incubator-cassandra-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Rüdiger Klaehn <rkla...@gmail.com>
Subject Re: Performance problem with large wide row inserts using CQL
Date Wed, 19 Feb 2014 19:06:11 GMT
Hi Yogi,

Both benchmarks go to different tables. I originally wanted to just write a
lot of data into an empty table and then evaluate what compression ratio I
can expect when I ran into the performance problem.

I am sorry, I forgot to mention this: I did not figure out how to create a
table using AST (it wasn't given in the example that I modified
https://github.com/Netflix/astyanax/blob/master/astyanax-examples/src/main/java/com/netflix/astyanax/examples/AstClient.java).
So the AstClient.java benchmark assumes that the table already exists.

cheers,

Rüdiger

On Wed, Feb 19, 2014 at 7:56 PM, Yogi Nerella <ynerella999@gmail.com> wrote:

> Rudger,
>
> I am trying this on 2.0.5 to see, but both Scala code and AST code are
> going to different tables?   Can you give the exact AST code you are trying?
>
> Yogi
>
>
> On Wed, Feb 19, 2014 at 10:49 AM, Sylvain Lebresne <sylvain@datastax.com>wrote:
>
>> On Wed, Feb 19, 2014 at 11:27 AM, Rüdiger Klaehn <rklaehn@gmail.com>wrote:
>>
>>>
>>> Am I doing something wrong, or is this a fundamental limitation of CQL.
>>>
>>
>> Neither. I believe you are running into
>> https://issues.apache.org/jira/browse/CASSANDRA-6737, which is a bug, a
>> performance bug, which we should and will fix. So thanks for the report. If
>> you could give a shot to the patch on that issue and check if it helps,
>> that would definitively be much appreciated.
>>
>> There is absolutely no fundamental reason why a CQL operation would be
>> more than 10 times slower than it's thrift equivalent, such dramatic
>> difference is indicative of a bug, something obviously wrong.
>>
>> --
>> Sylvain
>>
>
>

Mime
View raw message