[ 
https://issues.apache.org/jira/browse/BEAM-5791?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Henning Rohde reassigned BEAM-5791:
-----------------------------------

    Assignee:     (was: Henning Rohde)

> Bound the amount of data on the data plane by time.
> ---------------------------------------------------
>
>                 Key: BEAM-5791
>                 URL: https://issues.apache.org/jira/browse/BEAM-5791
>             Project: Beam
>          Issue Type: Improvement
>          Components: runner-dataflow, sdk-java-harness, sdk-py-harness
>            Reporter: Robert Bradshaw
>            Priority: Major
>          Time Spent: 3h
>  Remaining Estimate: 0h
>
> This is especially important for Fn API reads, where each element represents 
> a shard to read and may be very expensive, but many elements may be waiting 
> in the Fn API buffer.
> The need for this will be mitigated with full SDF support for liquid sharding 
> over the Fn API, but not eliminated unless the runner can "unread" elements 
> it has already sent. 
> This is especially important in for dataflow jobs that start out small but 
> then detect that they need more workers (e.g. due to the initial inputs being 
> an SDF).



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

Reply via email to