Re: Logging queries

[Igor Leão]

Thanks Bhuvan!

Matija, I'm looking forward to this new release. Cassandra-diagnostics is
just great and this feature will make it awesome.
Hope to hear from you soon.

2017-02-18 17:20 GMT-03:00 Bhuvan Rawal :

> Im not sure if you can create an index on system_traces keyspace for this
> use case.
>
> If the performance issue that you are trying to troubleshoot is consistent
> than you can switch on tracing for a while and do dump of
> system_traces.events table say using COPY into csv. You can do analysis on
> that for finding the problematic query.
>
> copy system_traces.events TO 'traces_dump.csv';
>
> Also do make sure you dont set trace probability to a high number if
> working on a production database as it can adversely impact performance.
>
> Regards,
>
> On Sun, Feb 19, 2017 at 1:28 AM, Igor Leão  wrote:
>
>> Hi Bhuvan,
>> Thanks a lot!
>>
>> Any idea if something can be done for C* 2.X?
>>
>> Best,
>> Igor
>>
>> 2017-02-18 16:41 GMT-03:00 Bhuvan Rawal :
>>
>>> Hi Igor,
>>>
>>> If you are using java driver, you can log slow queries on client side
>>> using QueryLogger.
>>> https://docs.datastax.com/en/developer/java-driver/2.1/manual/logging/
>>>
>>> Slow Query logger for server was introduced in C* 3.10 version. Details:
>>> https://issues.apache.org/jira/browse/CASSANDRA-12403
>>>
>>> Regards,
>>> Bhuvan
>>>
>>> On Sun, Feb 19, 2017 at 12:59 AM, Igor Leão  wrote:
>>>
 Hi there,

 I'm wondering how to log queries from Cassandra. These queries can be
 either slow queries or all queries. The only constraint is that I should do
 this on server side.

 I tried using `nodetool settraceprobability`, which writes all queries
 to the keyspace `system_traces`. When I try to see which queries are slower
 than a given number, I get:

 Result: ```InvalidRequest: code=2200 [Invalid query] message="No
 secondary indexes on the restricted columns support the provided operators:
 "```
 Query: `select * from events where source_elapsed >= 1000;`

 My goal is to debug performance issues in a production database. I want
 to know which queries are degrading the performance of the db.

 Thanks in advance!







>>>
>>
>>
>> --
>> Igor Leão  Site Reliability Engineer
>>
>> Mobile: +55 81 99727-1083 
>> Skype: *igorvpcleao*
>> Office: +55 81 4042-9757 
>> Website: inlocomedia.com 
>> [image: inlocomedia]
>> 
>>  [image: LinkedIn]
>> 
>>  [image: Facebook]  [image:
>> Twitter]
>> 
>>
>>
>>
>>
>>
>>
>>
>


-- 
Igor Leão  Site Reliability Engineer

Mobile: +55 81 99727-1083 
Skype: *igorvpcleao*
Office: +55 81 4042-9757 
Website: inlocomedia.com 
[image: inlocomedia]

 [image: LinkedIn]

 [image: Facebook]  [image: Twitter]

Re: Logging queries

[Bhuvan Rawal]

Im not sure if you can create an index on system_traces keyspace for this
use case.

If the performance issue that you are trying to troubleshoot is consistent
than you can switch on tracing for a while and do dump of
system_traces.events table say using COPY into csv. You can do analysis on
that for finding the problematic query.

copy system_traces.events TO 'traces_dump.csv';

Also do make sure you dont set trace probability to a high number if
working on a production database as it can adversely impact performance.

Regards,

On Sun, Feb 19, 2017 at 1:28 AM, Igor Leão  wrote:

> Hi Bhuvan,
> Thanks a lot!
>
> Any idea if something can be done for C* 2.X?
>
> Best,
> Igor
>
> 2017-02-18 16:41 GMT-03:00 Bhuvan Rawal :
>
>> Hi Igor,
>>
>> If you are using java driver, you can log slow queries on client side
>> using QueryLogger.
>> https://docs.datastax.com/en/developer/java-driver/2.1/manual/logging/
>>
>> Slow Query logger for server was introduced in C* 3.10 version. Details:
>> https://issues.apache.org/jira/browse/CASSANDRA-12403
>>
>> Regards,
>> Bhuvan
>>
>> On Sun, Feb 19, 2017 at 12:59 AM, Igor Leão  wrote:
>>
>>> Hi there,
>>>
>>> I'm wondering how to log queries from Cassandra. These queries can be
>>> either slow queries or all queries. The only constraint is that I should do
>>> this on server side.
>>>
>>> I tried using `nodetool settraceprobability`, which writes all queries
>>> to the keyspace `system_traces`. When I try to see which queries are slower
>>> than a given number, I get:
>>>
>>> Result: ```InvalidRequest: code=2200 [Invalid query] message="No
>>> secondary indexes on the restricted columns support the provided operators:
>>> "```
>>> Query: `select * from events where source_elapsed >= 1000;`
>>>
>>> My goal is to debug performance issues in a production database. I want
>>> to know which queries are degrading the performance of the db.
>>>
>>> Thanks in advance!
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>
>
>
> --
> Igor Leão  Site Reliability Engineer
>
> Mobile: +55 81 99727-1083 
> Skype: *igorvpcleao*
> Office: +55 81 4042-9757 
> Website: inlocomedia.com 
> [image: inlocomedia]
> 
>  [image: LinkedIn]
> 
>  [image: Facebook]  [image: Twitter]
> 
>
>
>
>
>
>
>

Re: Logging queries

[Matija Gobec]

Hi Igor,

Your best bet is to wait for our next release of diagnostics
 for 2.x branch. We
are planning it for next week.

