This is the documentation for Cloudera Enterprise 5.8.x. Documentation for other versions is available at Cloudera Documentation.

Single User Mode Requirements

In a conventional Cloudera Manager deployment, the Cloudera Manager Agent, which manages Hadoop processes on each host, runs as the root user. However, some environments restrict access to the root account.

Cloudera Manager 5.3 and higher provides single user mode, which satisfies the requirements of such environments. In single user mode, the Cloudera Manager Agent and all the processes run by services managed by Cloudera Manager are started as a single configured user and group. Single user mode prioritizes isolation between Hadoop and the rest of the system over isolation between Hadoop processes running on the system.

Within a Cloudera Manager deployment, single user mode is global and applies to all clusters managed by that instance of Cloudera Manager.

By default, the single user is cloudera-scm and the configuration steps described in the following sections assume that user. However, other users are supported. If you choose another user, replace cloudera-scm in the following steps with the selected user, and perform the additional steps in Using a Non-default Single User.

The following sections describe limitations of single user mode and the required configuration steps for the supported installation scenarios at specific points during the installation process.

Limitations

  • Switching between conventional and single user mode is not supported.
  • Single user mode is supported for clusters running CDH 5.2 and higher.
  • NFS Gateway is not supported in single user mode.
  • Cloudera Navigator data encryption components are not supported in single user mode.

Using a Non-default Single User

When configuring single user mode for a user other than the default (cloudera-scm), perform the following configuration steps:

  • Make the following directories writable by the single user:
    • /var/log/cloudera-scm-agent/
    • /var/lib/cloudera-scm-agent/
  • Cloudera Manager stores parcels under /opt/cloudera, which by default is owned by cloudera-scm. Do one of the following:
    • Change /opt/cloudera to be writable by the single user.
    • Change the parcel directory location to be writable by the single user:
      1. Go to Administration > Settings > Parcels.
      2. Set the Local Parcel Repository Path property.
      3. Click Save Changes.
  • For a single user username, create the process limits configuration file at /etc/security/limits.d/username.conf with the following settings: 
    username soft nofile 32768
username soft nproc 65536
username hard nofile 1048576
username hard nproc unlimited
username hard memlock unlimited
username soft memlock unlimited

Configuration Steps Before Starting Cloudera Manager Agents in Installation Paths B and C

  • If you manually install Agent packages, before starting the Agents, configure them to run as cloudera-scm by editing the file /etc/default/cloudera-scm-agent and uncommenting the line: 
    USER="cloudera-scm"
  • Configure the parcels directory. Do one of the following:
    • On each host, in the Agent configuration file /etc/cloudera-scm-agent/config.ini, set the parcel_dir property: 
      # Parcel directory.  Unpacked parcels will be stored in this directory.
# Downloaded parcels will be stored in <parcel_dir>/../parcel-cache
# parcel_dir=/opt/cloudera/parcels
      1. Click Hosts in the top navigation bar.
      2. Click the Configuration tab.
      3. Select Category > Parcels.
      4. Configure the value of the Parcel Directory property. The setting of the parcel_dir property in the Cloudera Manager Agent configuration file overrides this setting.
      5. Click Save Changes to commit the changes.
      6. Restart the Cloudera Manager Agent on all hosts.

Configuration Steps Before Running the Installation Wizard

Before configuring a cluster to run in single user mode, the following steps must be performed on all hosts in the cluster:
  • Give the single user passwordless sudo access. You must create the user if it doesn’t exist. One common way of achieving this is to add the user to the configured sudoers group by running the command: 
    usermod -a -G sudo cloudera-scm
    or adding a new sudo configuration for the cloudera-scm group by running the command visudo and then adding the following line: 
    %cloudera-scm ALL=(ALL) NOPASSWD: ALL
  • Sudo must be configured so that /usr/sbin is in the path when running sudo. One way to achieve this is by adding the following configuration to sudoers:
    1. Edit the /etc/sudoers file using the visudo command
    2. Add this line to the configuration file: 
      Defaults secure_path = /sbin:/bin:/usr/sbin:/usr/bin
  • Set up per user limits for su prior to setting up the Agent.
    1. Edit/etc/pam.d/su.
    2. Uncomment: 
      session required pam_limits.so
  • Roles that run on Tomcat require some directories to exist in non-configurable paths. The following directories must be created and be writable by cloudera-scm:
    • HDFS (HttpFS role) - /var/lib/hadoop-httpfs
    • Oozie Server - /var/lib/oozie
    • Sqoop 2 Server - /var/lib/sqoop2
    • Solr Server - /var/lib/solr
  • Cloudera recommends that you create a prefix directory (for example, /cm) owned by cloudera-scm under which all other service directories will be placed. In single user mode, the Cloudera Manager Agent creates directories under the prefix directory with the correct ownership. If hosts have additional volumes on them that will be used for data directories Cloudera recommends creating a directory on each volume (for example, /data0/cm and /data1/cm) that is writable by cloudera-scm.

