Return-Path: X-Original-To: apmail-hadoop-user-archive@minotaur.apache.org Delivered-To: apmail-hadoop-user-archive@minotaur.apache.org Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by minotaur.apache.org (Postfix) with SMTP id 3704B102EC for ; Mon, 30 Sep 2013 13:08:14 +0000 (UTC) Received: (qmail 33604 invoked by uid 500); 30 Sep 2013 13:08:07 -0000 Delivered-To: apmail-hadoop-user-archive@hadoop.apache.org Received: (qmail 33134 invoked by uid 500); 30 Sep 2013 13:08:06 -0000 Mailing-List: contact user-help@hadoop.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: user@hadoop.apache.org Delivered-To: mailing list user@hadoop.apache.org Received: (qmail 33127 invoked by uid 99); 30 Sep 2013 13:08:06 -0000 Received: from athena.apache.org (HELO athena.apache.org) (140.211.11.136) by apache.org (qpsmtpd/0.29) with ESMTP; Mon, 30 Sep 2013 13:08:06 +0000 X-ASF-Spam-Status: No, hits=-0.1 required=5.0 tests=HTML_MESSAGE,RCVD_IN_DNSWL_MED,SPF_PASS X-Spam-Check-By: apache.org Received-SPF: pass (athena.apache.org: domain of amits@infolinks.com designates 207.126.144.159 as permitted sender) Received: from [207.126.144.159] (HELO eu1sys200aog125.obsmtp.com) (207.126.144.159) by apache.org (qpsmtpd/0.29) with SMTP; Mon, 30 Sep 2013 13:07:59 +0000 Received: from mail-ie0-f170.google.com ([209.85.223.170]) (using TLSv1) by eu1sys200aob125.postini.com ([207.126.147.11]) with SMTP ID DSNKUkl3mS4R0sUOnstgdDcLn+paO7jtql97@postini.com; Mon, 30 Sep 2013 13:07:39 UTC Received: by mail-ie0-f170.google.com with SMTP id x13so10388142ief.29 for ; Mon, 30 Sep 2013 06:07:36 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:mime-version:date:message-id:subject:from:to :content-type; bh=gEigwrNBnWziDvigO4Y22svFF/dmWCH/XMyVSyzwXoc=; b=g1rS0S/Yiy4NT7R1E1+OCm3sb4h9L1oTU3XEWM8k8leUx+9CgEeE+xSiwGJa4nDAQA dDf1TJlv3ABrtpRffpjJNEJ6E6EWhP9UcYq5GaopdFBnj7SE5PLUCYhlpSW72HEsmZ1s qlUumPImsWOLMB7uM7WJP3mcgQZkb0TsCUogDRPi2EVMGhizMRgCtqUqVolqj9IS5saV WY4AufkhzW/pdBrrVTHXKGV4bHOTMrKJGjCMDAFTCWZJTUyIFNQtQO+rDciWGWhqzSVR WPDNyh1lII5uJHEVpHatDQdou4LaGvGhKDfoNMgfg/DhIe3yMLAtrT14tQLoHA/m9Xoc Nu9Q== X-Gm-Message-State: ALoCoQkA+5/s+p8bW7OeQ6s3D5CG8sa3uYqB6tJYzMzkoQk0FPY8aIbGLG9D3HvkWAzkjKsD0+owbj1hpBBrecRDxEB2l+9Ih0RO8msuskCmJ7q8t7jsFGzhBaIMOsjrJQictR8fE8qtXqApOPLrgg67EuiIZXpzs961GNmr4MZBUy8yVvgc3wo= X-Received: by 10.50.77.72 with SMTP id q8mr13829659igw.14.1380546456806; Mon, 30 Sep 2013 06:07:36 -0700 (PDT) MIME-Version: 1.0 X-Received: by 10.50.77.72 with SMTP id q8mr13829630igw.14.1380546456528; Mon, 30 Sep 2013 06:07:36 -0700 (PDT) Received: by 10.64.227.15 with HTTP; Mon, 30 Sep 2013 06:07:36 -0700 (PDT) Date: Mon, 30 Sep 2013 15:07:36 +0200 Message-ID: Subject: Add machine with bigger storage to cluster From: Amit Sela To: user@hadoop.apache.org Content-Type: multipart/alternative; boundary=047d7bdc0b16233cec04e7998589 X-Virus-Checked: Checked by ClamAV on apache.org --047d7bdc0b16233cec04e7998589 Content-Type: text/plain; charset=ISO-8859-1 I would like to add new machines to my existing cluster but they won't be similar to the current nodes. I have to scenarios I'm thinking of: 1. What are the implications (besides initial load balancing) of adding a new node to the cluster, if this node runs on a machine similar to all other nodes but has 10x storage ? 2.What are the implications of adding a new machine that is 10x "better" machine - 10x storage, faster disks, better CPU, more memory, etc. ? anything to consider besides factorizing the number of map / reduce tasks and the memory allocation for them on the "better" machine ? Thanks, Amit. --047d7bdc0b16233cec04e7998589 Content-Type: text/html; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable
I would like to add new machines to my existing= cluster but they won't be similar to the current nodes. I have to scen= arios I'm thinking of:
=A0
1. What are the implica= tions (besides initial load balancing) of adding a new node to the cluster,= if this node runs on a machine similar to all other nodes but has 10x stor= age ?

2.What are the implications of adding a new machine th= at is 10x "better" machine - 10x storage, faster disks, better CP= U, more memory, etc. ? anything to consider besides factorizing the number = of map / reduce tasks and the memory allocation for them on the "bette= r" machine ?

Thanks,=A0

Amit.
--047d7bdc0b16233cec04e7998589--