Mailing-List: contact user-help@cassandra.apache.org; run by ezmlm
Precedence: bulk
Reply-To: user@cassandra.apache.org
Received-SPF: neutral (athena.apache.org: local policy)
From: Roland Gude <roland.gude@yoochoose.com>
To: Jonathan Ellis <jbellis@gmail.com>, "user@cassandra.apache.org"
	<user@cassandra.apache.org>
CC: Juergen Link <juergen.link@yoochoose.com>, Johannes Hoerle
	<johannes.hoerle@yoochoose.com>
Date: Sat, 2 Apr 2011 03:38:23 -0700
Subject: AW: too many open files - maybe a fd leak in indexslicequeries
Thread-Topic: too many open files - maybe a fd leak in indexslicequeries
Thread-Index: AcvwIkdy+R5PCwZzQ8GmT3xW+6Ij/AA/4B5A
Message-ID: 
 <120CB7532EA53A4D8CA6B63F94B4ADB351E6D627DB@IE2RD2XVS021.red002.local>
References: 
 <120CB7532EA53A4D8CA6B63F94B4ADB351E6D62754@IE2RD2XVS021.red002.local>
 <AANLkTinSJdu1fVPOgh8oncHgrsCrrNELeGY7w-THYuaj@mail.gmail.com>
In-Reply-To: <AANLkTinSJdu1fVPOgh8oncHgrsCrrNELeGY7w-THYuaj@mail.gmail.com>
Accept-Language: de-DE, en-US
Content-Language: de-DE
acceptlanguage: de-DE, en-US
Content-Type: text/plain; charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
MIME-Version: 1.0


Hi,

The open file limit is 1024
Sstable count is somewhere around 20 or so thread count is in the same orde=
r of magnitude I guess
But lsof shows that deleted sstables still have open file handles. This see=
ms to be the issue as this number keeps growing.
Any ideas?

Roland.

-----Urspr=FCngliche Nachricht-----
Von: Jonathan Ellis [mailto:jbellis@gmail.com]=20
Gesendet: Freitag, 1. April 2011 06:07
An: user@cassandra.apache.org
Cc: Roland Gude; Juergen Link; Johannes Hoerle
Betreff: Re: too many open files - maybe a fd leak in indexslicequeries

Index queries (ColumnFamilyStore.scan) don't do any low-level i/o
themselves, they go through CFS.getColumnFamily, which is what normal
row fetches also go through.  So if there is a leak there it's
unlikely to be specific to indexes.

What is your open-file limit (remember that sockets count towards
this), thread count, sstable count?

On Thu, Mar 31, 2011 at 4:15 PM, Roland Gude <roland.gude@yoochoose.com> wr=
ote:
> I experience something that looks exactly like
> https://issues.apache.org/jira/browse/CASSANDRA-1178
>
> On cassandra 0.7.3 when using index slice queries (lots of them)
>
> Crashing multiple nodes and rendering the cluster useless. But I have no
> clue where to look if index queries still leak fd
>
>
>
> Does anybody know about it?
>
> Where could I look?
>
>
>
> Greetings,
>
> roland
>
>
>
> --
>
> YOOCHOOSE GmbH
>
>
>
> Roland Gude
>
> Software Engineer
>
>
>
> Im Mediapark 8, 50670 K=F6ln
>
>
>
> +49 221 4544151 (Tel)
>
> +49 221 4544159 (Fax)
>
> +49 171 7894057 (Mobil)
>
>
>
>
>
> Email:=A0roland.gude@yoochoose.com
>
> WWW: www.yoochoose.com
>
>
>
> YOOCHOOSE GmbH
>
> Gesch=E4ftsf=FChrer: Dr. Uwe Alkemper, Michael Friedmann
>
> Handelsregister: Amtsgericht K=F6ln HRB 65275
>
> Ust-Ident-Nr: DE 264 773 520
>
> Sitz der Gesellschaft: K=F6ln
>
>


--=20
Jonathan Ellis
Project Chair, Apache Cassandra
co-founder of DataStax, the source for professional Cassandra support
http://www.datastax.com