Configuration Steps Before Starting the Installation Wizard in Installation Paths B and C

Perform the following steps for the indicated scenarios:

  • Path C - Do one of the following:
    • Create and change the ownership of /var/lib/cloudera-scm-server to the single user.
    • Set the Cloudera Manager Server local storage directory to one owned by the single user:
      1. Go to Administration > Settings > Advanced.
      2. Set the Cloudera Manager Server Local Data Storage Directory property to a directory owned by the single user.
      3. Click Save Changes to commit the changes.
  • Path B and C when using already managed hosts - Configure single user mode:
    1. Go to Administration > Settings > Advanced.
    2. Check the Single User Mode checkbox.
    3. Click Save Changes to commit the changes.

Configuration Steps While Running the Installation Wizard

When configuring the first cluster in Cloudera Manager using the Installation wizard you’ll have the option to set up the cluster in single user mode. This configures the Agents to run as cloudera-scm.

During the review configuration step you confirm that all the configured paths are writable by cloudera-scm. The directories themselves don’t have to exist as long as the parent directory is writable by cloudera-scm.

Following the standard review configuration page, an additional paths configuration page shows all the configurable paths for the services that will be created in the cluster. These must also be modified to be locations writable by cloudera-scm. In most cases, the paths that need to be modified from their default locations fall under two categories:
  • Paths under /var - These are log, run, and data directories for the different services.
  • Per volume data directories - These are data directory configurations that list a directory per volume. Such configurations are used by HDFS, MapReduce, YARN and Impala.

Configuration for Secure Clusters

You must perform some additional configuration when setting up secure HDFS in single user mode:

Controlling Access to sudo Commands

To comply with security requirements, you may need to control access to the sudo commands run by Cloudera Manager Agents. You can control access by creating a “whitelist” of sudo commands that the Cloudera Manager Agent runs, or you can override the sudo command so that a custom script that denies some actions is called instead.

Cloudera Manager Agents use sudo for the following regular operations:
  • Running the update-alternatives command during upgrades and when updating parcels.
  • Adding new roles or services that require sudo access to the chown and chmod commands.
  • Running the mount and unmount commands when performing resource management activities that use Linux Control Groups (cgroups) and mounting a tmpfs mount point for temporary directories for cm_processes.
  • Collecting diagnostics, which requires reading files from the /proc and /etc directories and distribution-specific networking configuration files.

Whitelisting sudo Commands

The following commands may need to be whitelisted for the cloudera-scm-agent user. This can be either the default user, cloudera-scm, or a single user you specify. Use Linux tools to manage access to these commands as required for your deployment. (See the man page for sudoers.)

Regular Operation Commands
  • cat
  • chmod
  • chown
  • cp
  • mkdir
  • mount
  • rm
  • umount
  • update-alternatives
Support Bundle Collection Commands
  • bash
  • cat
  • date
  • df
  • dmesg
  • grep
  • hostname
  • ls
  • netstat
  • ps
  • rpm
  • uname
  • chkconfig
  • ethtool
  • ifconfig
  • iptables
  • lsmod
  • lspci
  • lvdisplay
  • service
  • sysctl
  • curl
  • dig
  • host
  • lsb_release
  • lscpu
  • nslookup
  • ntpstat
  • python
  • sar
  • top
  • uptime
  • vmstat
  • dmidecode
  • lsof
  • ntpq

Overriding the sudo Command

You can override the sudo command so that a custom script is called instead. This script can deny some actions.

