Re: too many open files - maybe a fd leak in indexslicequeries

2011-04-05 Thread Jonathan Ellis
sounds like they haven't been munmapped yet.  try forcing a GC.

On Sat, Apr 2, 2011 at 5:38 AM, Roland Gude  wrote:
>
> Hi,
>
> The open file limit is 1024
> Sstable count is somewhere around 20 or so thread count is in the same order 
> of magnitude I guess
> But lsof shows that deleted sstables still have open file handles. This seems 
> to be the issue as this number keeps growing.
> Any ideas?
>
> Roland.
>
> -Ursprüngliche Nachricht-
> Von: Jonathan Ellis [mailto:jbel...@gmail.com]
> 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  
> wrote:
>> 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 Köln
>>
>>
>>
>> +49 221 4544151 (Tel)
>>
>> +49 221 4544159 (Fax)
>>
>> +49 171 7894057 (Mobil)
>>
>>
>>
>>
>>
>> Email: roland.g...@yoochoose.com
>>
>> WWW: www.yoochoose.com
>>
>>
>>
>> YOOCHOOSE GmbH
>>
>> Geschäftsführer: Dr. Uwe Alkemper, Michael Friedmann
>>
>> Handelsregister: Amtsgericht Köln HRB 65275
>>
>> Ust-Ident-Nr: DE 264 773 520
>>
>> Sitz der Gesellschaft: Köln
>>
>>
>
>
>
> --
> Jonathan Ellis
> Project Chair, Apache Cassandra
> co-founder of DataStax, the source for professional Cassandra support
> http://www.datastax.com
>
>
>



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


Re: too many open files - maybe a fd leak in indexslicequeries

2011-03-31 Thread Jonathan Ellis
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  wrote:
> 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 Köln
>
>
>
> +49 221 4544151 (Tel)
>
> +49 221 4544159 (Fax)
>
> +49 171 7894057 (Mobil)
>
>
>
>
>
> Email: roland.g...@yoochoose.com
>
> WWW: www.yoochoose.com
>
>
>
> YOOCHOOSE GmbH
>
> Geschäftsführer: Dr. Uwe Alkemper, Michael Friedmann
>
> Handelsregister: Amtsgericht Köln HRB 65275
>
> Ust-Ident-Nr: DE 264 773 520
>
> Sitz der Gesellschaft: Köln
>
>



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