carbondata-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "xuchuanyin (JIRA)" <j...@apache.org>
Subject [jira] [Created] (CARBONDATA-2091) Enhance data loading performance by specifying range bounds for sort columns
Date Mon, 29 Jan 2018 07:58:00 GMT
xuchuanyin created CARBONDATA-2091:
--------------------------------------

             Summary: Enhance data loading performance by specifying range bounds for sort
columns
                 Key: CARBONDATA-2091
                 URL: https://issues.apache.org/jira/browse/CARBONDATA-2091
             Project: CarbonData
          Issue Type: Improvement
            Reporter: xuchuanyin
            Assignee: xuchuanyin


Currently in carbondata, data loading using node_sort (also known as local_sort) has the following
procedures:
 # convert the input data in batch. (*Convert*)
 # sort the batch and write to the sort temp files. (*TempSort*)
 # combine the sort temp files and do merge sort to get a bigger ordered sort temp file. (*MergeSort*)
 # combine all the sort temp files and do a final sort, its results will feed the next procedure.
(*FinalSort*)
 # get rows in order and convert rows to carbondata columnar format pages. (*produce*)
 # Write bundles of pages to files and write the corresponding index file. (*consume*)

The Step1~Step3 are done concurrently using multi-thread. The Step4 is done using only one
thread. The Step5 is done using multi-thread. So the Step4 is the bottleneck among all the
procedures. When observing the data loading performance, we can see that the CPU usage after
Step3 is low.

 

We can enhance the data loading performance by parallelizing Step4.

 

User can specify range bounds for the sort columns and carbondata internally distributes the
records to different ranges and process the data concurrently in different ranges.



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

Mime
View raw message