hadoop大数据平台手动搭建-hue

1.解压

tar -zxvf /opt/hue-3.9.0-cdh5.8.0.tar.gz

2. 编译安装

    make apss

    make install

3.修改hue.ini

# Hue configuration file

# ===================================

#

# For complete documentation about the contents of this file, run

#   $ /build/env/bin/hue config_help

#

# All .ini files under the current directory are treated equally.  Their

# contents are merged to form the Hue configuration, which can

# can be viewed on the Hue at

#   http://:/dump_config

 

 

###########################################################################

# General configuration for core Desktop features (authentication, etc)

###########################################################################

 

[desktop]

 

  # Set this to a random string, the longer the better.

  # This is used for secure hashing in the session store.

  secret_key=13edcqwertyuiopuioplkj

 

  # Execute this script to produce the Django secret key. This will be used when

  # `secret_key` is not set.

  ## secret_key_script=

 

  # Webserver listens on this address and port

  http_host=0.0.0.0

  http_port=8888

 

  # Time zone name

  time_zone=America/Los_Angeles

 

  # Enable or disable Django debug mode.

  django_debug_mode=false

 

  # Enable or disable database debug mode.

  ## database_logging=false

 

  # Whether to send debug messages from JavaScript to the server logs.

  ## send_dbug_messages=false

 

  # Enable or disable backtrace for server error

  http_500_debug_mode=false

 

  # Enable or disable memory profiling.

  ## memory_profiler=false

 

  # Server email for internal error messages

  ## django_server_email='[email protected]'

 

  # Email backend

  ## django_email_backend=django.core.mail.backends.smtp.EmailBackend

 

  # Webserver runs as this user

   server_user=hadoop

   server_group=hadoop

 

  # This should be the Hue admin and proxy user

   default_user=hadoop

 

  # This should be the hadoop cluster admin

   default_hdfs_superuser=hadoop

 

  # If set to false, runcpserver will not actually start the web server.

  # Used if Apache is being used as a WSGI container.

  ## enable_server=yes

 

  # Number of threads used by the CherryPy web server

  ## cherrypy_server_threads=40

 

  # Filename of SSL Certificate

  ## ssl_certificate=

 

  # Filename of SSL RSA Private Key

  ## ssl_private_key=

 

  # Filename of SSL Certificate Chain

  ## ssl_certificate_chain=

 

  # SSL certificate password

  ## ssl_password=

 

  # Execute this script to produce the SSL password. This will be used when `ssl_password` is not set.

  ## ssl_password_script=

 

  # List of allowed and disallowed ciphers in cipher list format.

  # See http://www.openssl.org/docs/apps/ciphers.html for more information on

  # cipher list format. This list is from

  # https://wiki.mozilla.org/Security/Server_Side_TLS v3.7 intermediate

  # recommendation, which should be compatible with Firefox 1, Chrome 1, IE 7,

  # Opera 5 and Safari 1.

  ## ssl_cipher_list=ECDHE-RSA-AES128-GCM-SHA256:ECDHE-ECDSA-AES128-GCM-SHA256:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-AES256-GCM-SHA384:DHE-RSA-AES128-GCM-SHA256:DHE-DSS-AES128-GCM-SHA256:kEDH+AESGCM:ECDHE-RSA-AES128-SHA256:ECDHE-ECDSA-AES128-SHA256:ECDHE-RSA-AES128-SHA:ECDHE-ECDSA-AES128-SHA:ECDHE-RSA-AES256-SHA384:ECDHE-ECDSA-AES256-SHA384:ECDHE-RSA-AES256-SHA:ECDHE-ECDSA-AES256-SHA:DHE-RSA-AES128-SHA256:DHE-RSA-AES128-SHA:DHE-DSS-AES128-SHA256:DHE-RSA-AES256-SHA256:DHE-DSS-AES256-SHA:DHE-RSA-AES256-SHA:AES128-GCM-SHA256:AES256-GCM-SHA384:AES128-SHA256:AES256-SHA256:AES128-SHA:AES256-SHA:AES:CAMELLIA:DES-CBC3-SHA:!aNULL:!eNULL:!EXPORT:!DES:!RC4:!MD5:!PSK:!aECDH:!EDH-DSS-DES-CBC3-SHA:!EDH-RSA-DES-CBC3-SHA:!KRB5-DES-CBC3-SHA

 

  # Path to default Certificate Authority certificates.

  ## ssl_cacerts=/etc/hue/cacerts.pem

 

  # Choose whether Hue should validate certificates received from the server.

  ## validate=true

 

  # Default LDAP/PAM/.. username and password of the hue user used for authentications with other services.

  # Inactive if password is empty.

  # e.g. LDAP pass-through authentication for HiveServer2 or Impala. Apps can override them individually.

  ## auth_username=hue

  ## auth_password=

 

  # Default encoding for site data

  ## default_site_encoding=utf-8

 

  # Help improve Hue with anonymous usage analytics.

  # Use Google Analytics to see how many times an application or specific section of an application is used, nothing more.

  ## collect_usage=true

 

  # Tile layer server URL for the Leaflet map charts

  # Read more on http://leafletjs.com/reference.html#tilelayer

  ## leaflet_tile_layer=http://{s}.tile.osm.org/{z}/{x}/{y}.png

 

  # The copyright message for the specified Leaflet maps Tile Layer

  ## leaflet_tile_layer_attribution='© OpenStreetMap contributors'

 

  # X-Frame-Options HTTP header value. Use 'DENY' to deny framing completely 

  ## http_x_frame_options=SAMEORIGIN

 

  # Enable X-Forwarded-Host header if the load balancer requires it.

  ## use_x_forwarded_host=false

 

  # Support for HTTPS termination at the load-balancer level with SECURE_PROXY_SSL_HEADER.

  ## secure_proxy_ssl_header=false

 

  # Comma-separated list of Django middleware classes to use.

  # See https://docs.djangoproject.com/en/1.4/ref/middleware/ for more details on middlewares in Django.

  ## middleware=desktop.auth.backend.LdapSynchronizationBackend

 

