cassandra-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Manu Zhang <owenzhang1...@gmail.com>
Subject Re: Why my Cassandra is compacting like mad
Date Tue, 16 Oct 2012 11:58:49 GMT
only 1/8 of heap is used. Only system-schema_columns cf is compacted. The
weird thing is that it never stops itself.

On Tue, Oct 16, 2012 at 5:14 PM, Alain RODRIGUEZ <arodrime@gmail.com> wrote:

> "I don't what hardware information may help"
>
> A low memory server will produce an intensive use of CPU and disk IO. It
> will write a lot of small SSTables which will need to be compacted very
> often. That was one of my thought when I asked.
>
> Alain
>
>
> 2012/10/15 Manu Zhang <owenzhang1990@gmail.com>
>
>> I use default option for compaction:
>>    in_memory_compaction_limit_in_mb: 64
>>    multithreaded_compaction: false
>>    compaction_throughput_mb_per_sec: 16
>>    compaction_preheat_key_cache: true
>>
>>
>> I aborted Cassandra after a timeout query;
>> my Cassandra is 1.2beta-2
>> I don't what hardware information may help
>>
>>
>> On Mon, Oct 15, 2012 at 11:19 PM, Michael Kjellman <
>> mkjellman@barracuda.com> wrote:
>>
>>> And to clarify my reply, this was a loop in compactions on
>>> system-schema_columns specifically.
>>>
>>> From: Michael Kjellman <mkjellman@barracuda.com>
>>> Reply-To: "user@cassandra.apache.org" <user@cassandra.apache.org>
>>> Date: Monday, October 15, 2012 8:11 AM
>>> To: "user@cassandra.apache.org" <user@cassandra.apache.org>
>>> Subject: Re: Why my Cassandra is compacting like mad
>>>
>>> I had a similar bug with 1.1.5 but I couldn't reproduce it so I didn't
>>> file a bug. I did a rolling restart of my nodes and things went back to
>>> normal.
>>>
>>> From: Manu Zhang <owenzhang1990@gmail.com>
>>> Reply-To: "user@cassandra.apache.org" <user@cassandra.apache.org>
>>> Date: Monday, October 15, 2012 8:02 AM
>>> To: "user@cassandra.apache.org" <user@cassandra.apache.org>
>>> Subject: Why my Cassandra is compacting like mad
>>>
>>> My Cassandra is compacting like mad (look at the following messages)
>>> after I restart it after a timeout query. It won't stop until I kill the
>>> process.
>>>
>>>
>>> INFO 22:57:41,839 Compacting
>>> [SSTableReader(path='/home/manuzhang/cassandra/data/system/schema_columns/system-schema_columns-ia-1258-Data.db')]
>>>  INFO 22:57:42,077 Compacted to
>>> [/home/manuzhang/cassandra/data/system/schema_columns/system-schema_columns-ia-1259-Data.db,].
>>>  4,377 to 4,377 (~100% of original) bytes for 3 keys at 0.017539MB/s.
>>>  Time: 238ms.
>>>  INFO 22:57:42,079 Compacting
>>> [SSTableReader(path='/home/manuzhang/cassandra/data/system/schema_columns/system-schema_columns-ia-1259-Data.db')]
>>>  INFO 22:57:42,309 Compacted to
>>> [/home/manuzhang/cassandra/data/system/schema_columns/system-schema_columns-ia-1260-Data.db,].
>>>  4,377 to 4,377 (~100% of original) bytes for 3 keys at 0.018149MB/s.
>>>  Time: 230ms.
>>>  INFO 22:57:42,311 Compacting
>>> [SSTableReader(path='/home/manuzhang/cassandra/data/system/schema_columns/system-schema_columns-ia-1260-Data.db')]
>>>  INFO 22:57:42,574 Compacted to
>>> [/home/manuzhang/cassandra/data/system/schema_columns/system-schema_columns-ia-1261-Data.db,].
>>>  4,377 to 4,377 (~100% of original) bytes for 3 keys at 0.015872MB/s.
>>>  Time: 263ms.
>>>  INFO 22:57:42,576 Compacting
>>> [SSTableReader(path='/home/manuzhang/cassandra/data/system/schema_columns/system-schema_columns-ia-1261-Data.db')]
>>>  INFO 22:57:42,814 Compacted to
>>> [/home/manuzhang/cassandra/data/system/schema_columns/system-schema_columns-ia-1262-Data.db,].
>>>  4,377 to 4,377 (~100% of original) bytes for 3 keys at 0.017539MB/s.
>>>  Time: 238ms.
>>>  INFO 22:57:42,816 Compacting
>>> [SSTableReader(path='/home/manuzhang/cassandra/data/system/schema_columns/system-schema_columns-ia-1262-Data.db')]
>>>  INFO 22:57:43,070 Compacted to
>>> [/home/manuzhang/cassandra/data/system/schema_columns/system-schema_columns-ia-1263-Data.db,].
>>>  4,377 to 4,377 (~100% of original) bytes for 3 keys at 0.016434MB/s.
>>>  Time: 254ms.
>>>
>>> ----------------------------------
>>> 'Like' us on Facebook for exclusive content and other resources on all
>>> Barracuda Networks solutions.
>>> Visit http://barracudanetworks.com/facebook
>>>   ­­
>>>
>>> ----------------------------------
>>> 'Like' us on Facebook for exclusive content and other resources on all
>>> Barracuda Networks solutions.
>>> Visit http://barracudanetworks.com/facebook
>>>   ­­
>>>
>>
>>
>

Mime
View raw message