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 A1D2E10B00 for ; Fri, 11 Oct 2013 20:06:53 +0000 (UTC) Received: (qmail 46977 invoked by uid 500); 11 Oct 2013 20:06:43 -0000 Delivered-To: apmail-cassandra-user-archive@cassandra.apache.org Received: (qmail 46926 invoked by uid 500); 11 Oct 2013 20:06:42 -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 46907 invoked by uid 99); 11 Oct 2013 20:06:42 -0000 Received: from nike.apache.org (HELO nike.apache.org) (192.87.106.230) by apache.org (qpsmtpd/0.29) with ESMTP; Fri, 11 Oct 2013 20:06:42 +0000 X-ASF-Spam-Status: No, hits=1.5 required=5.0 tests=HTML_MESSAGE,RCVD_IN_DNSWL_LOW,SPF_PASS X-Spam-Check-By: apache.org Received-SPF: pass (nike.apache.org: domain of rcoli@eventbrite.com designates 209.85.216.174 as permitted sender) Received: from [209.85.216.174] (HELO mail-qc0-f174.google.com) (209.85.216.174) by apache.org (qpsmtpd/0.29) with ESMTP; Fri, 11 Oct 2013 20:06:35 +0000 Received: by mail-qc0-f174.google.com with SMTP id v1so808780qcw.33 for ; Fri, 11 Oct 2013 13:06:14 -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:in-reply-to:references:date :message-id:subject:from:to:content-type; bh=QRYUsG4bFCWdsZfGuZevEu9govWj7GMsDAUhCC4rD3M=; b=Sb3lUXMwUGjoC+fuuPcnTjtAIyFNcQId6jhKezHAL5wbTlMz8HR7FPWTsc3yvMyQib y94PuSMua8jHTFmX4MtYTug72A/CWyxDRohT4zCKE2LepI8JUpPbMlVB32nhnHHtMJFR 0bPGMvwgANRn78Oa1zwzwYr+2p1l9QG+rfH9i1ehg5W9hK+evYaqVxrH77ypkJjveZWv 4pxrvMGArfBEG06YC5tZYinnsQ62aLQsZsqBY8CMgSgZpwzUdl3jlCoQMjY2ZIMm1If0 DpI7ukyV/Gk9jWkMvLF91iAqRkU1jiDWfYBDWB9g6ExIHR5woD7+I1OYlWJWRd7iAVrM pJDg== X-Gm-Message-State: ALoCoQmGqfV9VRWBK0vFxisExbyKsTlYDgvltrFayixIE671mbJeEPLnl/9oHOEOn1AY4kEvXoM4 MIME-Version: 1.0 X-Received: by 10.49.58.225 with SMTP id u1mr10339593qeq.55.1381521974148; Fri, 11 Oct 2013 13:06:14 -0700 (PDT) Received: by 10.49.58.210 with HTTP; Fri, 11 Oct 2013 13:06:14 -0700 (PDT) In-Reply-To: <5257F37F.60204@openmarket.com> References: <5257F37F.60204@openmarket.com> Date: Fri, 11 Oct 2013 13:06:14 -0700 Message-ID: Subject: Re: Heap requirement for Off-heap space From: Robert Coli To: "user@cassandra.apache.org" Content-Type: multipart/alternative; boundary=047d7b5db97884c76404e87ca68f X-Virus-Checked: Checked by ClamAV on apache.org --047d7b5db97884c76404e87ca68f Content-Type: text/plain; charset=ISO-8859-1 On Fri, Oct 11, 2013 at 5:47 AM, Artur Kronenberg < artur.kronenberg@openmarket.com> wrote: > I was playing around with cassandra off-heap options. I configured 3 GB > off-heap for my row cache and 2 GB Heap space for cassandra. > The row cache is only really useful in very specific cases involving very small, hot, and uniform in size datasets. Many more people have shot themselves in the foot by using it than have had great success. The off-heap row cache also invalidates on UPDATE, which is significantly different from what many people expect. > Is there a formula that maps heap space to off-heap? FWIW, I'd also like to know the answer to this question. =Rob --047d7b5db97884c76404e87ca68f Content-Type: text/html; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable
On Fri, Oct 11, 2013 at 5:47 AM, Artur Kronenberg <artur.kronenberg@openmarket.com> wrote:
I was playing aro= und with cassandra off-heap options. I configured 3 GB off-heap for my row = cache and 2 GB Heap space for cassandra.

The row cache is only really useful in ver= y specific cases involving very small, hot, and uniform in size datasets. M= any more people have shot themselves in the foot by using it than have had = great success.

The off-heap row cache also invalidates on UPDATE, whic= h is significantly different from what many people expect.=A0
=A0=
Is there a formula that maps heap space to off-heap?

<= /div>
FWIW, I'd also like to know the answer to this question.

=3DRob
--047d7b5db97884c76404e87ca68f--