  # Comma-separated list of regular expressions, which match the redirect URL.

  # For example, to restrict to your local domain and FQDN, the following value can be used:

  # ^\/.*$,^http:\/\/www.mydomain.com\/.*$

  ## redirect_whitelist=^(\/[a-zA-Z0-9]+.*|\/)$

 

  # Comma separated list of apps to not load at server startup.

  # e.g.: pig,zookeeper

  ## app_blacklist=

 

  # Choose whether to show the new SQL editor.

  ## use_new_editor=true

 

  # Enable saved default configurations for Hive, Impala, Spark, and Oozie.

  ## use_default_configuration=false

 

  # The directory where to store the auditing logs. Auditing is disable if the value is empty.

  # e.g. /var/log/hue/audit.log

  ## audit_event_log_dir=

 

  # Size in KB/MB/GB for audit log to rollover.

  ## audit_log_max_file_size=100MB

 

  # A json file containing a list of log redaction rules for cleaning sensitive data

  # from log files. It is defined as:

  #

  # {

  #   "version": 1,

  #   "rules": [

  #     {

  #       "description": "This is the first rule",

  #       "trigger": "triggerstring 1",

  #       "search": "regex 1",

  #       "replace": "replace 1"

  #     },

  #     {

  #       "description": "This is the second rule",

  #       "trigger": "triggerstring 2",

  #       "search": "regex 2",

  #       "replace": "replace 2"

  #     }

  #   ]

  # }

  #

  # Redaction works by searching a string for the [TRIGGER] string. If found,

  # the [REGEX] is used to replace sensitive information with the

  # [REDACTION_MASK].  If specified with `log_redaction_string`, the

  # `log_redaction_string` rules will be executed after the

  # `log_redaction_file` rules.

  #

  # For example, here is a file that would redact passwords and social security numbers:

 

  # {

  #   "version": 1,

  #   "rules": [

  #     {

  #       "description": "Redact passwords",

  #       "trigger": "password",

  #       "search": "password=\".*\"",

  #       "replace": "password=\"???\""

  #     },

  #     {

  #       "description": "Redact social security numbers",

  #       "trigger": "",

  #       "search": "\d{3}-\d{2}-\d{4}",

  #       "replace": "XXX-XX-XXXX"

  #     }

  #   ]

  # }

  ## log_redaction_file=

 

  # Comma separated list of strings representing the host/domain names that the Hue server can serve.

  # e.g.: localhost,domain1,*

  ## allowed_hosts=*

 

  # Administrators

  # ----------------

  [[django_admins]]

    ## [[[admin1]]]

    ## name=john

    ## [email protected]

 

  # UI customizations

  # -------------------

  [[custom]]

 

    # Top banner HTML code

    # e.g.

Test Lab A2 Hue Services

    ## banner_top_html=

 

    # Login splash HTML code

    # e.g. WARNING: You are required to have authorization before you proceed

    ## login_splash_html=

GetHue.com



WARNING: You have accessed a computer managed by GetHue. You are required to have authorization from GetHue before you proceed.

 

    # Cache timeout in milliseconds for the assist, autocomplete, etc.

    # defaults to 86400000 (1 day), set to 0 to disable caching

    ## cacheable_ttl=86400000

 

  # Configuration options for user authentication into the web application

  # ------------------------------------------------------------------------

  [[auth]]

 

    # Authentication backend. Common settings are:

    # - django.contrib.auth.backends.ModelBackend (entirely Django backend)

    # - desktop.auth.backend.AllowAllBackend (allows everyone)

    # - desktop.auth.backend.AllowFirstUserDjangoBackend

    #     (Default. Relies on Django and user manager, after the first login)

    # - desktop.auth.backend.LdapBackend

    # - desktop.auth.backend.PamBackend

    # - desktop.auth.backend.SpnegoDjangoBackend

    # - desktop.auth.backend.RemoteUserDjangoBackend

    # - libsaml.backend.SAML2Backend

    # - libopenid.backend.OpenIDBackend

    # - liboauth.backend.OAuthBackend

    #     (New oauth, support Twitter, Facebook, Google+ and Linkedin

    # Multiple Authentication backends are supported by specifying a comma-separated list in order of priority.

    # However, in order to enable OAuthBackend, it must be the ONLY backend configured.

    ## backend=desktop.auth.backend.AllowFirstUserDjangoBackend

 

    # Class which defines extra accessor methods for User objects.

    ## user_aug=desktop.auth.backend.DefaultUserAugmentor

 

    # The service to use when querying PAM.

    ## pam_service=login

 

    # When using the desktop.auth.backend.RemoteUserDjangoBackend, this sets

    # the normalized name of the header that contains the remote user.

    # The HTTP header in the request is converted to a key by converting

    # all characters to uppercase, replacing any hyphens with underscores

    # and adding an HTTP_ prefix to the name. So, for example, if the header

    # is called Remote-User that would be configured as HTTP_REMOTE_USER

    #

    # Defaults to HTTP_REMOTE_USER

    ## remote_user_header=HTTP_REMOTE_USER

 

    # Ignore the case of usernames when searching for existing users.

    # Supported in remoteUserDjangoBackend and SpnegoDjangoBackend

    ## ignore_username_case=true

 

    # Forcibly cast usernames to lowercase, takes precedence over force_username_uppercase

    # Supported in remoteUserDjangoBackend and SpnegoDjangoBackend

    ## force_username_lowercase=true

 

    # Forcibly cast usernames to uppercase, cannot be combined with force_username_lowercase

    ## force_username_uppercase=false

 

    # Users will expire after they have not logged in for 'n' amount of seconds.

    # A negative number means that users will never expire.

    ## expires_after=-1

 

    # Apply 'expires_after' to superusers.

    ## expire_superusers=true

 

    # Users will automatically be logged out after 'n' seconds of inactivity.

    # A negative number means that idle sessions will not be timed out.

    idle_session_timeout=-1

 

    # Force users to change password on first login with desktop.auth.backend.AllowFirstUserDjangoBackend

    ## change_default_password=false

 

