openstack
/
sahara
Code Issues Proposed changes
sahara/sahara/plugins/hdp/versions/version_2_0_6/resources/ambari-config-resource.json

3537 lines
177 KiB
JSON
Raw Blame History

{
"configurations": [
{
"tag": "global.xml",
"properties": [
{
"default_value": "/etc/ganglia/hdp",
"description": "",
"config_type": "string",
"applicable_target": "GANGLIA",
"is_optional": true,
"scope": "cluster",
"name": "ganglia_conf_dir"
},
{
"default_value": "/var/run/ganglia/hdp",
"description": "",
"config_type": "string",
"applicable_target": "GANGLIA",
"is_optional": true,
"scope": "cluster",
"name": "ganglia_runtime_dir"
},
{
"default_value": "nobody",
"description": "",
"config_type": "string",
"applicable_target": "GANGLIA",
"is_optional": true,
"scope": "cluster",
"name": "gmetad_user"
},
{
"default_value": "nobody",
"description": "",
"config_type": "string",
"applicable_target": "GANGLIA",
"is_optional": true,
"scope": "cluster",
"name": "gmond_user"
},
{
"default_value": "/var/lib/ganglia/rrds",
"description": "Location of rrd files.",
"config_type": "string",
"applicable_target": "GANGLIA",
"is_optional": true,
"scope": "cluster",
"name": "rrdcached_base_dir"
},
{
"default_value": "100",
"description": "Base Client Scanner Caching",
"config_type": "int",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "client_scannercaching"
},
{
"default_value": "/etc/hbase",
"description": "Config Directory for HBase.",
"config_type": "string",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hbase_conf_dir"
},
{
"default_value": "/apps/hbase/data",
"description": "HBase Relative Path to HDFS.",
"config_type": "string",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hbase_hdfs_root_dir"
},
{
"default_value": "/var/log/hbase",
"description": "Log Directories for HBase.",
"config_type": "string",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hbase_log_dir"
},
{
"default_value": "1024",
"description": "HBase Master Heap Size",
"config_type": "int",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hbase_master_heapsize"
},
{
"default_value": "/var/run/hbase",
"description": "Log Directories for HBase.",
"config_type": "string",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hbase_pid_dir"
},
{
"default_value": "1024",
"description": "Log Directories for HBase.",
"config_type": "int",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hbase_regionserver_heapsize"
},
{
"default_value": "hbase",
"description": "HBase User Name.",
"config_type": "string",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hbase_user"
},
{
"default_value": "true",
"description": "HDFS Short Circuit Read",
"config_type": "string",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hdfs_enable_shortcircuit_read"
},
{
"default_value": "true",
"description": "HDFS append support",
"config_type": "string",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hdfs_support_append"
},
{
"default_value": "0.40",
"description": "HFile block cache size.",
"config_type": "string",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hfile_blockcache_size"
},
{
"default_value": "10485760",
"description": "HBase Client Maximum key-value Size",
"config_type": "int",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hfile_max_keyvalue_size"
},
{
"default_value": "2",
"description": "HBase Region Block Multiplier",
"config_type": "int",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hregion_blockmultiplier"
},
{
"default_value": "604800000",
"description": "The time between major compactions of all HStoreFiles in a region. Set to 0 to disable automated major compactions.",
"config_type": "int",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hregion_majorcompaction"
},
{
"default_value": "10",
"description": "HStore blocking storefiles.",
"config_type": "int",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hstore_blockingstorefiles"
},
{
"default_value": "3",
"description": "HBase HStore compaction threshold.",
"config_type": "int",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hstore_compactionthreshold"
},
{
"default_value": "10737418240",
"description": "Maximum HStoreFile Size",
"config_type": "int",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hstorefile_maxsize"
},
{
"default_value": "60",
"description": "HBase RegionServer Handler",
"config_type": "int",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "regionserver_handlers"
},
{
"default_value": "true",
"description": "Region Server memstore.",
"config_type": "string",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "regionserver_memstore_lab"
},
{
"default_value": "0.38",
"description": "Region Server memstore lower limit.",
"config_type": "string",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "regionserver_memstore_lowerlimit"
},
{
"default_value": "0.4",
"description": "Region Server memstore upper limit.",
"config_type": "string",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "regionserver_memstore_upperlimit"
},
{
"default_value": "30000",
"description": "ZooKeeper Session Timeout",
"config_type": "int",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "zookeeper_sessiontimeout"
},
{
"default_value": "1073741824",
"description": "Reserved space for HDFS",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "datanode_du_reserved"
},
{
"default_value": "hbase",
"description": "Default Block Replication.",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs_block_local_path_access_user"
},
{
"default_value": "50010",
"description": "Port for datanode address.",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs_datanode_address"
},
{
"default_value": "/hadoop/hdfs/data",
"description": "Data directories for Data Nodes.",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs_datanode_data_dir"
},
{
"default_value": "750",
"description": "Datanode dir perms.",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs_datanode_data_dir_perm"
},
{
"default_value": "0",
"description": "DataNode volumes failure toleration",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs_datanode_failed_volume_tolerated"
},
{
"default_value": "50075",
"description": "Port for datanode address.",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs_datanode_http_address"
},
{
"default_value": "/hadoop/hdfs/namesecondary",
"description": "Secondary NameNode checkpoint dir.",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs_namenode_checkpoint_dir"
},
{
"default_value": "21600",
"description": "HDFS Maximum Checkpoint Delay",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs_namenode_checkpoint_period"
},
{
"default_value": "/hadoop/hdfs/namenode",
"description": "NameNode Directories.",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs_namenode_name_dir"
},
{
"default_value": "3",
"description": "Default Block Replication.",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs_replication"
