Re: performance getting even worse after optimization

[MohammadReza Zolfaghari]

Hi Xiaoting Ye,

Do you find a solution for your problem? 

Best,

On Thursday, January 8, 2015 at 9:39:16 PM UTC+3:30, Xiaoting Ye wrote:
>
> The index is of 149G, 19 shards with 1 replica.
>
> The es version is 1.4.1, and the java version is 1.7.0_71.
>
> I have specific routing strategy and the query used in testing only goes 
> to one shard: 
> heap.percentram.percent  load
> 5158  0.33
>
> (when it is under continues query, just one query at a time)
>
> This specific shard has 22502484 docs, 10GB in size.
>
> Thanks!
>
> On Thu, Jan 8, 2015 at 2:10 AM, Mark Walkom  > wrote:
>
>> How big is the index, how many shards and replicas?
>> What ES version? What java version?
>>
>> On 8 January 2015 at 20:40, Xiaoting Ye > 
>> wrote:
>>
>>> Hi,
>>>
>>>  I just did an _optimize operation on a cluster (10 data nodes, roughly 
>>> 350,000,000 docs in total). This a cluster only has one index.
>>>
>>> However, the performance gets even worse: the response time doubled or 
>>> even tripled.
>>>
>>> Any hint on this?
>>>
>>> Thanks!
>>>
>>> -- 
>>> You received this message because you are subscribed to the Google 
>>> Groups "elasticsearch" group.
>>> To unsubscribe from this group and stop receiving emails from it, send 
>>> an email to elasticsearc...@googlegroups.com .
>>> To view this discussion on the web visit 
>>> https://groups.google.com/d/msgid/elasticsearch/d9f9ba25-4a7f-4fba-978c-8368d74bc349%40googlegroups.com
>>>  
>>> 
>>> .
>>> For more options, visit https://groups.google.com/d/optout.
>>>
>>
>>  -- 
>> You received this message because you are subscribed to a topic in the 
>> Google Groups "elasticsearch" group.
>> To unsubscribe from this topic, visit 
>> https://groups.google.com/d/topic/elasticsearch/W49B4d9MWNk/unsubscribe.
>> To unsubscribe from this group and all its topics, send an email to 
>> elasticsearc...@googlegroups.com .
>> To view this discussion on the web visit 
>> https://groups.google.com/d/msgid/elasticsearch/CAEYi1X8B_qPdBA0S8JeXmhM2e013-YxQb5roZAJvEh-r1rxfQQ%40mail.gmail.com
>>  
>> 
>> .
>>
>> For more options, visit https://groups.google.com/d/optout.
>>
>
>

-- 
You received this message because you are subscribed to the Google Groups 
"elasticsearch" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to elasticsearch+unsubscr...@googlegroups.com.
To view this discussion on the web visit 
https://groups.google.com/d/msgid/elasticsearch/542cdeb0-2f76-4995-9343-cd64ac62b1a9%40googlegroups.com.
For more options, visit https://groups.google.com/d/optout.

Re: performance getting even worse after optimization

[Xiaoting Ye]

The index is of 149G, 19 shards with 1 replica.

The es version is 1.4.1, and the java version is 1.7.0_71.

I have specific routing strategy and the query used in testing only goes to
one shard:
heap.percentram.percent  load
5158  0.33

(when it is under continues query, just one query at a time)

This specific shard has 22502484 docs, 10GB in size.

Thanks!

On Thu, Jan 8, 2015 at 2:10 AM, Mark Walkom  wrote:

> How big is the index, how many shards and replicas?
> What ES version? What java version?
>
> On 8 January 2015 at 20:40, Xiaoting Ye  wrote:
>
>> Hi,
>>
>>  I just did an _optimize operation on a cluster (10 data nodes, roughly
>> 350,000,000 docs in total). This a cluster only has one index.
>>
>> However, the performance gets even worse: the response time doubled or
>> even tripled.
>>
>> Any hint on this?
>>
>> Thanks!
>>
>> --
>> You received this message because you are subscribed to the Google Groups
>> "elasticsearch" group.
>> To unsubscribe from this group and stop receiving emails from it, send an
>> email to elasticsearch+unsubscr...@googlegroups.com.
>> To view this discussion on the web visit
>> https://groups.google.com/d/msgid/elasticsearch/d9f9ba25-4a7f-4fba-978c-8368d74bc349%40googlegroups.com
>> 
>> .
>> For more options, visit https://groups.google.com/d/optout.
>>
>
>  --
> You received this message because you are subscribed to a topic in the
> Google Groups "elasticsearch" group.
> To unsubscribe from this topic, visit
> https://groups.google.com/d/topic/elasticsearch/W49B4d9MWNk/unsubscribe.
> To unsubscribe from this group and all its topics, send an email to
> elasticsearch+unsubscr...@googlegroups.com.
> To view this discussion on the web visit
> https://groups.google.com/d/msgid/elasticsearch/CAEYi1X8B_qPdBA0S8JeXmhM2e013-YxQb5roZAJvEh-r1rxfQQ%40mail.gmail.com
> 
> .
>
> For more options, visit https://groups.google.com/d/optout.
>

-- 
You received this message because you are subscribed to the Google Groups 
"elasticsearch" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to elasticsearch+unsubscr...@googlegroups.com.
To view this discussion on the web visit 
https://groups.google.com/d/msgid/elasticsearch/CAGVN9k7xZTBpchkOSqp%3DyLxqSKozo1WhVUveq%2BRaLDHmd81kpA%40mail.gmail.com.
For more options, visit https://groups.google.com/d/optout.

Re: performance getting even worse after optimization

[Mark Walkom]

How big is the index, how many shards and replicas?
What ES version? What java version?

On 8 January 2015 at 20:40, Xiaoting Ye  wrote:

> Hi,
>
>  I just did an _optimize operation on a cluster (10 data nodes, roughly
> 350,000,000 docs in total). This a cluster only has one index.
>
> However, the performance gets even worse: the response time doubled or
> even tripled.
>
> Any hint on this?
>
> Thanks!
>
> --
> You received this message because you are subscribed to the Google Groups
> "elasticsearch" group.
> To unsubscribe from this group and stop receiving emails from it, send an
> email to elasticsearch+unsubscr...@googlegroups.com.
> To view this discussion on the web visit
> https://groups.google.com/d/msgid/elasticsearch/d9f9ba25-4a7f-4fba-978c-8368d74bc349%40googlegroups.com
> 
> .
> For more options, visit https://groups.google.com/d/optout.
>

-- 
You received this message because you are subscribed to the Google Groups 
"elasticsearch" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to elasticsearch+unsubscr...@googlegroups.com.
To view this discussion on the web visit 
https://groups.google.com/d/msgid/elasticsearch/CAEYi1X8B_qPdBA0S8JeXmhM2e013-YxQb5roZAJvEh-r1rxfQQ%40mail.gmail.com.
For more options, visit https://groups.google.com/d/optout.

performance getting even worse after optimization

[Xiaoting Ye]

Hi,

 I just did an _optimize operation on a cluster (10 data nodes, roughly 
350,000,000 docs in total). This a cluster only has one index.

However, the performance gets even worse: the response time doubled or even 
tripled.

Any hint on this?

Thanks!

-- 
You received this message because you are subscribed to the Google Groups 
"elasticsearch" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to elasticsearch+unsubscr...@googlegroups.com.
To view this discussion on the web visit 
https://groups.google.com/d/msgid/elasticsearch/d9f9ba25-4a7f-4fba-978c-8368d74bc349%40googlegroups.com.
For more options, visit https://groups.google.com/d/optout.