    # Number of login attempts allowed before a record is created for failed logins

    ## login_failure_limit=3

 

    # After number of allowed login attempts are exceeded, do we lock out this IP and optionally user agent?

    ## login_lock_out_at_failure=false

 

    # If set, defines period of inactivity in seconds after which failed logins will be forgotten

    ## login_cooloff_time=60

 

    # If True, lock out based on an IP address AND a user agent.

    # This means requests from different user agents but from the same IP are treated differently.

    ## login_lock_out_use_user_agent=false

 

    # If True, lock out based on IP and user

    ## login_lock_out_by_combination_user_and_ip=false

 

  # Configuration options for connecting to LDAP and Active Directory

  # -------------------------------------------------------------------

  [[ldap]]

 

    # The search base for finding users and groups

    ## base_dn="DC=mycompany,DC=com"

 

    # URL of the LDAP server

    ## ldap_url=ldap://auth.mycompany.com

 

    # The NT domain used for LDAP authentication

    ## nt_domain=mycompany.com

 

    # A PEM-format file containing certificates for the CA's that

    # Hue will trust for authentication over TLS.

    # The certificate for the CA that signed the

    # LDAP server certificate must be included among these certificates.

    # See more here http://www.openldap.org/doc/admin24/tls.html.

    ## ldap_cert=

    ## use_start_tls=true

 

    # Distinguished name of the user to bind as -- not necessary if the LDAP server

    # supports anonymous searches

    ## bind_dn="CN=ServiceAccount,DC=mycompany,DC=com"

 

    # Password of the bind user -- not necessary if the LDAP server supports

    # anonymous searches

    ## bind_password=

 

    # Execute this script to produce the bind user password. This will be used

    # when `bind_password` is not set.

    ## bind_password_script=

 

    # Pattern for searching for usernames -- Use for the parameter

    # For use when using LdapBackend for Hue authentication

    ## ldap_username_pattern="uid=,ou=People,dc=mycompany,dc=com"

 

    # Create users in Hue when they try to login with their LDAP credentials

    # For use when using LdapBackend for Hue authentication

    ## create_users_on_login = true

 

    # Synchronize a users groups when they login

    ## sync_groups_on_login=false

 

    # Ignore the case of usernames when searching for existing users in Hue.

    ## ignore_username_case=true

 

    # Force usernames to lowercase when creating new users from LDAP.

    # Takes precedence over force_username_uppercase

    ## force_username_lowercase=true

 

    # Force usernames to uppercase, cannot be combined with force_username_lowercase

    ## force_username_uppercase=false

 

    # Use search bind authentication.

    ## search_bind_authentication=true

 

    # Choose which kind of subgrouping to use: nested or suboordinate (deprecated).

    ## subgroups=suboordinate

 

    # Define the number of levels to search for nested members.

    ## nested_members_search_depth=10

 

    # Whether or not to follow referrals

    ## follow_referrals=false

 

    # Enable python-ldap debugging.

    ## debug=false

 

    # Sets the debug level within the underlying LDAP C lib.

    ## debug_level=255

 

    # Possible values for trace_level are 0 for no logging, 1 for only logging the method calls with arguments,

    # 2 for logging the method calls with arguments and the complete results and 9 for also logging the traceback of method calls.

    ## trace_level=0

 

    [[[users]]]

 

      # Base filter for searching for users

      ## user_filter="objectclass=*"

 

      # The username attribute in the LDAP schema

      ## user_name_attr=sAMAccountName

 

    [[[groups]]]

 

      # Base filter for searching for groups

      ## group_filter="objectclass=*"

 

      # The group name attribute in the LDAP schema

      ## group_name_attr=cn

 

      # The attribute of the group object which identifies the members of the group

      ## group_member_attr=members

 

    [[[ldap_servers]]]

 

      ## [[[[mycompany]]]]

 

        # The search base for finding users and groups

        ## base_dn="DC=mycompany,DC=com"

 

        # URL of the LDAP server

        ## ldap_url=ldap://auth.mycompany.com

 

        # The NT domain used for LDAP authentication

        ## nt_domain=mycompany.com

 

        # A PEM-format file containing certificates for the CA's that

        # Hue will trust for authentication over TLS.

        # The certificate for the CA that signed the

        # LDAP server certificate must be included among these certificates.

        # See more here http://www.openldap.org/doc/admin24/tls.html.

        ## ldap_cert=

        ## use_start_tls=true

 

        # Distinguished name of the user to bind as -- not necessary if the LDAP server

        # supports anonymous searches

        ## bind_dn="CN=ServiceAccount,DC=mycompany,DC=com"

 

        # Password of the bind user -- not necessary if the LDAP server supports

        # anonymous searches

        ## bind_password=

 

        # Execute this script to produce the bind user password. This will be used

        # when `bind_password` is not set.

        ## bind_password_script=

 

        # Pattern for searching for usernames -- Use for the parameter

        # For use when using LdapBackend for Hue authentication

        ## ldap_username_pattern="uid=,ou=People,dc=mycompany,dc=com"

 

        ## Use search bind authentication.

        ## search_bind_authentication=true

 

        # Whether or not to follow referrals

        ## follow_referrals=false

 

        # Enable python-ldap debugging.

        ## debug=false

 

        # Sets the debug level within the underlying LDAP C lib.

        ## debug_level=255

 

        # Possible values for trace_level are 0 for no logging, 1 for only logging the method calls with arguments,

        # 2 for logging the method calls with arguments and the complete results and 9 for also logging the traceback of method calls.