},
{
"default_value": "true",
"description": "WebHDFS enabled",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs_webhdfs_enabled"
},
{
"default_value": "1024",
"description": "DataNode maximum Java heap size",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dtnode_heapsize"
},
{
"default_value": "0.5",
"description": "FS Checkpoint Size.",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "fs_checkpoint_size"
},
{
"default_value": "1024",
"description": "Hadoop maximum Java heap size",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "hadoop_heapsize"
},
{
"default_value": "/var/run/hadoop",
"description": "Hadoop PID Dir Prefix",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "hadoop_pid_dir_prefix"
},
{
"default_value": "/var/log/hadoop",
"description": "Hadoop Log Dir Prefix",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "hdfs_log_dir_prefix"
},
{
"default_value": "hdfs",
"description": "User and Groups.",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "hdfs_user"
},
{
"default_value": "EXAMPLE.COM",
"description": "Kerberos realm.",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "kerberos_domain"
},
{
"default_value": "/etc/security/keytabs",
"description": "Kerberos keytab path.",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "keytab_path"
},
{
"default_value": "true",
"description": "LZO compression enabled",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "lzo_enabled"
},
{
"default_value": "/var/run/hadoop/hdfs/namenode/formatted/",
"description": "Formatteed Mark Directory.",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "namenode_formatted_mark_dir"
},
{
"default_value": "1024",
"description": "NameNode Java heap size",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "namenode_heapsize"
},
{
"default_value": "200",
"description": "NameNode maximum new generation size",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "namenode_opt_maxnewsize"
},
{
"default_value": "200",
"description": "NameNode new generation size",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "namenode_opt_newsize"
},
{
"default_value": "users",
"description": "Proxy user group.",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "proxyuser_group"
},
{
"default_value": "false",
"description": "Hadoop Security",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "security_enabled"
},
{
"default_value": "/var/log/hadoop-mapreduce",
"description": "Mapreduce Log Dir Prefix",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapred_log_dir_prefix"
},
{
"default_value": "/var/run/hadoop-mapreduce",
"description": "Mapreduce PID Dir Prefix",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapred_pid_dir_prefix"
},
{
"default_value": "mapred",
"description": "Mapreduce User",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapred_user"
},
{
"default_value": "nagios",
"description": "",
"config_type": "string",
"applicable_target": "NAGIOS",
"is_optional": true,
"scope": "cluster",
"name": "nagios_group"
},
{
"default_value": "nagios",
"description": "Nagios process user.",
"config_type": "string",
"applicable_target": "NAGIOS",
"is_optional": true,
"scope": "cluster",
"name": "nagios_user"
},
{
"default_value": "nagiosadmin",
"description": "Web user name.",
"config_type": "string",
"applicable_target": "NAGIOS",
"is_optional": true,
"scope": "cluster",
"name": "nagios_web_login"
},
{
"default_value": "/var/log/webhcat",
"description": "",
"config_type": "string",
"applicable_target": "WEBHCAT",
"is_optional": true,
"scope": "cluster",
"name": "hcat_log_dir"
},
{
"default_value": "/var/run/webhcat",
"description": "",
"config_type": "string",
"applicable_target": "WEBHCAT",
"is_optional": true,
"scope": "cluster",
"name": "hcat_pid_dir"
},
{
"default_value": "hcat",
"description": "",
"config_type": "string",
"applicable_target": "WEBHCAT",
"is_optional": true,
"scope": "cluster",
"name": "hcat_user"
},
{
"default_value": "hcat",
"description": "",
"config_type": "string",
"applicable_target": "WEBHCAT",
"is_optional": true,
"scope": "cluster",
"name": "webhcat_user"
},
{
"default_value": "1024",
"description": "Max heapsize for NodeManager using a numerical value in the scale of MB",
"config_type": "int",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "nodemanager_heapsize"
},
{
"default_value": "1024",
"description": "Max heapsize for ResourceManager using a numerical value in the scale of MB",
"config_type": "int",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "resourcemanager_heapsize"
},
{
"default_value": "1024",
"description": "Max heapsize for all YARN components using a numerical value in the scale of MB",
"config_type": "int",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn_heapsize"
},
{
"default_value": "/var/log/hadoop-yarn",
"description": "YARN Log Dir Prefix",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn_log_dir_prefix"
},
{
"default_value": "/var/run/hadoop-yarn",
"description": "YARN PID Dir Prefix",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn_pid_dir_prefix"
},
{
"default_value": "yarn",
"description": "YARN User",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn_user"
},
{
"default_value": "2181",
"description": "Port for running ZK Server.",
"config_type": "int",
"applicable_target": "ZOOKEEPER",
"is_optional": true,
"scope": "cluster",
"name": "clientPort"
},
{
"default_value": "10",
"description": "Ticks to allow for sync at Init.",
"config_type": "int",
"applicable_target": "ZOOKEEPER",
"is_optional": true,
"scope": "cluster",
"name": "initLimit"
},
{
"default_value": "5",
"description": "Ticks to allow for sync at Runtime.",
"config_type": "int",
"applicable_target": "ZOOKEEPER",
"is_optional": true,
"scope": "cluster",
"name": "syncLimit"
},
{
"default_value": "2000",
"description": "The length of a single tick in milliseconds,which is the basic time unit used by ZooKeeper",
"config_type": "int",
"applicable_target": "ZOOKEEPER",
"is_optional": true,
"scope": "cluster",
"name": "tickTime"
},
{
"default_value": "/hadoop/zookeeper",
"description": "Data directory for ZooKeeper.",
"config_type": "string",
"applicable_target": "ZOOKEEPER",
"is_optional": true,
"scope": "cluster",
"name": "zk_data_dir"
},
{
"default_value": "/var/log/zookeeper",
"description": "ZooKeeper Log Dir",
"config_type": "string",
"applicable_target": "ZOOKEEPER",
"is_optional": true,
"scope": "cluster",
"name": "zk_log_dir"
},
{
"default_value": "/var/run/zookeeper",
"description": "ZooKeeper Pid Dir",
"config_type": "string",
"applicable_target": "ZOOKEEPER",
"is_optional": true,
"scope": "cluster",
"name": "zk_pid_dir"
},
{
"default_value": "/var/run/zookeeper/zookeeper_server.pid",
"description": "ZooKeeper Pid File",
"config_type": "string",
"applicable_target": "ZOOKEEPER",
"is_optional": true,
"scope": "cluster",
"name": "zk_pid_file"