To configure the location of this script:
  1. Edit the /etc/cloudera-scm-agent/config.ini file on all cluster hosts and add the following line: 
    sudo_command=path_to_script
  2. Restart the Cloudera Manager Agent on all cluster hosts: 
    service cloudera-scm-agent restart

To help determine which commands to override, see the following samples of typical commands run by Cloudera Manager Agent.

Commands run by the Cloudera Manager Agent while it brings up roles for new services on a single host: 
/bin/cat /proc/cgroups
/bin/chmod -R ugo+r /etc/accumulo/*
/bin/chmod -R ugo+r /etc/hadoop/*
/bin/chmod -R ugo+r /etc/hbase/*
/bin/chmod -R ugo+r /etc/hive/*
/bin/chmod -R ugo+r /etc/solr/*
/bin/chmod -R ugo+r /etc/spark/*
/bin/chmod -R ugo+r /etc/sqoop/*
/bin/chmod 0644 /ngs/app/searchp/var/run/cloudera-scm-agent/process/*/topology.map
/bin/chmod 0755 /ngs/app/searchp/opt/parcels/CDH*/lib/hue/desktop
/bin/chmod 0755 /ngs/app/searchp/var/run/cloudera-scm-agent/process/*/topology.py
/bin/chmod 4754 /ngs/app/searchp/opt/parcels/CDH*/lib/hadoop-0.20-mapreduce/sbin/Linux/task-controller
/bin/chmod 6050 /ngs/app/searchp/opt/parcels/CDH*/lib/hadoop-yarn/bin/container-executor
/bin/chown -R cloudera-scm:cloudera-scm /tmp/*
/bin/chown searchp:searchp /etc/hadoop/*/topology.map
/bin/chown searchp:searchp /etc/hadoop/*/topology.py
/bin/chown searchp:searchp /ngs/app/searchp/var/run/searchp-agent/process/*/topology.map
/bin/chown searchp:searchp /ngs/app/searchp/var/run/searchp-agent/process/*/topology.py
/bin/chown root /etc/accumulo/*
/bin/chown root /etc/hadoop/*
/bin/chown root /etc/hbase/*
/bin/chown root /etc/hive/*
/bin/chown root /etc/solr/*
/bin/chown root /etc/spark/*
/bin/chown root /etc/sqoop/*
/bin/chown root /ngs/app/searchp/opt/parcels/CDH*/lib/hadoop-0.20-mapreduce/sbin/Linux/task-controller
/bin/chown root /ngs/app/searchp/opt/parcels/CDH*/lib/hadoop-yarn/bin/container-executor
/bin/cp -a /ngs/app/searchp/var/run/cloudera-scm-agent/process/*/accumulo-conf /etc/accumulo/*
/bin/cp -a /ngs/app/searchp/var/run/cloudera-scm-agent/process/*/hadoop-conf /etc/hadoop/*
/bin/cp -a /ngs/app/searchp/var/run/cloudera-scm-agent/process/*/yarn-conf /etc/hadoop/*
/bin/cp -a /ngs/app/searchp/var/run/cloudera-scm-agent/process/*/hadoop-conf /etc/hadoop/*
/bin/cp -a /ngs/app/searchp/var/run/cloudera-scm-agent/process/*/yarn-conf /etc/hadoop/*
/bin/cp -a /ngs/app/searchp/var/run/cloudera-scm-agent/process/*/hadoop-conf /etc/hadoop/*
/bin/cp -a /ngs/app/searchp/var/run/cloudera-scm-agent/process/*/hadoop-conf /etc/hadoop/*
/bin/cp -a /ngs/app/searchp/var/run/cloudera-scm-agent/process/*/hbase-conf /etc/hbase/*
/bin/cp -a /ngs/app/searchp/var/run/cloudera-scm-agent/process/*/hbase-conf /etc/hbase/*
/bin/cp -a /ngs/app/searchp/var/run/cloudera-scm-agent/process/*/hive-conf /etc/hive/*
/bin/cp -a /ngs/app/searchp/var/run/cloudera-scm-agent/process/*/hive-conf /etc/hive/*
/bin/cp -a /ngs/app/searchp/var/run/cloudera-scm-agent/process/*/solr-conf /etc/solr/*