        ## trace_level=0

 

        ## [[[[[users]]]]]

 

          # Base filter for searching for users

          ## user_filter="objectclass=Person"

 

          # The username attribute in the LDAP schema

          ## user_name_attr=sAMAccountName

 

        ## [[[[[groups]]]]]

 

          # Base filter for searching for groups

          ## group_filter="objectclass=groupOfNames"

 

          # The username attribute in the LDAP schema

          ## group_name_attr=cn

 

  # Configuration options for specifying the Desktop Database. For more info,

  # see http://docs.djangoproject.com/en/1.4/ref/settings/#database-engine

  # ------------------------------------------------------------------------

  [[database]]

    # Database engine is typically one of:

    # postgresql_psycopg2, mysql, sqlite3 or oracle.

    #

    # Note that for sqlite3, 'name', below is a path to the filename. For other backends, it is the database name

    # Note for Oracle, options={"threaded":true} must be set in order to avoid crashes.

    # Note for Oracle, you can use the Oracle Service Name by setting "host=" and "port=" and then "name=:/".

    # Note for MariaDB use the 'mysql' engine.

    engine=mysql

    host=master

    port=3306

    user=hadoop

    password=123456

    # Execute this script to produce the database password. This will be used when `password` is not set.

    ## password_script=/path/script

    name=hue

    ## options={}

 

  # Configuration options for specifying the Desktop session.

  # For more info, see https://docs.djangoproject.com/en/1.4/topics/http/sessions/

  # ------------------------------------------------------------------------

  [[session]]

    # The cookie containing the users' session ID will expire after this amount of time in seconds.

    # Default is 2 weeks.

    ## ttl=1209600

 

    # The cookie containing the users' session ID will be secure.

    # Should only be enabled with HTTPS.

    ## secure=false

 

    # The cookie containing the users' session ID will use the HTTP only flag.

    ## http_only=true

 

    # Use session-length cookies. Logs out the user when she closes the browser window.

    ## expire_at_browser_close=false

 

 

  # Configuration options for connecting to an external SMTP server

  # ------------------------------------------------------------------------

  [[smtp]]

 

    # The SMTP server information for email notification delivery

    host=localhost

    port=25

    user=

    password=

 

    # Whether to use a TLS (secure) connection when talking to the SMTP server

    tls=no

 

    # Default email address to use for various automated notification from Hue

    ## default_from_email=hue@localhost

 

 

  # Configuration options for Kerberos integration for secured Hadoop clusters

  # ------------------------------------------------------------------------

  [[kerberos]]

 

    # Path to Hue's Kerberos keytab file

    ## hue_keytab=

    # Kerberos principal name for Hue

    ## hue_principal=hue/hostname.foo.com

    # Path to kinit

    ## kinit_path=/path/to/kinit

 

 

  # Configuration options for using OAuthBackend (Core) login

  # ------------------------------------------------------------------------

  [[oauth]]

    # The Consumer key of the application

    ## consumer_key=XXXXXXXXXXXXXXXXXXXXX

 

    # The Consumer secret of the application

    ## consumer_secret=XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX

 

    # The Request token URL

    ## request_token_url=https://api.twitter.com/oauth/request_token

 

    # The Access token URL

    ## access_token_url=https://api.twitter.com/oauth/access_token

 

    # The Authorize URL

    ## authenticate_url=https://api.twitter.com/oauth/authorize

 

  # Configuration options for Metrics

  # ------------------------------------------------------------------------

  [[metrics]]

 

   # Enable the metrics URL "/desktop/metrics"

   ## enable_web_metrics=True

 

   # If specified, Hue will write metrics to this file.

   ## location=/var/log/hue/metrics.json

 

   # Time in milliseconds on how frequently to collect metrics

   ## collection_interval=30000

 

 

###########################################################################

# Settings to configure the snippets available in the Notebook

###########################################################################

 

[notebook]

 

  ## Show the notebook menu or not

  # show_notebooks=true

 

  ## Base URL to Remote GitHub Server

  # github_remote_url=https://github.com

 

  ## Base URL to GitHub API

  # github_api_url=https://api.github.com

 

  ## Client ID for Authorized GitHub Application

  # github_client_id=

 

  ## Client Secret for Authorized GitHub Application

  # github_client_secret=

 

  # One entry for each type of snippet. The first 5 will appear in the wheel.

  [[interpreters]]

    # Define the name and how to connect and execute the language.

 

    [[[hive]]]

      # The name of the snippet.

      name=Hive

      # The backend connection to use to communicate with the server.

      interface=hiveserver2

 

    [[[impala]]]

      name=Impala

      interface=hiveserver2

 

    # [[[sparksql]]]

    #   name=SparkSql

    #   interface=hiveserver2

 

    [[[spark]]]

      name=Scala

      interface=livy

 

    [[[pyspark]]]

      name=PySpark

      interface=livy

 

    [[[r]]]

      name=R

      interface=livy

 

    [[[jar]]]

      name=Spark Submit Jar

      interface=livy-batch

 

    [[[py]]]

      name=Spark Submit Python

      interface=livy-batch

 

    [[[pig]]]

      name=Pig

      interface=pig

 

    [[[text]]]

      name=Text

      interface=text

 

    [[[markdown]]]

      name=Markdown

      interface=text

 

    [[[mysql]]]

      name = MySQL

      interface=rdbms

 

    [[[sqlite]]]

      name = SQLite

      interface=rdbms

 

    [[[postgresql]]]

      name = PostgreSQL

      interface=rdbms

 

    [[[oracle]]]

      name = Oracle

      interface=rdbms

 

    [[[solr]]]

      name = Solr SQL

      interface=solr

      ## Name of the collection handler

      # options='{"collection": "default"}'

 

    # [[[mysql]]]

    #   name=MySql JDBC

    #   interface=jdbc

    #   ## Specific options for connecting to the server.

    #   ## The JDBC connectors, e.g. mysql.jar, need to be in the CLASSPATH environment variable.

    #   ## If 'user' and 'password' are omitted, they will be prompted in the UI.

    #   options='{"url": "jdbc:mysql://localhost:3306/hue", "driver": "com.mysql.jdbc.Driver", "user": "root", "password": "root"}'

 

  ## Main flag to override the automatic starting of the DBProxy server.

  # enable_dbproxy_server=true

 

  ## Flag to enable the SQL query builder of the table assist.

  # enable_query_builder=true

 

  ## Flag to enable the creation of a coordinator for the current SQL query.

  # enable_query_scheduling=true

 

 

###########################################################################

# Settings to configure your Hadoop cluster.

###########################################################################

 

[hadoop]

 

