You are viewing a plain text version of this content. The canonical link for it is here.
Posted to user@kylin.apache.org by Hoang Le Trung <ho...@orenj.com> on 2017/01/06 07:39:26 UTC

Kylin query performance always slows in first time

Hi team,

I have faced problem about query performance on Kylin.
I run two instance Kylin(job) and Kylin(query) on two node of my hadoop cluster.

When my cluster have high load, it make kylin query running slow. I think high load affect to Hbase so that it make kylin read data from Hbase slower.
But
When my cluster have normal load (average below 10% CPU). I login Kylin and test one query, It always slow on first time. When I repeat this query again, I see it's faster.
I test with a lot of queries, but it's always slow on 1st try.

I wonder Do Kylin have slower when open connection and faster after that ?

If not So any solution to fix my issue?




Thanks!


________________________________
This e-mail may contain confidential or privileged information. If you received this e-mail by mistake, please don't forward it to anyone else, please erase it from your device and let me know so I don't do it again.

Re: Kylin query performance always slows in first time

Posted by Li Yang <li...@apache.org>.
If not exactly same query, similar subsequent queries can also benefit from
cache in HBase / HDFS.

On Fri, Jan 6, 2017 at 4:30 PM, Billy Liu <bi...@apache.org> wrote:

> If you repeat the same query again, it will hit the query cache I think.
>
> 2017-01-06 15:39 GMT+08:00 Hoang Le Trung <ho...@orenj.com>:
>
>> Hi team,
>>
>>
>>
>> I have faced problem about query performance on Kylin.
>>
>> I run two instance Kylin(job) and Kylin(query) on two node of my hadoop
>> cluster.
>>
>>
>>
>> When my cluster have high load, it make kylin query running slow. I
>> think high load affect to Hbase so that it make kylin read data from
>> Hbase slower.
>>
>> But
>>
>> When my cluster have normal load (average below 10% CPU). I login Kylin
>> and test one query, It always slow on first time. When I repeat this query
>> again, I see it’s faster.
>>
>> I test with a lot of queries, but it’s always slow on 1st try.
>>
>>
>>
>> I wonder Do Kylin have slower when open connection and faster after that
>> ?
>>
>>
>>
>> If not So any solution to fix my issue?
>>
>>
>>
>>
>>
>>
>>
>>
>>
>> Thanks!
>>
>>
>>
>> ------------------------------
>> This e-mail may contain confidential or privileged information. If you
>> received this e-mail by mistake, please don't forward it to anyone else,
>> please erase it from your device and let me know so I don't do it again.
>>
>
>

Re: Kylin query performance always slows in first time

Posted by Billy Liu <bi...@apache.org>.
If you repeat the same query again, it will hit the query cache I think.

2017-01-06 15:39 GMT+08:00 Hoang Le Trung <ho...@orenj.com>:

> Hi team,
>
>
>
> I have faced problem about query performance on Kylin.
>
> I run two instance Kylin(job) and Kylin(query) on two node of my hadoop
> cluster.
>
>
>
> When my cluster have high load, it make kylin query running slow. I think
> high load affect to Hbase so that it make kylin read data from Hbase
> slower.
>
> But
>
> When my cluster have normal load (average below 10% CPU). I login Kylin
> and test one query, It always slow on first time. When I repeat this query
> again, I see it’s faster.
>
> I test with a lot of queries, but it’s always slow on 1st try.
>
>
>
> I wonder Do Kylin have slower when open connection and faster after that ?
>
>
>
> If not So any solution to fix my issue?
>
>
>
>
>
>
>
>
>
> Thanks!
>
>
>
> ------------------------------
> This e-mail may contain confidential or privileged information. If you
> received this e-mail by mistake, please don't forward it to anyone else,
> please erase it from your device and let me know so I don't do it again.
>