/bin/cp -a /ngs/app/searchp/var/run/cloudera-scm-agent/process/*/solr-conf /etc/solr/*
/bin/cp -a /ngs/app/searchp/var/run/cloudera-scm-agent/process/*/spark-conf /etc/spark/*
/bin/cp -a /ngs/app/searchp/var/run/cloudera-scm-agent/process/*/spark-conf /etc/spark/*
/bin/cp -a /ngs/app/searchp/var/run/cloudera-scm-agent/process/*/sqoop-conf /etc/sqoop/*
/bin/cp -a /ngs/app/searchp/var/run/cloudera-scm-agent/process/*/sqoop-conf /etc/sqoop/*
/bin/cp -p /ngs/app/searchp/var/run/cloudera-scm-agent/process/*/topology.map /etc/hadoop/*/topology.map
/bin/cp -p /ngs/app/searchp/var/run/cloudera-scm-agent/process/*/topology.py /etc/hadoop/*/topology.py
/bin/mkdir -p /etc/accumulo
/bin/mkdir -p /etc/flume-ng
/bin/mkdir -p /etc/hadoop
/bin/mkdir -p /etc/hadoop-httpfs
/bin/mkdir -p /etc/hadoop-kms
/bin/mkdir -p /etc/hbase
/bin/mkdir -p /etc/hbase-solr
/bin/mkdir -p /etc/hive
/bin/mkdir -p /etc/hive-hcatalog
/bin/mkdir -p /etc/hive-webhcat
/bin/mkdir -p /etc/hue
/bin/mkdir -p /etc/impala
/bin/mkdir -p /etc/llama
/bin/mkdir -p /etc/mahout
/bin/mkdir -p /etc/oozie
/bin/mkdir -p /etc/pig
/bin/mkdir -p /etc/sentry
/bin/mkdir -p /etc/solr
/bin/mkdir -p /etc/spark
/bin/mkdir -p /etc/sqoop
/bin/mkdir -p /etc/sqoop2
/bin/mkdir -p /etc/zookeeper
/bin/mount -t cgroup -o blkio cm_cgroups /tmp/*
/bin/mount -t cgroup -o cpu cm_cgroups /tmp/*
/bin/mount -t cgroup -o cpuacct cm_cgroups /tmp/*
/bin/mount -t cgroup -o memory cm_cgroups /tmp/*
/bin/mount -t tmpfs cm_processes /ngs/app/searchp/var/run/cloudera-scm-agent/process -o mode
/bin/rm
/bin/rm -rf /etc/accumulo/*
/bin/rm -rf /etc/hadoop/*
/bin/rm -rf /etc/hbase/*
/bin/rm -rf /etc/hive/*
/bin/rm -rf /etc/solr/*
/bin/rm -rf /etc/spark/*
/bin/rm -rf /etc/sqoop/*
/bin/umount /tmp/*
/usr/sbin/update-alternatives --admindir /var/lib/alternatives --altdir /etc/alternatives --display ip6tables.x86_64
/usr/sbin/update-alternatives --admindir /var/lib/alternatives --altdir /etc/alternatives --display iptables.x86_64
/usr/sbin/update-alternatives --admindir /var/lib/alternatives --altdir /etc/alternatives --display mta
/usr/sbin/update-alternatives --admindir /var/lib/alternatives --altdir /etc/alternatives --display print
/usr/sbin/update-alternatives --auto accumulo-conf
/usr/sbin/update-alternatives --auto hadoop-conf
/usr/sbin/update-alternatives --auto hbase-conf
/usr/sbin/update-alternatives --auto hive-conf
/usr/sbin/update-alternatives --auto solr-conf
/usr/sbin/update-alternatives --auto spark-conf
/usr/sbin/update-alternatives --auto sqoop-conf
/usr/sbin/update-alternatives --install /etc/accumulo/conf accumulo-conf /etc/accumulo/* 51
/usr/sbin/update-alternatives --install /etc/flume-ng/conf flume-ng-conf /ngs/app/searchp/opt/parcels/CDH*/etc/flume-ng/conf.empty 10
/usr/sbin/update-alternatives --install /etc/hadoop-httpfs/conf hadoop-httpfs-conf /ngs/app/searchp/opt/parcels/CDH*/etc/hadoop-httpfs/conf.empty 10
/usr/sbin/update-alternatives --install /etc/hadoop-kms/conf hadoop-kms-conf /ngs/app/searchp/opt/parcels/CDH*/etc/hadoop-kms/conf.dist 10
