[jira] [Commented] (HIVE-9153) Perf enhancement on CombineHiveInputFormat and HiveInputFormat

["liyunzhang_intel (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/HIVE-9153?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15763251#comment-15763251 ] 

liyunzhang_intel commented on HIVE-9153:
----------------------------------------

[~lirui]:  in [hive on spark wiki|https://cwiki.apache.org/confluence/display/Hive/Hive+on+Spark%3A+Getting+Started], it said that the recommended value for "mapreduce.input.fileinputformat.split.maxsize" is 750000000(750MB). is this configuration suitable for all cases? for example, if the input data is 1.5G, there will be 2 mappers when "mapreduce.input.fileinputformat.split.maxsize" is 750M and there will be 4 mappers when "mapreduce.input.fileinputformat.split.maxsize" is 375M.  But if we can start 4 mappers  when the job starts, there is no obvious  difference in execution time when setting "mapreduce.input.fileinputformat.split.maxsize" as 750M or 375M because there is 1 round of run in these two cases. 
Another question: can you kindly print out some jira numbers about performance test of hive on spark as you are familiar with this project? currently i only find HIVE-9134.

> Perf enhancement on CombineHiveInputFormat and HiveInputFormat
> --------------------------------------------------------------
>
>                 Key: HIVE-9153
>                 URL: https://issues.apache.org/jira/browse/HIVE-9153
>             Project: Hive
>          Issue Type: Sub-task
>          Components: Spark
>            Reporter: Brock Noland
>            Assignee: Rui Li
>             Fix For: 1.1.0
>
>         Attachments: HIVE-9153.1-spark.patch, HIVE-9153.1-spark.patch, HIVE-9153.2.patch, HIVE-9153.3.patch, screenshot.PNG
>
>
> The default InputFormat is {{CombineHiveInputFormat}} and thus HOS uses this. However, Tez uses {{HiveInputFormat}}. Since tasks are relatively cheap in Spark, it might make sense for us to use {{HiveInputFormat}} as well. We should evaluate this on a query which has many input splits such as {{select count(\*) from store_sales where something is not null}}.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)