},
{
"default_value": "zookeeper",
"description": "ZooKeeper User.",
"config_type": "string",
"applicable_target": "ZOOKEEPER",
"is_optional": true,
"scope": "cluster",
"name": "zk_user"
},
{
"default_value": "/var/run/oozie",
"description": "...",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie_pid_dir"
},
{
"default_value": "/var/run/hive",
"description": "...",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive_pid_dir"
},
{
"default_value": "localhost",
"description": "...",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie_hostname"
},
{
"default_value": "ambari-qa",
"description": "...",
"config_type": "string",
"applicable_target": "general",
"is_optional": true,
"scope": "cluster",
"name": "smokeuser"
},
{
"default_value": "MySQL",
"description": "...",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive_ambari_database"
},
{
"default_value": "/var/log/oozie",
"description": "...",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie_log_dir"
},
{
"default_value": "com.mysql.jdbc.Driver",
"description": "...",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive_jdbc_driver"
},
{
"default_value": "oozie",
"description": "...",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie_user"
},
{
"default_value": "",
"description": "...",
"config_type": "string",
"applicable_target": "WEBHCAT",
"is_optional": true,
"scope": "cluster",
"name": "hcat_conf_dir"
},
{
"default_value": "/hadoop/oozie/data",
"description": "...",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie_data_dir"
},
{
"default_value": "hive",
"description": "...",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive_user"
},
{
"default_value": "localhost",
"description": "...",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive_hostname"
},
{
"default_value": "9083",
"description": "...",
"config_type": "int",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive_metastore_port"
},
{
"default_value": "mysql",
"description": "...",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive_database_type"
},
{
"default_value": "New Derby Database",
"description": "...",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie_database"
},
{
"default_value": "admin@nowhere.com",
"description": "...",
"config_type": "string",
"applicable_target": "NAGIOS",
"is_optional": true,
"scope": "cluster",
"name": "nagios_contact"
},
{
"default_value": "New MySQL Database",
"description": "...",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive_database"
},
{
"default_value": "admin",
"description": "...",
"config_type": "string",
"applicable_target": "NAGIOS",
"is_optional": true,
"scope": "cluster",
"name": "nagios_web_password"
},
{
"default_value": "Derby",
"description": "...",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie_derby_database"
},
{
"default_value": "derby",
"description": "...",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie_database_type"
},
{
"default_value": "org.apache.derby.jdbc.EmbeddedDriver",
"description": "...",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie_jdbc_driver"
},
{
"default_value": "/var/log/hive",
"description": "...",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive_log_dir"
},
{
"default_value": "hadoop",
"description": "...",
"config_type": "string",
"applicable_target": "general",
"is_optional": true,
"scope": "cluster",
"name": "user_group"
},
{
"default_value": "/usr/lib/hcatalog/share/hcatalog/hcatalog-core.jar",
"description": "...",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive_aux_jars_path"
}
]
},
{
"tag": "hbase-site.xml",
"properties": [
{
"default_value": "/var/lib/hadoop-hdfs/dn_socket",
"description": "Path to domain socket.",
"config_type": "string",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "dfs.domain.socket.path"
},
{
"default_value": "10485760",
"description": "Specifies the combined maximum allowed size of a KeyValue\n instance. This is to set an upper boundary for a single entry saved in a\n storage file. Since they cannot be split it helps avoiding that a region\n cannot be split any further because the data is too large. It seems wise\n to set this to a fraction of the maximum region size. Setting it to zero\n or less disables the check.\n ",
"config_type": "int",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hbase.client.keyvalue.maxsize"
},
{
"default_value": "100",
"description": "Number of rows that will be fetched when calling next\n on a scanner if it is not served from (local,client) memory. Higher\n caching values will enable faster scanners but will eat up more memory\n and some calls of next may take longer and longer times when the cache is empty.\n Do not set this value such that the time between invocations is greater\n than the scanner timeout; i.e. hbase.regionserver.lease.period\n ",
"config_type": "int",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hbase.client.scanner.caching"
},
{
"default_value": "true",
"description": "The mode the cluster will be in. Possible values are\n false for standalone mode and true for distributed mode. If\n false,startup will run all HBase and ZooKeeper daemons together\n in the one JVM.\n ",
"config_type": "string",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hbase.cluster.distributed"
},
{
"default_value": "true",
"description": "Disables version verification.",
"config_type": "string",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hbase.defaults.for.version.skip"
},
{
"default_value": "86400000",
"description": "The time (in milliseconds) between 'major' compactions of all\n HStoreFiles in a region. Default: 1 day.\n Set to 0 to disable automated major compactions.\n ",
"config_type": "int",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hbase.hregion.majorcompaction"
},
{
"default_value": "10737418240",
"description": "\n Maximum HStoreFile size. If any one of a column families' HStoreFiles has\n grown to exceed this value,the hosting HRegion is split in two.\n Default: 1G.\n ",
"config_type": "int",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hbase.hregion.max.filesize"
},
{
"default_value": "2",
"description": "Block updates if memstore has hbase.hregion.memstore.block.multiplier\n time hbase.hregion.flush.size bytes. Useful preventing\n runaway memstore during spikes in update traffic. Without an\n upper-bound,memstore fills such that when it flushes the\n resultant flush files take a long time to compact or split,or\n worse,we OOME\n ",
"config_type": "int",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hbase.hregion.memstore.block.multiplier"
},
{
"default_value": "134217728",
"description": "\n Memstore will be flushed to disk if size of the memstore\n exceeds this number of bytes. Value is checked by a thread that runs\n every hbase.server.thread.wakefrequency.\n ",
