onefoursix

<dependencies>
	
	<dependency>
		<groupId>org.apache.hive</groupId>
		<artifactId>hive-jdbc</artifactId>
		<version>0.10.0-cdh4.7.0</version>
	</dependency>

	<dependency>
		<groupId>org.apache.hive</groupId>

onefoursix

<dependencies>
	
	<dependency>
		<groupId>org.apache.hive</groupId>
		<artifactId>hive-jdbc</artifactId>
		<version>0.12.0-cdh5.1.0</version>
	</dependency>

	<dependency>
		<groupId>org.apache.hive</groupId>

onefoursix

#!/usr/bin/python

## **********************************************************************
## restart-hs2-role.py 
## 
## Example of how to restart the HS2 role in the Hive Service using the Cloudera Manager API
##
## Make sure to set the CM Host, CM Port, login, password, Cluster Name and Hive Service name
##  in the "Settings" section below
## 

onefoursix

#!/usr/bin/python

## *******************************************************************************************
##  impalaQueries.py
##
##  Getting Info on Impala Queries
##
##  Usage: ./impalaQueries.py  
##
## *******************************************************************************************

onefoursix

#!/usr/bin/python

## ********************************************************************************
## get-bdr-history.py 
## 
## Example of how to retrieve BDR command history using the Cloudera Manager API
##
## Usage: ./get-bdr-history.py <limit>
## 
##        <limit> is the maximum number of replication commands to retrieve 

onefoursix

#!/usr/bin/python

## ********************************************************************************
## get-hive-yarn-jobs-for-sentry-user.py 
## 
## Example of how to retrieve info on YARN Hive jobs for a given Sentry user 
## using the Cloudera Manager API
##
## Usage: ./get-hive-yarn-jobs-for-sentry-user.py <sentry_user_name>
## 

onefoursix

#!/usr/bin/python

## ********************************************************************************
## get-yarn-long-running-jobs.py 
## 
## Usage: ./get-yarn-long-running-jobs.py
## 
## Edit the settings below to connect to your Cluster
##
## ********************************************************************************

onefoursix

#!/usr/bin/python

import sys
from cm_api.api_client import ApiResource

##  ** CM Connection Settings ******************************
cm_host = "localhost"
cm_port = "7180"
cm_login = "admin"
cm_password = "admin"

onefoursix

#!/usr/bin/python

## ********************************************************************************
## mr-usage-by-user.py 
##
## Aggregates YARN MapReduce usage by day and user and writes the results to the console and to a file
##
## As the CM-API call "yarn.get_yarn_applications" can only return 1000 jobs max per call the script will make
## multiple calls to yarn.get_yarn_applications and aggregate all results between the script's global start and end times
##

onefoursix

FROM streamsets/datacollector:3.11.0
RUN sudo chgrp -R 0 /etc/sdc /logs /data /resources /opt/streamsets-datacollector-3.11.0 && sudo chmod -R g=u /etc/sdc /logs /data /resources /opt/streamsets-datacollector-3.11.0 
RUN sudo sed -i 's/http.realm.file.permission.check=true/http.realm.file.permission.check=false/' /etc/sdc/sdc.properties