Return-Path: 
 <user-return-27569-apmail-cassandra-user-archive=cassandra.apache.org@cassandra.apache.org>
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 A50B8D588
	for <apmail-cassandra-user-archive@www.apache.org>;
 Wed, 11 Jul 2012 10:38:22 +0000 (UTC)
Received: (qmail 26174 invoked by uid 500); 11 Jul 2012 10:38:20 -0000
Delivered-To: apmail-cassandra-user-archive@cassandra.apache.org
Received: (qmail 25798 invoked by uid 500); 11 Jul 2012 10:38:19 -0000
Mailing-List: contact user-help@cassandra.apache.org; run by ezmlm
Precedence: bulk
List-Help: <mailto:user-help@cassandra.apache.org>
List-Unsubscribe: <mailto:user-unsubscribe@cassandra.apache.org>
List-Post: <mailto:user@cassandra.apache.org>
List-Id: <user.cassandra.apache.org>
Reply-To: user@cassandra.apache.org
Delivered-To: mailing list user@cassandra.apache.org
Received: (qmail 25760 invoked by uid 99); 11 Jul 2012 10:38:18 -0000
Received: from nike.apache.org (HELO nike.apache.org) (192.87.106.230)
    by apache.org (qpsmtpd/0.29) with ESMTP; Wed, 11 Jul 2012 10:38:18 +0000
X-ASF-Spam-Status: No, hits=1.5 required=5.0
	tests=FSL_RCVD_USER,HTML_MESSAGE,RCVD_IN_DNSWL_LOW,SPF_PASS
X-Spam-Check-By: apache.org
Received-SPF: pass (nike.apache.org: domain of omidaladini@gmail.com
 designates 209.85.160.44 as permitted sender)
Received: from [209.85.160.44] (HELO mail-pb0-f44.google.com) (209.85.160.44)
    by apache.org (qpsmtpd/0.29) with ESMTP; Wed, 11 Jul 2012 10:38:10 +0000
Received: by pbcwy7 with SMTP id wy7so1942620pbc.31
        for <user@cassandra.apache.org>; Wed, 11 Jul 2012 03:37:49 -0700 (PDT)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=gmail.com; s=20120113;
        h=mime-version:from:date:message-id:subject:to:content-type;
        bh=Yef5Dyvj0iJNRRmWIoEhRWAznGyx/1nc/FbokIvXVNs=;
        b=RCMJ0kfRjeQhqgIMQ536vSeptWcIURo2mlWer1D/9OHBpYwo+G/8ENa+SXSm6CjLoo
         edrMRlmnFS9KwwruFQXSbO08Jk3ES1KcG4xsOS4XACCr185WPuXYsG7BMchP/ZtwvPWg
         GwhsgGYpsg9fcs16hCangFyCtY2EZ6TTp1pU+7Mn6UV1w8+VWBs/Wi5IZxH0J0+MZUMt
         unxXDyij9aEVGFmUnGOFuBI3F4CDEYZ22NCIbuFXqhLM1TN1eeXKgxqadj0zDZwIeS7M
         UCK8ZyhF3/d8aUMVAEXs0cyc13j4FUYFmmOvwWkpe3AWJ8l9DD7pc8F9OtMVOEUPTuKV
         LRzw==
Received: by 10.68.233.132 with SMTP id tw4mr77185614pbc.61.1342003069313;
 Wed, 11 Jul 2012 03:37:49 -0700 (PDT)
MIME-Version: 1.0
Received: by 10.68.10.161 with HTTP; Wed, 11 Jul 2012 03:37:09 -0700 (PDT)
From: Omid Aladini <omidaladini@gmail.com>
Date: Wed, 11 Jul 2012 12:37:09 +0200
Message-ID: 
 <CAH-t0tbXn5WAQjoP2G7gfeJUGix2AL6WjoPFfP8=eqTAdGiZ9Q@mail.gmail.com>
Subject: Reduced key-cache due to memory pressure and cache size estimate
To: user@cassandra.apache.org
Content-Type: multipart/alternative; boundary=047d7b33cac63be21904c48b70b7

--047d7b33cac63be21904c48b70b7
Content-Type: text/plain; charset=UTF-8

Hi,

I'm trying to tune, memtable size, key cache size and heap size on
Cassandra 1.1.0 but I keep having memory pressure and reduced cache size.
With the following settings:

heap size: 10GB (had the same issue with 8GB so I'm testing with increased
heap size)
memtable_total_space_in_mb: 2GB
key_cache_size_in_mb: 2GB   (global key cache capacity)

Still, heap usage hits flush_largest_memtables_at (= 0.75) many times in a
short period of time before hitting reduce_cache_sizes_at (= 0.85) that
reduces the cache size and resolves memory pressure.

In one instance, cache size is reported to be 1450MB before reduction and
~870MB after reduction, but the gain in heap space due to reduction in
cache size is about 3GB.

Could it be that the cache size estimate in megabytes isn't accurate?

Thanks,
Omid

--047d7b33cac63be21904c48b70b7
Content-Type: text/html; charset=UTF-8
Content-Transfer-Encoding: quoted-printable

<div dir=3D"ltr">Hi,<div><br></div><div>I&#39;m trying to tune, memtable si=
ze, key cache size and heap size on Cassandra 1.1.0 but I keep having memor=
y pressure and reduced cache size. With the following settings:</div><div>

<br></div><div>heap size: 10GB (had the same issue with 8GB so I&#39;m test=
ing with increased heap size)</div><div>memtable_total_space_in_mb: 2GB</di=
v><div>key_cache_size_in_mb: 2GB =C2=A0 (global key cache capacity)</div><d=
iv>

<br></div><div>Still, heap usage hits flush_largest_memtables_at (=3D 0.75)=
 many times in a short period of time before hitting reduce_cache_sizes_at =
(=3D 0.85) that reduces the cache size and resolves memory pressure.</div>
<div>
<br></div><div>In one instance, cache size is reported to be 1450MB before =
reduction and ~870MB after reduction, but the gain in heap space due to red=
uction in cache size is about 3GB.</div><div><br></div><div>Could it be tha=
t the cache size estimate in megabytes isn&#39;t accurate?</div>

<div><br></div><div>Thanks,</div><div>Omid<br><br>
</div></div>

--047d7b33cac63be21904c48b70b7--