  # Configuration for HDFS NameNode

  # ------------------------------------------------------------------------

  [[hdfs_clusters]]

    # HA support by using HttpFs

 

    [[[default]]]

      # Enter the filesystem uri

      fs_defaultfs=hdfs://master:9000

 

      # NameNode logical name.

      ## logical_name=

 

      # Use WebHdfs/HttpFs as the communication mechanism.

      # Domain should be the NameNode or HttpFs host.

      # Default port is 14000 for HttpFs.

       webhdfs_url=http://master:50070/webhdfs/v1

 

      # Change this if your HDFS cluster is Kerberos-secured

      ## security_enabled=false

 

      # In secure mode (HTTPS), if SSL certificates from YARN Rest APIs

      # have to be verified against certificate authority

      ## ssl_cert_ca_verify=True

 

      # Directory of the Hadoop configuration

      hadoop_conf_dir=/opt/hadoop-2.6.0-cdh5.8.0/etc/hadoop

 

  # Configuration for YARN (MR2)

  # ------------------------------------------------------------------------

  [[yarn_clusters]]

 

    [[[default]]]

      # Enter the host on which you are running the ResourceManager

       resourcemanager_host=master

 

      # The port where the ResourceManager IPC listens on

      resourcemanager_port=8080

 

      # Whether to submit jobs to this cluster

      submit_to=True

 

      # Resource Manager logical name (required for HA)

      ## logical_name=

 

      # Change this if your YARN cluster is Kerberos-secured

      ## security_enabled=false

 

      # URL of the ResourceManager API

      resourcemanager_api_url=http://master:8088

 

      # URL of the ProxyServer API

      proxy_api_url=http://master:8088

 

      # URL of the HistoryServer API

      history_server_api_url=http://slave2:19888

 

      # URL of the Spark History Server

      ## spark_history_server_url=http://localhost:18088

 

      # In secure mode (HTTPS), if SSL certificates from YARN Rest APIs

      # have to be verified against certificate authority

      ## ssl_cert_ca_verify=True

 

    # HA support by specifying multiple clusters.

    # Redefine different properties there.

    # e.g.

 

    # [[[ha]]]

      # Resource Manager logical name (required for HA)

      ## logical_name=my-rm-name

 

      # Un-comment to enable

      ## submit_to=True

 

      # URL of the ResourceManager API

      ## resourcemanager_api_url=http://localhost:8088

 

      # ...

 

  # Configuration for MapReduce (MR1)

  # ------------------------------------------------------------------------

  [[mapred_clusters]]

 

    [[[default]]]

      # Enter the host on which you are running the Hadoop JobTracker

      ## jobtracker_host=localhost

 

      # The port where the JobTracker IPC listens on

      ## jobtracker_port=8021

 

      # JobTracker logical name for HA

      ## logical_name=

 

      # Thrift plug-in port for the JobTracker

      ## thrift_port=9290

 

      # Whether to submit jobs to this cluster

      submit_to=False

 

      # Change this if your MapReduce cluster is Kerberos-secured

      ## security_enabled=false

 

    # HA support by specifying multiple clusters

    # e.g.

 

    # [[[ha]]]

      # Enter the logical name of the JobTrackers

      ## logical_name=my-jt-name

 

 

###########################################################################

# Settings to configure Beeswax with Hive

###########################################################################

 

[beeswax]

 

  # Host where HiveServer2 is running.

  # If Kerberos security is enabled, use fully-qualified domain name (FQDN).

   hive_server_host=master

 

  # Port where HiveServer2 Thrift server runs on.

   hive_server_port=10000

 

  # Hive configuration directory, where hive-site.xml is located

   hive_conf_dir=/opt/hive-1.1.0-cdh5.8.0/conf

 

  # Timeout in seconds for thrift calls to Hive service

  ## server_conn_timeout=120

 

  # Choose whether to use the old GetLog() thrift call from before Hive 0.14 to retrieve the logs.

  # If false, use the FetchResults() thrift call from Hive 1.0 or more instead.

  ## use_get_log_api=false

 

  # Limit the number of partitions that can be listed.

  ## list_partitions_limit=10000

 

  # The maximum number of partitions that will be included in the SELECT * LIMIT sample query for partitioned tables.

  ## query_partitions_limit=10

 

  # A limit to the number of cells (rows * columns) that can be downloaded from a query

  # (e.g. - 10K rows * 1K columns = 10M cells.)

  # A value of -1 means there will be no limit.

  ## download_cell_limit=10000000

 

  # Hue will try to close the Hive query when the user leaves the editor page.

  # This will free all the query resources in HiveServer2, but also make its results inaccessible.

  ## close_queries=false

 

  # Thrift version to use when communicating with HiveServer2.

  # New column format is from version 7.

  ## thrift_version=7

 

  # A comma-separated list of white-listed Hive configuration properties that users are authorized to set.

  ## config_whitelist=hive.map.aggr,hive.exec.compress.output,hive.exec.parallel,hive.execution.engine,mapreduce.job.queuename

 

  # Override the default desktop username and password of the hue user used for authentications with other services.

  # e.g. Used for LDAP/PAM pass-through authentication.

  ## auth_username=hue

  ## auth_password=

 

  [[ssl]]

    # Path to Certificate Authority certificates.

    ## cacerts=/etc/hue/cacerts.pem

 

    # Choose whether Hue should validate certificates received from the server.

    ## validate=true

 

 

###########################################################################

# Settings to configure Impala

###########################################################################

 

[impala]

  # Host of the Impala Server (one of the Impalad)

  ## server_host=localhost

 

  # Port of the Impala Server

  ## server_port=21050

 

  # Kerberos principal

  ## impala_principal=impala/hostname.foo.com

 

  # Turn on/off impersonation mechanism when talking to Impala

  ## impersonation_enabled=False

 

  # Number of initial rows of a result set to ask Impala to cache in order

  # to support re-fetching them for downloading them.

  # Set to 0 for disabling the option and backward compatibility.

  ## querycache_rows=50000

 

  # Timeout in seconds for thrift calls

  ## server_conn_timeout=120

 

