Mailing-List: contact dev-help@hama.apache.org; run by ezmlm
Precedence: bulk
Reply-To: dev@hama.apache.org
Date: Fri, 10 Jan 2014 06:48:50 +0000 (UTC)
From: "Edward J. Yoon (JIRA)" <jira@apache.org>
To: dev@hama.apache.org
Message-ID: <JIRA.12688195.1389336504167.74683.1389336530588@arcas>
In-Reply-To: <JIRA.12688195.1389336504167@arcas>
References: <JIRA.12688195.1389336504167@arcas>
Subject: [jira] [Created] (HAMA-843) Message communication overhead between
 master aggregation and vertex computation supersteps
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit

Edward J. Yoon created HAMA-843:
-----------------------------------

             Summary: Message communication overhead between master aggregation and vertex computation supersteps
                 Key: HAMA-843
                 URL: https://issues.apache.org/jira/browse/HAMA-843
             Project: Hama
          Issue Type: Improvement
          Components: graph
    Affects Versions: 0.6.3
            Reporter: Edward J. Yoon
             Fix For: 0.7.0


Within doAggregationUpdates() method, we sends unconsumed messages to next superstep using send() method. This is huge overhead.

{code}
    // in case we need to sync, we need to replay the messages that already
    // are added to the queue. This prevents loosing messages when using
    // aggregators.
    if (firstVertexMessage != null) {
      peer.send(peer.getPeerName(), firstVertexMessage);
    }

    GraphJobMessage msg = null;
    while ((msg = peer.getCurrentMessage()) != null) {
      peer.send(peer.getPeerName(), msg);
    }
{code}

Once HAMA-842 is done, we can get rid of this overhead.


--
This message was sent by Atlassian JIRA
(v6.1.5#6160)