[
https://issues.apache.org/jira/browse/FLINK-16012?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Piotr Nowojski closed FLINK-16012.
----------------------------------
Resolution: Won't Fix
I think not. As part of FLIP-183 we will try to implement a solution that would
decrease the amount of in-flight data without sacrificing performance.
Initially FLIP-183 will be only about shrinking the buffer size, but when step
in the future that we are planning, is that if buffer size is approximately
already as large as the record size, then we want to start automatically
reducing the amount of in-flight buffers (and thus integrating with your
changes from FLINK-16428). In this context, keeping 2 exclusive buffers as
default makes more sense.
Also my previous intention as part of this ticket was to document two different
configuration settings:
# high throughput mode
# low in-flight data mode
But also let's wait for FLIP-183, as it will significantly alter configuration
and documentation.
So let me close this ticket.
> Reduce the default number of exclusive buffers from 2 to 1 on receiver side
> ---------------------------------------------------------------------------
>
> Key: FLINK-16012
> URL: https://issues.apache.org/jira/browse/FLINK-16012
> Project: Flink
> Issue Type: Sub-task
> Components: Runtime / Network
> Reporter: Zhijiang
> Assignee: Yingjie Cao
> Priority: Major
> Labels: pull-request-available
> Fix For: 1.14.0
>
> Time Spent: 10m
> Remaining Estimate: 0h
>
> In order to reduce the inflight buffers for checkpoint in the case of back
> pressure, we can reduce the number of exclusive buffers for remote input
> channel from default 2 to 1 as the first step. Besides that, the total
> required buffers are also reduced as a result. We can further verify the
> performance effect via various of benchmarks.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
