[ https://issues.apache.org/jira/browse/KNOX-1524?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16650272#comment-16650272 ]
Kevin Risden edited comment on KNOX-1524 at 10/15/18 2:26 PM: -------------------------------------------------------------- h2. Result Interpretation There is a JVM startup time of about 2 seconds as shown by the HDFS native results. HiveServer2 adds quite a bit of overhead compared to reading the file directly from HDFS. Doubling the time from HDFS native to return the results with HiveServer2. HiveServer2 Binary mode is more efficient than HTTP mode. The Knox overhead is about the same as the binary vs http mode overhead. There are probably some improvements that can be made to HiveServer2 to improve the performance. was (Author: risdenk): h2. Result Interpretation HiveServer2 adds quite a bit of overhead compared to reading the file directly from HDFS. Binary mode of HiveServer2 is more efficient than HTTP mode. The Knox overhead is minimal compared to the HiveServer2 overhead. There are probably some improvements that can be made to HiveServer2 to improve the performance. > Hive "select *" performance evaluation > -------------------------------------- > > Key: KNOX-1524 > URL: https://issues.apache.org/jira/browse/KNOX-1524 > Project: Apache Knox > Issue Type: Task > Reporter: Kevin Risden > Assignee: Kevin Risden > Priority: Major > Fix For: 1.2.0 > > > While looking at WebHDFS performance in KNOX-1221, I decided to look a bit > more into performance for common use cases. Hive performance is another area > that could use some research. -- This message was sent by Atlassian JIRA (v7.6.3#76005)