"config_type": "int",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hbase.hregion.memstore.flush.size"
},
{
"default_value": "true",
"description": "\n Enables the MemStore-Local Allocation Buffer,\n a feature which works to prevent heap fragmentation under\n heavy write loads. This can reduce the frequency of stop-the-world\n GC pauses on large heaps.\n ",
"config_type": "string",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hbase.hregion.memstore.mslab.enabled"
},
{
"default_value": "10",
"description": "\n If more than this number of StoreFiles in any one Store\n (one StoreFile is written per flush of MemStore) then updates are\n blocked for this HRegion until a compaction is completed,or\n until hbase.hstore.blockingWaitTime has been exceeded.\n ",
"config_type": "int",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hbase.hstore.blockingStoreFiles"
},
{
"default_value": "3",
"description": "\n If more than this number of HStoreFiles in any one HStore\n (one HStoreFile is written per flush of memstore) then a compaction\n is run to rewrite all HStoreFiles files as one. Larger numbers\n put off compaction but when it runs,it takes longer to complete.\n ",
"config_type": "int",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hbase.hstore.compactionThreshold"
},
{
"default_value": "120",
"description": "\n The number of times the region flush operation will be retried.\n ",
"config_type": "int",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hbase.hstore.flush.retries.number"
},
{
"default_value": "0.38",
"description": "When memstores are being forced to flush to make room in\n memory,keep flushing until we hit this mark. Defaults to 35% of heap.\n This value equal to hbase.regionserver.global.memstore.upperLimit causes\n the minimum possible flushing to occur when updates are blocked due to\n memstore limiting.\n ",
"config_type": "string",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hbase.regionserver.global.memstore.lowerLimit"
},
{
"default_value": "0.4",
"description": "Maximum size of all memstores in a region server before new\n updates are blocked and flushes are forced. Defaults to 40% of heap\n ",
"config_type": "string",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hbase.regionserver.global.memstore.upperLimit"
},
{
"default_value": "60",
"description": "Count of RPC Listener instances spun up on RegionServers.\n Same property is used by the Master for count of master handlers.\n Default is 10.\n ",
"config_type": "int",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hbase.regionserver.handler.count"
},
{
"default_value": "hdfs://localhost:8020/apps/hbase/data",
"description": "The directory shared by region servers and into\n which HBase persists. The URL should be 'fully-qualified'\n to include the filesystem scheme. For example,to specify the\n HDFS directory '/hbase' where the HDFS instance's namenode is\n running at namenode.example.org on port 9000,set this value to:\n hdfs://namenode.example.org:9000/hbase. By default HBase writes\n into /tmp. Change this configuration else all data will be lost\n on machine restart.\n ",
"config_type": "string",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hbase.rootdir"
},
{
"default_value": "simple",
"description": "...",
"config_type": "string",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hbase.security.authentication"
},
{
"default_value": "false",
"description": "Enables HBase authorization. Set the value of this property to false to disable HBase authorization.\n ",
"config_type": "string",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hbase.security.authorization"
},
{
"default_value": "hbase",
"description": "List of users or groups (comma-separated),who are allowed\n full privileges,regardless of stored ACLs,across the cluster.\n Only used when HBase security is enabled.\n ",
"config_type": "string",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hbase.superuser"
},
{
"default_value": "/hadoop/hbase",
"description": "Temporary directory on the local filesystem.\n Change this setting to point to a location more permanent\n than '/tmp' (The '/tmp' directory is often cleared on\n machine restart).\n ",
"config_type": "string",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hbase.tmp.dir"
},
{
"default_value": "2181",
"description": "Property from ZooKeeper's config zoo.cfg.\n The port at which the clients will connect.\n ",
"config_type": "int",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hbase.zookeeper.property.clientPort"
},
{
"default_value": "localhost",
"description": "Comma separated list of servers in the ZooKeeper Quorum.\n For example,\"host1.mydomain.com,host2.mydomain.com,host3.mydomain.com\".\n By default this is set to localhost for local and pseudo-distributed modes\n of operation. For a fully-distributed setup,this should be set to a full\n list of ZooKeeper quorum servers. If HBASE_MANAGES_ZK is set in hbase-env.sh\n this is the list of servers which we will start/stop ZooKeeper on.\n ",
"config_type": "string",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hbase.zookeeper.quorum"
},
{
"default_value": "true",
"description": "Instructs HBase to make use of ZooKeeper's multi-update functionality.\n This allows certain ZooKeeper operations to complete more quickly and prevents some issues\n with rare Replication failure scenarios (see the release note of HBASE-2611 for an example).\u00b7\n IMPORTANT: only set this to true if all ZooKeeper servers in the cluster are on version 3.4+\n and will not be downgraded. ZooKeeper versions before 3.4 do not support multi-update and will\n not fail gracefully if multi-update is invoked (see ZOOKEEPER-1495).\n ",
"config_type": "string",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hbase.zookeeper.useMulti"
},
{
"default_value": "0.40",
"description": "\n Percentage of maximum heap (-Xmx setting) to allocate to block cache\n used by HFile/StoreFile. Default of 0.25 means allocate 25%.\n Set to 0 to disable but it's not recommended.\n ",
"config_type": "string",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "hfile.block.cache.size"
},
{
"default_value": "30000",
"description": "ZooKeeper session timeout.\n HBase passes this to the zk quorum as suggested maximum time for a\n session (This setting becomes zookeeper's 'maxSessionTimeout'). See\n http://hadoop.apache.org/zookeeper/docs/current/zookeeperProgrammers.html#ch_zkSessions\n \"The client sends a requested timeout,the server responds with the\n timeout that it can give the client. \" In milliseconds.\n ",
"config_type": "int",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "zookeeper.session.timeout"
},
{
"default_value": "/hbase-unsecure",
"description": "Root ZNode for HBase in ZooKeeper. All of HBase's ZooKeeper\n files that are configured with a relative path will go under this node.\n By default,all of HBase's ZooKeeper file path are configured with a\n relative path,so they will all go under this directory unless changed.\n ",