  # Hue will try to close the Impala query when the user leaves the editor page.

  # This will free all the query resources in Impala, but also make its results inaccessible.

  ## close_queries=true

 

  # If > 0, the query will be timed out (i.e. cancelled) if Impala does not do any work

  # (compute or send back results) for that query within QUERY_TIMEOUT_S seconds.

  ## query_timeout_s=600

 

  # If > 0, the session will be timed out (i.e. cancelled) if Impala does not do any work

  # (compute or send back results) for that session within QUERY_TIMEOUT_S seconds (default 12hours).

  ## session_timeout_s=43200

 

  # Override the desktop default username and password of the hue user used for authentications with other services.

  # e.g. Used for LDAP/PAM pass-through authentication.

  ## auth_username=hue

  ## auth_password=

 

  # A comma-separated list of white-listed Impala configuration properties that users are authorized to set.

  # config_whitelist=debug_action,explain_level,mem_limit,optimize_partition_key_scans,query_timeout_s,request_pool

 

  [[ssl]]

    # SSL communication enabled for this server.

    ## enabled=false

 

    # Path to Certificate Authority certificates.

    ## cacerts=/etc/hue/cacerts.pem

 

    # Choose whether Hue should validate certificates received from the server.

    ## validate=true

 

 

###########################################################################

# Settings to configure the Spark application.

###########################################################################

 

[spark]

  # Host address of the Livy Server.

  ## livy_server_host=localhost

 

  # Port of the Livy Server.

  ## livy_server_port=8998

 

  # Configure livy to start in local 'process' mode, or 'yarn' workers.

  ## livy_server_session_kind=process

 

  # If livy should use proxy users when submitting a job.

  ## livy_impersonation_enabled=true

 

  # Host of the Sql Server

  ## sql_server_host=localhost

 

  # Port of the Sql Server

  ## sql_server_port=10000

 

 

###########################################################################

# Settings to configure the Oozie app

###########################################################################

 

[oozie]

  # Location on local FS where the examples are stored.

  ## local_data_dir=..../examples

 

  # Location on local FS where the data for the examples is stored.

  ## sample_data_dir=...thirdparty/sample_data

 

  # Location on HDFS where the oozie examples and workflows are stored.

  ## remote_data_dir=/user/hue/oozie/workspaces

 

  # Maximum of Oozie workflows or coodinators to retrieve in one API call.

  ## oozie_jobs_count=50

 

  # Use Cron format for defining the frequency of a Coordinator instead of the old frequency number/unit.

  ## enable_cron_scheduling=true

 

 

###########################################################################

# Settings to configure the Filebrowser app

###########################################################################

 

[filebrowser]

  # Location on local filesystem where the uploaded archives are temporary stored.

  ## archive_upload_tempdir=/tmp

 

  # Show Download Button for HDFS file browser.

  ## show_download_button=false

 

  # Show Upload Button for HDFS file browser.

  ## show_upload_button=false

 

 

###########################################################################

# Settings to configure Pig

###########################################################################

 

[pig]

  # Location of piggybank.jar on local filesystem.

  ## local_sample_dir=/usr/share/hue/apps/pig/examples

 

  # Location piggybank.jar will be copied to in HDFS.

  ## remote_data_dir=/user/hue/pig/examples

 

 

###########################################################################

# Settings to configure Sqoop2

###########################################################################

 

[sqoop]

  # For autocompletion, fill out the librdbms section.

 

  # Sqoop server URL

  server_url=http://master:12000/sqoop

 

  # Path to configuration directory

   sqoop_conf_dir=/opt/sqoop-1.4.6-cdh5.8.0/conf

 

 

###########################################################################

# Settings to configure Proxy

###########################################################################

 

[proxy]

  # Comma-separated list of regular expressions,

  # which match 'host:port' of requested proxy target.

  ## whitelist=(localhost|127\.0\.0\.1):(50030|50070|50060|50075)

 

  # Comma-separated list of regular expressions,

  # which match any prefix of 'host:port/path' of requested proxy target.

  # This does not support matching GET parameters.

  ## blacklist=

 

 

###########################################################################

# Settings to configure HBase Browser

###########################################################################

 

[hbase]

  # Comma-separated list of HBase Thrift servers for clusters in the format of '(name|host:port)'.

  # Use full hostname with security.

  # If using Kerberos we assume GSSAPI SASL, not PLAIN.

  hbase_clusters=(Cluster|master:9090)

 

  # HBase configuration directory, where hbase-site.xml is located.

  hbase_conf_dir=/opt/hbase-1.2.0-cdh5.8.0/conf

 

  # Hard limit of rows or columns per row fetched before truncating.

  ## truncate_limit = 500

 

  # 'buffered' is the default of the HBase Thrift Server and supports security.

  # 'framed' can be used to chunk up responses,

  # which is useful when used in conjunction with the nonblocking server in Thrift.

  ## thrift_transport=buffered

 

 

###########################################################################

# Settings to configure Solr Search

###########################################################################

 

[search]

 

  # URL of the Solr Server

  ## solr_url=http://localhost:8983/solr/

 

  # Requires FQDN in solr_url if enabled

  ## security_enabled=false

 

  ## Query sent when no term is entered

  ## empty_query=*:*

 

  # Use latest Solr 5.2+ features.

  ## latest=false

 

 

###########################################################################

# Settings to configure Solr API lib

###########################################################################

 

[libsolr]

 

  # Choose whether Hue should validate certificates received from the server.

  ## ssl_cert_ca_verify=true

 

 

###########################################################################

# Settings to configure Solr Indexer

###########################################################################

 

[indexer]

 

  # Location of the solrctl binary.

  ## solrctl_path=/usr/bin/solrctl

 

 

###########################################################################

# Settings to configure Job Designer

###########################################################################

 

[jobsub]

 

  # Location on local FS where examples and template are stored.

  ## local_data_dir=..../data

 

  # Location on local FS where sample data is stored

  ## sample_data_dir=...thirdparty/sample_data

 

 

###########################################################################

# Settings to configure Job Browser.

###########################################################################

 

