Mailing-List: contact issues-help@ignite.incubator.apache.org; run by ezmlm
Precedence: bulk
Reply-To: dev@ignite.incubator.apache.org
Date: Wed, 29 Jul 2015 08:54:04 +0000 (UTC)
From: "Denis Magda (JIRA)" <jira@apache.org>
To: issues@ignite.incubator.apache.org
Message-ID: <JIRA.12820951.1429043085000.316764.1438160044938@Atlassian.JIRA>
In-Reply-To: <JIRA.12820951.1429043085000@Atlassian.JIRA>
References: <JIRA.12820951.1429043085000@Atlassian.JIRA>
 <JIRA.12820951.1429043085473@arcas>
Subject: [jira] [Updated] (IGNITE-752) Speed up failure detection
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit


     [ https://issues.apache.org/jira/browse/IGNITE-752?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Denis Magda updated IGNITE-752:
-------------------------------
    Attachment: 475-2.patch
                failure_detection_timeout_node_left.zip

> Speed up failure detection
> --------------------------
>
>                 Key: IGNITE-752
>                 URL: https://issues.apache.org/jira/browse/IGNITE-752
>             Project: Ignite
>          Issue Type: Bug
>            Reporter: Yakov Zhdanov
>            Assignee: Denis Magda
>            Priority: Blocker
>             Fix For: sprint-7
>
>         Attachments: 475-2.patch, 882.patch, failure_detection_timeout_node_left.zip, ignite-752.patch
>
>
> I think we can (1) make grid configuration significantly easier and (2) speed up failure detection.
> Here are disco SPI configuration properties which are responsible for failure detection:
> # reconnectCount,
> # sockTimeout,
> # networkTImeout, 
> # ackTImeout, 
> # maxAckTimeout,
> # heartbeatFrequency 
> # maxMissedHearbeats
> Same for communication SPI
> # reconnectCount, 
> # maxConnTimeout, 
> # connTimeout
> So, we have 10 or even more properties.
> We did it to address half-opened sockets problem (which is pretty common for cloud environment) and GC pauses which may happen on cluster nodes - we can increase ack timeouts to prevent them from being kicked off the topology.
> By setting value for these props I set timeout for failure detection. Why do we need such great number of parameters instead of having 1 on IgniteConfiguration - nodeResponseThreshold (or failureDetectionThreshold - can anyone propose better name?).
> All other parameters will be calculated automatically (I think user can still set some of them for full control over situation - need to decide if this is needed.)


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