/usr/sbin/update-alternatives --install /etc/hadoop/conf hadoop-conf /etc/hadoop/* 90
/usr/sbin/update-alternatives --install /etc/hadoop/conf hadoop-conf /etc/hadoop/* 91
/usr/sbin/update-alternatives --install /etc/hadoop/conf hadoop-conf /etc/hadoop/* 92
/usr/sbin/update-alternatives --install /etc/hadoop/conf hadoop-conf /ngs/app/searchp/opt/parcels/CDH*/etc/hadoop/conf.empty 10
/usr/sbin/update-alternatives --install /etc/hbase-solr/conf hbase-solr-conf /ngs/app/searchp/opt/parcels/CDH*/etc/hbase-solr/conf.dist 10
/usr/sbin/update-alternatives --install /etc/hbase/conf hbase-conf /etc/hbase/* 90
/usr/sbin/update-alternatives --install /etc/hbase/conf hbase-conf /ngs/app/searchp/opt/parcels/CDH*/etc/hbase/conf.dist 10
/usr/sbin/update-alternatives --install /etc/hive-hcatalog/conf hive-hcatalog-conf /ngs/app/searchp/opt/parcels/CDH*/etc/hive-hcatalog/conf.dist 10
/usr/sbin/update-alternatives --install /etc/hive-webhcat/conf hive-webhcat-conf /ngs/app/searchp/opt/parcels/CDH*/etc/hive-webhcat/conf.dist 10
/usr/sbin/update-alternatives --install /etc/hive/conf hive-conf /etc/hive/* 90
/usr/sbin/update-alternatives --install /etc/hive/conf hive-conf /ngs/app/searchp/opt/parcels/CDH*/etc/hive/conf.dist 10
/usr/sbin/update-alternatives --install /etc/hue/conf hue-conf /ngs/app/searchp/opt/parcels/CDH*/etc/hue/conf.empty 10
/usr/sbin/update-alternatives --install /etc/impala/conf impala-conf /ngs/app/searchp/opt/parcels/CDH*/etc/impala/conf.dist 10
/usr/sbin/update-alternatives --install /etc/llama/conf llama-conf /ngs/app/searchp/opt/parcels/CDH*/etc/llama/conf.dist 10
/usr/sbin/update-alternatives --install /etc/mahout/conf mahout-conf /ngs/app/searchp/opt/parcels/CDH*/etc/mahout/conf.dist 10
/usr/sbin/update-alternatives --install /etc/oozie/conf oozie-conf /ngs/app/searchp/opt/parcels/CDH*/etc/oozie/conf.dist 10
/usr/sbin/update-alternatives --install /etc/pig/conf pig-conf /ngs/app/searchp/opt/parcels/CDH*/etc/pig/conf.dist 10
/usr/sbin/update-alternatives --install /etc/sentry/conf sentry-conf /ngs/app/searchp/opt/parcels/CDH*/etc/sentry/conf.dist 10
/usr/sbin/update-alternatives --install /etc/solr/conf solr-conf /etc/solr/* 90
/usr/sbin/update-alternatives --install /etc/solr/conf solr-conf /ngs/app/searchp/opt/parcels/CDH*/etc/solr/conf.dist 10
/usr/sbin/update-alternatives --install /etc/spark/conf spark-conf /etc/spark/* 51
/usr/sbin/update-alternatives --install /etc/spark/conf spark-conf /ngs/app/searchp/opt/parcels/CDH*/etc/spark/conf.dist 10
/usr/sbin/update-alternatives --install /etc/sqoop/conf sqoop-conf /etc/sqoop/* 50
/usr/sbin/update-alternatives --install /etc/sqoop/conf sqoop-conf /ngs/app/searchp/opt/parcels/CDH*/etc/sqoop/conf.dist 10
/usr/sbin/update-alternatives --install /etc/sqoop2/conf sqoop2-conf /ngs/app/searchp/opt/parcels/CDH*/etc/sqoop2/conf.dist 10
/usr/sbin/update-alternatives --install /etc/zookeeper/conf zookeeper-conf /ngs/app/searchp/opt/parcels/CDH*/etc/zookeeper/conf.dist 10
/usr/sbin/update-alternatives --install /usr/bin/accumulo accumulo /ngs/app/searchp/opt/parcels/ACCUMULO-1.6.0-1.cdh5.1.0.p0.51/bin/accumulo 10