"config_type": "string",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "zookeeper.znode.parent"
}
]
},
{
"tag": "hbase-policy.xml",
"properties": [
{
"default_value": "*",
"description": "ACL for HMasterInterface protocol implementation (ie. \n clients talking to HMaster for admin operations).\n The ACL is a comma-separated list of user and group names. The user and \n group list is separated by a blank. For e.g. \"alice,bob users,wheel\". \n A special value of \"*\" means all users are allowed.",
"config_type": "string",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "security.admin.protocol.acl"
},
{
"default_value": "*",
"description": "ACL for HMasterRegionInterface protocol implementations\n (for HRegionServers communicating with HMaster)\n The ACL is a comma-separated list of user and group names. The user and \n group list is separated by a blank. For e.g. \"alice,bob users,wheel\". \n A special value of \"*\" means all users are allowed.",
"config_type": "string",
"applicable_target": "HBASE",
"is_optional": true,
"scope": "cluster",
"name": "security.masterregion.protocol.acl"
}
]
},
{
"tag": "hdfs-site.xml",
"properties": [
{
"default_value": "true",
"description": "\nIf \"true\",access tokens are used as capabilities for accessing datanodes.\nIf \"false\",no access tokens are checked on accessing datanodes.\n",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.block.access.token.enable"
},
{
"default_value": "120",
"description": "Delay for first block report in seconds.",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.blockreport.initialDelay"
},
{
"default_value": "134217728",
"description": "The default block size for new files.",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.blocksize"
},
{
"default_value": "true",
"description": "\n This configuration parameter turns on short-circuit local reads.\n ",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.client.read.shortcircuit"
},
{
"default_value": "4096",
"description": "\n The DFSClient maintains a cache of recently opened file descriptors. This\n parameter controls the size of that cache. Setting this higher will use\n more file descriptors,but potentially provide better performance on\n workloads involving lots of seeks.\n ",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.client.read.shortcircuit.streams.cache.size"
},
{
"default_value": " hdfs",
"description": "ACL for who all can view the default servlets in the HDFS",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.cluster.administrators"
},
{
"default_value": "0.0.0.0:50010",
"description": "...",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.datanode.address"
},
{
"default_value": "6250000",
"description": "\n Specifies the maximum amount of bandwidth that each datanode\n can utilize for the balancing purpose in term of\n the number of bytes per second.\n ",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.datanode.balance.bandwidthPerSec"
},
{
"default_value": "750",
"description": "The permissions that should be there on dfs.datanode.data.dir\ndirectories. The datanode will not come up if the permissions are\ndifferent on existing dfs.datanode.data.dir directories. If the directories\ndon't exist,they will be created with this permission.",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.datanode.data.dir.perm"
},
{
"default_value": "1073741824",
"description": "Reserved space in bytes per volume. Always leave this much space free for non dfs use.\n",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.datanode.du.reserved"
},
{
"default_value": "0",
"description": "#of failed disks dn would tolerate",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.datanode.failed.volumes.tolerated"
},
{
"default_value": "0.0.0.0:50075",
"description": "...",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.datanode.http.address"
},
{
"default_value": "0.0.0.0:8010",
"description": "\nThe datanode ipc server address and port.\nIf the port is 0 then the server will start on a free port.\n",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.datanode.ipc.address"
},
{
"default_value": "1024",
"description": "PRIVATE CONFIG VARIABLE",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.datanode.max.transfer.threads"
},
{
"default_value": "3",
"description": "Determines datanode heartbeat interval in seconds.",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.heartbeat.interval"
},
{
"default_value": "50470",
"description": "\n This property is used by HftpFileSystem.\n ",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.https.port"
},
{
"default_value": "/grid/0/hdfs/journal",
"description": "The path where the JournalNode daemon will store its local state. ",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.journalnode.edits.dir"
},
{
"default_value": "0.0.0.0:8480",
"description": "The address and port the JournalNode web UI listens on.\n If the port is 0 then the server will start on a free port. ",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.journalnode.http-address"
},
{
"default_value": "0",
"description": "The access time for HDFS file is precise upto this value.\n The default value is 1 hour. Setting a value of 0 disables\n access times for HDFS.\n ",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.namenode.accesstime.precision"
},
{
"default_value": "true",
"description": "\n Indicate whether or not to avoid reading from stale datanodes whose\n heartbeat messages have not been received by the namenode for more than a\n specified time interval.\n ",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.namenode.avoid.read.stale.datanode"
},
{
"default_value": "true",
"description": "\n Indicate whether or not to avoid writing to stale datanodes whose\n heartbeat messages have not been received by the namenode for more than a\n specified time interval.\n ",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.namenode.avoid.write.stale.datanode"
},
{
"default_value": "${dfs.namenode.checkpoint.dir}",
"description": "Determines where on the local filesystem the DFS secondary\n name node should store the temporary edits to merge.\n If this is a comma-delimited list of directoires then teh edits is\n replicated in all of the directoires for redundancy.\n Default value is same as dfs.namenode.checkpoint.dir\n ",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.namenode.checkpoint.edits.dir"
},
{
"default_value": "100",
"description": "Added to grow Queue size so that more client connections are allowed",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.namenode.handler.count"
},
{
"default_value": "1.0f",
"description": "\n Specifies the percentage of blocks that should satisfy\n the minimal replication requirement defined by dfs.namenode.replication.min.\n Values less than or equal to 0 mean not to start in safe mode.\n Values greater than 1 will make safe mode permanent.\n ",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.namenode.safemode.threshold-pct"
},
{
"default_value": "30000",
"description": "Datanode is stale after not getting a heartbeat in this interval in ms",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.namenode.stale.datanode.interval"
},
{
"default_value": "1.0f",
"description": "When the ratio of number stale datanodes to total datanodes marked is greater\n than this ratio,stop avoiding writing to stale nodes so as to prevent causing hotspots.\n ",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.namenode.write.stale.datanode.ratio"
},
{
"default_value": "true",
"description": "\nIf \"true\",enable permission checking in HDFS.\nIf \"false\",permission checking is turned off,\nbut all other behavior is unchanged.\nSwitching from one parameter value to the other does not change the mode,\nowner or group of files or directories.\n",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.permissions.enabled"
},
{
"default_value": "hdfs",
"description": "The name of the group of super-users.",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.permissions.superusergroup"
},
{
"default_value": "3",
"description": "Default block replication.\n ",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.replication"
},
{
"default_value": "50",
"description": "Maximal block replication.\n ",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.replication.max"
},
{
"default_value": "true",
"description": "to enable dfs append",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.support.append"
},
{
"default_value": "true",
"description": "to enable webhdfs",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.webhdfs.enabled"
},
{
"default_value": "022",
"description": "\nThe octal umask used when creating files and directories.\n",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "fs.permissions.umask-mode"
},
{
"default_value": "67108864",
"description": "...",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "fs.checkpoint.size"
},
{
"default_value": "%NN_HOST%:50470",
"description": "...",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.namenode.https-address"
},
{
"default_value": "/mnt/hadoop/hdfs/namesecondary",
"description": "...",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.namenode.checkpoint.dir"
},
{
"default_value": "/mnt/hadoop/hdfs/data",
"description": "...",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.datanode.data.dir"
},
{
"default_value": "%NN_HOST%:50070",
"description": "...",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.namenode.http-address"
},
{
"default_value": "%SNN_HOST%:50090",
"description": "...",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.namenode.secondary.http-address"
},
{
"default_value": "/etc/hadoop/conf/dfs.exclude",
"description": "...",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.hosts.exclude"
},
{
"default_value": "21600",
"description": "...",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.namenode.checkpoint.period"
},
{
"default_value": "true",
"description": "...",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.namenode.name.dir.restore"
},
{
"default_value": "/mnt/hadoop/hdfs/namenode",
"description": "...",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "dfs.namenode.name.dir"
}
]
},
{
"tag": "core-site.xml",
"properties": [
{
"default_value": "360",
"description": "Number of minutes between trash checkpoints.\n If zero,the trash feature is disabled.\n ",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "fs.trash.interval"
},
{
"default_value": "\n RULE:[2:$1@$0]([rn]m@.*)s/.*/yarn/\n RULE:[2:$1@$0](jhs@.*)s/.*/mapred/\n RULE:[2:$1@$0]([nd]n@.*)s/.*/hdfs/\n RULE:[2:$1@$0](hm@.*)s/.*/hbase/\n RULE:[2:$1@$0](rs@.*)s/.*/hbase/\n DEFAULT\n ",
"description": "The mapping from kerberos principal names to local OS mapreduce.job.user.names.\n So the default rule is just \"DEFAULT\" which takes all principals in your default domain to their first component.\n \"omalley@APACHE.ORG\" and \"omalley/admin@APACHE.ORG\" to \"omalley\",if your default domain is APACHE.ORG.\nThe translations rules have 3 sections:\n base filter substitution\nThe base consists of a number that represents the number of components in the principal name excluding the realm and the pattern for building the name from the sections of the principal name. The base uses $0 to mean the realm,$1 to mean the first component and $2 to mean the second component.\n\n[1:$1@$0] translates \"omalley@APACHE.ORG\" to \"omalley@APACHE.ORG\"\n[2:$1] translates \"omalley/admin@APACHE.ORG\" to \"omalley\"\n[2:$1%$2] translates \"omalley/admin@APACHE.ORG\" to \"omalley%admin\"\n\nThe filter is a regex in parens that must the generated string for the rule to apply.\n\n\"(.*%admin)\" will take any string that ends in \"%admin\"\n\"(.*@ACME.COM)\" will take any string that ends in \"@ACME.COM\"\n\nFinally,the substitution is a sed rule to translate a regex into a fixed string.\n\n\"s/@ACME\\.COM//\" removes the first instance of \"@ACME.COM\".\n\"s/@[A-Z]*\\.COM//\" removes the first instance of \"@\" followed by a name followed by \".COM\".\n\"s/X/Y/g\" replaces all of the \"X\" in the name with \"Y\"\n\nSo,if your default realm was APACHE.ORG,but you also wanted to take all principals from ACME.COM that had a single component \"joe@ACME.COM\",you'd do:\n\nRULE:[1:$1@$0](.@ACME.ORG)s/@.//\nDEFAULT\n\nTo also translate the names with a second component,you'd make the rules:\n\nRULE:[1:$1@$0](.@ACME.ORG)s/@.//\nRULE:[2:$1@$0](.@ACME.ORG)s/@.//\nDEFAULT\n\nIf you want to treat all principals from APACHE.ORG with /admin as \"admin\",your rules would look like:\n\nRULE[2:$1%$2@$0](.%admin@APACHE.ORG)s/./admin/\nDEFAULT\n ",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "hadoop.security.auth_to_local"
},
{
"default_value": "simple",
"description": "\n Set the authentication for the cluster. Valid values are: simple or\n kerberos.\n ",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "hadoop.security.authentication"
},
{
"default_value": "false",
"description": "\n Enable authorization for different protocols.\n ",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "hadoop.security.authorization"
},
{
"default_value": "org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.DefaultCodec",
"description": "A list of the compression codec classes that can be used\n for compression/decompression.",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "io.compression.codecs"
},
{
"default_value": "131072",
"description": "The size of buffer for use in sequence files.\n The size of this buffer should probably be a multiple of hardware\n page size (4096 on Intel x86),and it determines how much data is\n buffered during read and write operations.",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "io.file.buffer.size"
},
{
"default_value": "org.apache.hadoop.io.serializer.WritableSerialization",
"description": "...",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "io.serializations"
},
{
"default_value": "50",
"description": "Defines the maximum number of retries for IPC connections.",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "ipc.client.connect.max.retries"
},
{
"default_value": "30000",
"description": "The maximum time after which a client will bring down the\n connection to the server.\n ",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "ipc.client.connection.maxidletime"
},
{
"default_value": "8000",
"description": "Defines the threshold number of connections after which\n connections will be inspected for idleness.\n ",
"config_type": "int",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "ipc.client.idlethreshold"
},
{
"default_value": "false",
"description": " If set to true,the web interfaces of JT and NN may contain\n actions,such as kill job,delete file,etc.,that should\n not be exposed to public. Enable this option if the interfaces\n are only reachable by those who have the right authorization.\n ",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.jobtracker.webinterface.trusted"
},
{
"default_value": "users",
"description": "...",
"config_type": "string",
"applicable_target": "WEBHCAT",
"is_optional": true,
"scope": "cluster",
"name": "hadoop.proxyuser.hcat.groups"
},
{
"default_value": "%WEBHCAT_HOST%",
"description": "...",
"config_type": "string",
"applicable_target": "WEBHCAT",
"is_optional": true,
"scope": "cluster",
"name": "hadoop.proxyuser.hcat.hosts"
},
{
"default_value": "users",
"description": "...",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "hadoop.proxyuser.oozie.groups"
},
{
"default_value": "users",
"description": "...",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hadoop.proxyuser.hive.groups"
},
{
"default_value": "null",
"description": "...",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "fs.AbstractFileSystem.glusterfs.impl"
},
{
"default_value": "localhost",
"description": "...",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hadoop.proxyuser.hive.hosts"
},
{
"default_value": "localhost",
"description": "...",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "hadoop.proxyuser.oozie.hosts"
},
{
"default_value": "hdfs://localhost:8020",
"description": "...",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "fs.defaultFS"
}
]
},
{
"tag": "hadoop-policy.xml",
"properties": [
{
"default_value": "hadoop",
"description": "ACL for AdminOperationsProtocol. Used for admin commands.\n The ACL is a comma-separated list of user and group names. The user and\n group list is separated by a blank. For e.g. \"alice,bob users,wheel\".\n A special value of \"*\" means all users are allowed.",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "security.admin.operations.protocol.acl"
},
{
"default_value": "*",
"description": "ACL for ClientDatanodeProtocol,the client-to-datanode protocol\n for block recovery.\n The ACL is a comma-separated list of user and group names. The user and\n group list is separated by a blank. For e.g. \"alice,bob users,wheel\".\n A special value of \"*\" means all users are allowed.",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "security.client.datanode.protocol.acl"
},
{
"default_value": "*",
"description": "ACL for ClientProtocol,which is used by user code\n via the DistributedFileSystem.\n The ACL is a comma-separated list of user and group names. The user and\n group list is separated by a blank. For e.g. \"alice,bob users,wheel\".\n A special value of \"*\" means all users are allowed.",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "security.client.protocol.acl"
},
{
"default_value": "*",
"description": "ACL for DatanodeProtocol,which is used by datanodes to\n communicate with the namenode.\n The ACL is a comma-separated list of user and group names. The user and\n group list is separated by a blank. For e.g. \"alice,bob users,wheel\".\n A special value of \"*\" means all users are allowed.",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "security.datanode.protocol.acl"
},
{
"default_value": "*",
"description": "ACL for InterDatanodeProtocol,the inter-datanode protocol\n for updating generation timestamp.\n The ACL is a comma-separated list of user and group names. The user and\n group list is separated by a blank. For e.g. \"alice,bob users,wheel\".\n A special value of \"*\" means all users are allowed.",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "security.inter.datanode.protocol.acl"
},
{
"default_value": "*",
"description": "ACL for InterTrackerProtocol,used by the tasktrackers to\n communicate with the jobtracker.\n The ACL is a comma-separated list of user and group names. The user and\n group list is separated by a blank. For e.g. \"alice,bob users,wheel\".\n A special value of \"*\" means all users are allowed.",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "security.inter.tracker.protocol.acl"
},
{
"default_value": "*",
"description": "ACL for JobSubmissionProtocol,used by job clients to\n communciate with the jobtracker for job submission,querying job status etc.\n The ACL is a comma-separated list of user and group names. The user and\n group list is separated by a blank. For e.g. \"alice,bob users,wheel\".\n A special value of \"*\" means all users are allowed.",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "security.job.client.protocol.acl"
},
{
"default_value": "*",
"description": "ACL for TaskUmbilicalProtocol,used by the map and reduce\n tasks to communicate with the parent tasktracker.\n The ACL is a comma-separated list of user and group names. The user and\n group list is separated by a blank. For e.g. \"alice,bob users,wheel\".\n A special value of \"*\" means all users are allowed.",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "security.job.task.protocol.acl"
},
{
"default_value": "*",
"description": "ACL for NamenodeProtocol,the protocol used by the secondary\n namenode to communicate with the namenode.\n The ACL is a comma-separated list of user and group names. The user and\n group list is separated by a blank. For e.g. \"alice,bob users,wheel\".\n A special value of \"*\" means all users are allowed.",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "security.namenode.protocol.acl"
},
{
"default_value": "hadoop",
"description": "ACL for RefreshAuthorizationPolicyProtocol,used by the\n dfsadmin and mradmin commands to refresh the security policy in-effect.\n The ACL is a comma-separated list of user and group names. The user and\n group list is separated by a blank. For e.g. \"alice,bob users,wheel\".\n A special value of \"*\" means all users are allowed.",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "security.refresh.policy.protocol.acl"
