From common-commits-return-11618-apmail-hadoop-common-commits-archive=hadoop.apache.org@hadoop.apache.org Mon Aug 16 06:12:35 2010 Return-Path: Delivered-To: apmail-hadoop-common-commits-archive@www.apache.org Received: (qmail 79981 invoked from network); 16 Aug 2010 06:12:35 -0000 Received: from unknown (HELO mail.apache.org) (140.211.11.3) by 140.211.11.9 with SMTP; 16 Aug 2010 06:12:35 -0000 Received: (qmail 73062 invoked by uid 500); 16 Aug 2010 06:12:35 -0000 Delivered-To: apmail-hadoop-common-commits-archive@hadoop.apache.org Received: (qmail 72822 invoked by uid 500); 16 Aug 2010 06:12:32 -0000 Mailing-List: contact common-commits-help@hadoop.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: common-dev@hadoop.apache.org Delivered-To: mailing list common-commits@hadoop.apache.org Received: (qmail 72815 invoked by uid 500); 16 Aug 2010 06:12:31 -0000 Delivered-To: apmail-hadoop-core-commits@hadoop.apache.org Received: (qmail 72812 invoked by uid 99); 16 Aug 2010 06:12:31 -0000 Received: from nike.apache.org (HELO nike.apache.org) (192.87.106.230) by apache.org (qpsmtpd/0.29) with ESMTP; Mon, 16 Aug 2010 06:12:31 +0000 X-ASF-Spam-Status: No, hits=-2000.0 required=10.0 tests=ALL_TRUSTED X-Spam-Check-By: apache.org Received: from [140.211.11.131] (HELO eos.apache.org) (140.211.11.131) by apache.org (qpsmtpd/0.29) with ESMTP; Mon, 16 Aug 2010 06:12:28 +0000 Received: from eosnew.apache.org (localhost [127.0.0.1]) by eos.apache.org (Postfix) with ESMTP id 09FDE772; Mon, 16 Aug 2010 06:12:06 +0000 (UTC) MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable From: Apache Wiki To: Apache Wiki Date: Mon, 16 Aug 2010 06:12:05 -0000 Message-ID: <20100816061205.91264.23738@eosnew.apache.org> Subject: =?utf-8?q?=5BHadoop_Wiki=5D_Update_of_=22ZooKeeper/GSoCFailureDetector=22?= =?utf-8?q?_by_AbmarBarros?= X-Virus-Checked: Checked by ClamAV on apache.org Dear Wiki user, You have subscribed to a wiki page or wiki category on "Hadoop Wiki" for ch= ange notification. The "ZooKeeper/GSoCFailureDetector" page has been changed by AbmarBarros. http://wiki.apache.org/hadoop/ZooKeeper/GSoCFailureDetector?action=3Ddiff&r= ev1=3D8&rev2=3D9 -------------------------------------------------- 1. --(Refactor client-side code of the client-server monitoring to use t= he proposed FailureDetector interface)-- 1. --(Make the failure detection and its parameters configurable on the = client)-- 1. --(Refactor server-side code of the client-server monitoring to use t= he proposed FailureDetector interface)-- - 1. Refactor the code of the server-server monitoring to use the proposed= FailureDetector interface + 1. --(Refactor the code of the server-server monitoring to use the propo= sed FailureDetector interface)-- - 1. Make the failure detection and its parameters configurable on the ser= ver (to server-server and client-server monitoring) + 1. --(Make the failure detection and its parameters configurable on the = server (to server-server and client-server monitoring))-- 1. Evaluate the QoS metrics with experimentation - 1. Write Forrest docs + 1. --(Write Forrest docs)-- = =3D=3D Related JIRA =3D=3D * [[https://issues.apache.org/jira/browse/ZOOKEEPER-702|ZOOKEEPER-702: G= SoC 2010: Failure Detector Model]] @@ -82, +82 @@ * Created a new FailureDetector, which groups monitoreds by their tick t= ime, similar to what the SessionTracking does. * Made the server-client failure detector (and its parameters) options o= f the ZooKeeper configuration file. = - =3D=3D=3D Currently working on =3D=3D=3D - * Refactoring the code of the server-server monitoring to use the propos= ed FailureDetector interface + =3D=3D=3D=3D 23/Jul/10 =3D=3D=3D=3D + * Made Learners track client heartbeats and send statistical data of the= heartbeat sampling window to the Learner + * Analyzed paper about application message used as heartbeat. = + = + =3D=3D=3D=3D 30/Jul/10 =3D=3D=3D=3D + * Refactored the code of the Leader-Learner monitoring in order to use f= ailure detector module + * Added options in configuration file to configure Leader-Learner monito= ring + * Fixed bugs in FDs initialization and in some cases of session register= ing + * Fixed bug in server recovery on the client side + = + =3D=3D=3D=3D 09/Aug/10 =3D=3D=3D=3D + * Set up first experiments in Emulab + * Instrumented code to report some detection metrics as false suspicion = and detection time + * Enhanced java documentation, started to write forrest docs + = + =3D=3D=3D=3D 14/Aug/10 =3D=3D=3D=3D + * Kept on changing experimentation scenarios to check the behaviour of t= he failure detectors + * Tuned some initialization parameters of the failure detectors based on= some experimentation results + * Finished writing forrest documentation + * Added a new parameter to phi accrual FD - the minimum window size to b= egin timeout adaptation. + * Added a moderation step to Bertier FD, to comply with second level tas= k described in his paper + * Made Chen's alpha parameter configurable, and not a quarter of the tim= eout + = + =3D=3D=3D=3D 16/Aug/10 =3D=3D=3D=3D = ---- = + =3D=3D Experimentation =3D=3D + = + =3D=3D=3D=3D Experimental design =3D=3D=3D=3D + = + =3D=3D=3D=3D Results and conclusions =3D=3D=3D=3D + = + ---- =3D=3D Design decisions =3D=3D = =3D=3D=3D=3D Should a failure detector instance (FD) run in a separate th= read from the application? =3D=3D=3D=3D