/usr/sbin/update-alternatives --install /usr/bin/accumulo-tool accumulo-tool /ngs/app/searchp/opt/parcels/ACCUMULO-1.6.0-1.cdh5.1.0.p0.51/bin/accumulo-tool 10
/usr/sbin/update-alternatives --install /usr/bin/avro-tools avro-tools /ngs/app/searchp/opt/parcels/CDH*/bin/avro-tools 10
/usr/sbin/update-alternatives --install /usr/bin/beeline beeline /ngs/app/searchp/opt/parcels/CDH*/bin/beeline 10
/usr/sbin/update-alternatives --install /usr/bin/catalogd catalogd /ngs/app/searchp/opt/parcels/CDH*/bin/catalogd 10
/usr/sbin/update-alternatives --install /usr/bin/cli_mt cli_mt /ngs/app/searchp/opt/parcels/CDH*/bin/cli_mt 10
/usr/sbin/update-alternatives --install /usr/bin/cli_st cli_st /ngs/app/searchp/opt/parcels/CDH*/bin/cli_st 10
/usr/sbin/update-alternatives --install /usr/bin/flume-ng flume-ng /ngs/app/searchp/opt/parcels/CDH*/bin/flume-ng 10
/usr/sbin/update-alternatives --install /usr/bin/hadoop hadoop /ngs/app/searchp/opt/parcels/CDH*/bin/hadoop 10
/usr/sbin/update-alternatives --install /usr/bin/hadoop-0.20 hadoop-0.20 /ngs/app/searchp/opt/parcels/CDH*/bin/hadoop-0.20 10
/usr/sbin/update-alternatives --install /usr/bin/hadoop-fuse-dfs hadoop-fuse-dfs /ngs/app/searchp/opt/parcels/CDH*/bin/hadoop-fuse-dfs 10
/usr/sbin/update-alternatives --install /usr/bin/hbase hbase /ngs/app/searchp/opt/parcels/CDH*/bin/hbase 10
/usr/sbin/update-alternatives --install /usr/bin/hbase-indexer hbase-indexer /ngs/app/searchp/opt/parcels/CDH*/bin/hbase-indexer 10
/usr/sbin/update-alternatives --install /usr/bin/hcat hcat /ngs/app/searchp/opt/parcels/CDH*/bin/hcat 10
/usr/sbin/update-alternatives --install /usr/bin/hdfs hdfs /ngs/app/searchp/opt/parcels/CDH*/bin/hdfs 10
/usr/sbin/update-alternatives --install /usr/bin/hive hive /ngs/app/searchp/opt/parcels/CDH*/bin/hive 10
/usr/sbin/update-alternatives --install /usr/bin/hiveserver2 hiveserver2 /ngs/app/searchp/opt/parcels/CDH*/bin/hiveserver2 10
/usr/sbin/update-alternatives --install /usr/bin/impala-shell impala-shell /ngs/app/searchp/opt/parcels/CDH*/bin/impala-shell 10
/usr/sbin/update-alternatives --install /usr/bin/impalad impalad /ngs/app/searchp/opt/parcels/CDH*/bin/impalad 10
/usr/sbin/update-alternatives --install /usr/bin/kite-dataset kite-dataset /ngs/app/searchp/opt/parcels/CDH*/bin/kite-dataset 10
/usr/sbin/update-alternatives --install /usr/bin/llama llama /ngs/app/searchp/opt/parcels/CDH*/bin/llama 10
/usr/sbin/update-alternatives --install /usr/bin/llamaadmin llamaadmin /ngs/app/searchp/opt/parcels/CDH*/bin/llamaadmin 10
/usr/sbin/update-alternatives --install /usr/bin/load_gen load_gen /ngs/app/searchp/opt/parcels/CDH*/bin/load_gen 10
/usr/sbin/update-alternatives --install /usr/bin/mahout mahout /ngs/app/searchp/opt/parcels/CDH*/bin/mahout 10
/usr/sbin/update-alternatives --install /usr/bin/mapred mapred /ngs/app/searchp/opt/parcels/CDH*/bin/mapred 10
/usr/sbin/update-alternatives --install /usr/bin/oozie oozie /ngs/app/searchp/opt/parcels/CDH*/bin/oozie 10
/usr/sbin/update-alternatives --install /usr/bin/pig pig /ngs/app/searchp/opt/parcels/CDH*/bin/pig 10
/usr/sbin/update-alternatives --install /usr/bin/pyspark pyspark /ngs/app/searchp/opt/parcels/CDH*/bin/pyspark 10
/usr/sbin/update-alternatives --install /usr/bin/sentry sentry /ngs/app/searchp/opt/parcels/CDH*/bin/sentry 10
/usr/sbin/update-alternatives --install /usr/bin/solrctl solrctl /ngs/app/searchp/opt/parcels/CDH*/bin/solrctl 10
/usr/sbin/update-alternatives --install /usr/bin/spark-executor spark-executor /ngs/app/searchp/opt/parcels/CDH*/bin/spark-executor 10
/usr/sbin/update-alternatives --install /usr/bin/spark-shell spark-shell /ngs/app/searchp/opt/parcels/CDH*/bin/spark-shell 10
/usr/sbin/update-alternatives --install /usr/bin/spark-submit spark-submit /ngs/app/searchp/opt/parcels/CDH*/bin/spark-submit 10
/usr/sbin/update-alternatives --install /usr/bin/sqoop sqoop /ngs/app/searchp/opt/parcels/CDH*/bin/sqoop 10
/usr/sbin/update-alternatives --install /usr/bin/sqoop-codegen sqoop-codegen /ngs/app/searchp/opt/parcels/CDH*/bin/sqoop-codegen 10
/usr/sbin/update-alternatives --install /usr/bin/sqoop-create-hive-table sqoop-create-hive-table /ngs/app/searchp/opt/parcels/CDH*/bin/sqoop-create-hive-table 10
/usr/sbin/update-alternatives --install /usr/bin/sqoop-eval sqoop-eval /ngs/app/searchp/opt/parcels/CDH*/bin/sqoop-eval 10
/usr/sbin/update-alternatives --install /usr/bin/sqoop-export sqoop-export /ngs/app/searchp/opt/parcels/CDH*/bin/sqoop-export 10
/usr/sbin/update-alternatives --install /usr/bin/sqoop-help sqoop-help /ngs/app/searchp/opt/parcels/CDH*/bin/sqoop-help 10
/usr/sbin/update-alternatives --install /usr/bin/sqoop-import sqoop-import /ngs/app/searchp/opt/parcels/CDH*/bin/sqoop-import 10
/usr/sbin/update-alternatives --install /usr/bin/sqoop-import-all-tables sqoop-import-all-tables /ngs/app/searchp/opt/parcels/CDH*/bin/sqoop-import-all-tables 10
/usr/sbin/update-alternatives --install /usr/bin/sqoop-job sqoop-job /ngs/app/searchp/opt/parcels/CDH*/bin/sqoop-job 10
/usr/sbin/update-alternatives --install /usr/bin/sqoop-list-databases sqoop-list-databases /ngs/app/searchp/opt/parcels/CDH*/bin/sqoop-list-databases 10
/usr/sbin/update-alternatives --install /usr/bin/sqoop-list-tables sqoop-list-tables /ngs/app/searchp/opt/parcels/CDH*/bin/sqoop-list-tables 10
/usr/sbin/update-alternatives --install /usr/bin/sqoop-merge sqoop-merge /ngs/app/searchp/opt/parcels/CDH*/bin/sqoop-merge 10
/usr/sbin/update-alternatives --install /usr/bin/sqoop-metastore sqoop-metastore /ngs/app/searchp/opt/parcels/CDH*/bin/sqoop-metastore 10
/usr/sbin/update-alternatives --install /usr/bin/sqoop-version sqoop-version /ngs/app/searchp/opt/parcels/CDH*/bin/sqoop-version 10
/usr/sbin/update-alternatives --install /usr/bin/sqoop2 sqoop2 /ngs/app/searchp/opt/parcels/CDH*/bin/sqoop2 10
/usr/sbin/update-alternatives --install /usr/bin/statestored statestored /ngs/app/searchp/opt/parcels/CDH*/bin/statestored 10
/usr/sbin/update-alternatives --install /usr/bin/whirr whirr /ngs/app/searchp/opt/parcels/CDH*/bin/whirr 10
