[
https://issues.apache.org/jira/browse/PIG-200?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13260155#comment-13260155
]
Jie Li commented on PIG-200:
----------------------------
Did anyone notice that pig-0.9.0 uses an extra job for L9 than pig-0.8.1?
L9 is very simple: (slightly changed for setting the default_parallel)
{code}
SET default_parallel $factor
register ../pigperf.jar;
A = load '$input/pigmix_page_views' using
org.apache.pig.test.udf.storefunc.PigPerformanceLoader()
as (user, action, timespent, query_term, ip_addr, timestamp,
estimated_revenue, page_info, page_links);
B = order A by query_term;
store B into '$output/L9out';
{code}
{panel:title=Output information of 0.8.1}
JobId Maps Reduces MaxMapTime MinMapTIme AvgMapTime
MaxReduceTime MinReduceTime AvgReduceTime Alias Feature Outputs
job_201204222028_0192 60 1 33 12 20 102 102
102 B SAMPLER
job_201204222028_0193 60 17 78 39 57 533 147
360 B ORDER_BY /tmp/10m-0.8.1/L9out,
{panel}
{panel:title=Output information of 0.9.0}
JobId Maps Reduces MaxMapTime MinMapTIme AvgMapTime
MaxReduceTime MinReduceTime AvgReduceTime Alias
Feature Outputs
job_201204222028_0269 60 0 171 27 116 0 0
0 A MAP_ONLY
job_201204222028_0270 60 1 63 9 26 136 136
136 B SAMPLER
job_201204222028_0271 60 17 183 30 66 657 262
446 B ORDER_BY /tmp/10m-0.9.0/L9out,
{panel}
We can see, 0.9.0 uses a MAP_ONLY job to load the data, which is almost as
expensive as the ORDER_BY job. In my environment with 4 slave nodes processing
10m records, it increases time from 1021 seconds (0.8.1) to 1921 seconds
(0.9.0)!
Does anybody know what happened?
> Pig Performance Benchmarks
> --------------------------
>
> Key: PIG-200
> URL: https://issues.apache.org/jira/browse/PIG-200
> Project: Pig
> Issue Type: Task
> Reporter: Amir Youssefi
> Assignee: Alan Gates
> Fix For: 0.2.0
>
> Attachments: generate_data.pl, perf-0.6.patch, perf.hadoop.patch,
> perf.patch, pigmix2.patch, pigmix_pig0.11.patch
>
>
> To benchmark Pig performance, we need to have a TPC-H like Large Data Set
> plus Script Collection. This is used in comparison of different Pig releases,
> Pig vs. other systems (e.g. Pig + Hadoop vs. Hadoop Only).
> Here is Wiki for small tests: http://wiki.apache.org/pig/PigPerformance
> I am currently running long-running Pig scripts over data-sets in the order
> of tens of TBs. Next step is hundreds of TBs.
> We need to have an open large-data set (open source scripts which generate
> data-set) and detailed scripts for important operations such as ORDER,
> AGGREGATION etc.
> We can call those the Pig Workouts: Cardio (short processing), Marathon (long
> running scripts) and Triathlon (Mix).
> I will update this JIRA with more details of current activities soon.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators:
https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira
