Return-Path: X-Original-To: apmail-cassandra-user-archive@www.apache.org Delivered-To: apmail-cassandra-user-archive@www.apache.org Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by minotaur.apache.org (Postfix) with SMTP id 42B529686 for ; Wed, 19 Oct 2011 03:41:17 +0000 (UTC) Received: (qmail 11230 invoked by uid 500); 19 Oct 2011 03:41:15 -0000 Delivered-To: apmail-cassandra-user-archive@cassandra.apache.org Received: (qmail 11163 invoked by uid 500); 19 Oct 2011 03:41:14 -0000 Mailing-List: contact user-help@cassandra.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: user@cassandra.apache.org Delivered-To: mailing list user@cassandra.apache.org Received: (qmail 11155 invoked by uid 99); 19 Oct 2011 03:41:13 -0000 Received: from athena.apache.org (HELO athena.apache.org) (140.211.11.136) by apache.org (qpsmtpd/0.29) with ESMTP; Wed, 19 Oct 2011 03:41:13 +0000 X-ASF-Spam-Status: No, hits=2.2 required=5.0 tests=HTML_MESSAGE,RCVD_IN_DNSWL_LOW,SPF_NEUTRAL X-Spam-Check-By: apache.org Received-SPF: neutral (athena.apache.org: local policy) Received: from [209.85.212.44] (HELO mail-vw0-f44.google.com) (209.85.212.44) by apache.org (qpsmtpd/0.29) with ESMTP; Wed, 19 Oct 2011 03:41:08 +0000 Received: by vws5 with SMTP id 5so1052388vws.31 for ; Tue, 18 Oct 2011 20:40:46 -0700 (PDT) MIME-Version: 1.0 Received: by 10.52.17.43 with SMTP id l11mr5407677vdd.28.1318995646728; Tue, 18 Oct 2011 20:40:46 -0700 (PDT) Received: by 10.52.111.226 with HTTP; Tue, 18 Oct 2011 20:40:46 -0700 (PDT) In-Reply-To: <1318994069.19606.6.camel@greenlantern.local> References: <1318994069.19606.6.camel@greenlantern.local> Date: Tue, 18 Oct 2011 20:40:46 -0700 Message-ID: Subject: Re: Size calculations for off heap caching From: Chris Goffinet To: user@cassandra.apache.org Content-Type: multipart/alternative; boundary=bcaec5040be6fbcae004af9e9a5c --bcaec5040be6fbcae004af9e9a5c Content-Type: text/plain; charset=ISO-8859-1 My best advice on this is, insert a bit of data into the tree, and then do a heap dump to calculate the extra overhead. It's unfortunately more than you would like from our testing. On Tue, Oct 18, 2011 at 8:14 PM, Todd Nine wrote: > ** > Hi guys, > We've just built a K tree implementation in cassandra. We're going for > relatively "wide" nodes in our tree to minimize our tree depth and increase > our search times. Most of the links between parent/child nodes are longs. > We're ready to start tuning the size of K so that our most access paths in > our tree will be row cached in Cassandra. We're on Cassandra 0.8.7, and I > can't find any documentation regarding the actual memory size of the off > heap row cache. Can someone explain how much additional space will be used > when caching rows? For instance, if our links between nodes are all Longs, > and we have 100 children (cols), that gives us 900 bytes with a 0 byte > placeholder value. What is the additional overhead when using the off heap > storage? > > Thanks, > Todd > --bcaec5040be6fbcae004af9e9a5c Content-Type: text/html; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable My best advice on this is, insert a bit of data into the tree, and then do = a heap dump to calculate the extra overhead. It's unfortunately more th= an you would like from our testing.

On T= ue, Oct 18, 2011 at 8:14 PM, Todd Nine <todd@spidertracks.com> wrote:
=20 =20
Hi guys,
=A0 We've just built a K tree implementation in cassandra.=A0 We're= going for relatively "wide" nodes in our tree to minimize our tr= ee depth and increase our search times.=A0=A0 Most of the links between par= ent/child nodes are longs.=A0 We're ready to start tuning the size of K= so that our most access paths in our tree will be row cached in Cassandra.= =A0 We're on Cassandra 0.8.7, and I can't find any documentation re= garding the actual memory size of the off heap row cache.=A0 Can someone ex= plain how much additional space will be used when caching rows?=A0 For inst= ance, if our links between nodes are all Longs, and we have 100 children (c= ols), that gives us 900 bytes with a 0 byte placeholder value.=A0 What is t= he additional overhead when using the off heap storage?

Thanks,
Todd

--bcaec5040be6fbcae004af9e9a5c--