Mailing-List: contact issues-help@flink.apache.org; run by ezmlm
Precedence: bulk
Reply-To: dev@flink.apache.org
Date: Tue, 19 Sep 2017 04:45:03 +0000 (UTC)
From: "ASF GitHub Bot (JIRA)" <jira@apache.org>
To: issues@flink.apache.org
Message-ID: <JIRA.13093374.1502257151000.143410.1505796303338@Atlassian.JIRA>
In-Reply-To: <JIRA.13093374.1502257151000@Atlassian.JIRA>
References: <JIRA.13093374.1502257151000@Atlassian.JIRA> <JIRA.13093374.1502257151323@jira-lw-us.apache.org>
Subject: [jira] [Commented] (FLINK-7394) Implement basic InputChannel for
 credit-based logic
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit
archived-at: Tue, 19 Sep 2017 04:45:13 -0000


    [ https://issues.apache.org/jira/browse/FLINK-7394?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16171114#comment-16171114 ] 

ASF GitHub Bot commented on FLINK-7394:
---------------------------------------

Github user zhijiangW commented on a diff in the pull request:

    https://github.com/apache/flink/pull/4499#discussion_r139596400
  
    --- Diff: flink-runtime/src/main/java/org/apache/flink/runtime/io/network/partition/consumer/RemoteInputChannel.java ---
    @@ -183,18 +214,40 @@ void notifySubpartitionConsumed() {
     	}
     
     	/**
    -	 * Releases all received buffers and closes the partition request client.
    +	 * Releases all received and available buffers, closes the partition request client.
     	 */
     	@Override
     	void releaseAllResources() throws IOException {
     		if (isReleased.compareAndSet(false, true)) {
    +
    +			final List<MemorySegment> recyclingSegments = new ArrayList<>();
    +
     			synchronized (receivedBuffers) {
     				Buffer buffer;
     				while ((buffer = receivedBuffers.poll()) != null) {
    -					buffer.recycle();
    +					if (buffer.getRecycler() == this) {
    +						recyclingSegments.add(buffer.getMemorySegment());
    --- End diff --
    
    I also considered this issue when implementation. The current way seems more verbose than directly calling `recycle()`, but there are two advantages:
    
    1. Exclusive buffers are recycled in batch which may be more performant as you mentioned above. 
    2. If calling `recycle()` directly, it should add extra check `isReleased` process outside the synchronized in `RemoteInputChannel#recycle` method.  It seems not elegant to do so. What do you think of this issue?


> Implement basic InputChannel for credit-based logic
> ---------------------------------------------------
>
>                 Key: FLINK-7394
>                 URL: https://issues.apache.org/jira/browse/FLINK-7394
>             Project: Flink
>          Issue Type: Sub-task
>          Components: Core
>            Reporter: zhijiang
>            Assignee: zhijiang
>             Fix For: 1.4.0
>
>
> This is a part of work for credit-based network flow control. 
> The basic works are:
> * Propose the {{BufferListener}} interface for notifying buffer availability and buffer destroyed.
> * {{RemoteInputChannel}} implements {{BufferRecycler}} interface to manage the exclusive buffers itself.
> * {{RemoteInputChannel}} implements {{BufferListener}} interface to be notified repeatedly .
> * {{RemoteInputChannel}} maintains and notifies of unannounced credit.
> * {{RemoteInputChannel}} maintains current sender backlog to trigger requests of floating buffers.


--
This message was sent by Atlassian JIRA
(v6.4.14#64029)