Best,
Matija

On Sat, Feb 18, 2017 at 8:58 PM, Igor Leão  wrote:

> Hi Bhuvan,
> Thanks a lot!
>
> Any idea if something can be done for C* 2.X?
>
> Best,
> Igor
>
> 2017-02-18 16:41 GMT-03:00 Bhuvan Rawal :
>
>> Hi Igor,
>>
>> If you are using java driver, you can log slow queries on client side
>> using QueryLogger.
>> https://docs.datastax.com/en/developer/java-driver/2.1/manual/logging/
>>
>> Slow Query logger for server was introduced in C* 3.10 version. Details:
>> https://issues.apache.org/jira/browse/CASSANDRA-12403
>>
>> Regards,
>> Bhuvan
>>
>> On Sun, Feb 19, 2017 at 12:59 AM, Igor Leão  wrote:
>>
>>> Hi there,
>>>
>>> I'm wondering how to log queries from Cassandra. These queries can be
>>> either slow queries or all queries. The only constraint is that I should do
>>> this on server side.
>>>
>>> I tried using `nodetool settraceprobability`, which writes all queries
>>> to the keyspace `system_traces`. When I try to see which queries are slower
>>> than a given number, I get:
>>>
>>> Result: ```InvalidRequest: code=2200 [Invalid query] message="No
>>> secondary indexes on the restricted columns support the provided operators:
>>> "```
>>> Query: `select * from events where source_elapsed >= 1000;`
>>>
>>> My goal is to debug performance issues in a production database. I want
>>> to know which queries are degrading the performance of the db.
>>>
>>> Thanks in advance!
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>
>
>
> --
> Igor Leão  Site Reliability Engineer
>
> Mobile: +55 81 99727-1083 
> Skype: *igorvpcleao*
> Office: +55 81 4042-9757 
> Website: inlocomedia.com 
> [image: inlocomedia]
> 
>  [image: LinkedIn]
> 
>  [image: Facebook]  [image: Twitter]
> 
>
>
>
>
>
>
>

Re: Logging queries

[Igor Leão]

Hi Bhuvan,
Thanks a lot!

Any idea if something can be done for C* 2.X?

Best,
Igor

2017-02-18 16:41 GMT-03:00 Bhuvan Rawal :

> Hi Igor,
>
> If you are using java driver, you can log slow queries on client side
> using QueryLogger.
> https://docs.datastax.com/en/developer/java-driver/2.1/manual/logging/
>
> Slow Query logger for server was introduced in C* 3.10 version. Details:
> https://issues.apache.org/jira/browse/CASSANDRA-12403
>
> Regards,
> Bhuvan
>
> On Sun, Feb 19, 2017 at 12:59 AM, Igor Leão  wrote:
>
>> Hi there,
>>
>> I'm wondering how to log queries from Cassandra. These queries can be
>> either slow queries or all queries. The only constraint is that I should do
>> this on server side.
>>
>> I tried using `nodetool settraceprobability`, which writes all queries to
>> the keyspace `system_traces`. When I try to see which queries are slower
>> than a given number, I get:
>>
>> Result: ```InvalidRequest: code=2200 [Invalid query] message="No
>> secondary indexes on the restricted columns support the provided operators:
>> "```
>> Query: `select * from events where source_elapsed >= 1000;`
>>
>> My goal is to debug performance issues in a production database. I want
>> to know which queries are degrading the performance of the db.
>>
>> Thanks in advance!
>>
>>
>>
>>
>>
>>
>>
>


-- 
Igor Leão  Site Reliability Engineer

Mobile: +55 81 99727-1083 
Skype: *igorvpcleao*
Office: +55 81 4042-9757 
Website: inlocomedia.com 
[image: inlocomedia]

 [image: LinkedIn]

 [image: Facebook]  [image: Twitter]

Re: Logging queries

[Bhuvan Rawal]

Hi Igor,

If you are using java driver, you can log slow queries on client side using
QueryLogger.
https://docs.datastax.com/en/developer/java-driver/2.1/manual/logging/

Slow Query logger for server was introduced in C* 3.10 version. Details:
https://issues.apache.org/jira/browse/CASSANDRA-12403

Regards,
Bhuvan

On Sun, Feb 19, 2017 at 12:59 AM, Igor Leão  wrote:

> Hi there,
>
> I'm wondering how to log queries from Cassandra. These queries can be
> either slow queries or all queries. The only constraint is that I should do
> this on server side.
>
> I tried using `nodetool settraceprobability`, which writes all queries to
> the keyspace `system_traces`. When I try to see which queries are slower
> than a given number, I get:
>
> Result: ```InvalidRequest: code=2200 [Invalid query] message="No secondary
> indexes on the restricted columns support the provided operators: "```
> Query: `select * from events where source_elapsed >= 1000;`
>
> My goal is to debug performance issues in a production database. I want to
> know which queries are degrading the performance of the db.
>
> Thanks in advance!
>
>
>
>
>
>
>