatorIOMetricGroup:
>  1. latency(ms): record processing time as a histogram metric.
>  2. procTimeCostPerSecond(ms): record processing time accumulated per second, it measure record processing percentage to check if it's a main time costing
>  3. delay(ms): the time between upstream emit record and downstream start record processing 



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)