[jobbrowser]

  # Share submitted jobs information with all users. If set to false,

  # submitted jobs are visible only to the owner and administrators.

  ## share_jobs=true

 

  # Whether to disalbe the job kill button for all users in the jobbrowser

  ## disable_killing_jobs=false

 

 

###########################################################################

# Settings to configure Sentry / Security App.

###########################################################################

 

[security]

 

  # Use Sentry API V1 for Hive.

  ## hive_v1=true

 

  # Use Sentry API V2 for Hive.

  ## hive_v2=false

 

  # Use Sentry API V2 for Solr.

  ## solr_v2=true

 

 

###########################################################################

# Settings to configure the Zookeeper application.

###########################################################################

 

[zookeeper]

 

  [[clusters]]

 

    [[[default]]]

      # Zookeeper ensemble. Comma separated list of Host/Port.

      # e.g. localhost:2181,localhost:2182,localhost:2183

      ## host_ports=localhost:2181

 

      # The URL of the REST contrib service (required for znode browsing).

      ## rest_url=http://localhost:9998

 

      # Name of Kerberos principal when using security.

      ## principal_name=zookeeper

 

 

###########################################################################

# Settings for the User Admin application

###########################################################################

 

[useradmin]

  # Default home directory permissions

  ## home_dir_permissions=0755

 

  # The name of the default user group that users will be a member of

  ## default_user_group=default

 

  [[password_policy]]

    # Set password policy to all users. The default policy requires password to be at least 8 characters long,

    # and contain both uppercase and lowercase letters, numbers, and special characters.

 

    ## is_enabled=false

    ## pwd_regex="^(?=.*?[A-Z])(?=(.*[a-z]){1,})(?=(.*[\d]){1,})(?=(.*[\W_]){1,}).{8,}$"

    ## pwd_hint="The password must be at least 8 characters long, and must contain both uppercase and lowercase letters, at least one number, and at least one special character."

    ## pwd_error_message="The password must be at least 8 characters long, and must contain both uppercase and lowercase letters, at least one number, and at least one special character."

 

 

###########################################################################

# Settings to configure liboozie

###########################################################################

 

[liboozie]

  # The URL where the Oozie service runs on. This is required in order for

  # users to submit jobs. Empty value disables the config check.

  ## oozie_url=http://localhost:11000/oozie

 

  # Requires FQDN in oozie_url if enabled

  ## security_enabled=false

 

  # Location on HDFS where the workflows/coordinator are deployed when submitted.

  ## remote_deployement_dir=/user/hue/oozie/deployments

 

 

###########################################################################

# Settings for the AWS lib

###########################################################################

 

[aws]

  [[aws_accounts]]

    # Default AWS account

    [[[default]]]

      # AWS credentials

      ## access_key_id=

      ## secret_access_key=

 

      # Allow to use either environment variables or

      # EC2 InstanceProfile to retrieve AWS credentials.

      ## allow_environment_credentials=yes

 

      # AWS region to use

      ## region=us-east-1

 

 

###########################################################################

# Settings for the Sentry lib

###########################################################################

 

[libsentry]

  # Hostname or IP of server.

  ## hostname=localhost

 

  # Port the sentry service is running on.

  ## port=8038

 

  # Sentry configuration directory, where sentry-site.xml is located.

  ## sentry_conf_dir=/etc/sentry/conf

 

 

###########################################################################

# Settings to configure the ZooKeeper Lib

###########################################################################

 

[libzookeeper]

  # ZooKeeper ensemble. Comma separated list of Host/Port.

  # e.g. localhost:2181,localhost:2182,localhost:2183

  ## ensemble=localhost:2181

 

  # Name of Kerberos principal when using security.

  ## principal_name=zookeeper

 

 

###########################################################################

# Settings for the RDBMS application

###########################################################################

 

[librdbms]

  # The RDBMS app can have any number of databases configured in the databases

  # section. A database is known by its section name

  # (IE sqlite, mysql, psql, and oracle in the list below).

 

  [[databases]]

    # sqlite configuration.

    ## [[[sqlite]]]

      # Name to show in the UI.

      ## nice_name=SQLite

 

      # For SQLite, name defines the path to the database.

      ## name=/tmp/sqlite.db

 

      # Database backend to use.

      ## engine=sqlite

 

      # Database options to send to the server when connecting.

      # https://docs.djangoproject.com/en/1.4/ref/databases/

      ## options={}

 

    # mysql, oracle, or postgresql configuration.

    ## [[[mysql]]]

      # Name to show in the UI.

      ## nice_name="My SQL DB"

 

      # For MySQL and PostgreSQL, name is the name of the database.

      # For Oracle, Name is instance of the Oracle server. For express edition

      # this is 'xe' by default.

      ## name=mysqldb

 

      # Database backend to use. This can be:

      # 1. mysql

      # 2. postgresql

      # 3. oracle

      ## engine=mysql

 

      # IP or hostname of the database to connect to.

      ## host=localhost

 

      # Port the database server is listening to. Defaults are:

      # 1. MySQL: 3306

      # 2. PostgreSQL: 5432

      # 3. Oracle Express Edition: 1521

      ## port=3306

 

      # Username to authenticate with when connecting to the database.

      ## user=example

 

      # Password matching the username to authenticate with when

      # connecting to the database.

      ## password=example

 

      # Database options to send to the server when connecting.

      # https://docs.djangoproject.com/en/1.4/ref/databases/

      ## options={}

 

 

###########################################################################

# Settings to configure SAML

###########################################################################

 

[libsaml]

  # Xmlsec1 binary path. This program should be executable by the user running Hue.

  ## xmlsec_binary=/usr/local/bin/xmlsec1

 

  # Entity ID for Hue acting as service provider.

  # Can also accept a pattern where '' will be replaced with server URL base.

  ## entity_id="/saml2/metadata/"

 

  # Create users from SSO on login.

  ## create_users_on_login=true

 

  # Required attributes to ask for from IdP.

  # This requires a comma separated list.

  ## required_attributes=uid

 

  # Optional attributes to ask for from IdP.

  # This requires a comma separated list.

  ## optional_attributes=

 

  # IdP metadata in the form of a file. This is generally an XML file containing metadata that the Identity Provider generates.

