Mailing-List: contact user-help@cassandra.apache.org; run by ezmlm
Precedence: bulk
Reply-To: user@cassandra.apache.org
Received-SPF: pass (athena.apache.org: domain of ruslan.usifov@gmail.com
 designates 209.85.161.172 as permitted sender)
MIME-Version: 1.0
In-Reply-To: 
 <CALdd-zig0_LqsRFNx3+AHcfY=sQBNa7_E2wGc+WtA=rSjrfo-Q@mail.gmail.com>
References: 
 <CAHULbC=u03JVYuCJQo_wPfvUEeVqXn9QO3KYcYCFNJ2ZsG_CEQ@mail.gmail.com>
	<CAHULbCkPTLG2beAZOPcqYr3qg7aFQLqmbsVmknKnTMbo=wn+jg@mail.gmail.com>
	<CADVHTB9VD6HEPCxnqDc7czUY=pJ2ZncP=Y15RY+FZTAHvb=WFQ@mail.gmail.com>
	<CAHULbCk2ENwqRTjfpMoaZ2Mq9zLV-3pGb-pN7E=mmP7B-5=zCw@mail.gmail.com>
	<CADVHTB8FUxia_FPqd7D9oP-4kDF9HNB_e+XWoRNkzu6YiMG_SQ@mail.gmail.com>
	<0D3E437F-20EC-4B36-BDE2-F66E1C2A89EA@thelastpickle.com>
	<CALdd-zig0_LqsRFNx3+AHcfY=sQBNa7_E2wGc+WtA=rSjrfo-Q@mail.gmail.com>
Date: Wed, 18 Apr 2012 16:59:26 +0400
Message-ID: 
 <CAHULbC=jL=+pd6CNTYo-LN9aZP6-Cj2ypr4tQgKjcdEncBYY7g@mail.gmail.com>
Subject: Re: swap grows
From: ruslan usifov <ruslan.usifov@gmail.com>
To: user@cassandra.apache.org
Content-Type: multipart/alternative; boundary=20cf305b0e3c0f1f7304bdf3a048

--20cf305b0e3c0f1f7304bdf3a048
Content-Type: text/plain; charset=ISO-8859-1

Thanks for link. But for me still present question about  free memory. In
out cluster we have 200 IOPS in peaks, but still have about 3GB of free
memory on each server (cluster have 6 nodes tho there are 3*6=18 GB of
unused memry). I think that OS must fill all memory with pagecache (we do
backups throw DirectIO) of SStables, but it doesn't do that and i doesn't
understand  why. I can't find any sysctl that can tune pagecache thresholds
or ratio.

Any suggestion????

2012/4/18 Jonathan Ellis <jbellis@gmail.com>

> what-is-the-linux-kernel-parameter-vm-swappiness<http://www.linuxvox.com/2009/10/what-is-the-linux-kernel-parameter-vm-swappiness>

--20cf305b0e3c0f1f7304bdf3a048
Content-Type: text/html; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable

Thanks for link. But for me still present question about=A0 free memory. In=
 out cluster we have 200 IOPS in peaks, but still have about 3GB of free me=
mory on each server (cluster have 6 nodes tho there are 3*6=3D18 GB of unus=
ed memry). I think that OS must fill all memory with pagecache (we do backu=
ps throw DirectIO) of SStables, but it doesn&#39;t do that and i doesn&#39;=
t understand=A0 why. I can&#39;t find any sysctl that can tune pagecache th=
resholds or ratio. <br>
<br>Any suggestion????<br><br><div class=3D"gmail_quote">2012/4/18 Jonathan=
 Ellis <span dir=3D"ltr">&lt;<a href=3D"mailto:jbellis@gmail.com">jbellis@g=
mail.com</a>&gt;</span><br><blockquote class=3D"gmail_quote" style=3D"margi=
n:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<a href=3D"http://www.linuxvox.com/2009/10/what-is-the-linux-kernel-paramet=
er-vm-swappiness" target=3D"_blank">what-is-the-linux-kernel-parameter-vm-s=
wappiness</a></blockquote></div><br>

--20cf305b0e3c0f1f7304bdf3a048--