/usr/sbin/update-alternatives --install /usr/bin/yarn yarn /ngs/app/searchp/opt/parcels/CDH*/bin/yarn 10
/usr/sbin/update-alternatives --install /usr/bin/zookeeper-client zookeeper-client /ngs/app/searchp/opt/parcels/CDH*/bin/zookeeper-client 10
/usr/sbin/update-alternatives --install /usr/bin/zookeeper-server zookeeper-server /ngs/app/searchp/opt/parcels/CDH*/bin/zookeeper-server 10
/usr/sbin/update-alternatives --install /usr/bin/zookeeper-server-cleanup zookeeper-server-cleanup /ngs/app/searchp/opt/parcels/CDH*/bin/zookeeper-server-cleanup 10
/usr/sbin/update-alternatives --install /usr/bin/zookeeper-server-initialize zookeeper-server-initialize /ngs/app/searchp/opt/parcels/CDH*/bin/zookeeper-server-initialize 10
/usr/sbin/update-alternatives --remove accumulo-conf /etc/accumulo/*
/usr/sbin/update-alternatives --remove hadoop-conf /etc/hadoop/*
/usr/sbin/update-alternatives --remove hbase-conf /etc/hbase/*
/usr/sbin/update-alternatives --remove hive-conf /etc/hive/*
/usr/sbin/update-alternatives --remove solr-conf /etc/solr/*
/usr/sbin/update-alternatives --remove spark-conf /etc/spark/*
/usr/sbin/update-alternatives --remove sqoop-conf /etc/sqoop/*
Commands run by the Cloudera Manager Agent while creating a diagnostic bundle: 
/bin/bash -c cd ..; find -maxdepth
/bin/bash -c for x in /etc/security/limits.d/*;
/bin/bash -c PATH
/bin/cat /etc/apt/sources.list
/bin/cat /etc/host.conf
/bin/cat /etc/hostname
/bin/cat /etc/hosts
/bin/cat /etc/issue
/bin/cat /etc/krb5.conf
/bin/cat /etc/nsswitch.conf
/bin/cat /etc/redhat-release
/bin/cat /etc/resolv.conf
/bin/cat /etc/security/limits.conf
/bin/cat /etc/suse-release
/bin/cat /etc/sysconfig/network
/bin/cat /etc/sysconfig/network/ifcfg-eth0
/bin/cat /etc/sysconfig/network-scripts/ifcfg-eth0
/bin/cat /etc/sysconfig/selinux
/bin/cat /proc/cpuinfo
/bin/cat /proc/diskstats
/bin/cat /proc/interrupts
/bin/cat /proc/meminfo
/bin/cat /proc/mounts
/bin/cat /proc/partitions
/bin/cat /proc/swaps
/bin/cat /proc/sys/vm/swappiness
/bin/cat /proc/vmstat
/bin/cat /var/kerberos/krb5kdc/kadm5.acl
/bin/cat /var/kerberos/krb5kdc/kdc.conf
/bin/cat /var/log/kern.log
/bin/cat /var/log/messages
/bin/date
/bin/df -i
/bin/df -k
/bin/dmesg
/bin/grep -r . /sys/kernel/mm
/bin/hostname --fqdn
/bin/ls /etc/yum.repos.d
/bin/netstat -s
/bin/ps aux
/bin/rpm -qa
/bin/uname -a
/bin/uname -r
/sbin/chkconfig --list
/sbin/ethtool eth0
/sbin/ethtool -S eth0
/sbin/ifconfig -a
/sbin/iptables -L -v -n
/sbin/lsmod
/sbin/lspci
/sbin/lvdisplay
/sbin/service --status-all
/sbin/sysctl -A
/usr/bin/curl -m 1 http://169.254.169.254/2011-01-01/meta-data/instance-type
/usr/bin/dig any test-1.ent.cloudera.com
/usr/bin/host -v -t A test-1.ent.cloudera.com
/usr/bin/lsb_release -a
/usr/bin/lscpu
/usr/bin/nslookup -query
/usr/bin/ntpstat
/usr/bin/python -c import socket; print socket.getfqdn();
/usr/bin/sar -A
/usr/bin/top -b -n 1
/usr/bin/uptime
/usr/bin/vmstat
/usr/sbin/dmidecode
/usr/sbin/lsof -n -P
/usr/sbin/ntpq -pn
Page generated July 8, 2016.