  ## metadata_file=

 

  # Private key to encrypt metadata with.

  ## key_file=

 

  # Signed certificate to send along with encrypted metadata.

  ## cert_file=

 

  # Path to a file containing the password private key.

  ## key_file_password=/path/key

 

  # Execute this script to produce the private key password. This will be used when `key_file_password` is not set.

  ## key_file_password_script=/path/pwd.sh

 

  # A mapping from attributes in the response from the IdP to django user attributes.

  ## user_attribute_mapping={'uid': ('username', )}

 

  # Have Hue initiated authn requests be signed and provide a certificate.

  ## authn_requests_signed=false

 

  # Have Hue initiated logout requests be signed and provide a certificate.

  ## logout_requests_signed=false

 

  # Username can be sourced from 'attributes' or 'nameid'.

  ## username_source=attributes

 

  # Performs the logout or not.

  ## logout_enabled=true

 

 

###########################################################################

# Settings to configure OpenID

###########################################################################

 

[libopenid]

  # (Required) OpenId SSO endpoint url.

  ## server_endpoint_url=https://www.google.com/accounts/o8/id

 

  # OpenId 1.1 identity url prefix to be used instead of SSO endpoint url

  # This is only supported if you are using an OpenId 1.1 endpoint

  ## identity_url_prefix=https://app.onelogin.com/openid/your_company.com/

 

  # Create users from OPENID on login.

  ## create_users_on_login=true

 

  # Use email for username

  ## use_email_for_username=true

 

 

###########################################################################

# Settings to configure OAuth

###########################################################################

 

[liboauth]

  # NOTE:

  # To work, each of the active (i.e. uncommented) service must have

  # applications created on the social network.

  # Then the "consumer key" and "consumer secret" must be provided here.

  #

  # The addresses where to do so are:

  # Twitter:  https://dev.twitter.com/apps

  # Google+ : https://cloud.google.com/

  # Facebook: https://developers.facebook.com/apps

  # Linkedin: https://www.linkedin.com/secure/developer

  #

  # Additionnaly, the following must be set in the application settings:

  # Twitter:  Callback URL (aka Redirect URL) must be set to http://YOUR_HUE_IP_OR_DOMAIN_NAME/oauth/social_login/oauth_authenticated

  # Google+ : CONSENT SCREEN must have email address

  # Facebook: Sandbox Mode must be DISABLED

  # Linkedin: "In OAuth User Agreement", r_emailaddress is REQUIRED

 

  # The Consumer key of the application

  ## consumer_key_twitter=

  ## consumer_key_google=

  ## consumer_key_facebook=

  ## consumer_key_linkedin=

 

  # The Consumer secret of the application

  ## consumer_secret_twitter=

  ## consumer_secret_google=

  ## consumer_secret_facebook=

  ## consumer_secret_linkedin=

 

  # The Request token URL

  ## request_token_url_twitter=https://api.twitter.com/oauth/request_token

  ## request_token_url_google=https://accounts.google.com/o/oauth2/auth

  ## request_token_url_linkedin=https://www.linkedin.com/uas/oauth2/authorization

  ## request_token_url_facebook=https://graph.facebook.com/oauth/authorize

 

  # The Access token URL

  ## access_token_url_twitter=https://api.twitter.com/oauth/access_token

  ## access_token_url_google=https://accounts.google.com/o/oauth2/token

  ## access_token_url_facebook=https://graph.facebook.com/oauth/access_token

  ## access_token_url_linkedin=https://api.linkedin.com/uas/oauth2/accessToken

 

  # The Authenticate URL

  ## authenticate_url_twitter=https://api.twitter.com/oauth/authorize

  ## authenticate_url_google=https://www.googleapis.com/oauth2/v1/userinfo?access_token=

  ## authenticate_url_facebook=https://graph.facebook.com/me?access_token=

  ## authenticate_url_linkedin=https://api.linkedin.com/v1/people/~:(email-address)?format=json&oauth2_access_token=

 

  # Username Map. Json Hash format.

  # Replaces username parts in order to simplify usernames obtained

  # Example: {"@sub1.domain.com":"_S1", "@sub2.domain.com":"_S2"}

  # converts '[email protected]' to 'email_S1'

  ## username_map={}

 

  # Whitelisted domains (only applies to Google OAuth). CSV format.

  ## whitelisted_domains_google=

 

 

###########################################################################

# Settings to configure Metadata

###########################################################################

 

[metadata]

  # For metadata tagging and enhancement features

 

  [[optimizer]]

    # For SQL query and table analysis

    # Base URL to Optimizer API.

    ## api_url=https://alpha.optimizer.cloudera.com

    # The name of the product or group which will have API access to the emails associated with it.

    ## product_name=hue

    # A secret passphrase associated with the productName

    ## product_secret=hue

    # Execute this script to produce the product secret. This will be used when `product_secret` is not set.

    ## product_secret_script=

 

    # The email of the Optimizer account you want to associate with the Product.

    ## [email protected]

    # The password associated with the Optimizer account you to associate with the Product.

    ## email_password=hue

    # Execute this script to produce the email password. This will be used when `email_password` is not set.

    ## password_script=

 

    # In secure mode (HTTPS), if Optimizer SSL certificates have to be verified against certificate authority.

    ## ssl_cert_ca_verify=True

 

  [[navigator]]

    # For tagging tables, files and getting lineage of data.

    # Navigator API URL (without version suffix)

    ## api_url=http://localhost:7187/api

 

    # Navigator API HTTP authentication username and password

    # Override the desktop default username and password of the hue user used for authentications with other services.

    # e.g. Used for LDAP/PAM pass-through authentication.

    ## auth_username=hue

    ## auth_password=

-------------------------------------------------------------------------

 

4.通过URL访问:http://slave1:8888/

 
hadoop大数据平台手动搭建-hue_第1张图片
 

你可能感兴趣的:(hue)