},
{
"default_value": "hadoop",
"description": "ACL for RefreshUserMappingsProtocol. Used to refresh\n users mappings. The ACL is a comma-separated list of user and\n group names. The user and group list is separated by a blank. For\n e.g. \"alice,bob users,wheel\". A special value of \"*\" means all\n users are allowed.",
"config_type": "string",
"applicable_target": "HDFS",
"is_optional": true,
"scope": "cluster",
"name": "security.refresh.usertogroups.mappings.protocol.acl"
}
]
},
{
"tag": "hive-site.xml",
"properties": [
{
"default_value": "hive",
"description": "Database name used as the Hive Metastore",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "ambari.hive.db.schema.name"
},
{
"default_value": "true",
"description": "...",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "fs.file.impl.disable.cache"
},
{
"default_value": "true",
"description": "...",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "fs.hdfs.impl.disable.cache"
},
{
"default_value": "true",
"description": "Whether Hive enable the optimization about converting common\n join into mapjoin based on the input file size.",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive.auto.convert.join"
},
{
"default_value": "true",
"description": "Whether Hive enable the optimization about converting common join into mapjoin based on the input file\n size. If this paramater is on,and the sum of size for n-1 of the tables/partitions for a n-way join is smaller than the\n specified size,the join is directly converted to a mapjoin (there is no conditional task).\n ",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive.auto.convert.join.noconditionaltask"
},
{
"default_value": "1000000000",
"description": "If hive.auto.convert.join.noconditionaltask is off,this parameter does not take affect. However,if it\n is on,and the sum of size for n-1 of the tables/partitions for a n-way join is smaller than this size,the join is directly\n converted to a mapjoin(there is no conditional task). The default is 10MB.\n ",
"config_type": "int",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive.auto.convert.join.noconditionaltask.size"
},
{
"default_value": "true",
"description": "Will the join be automatically converted to a sort-merge join,if the joined tables pass\n the criteria for sort-merge join.\n ",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive.auto.convert.sortmerge.join"
},
{
"default_value": "true",
"description": "...",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive.auto.convert.sortmerge.join.noconditionaltask"
},
{
"default_value": "true",
"description": "Whether bucketing is enforced. If true,while inserting into the table,bucketing is enforced.",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive.enforce.bucketing"
},
{
"default_value": "true",
"description": "Whether sorting is enforced. If true,while inserting into the table,sorting is enforced.",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive.enforce.sorting"
},
{
"default_value": "true",
"description": "Whether to use map-side aggregation in Hive Group By queries.",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive.map.aggr"
},
{
"default_value": "10000",
"description": "\n Size per reducer.The default is 1G,i.e if the input size is 10G,it\n will use 10 reducers.\n ",
"config_type": "int",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive.mapjoin.bucket.cache.size"
},
{
"default_value": "false",
"description": "Whether speculative execution for reducers should be turned on.",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive.mapred.reduce.tasks.speculative.execution"
},
{
"default_value": "Table,Database,Type,FieldSchema,Order",
"description": "List of comma separated metastore object types that should be pinned in the cache",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive.metastore.cache.pinobjtypes"
},
{
"default_value": "60",
"description": "MetaStore Client socket timeout in seconds",
"config_type": "int",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive.metastore.client.socket.timeout"
},
{
"default_value": "true",
"description": "In unsecure mode,setting this property to true will cause the metastore to execute DFS operations using the client's reported user and group permissions. Note that this property must be set on both the client and server sides. Further note that its best effort. If client sets its to true and server sets it to false,client setting will be ignored.",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive.metastore.execute.setugi"
},
{
"default_value": "thrift://localhost:9083",
"description": "URI for client to contact metastore server",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive.metastore.uris"
},
{
"default_value": "/apps/hive/warehouse",
"description": "location of default database for the warehouse",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive.metastore.warehouse.dir"
},
{
"default_value": "true",
"description": "...",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive.optimize.bucketmapjoin"
},
{
"default_value": "true",
"description": "...",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive.optimize.bucketmapjoin.sortedmerge"
},
{
"default_value": "true",
"description": "\n Whether to enable automatic use of indexes\n ",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive.optimize.index.filter"
},
{
"default_value": "true",
"description": "If hive.auto.convert.join is off,this parameter does not take\n affect. If it is on,and if there are map-join jobs followed by a map-reduce\n job (for e.g a group by),each map-only job is merged with the following\n map-reduce job.\n ",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive.optimize.mapjoin.mapreduce"
},
{
"default_value": "true",
"description": "...",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive.optimize.reducededuplication"
},
{
"default_value": "1",
"description": "Reduce deduplication merges two RSs by moving key/parts/reducer-num of the child RS to parent RS.\n That means if reducer-num of the child RS is fixed (order by or forced bucketing) and small,it can make very slow,single MR.\n The optimization will be disabled if number of reducers is less than specified value.\n ",
"config_type": "int",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive.optimize.reducededuplication.min.reducer"
},
{
"default_value": "org.apache.hadoop.hive.ql.security.ProxyUserAuthenticator",
"description": "Hive client authenticator manager class name. The user-defined authenticator class should implement interface org.apache.hadoop.hive.ql.security.HiveAuthenticationProvider. ",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive.security.authenticator.manager"
},
{
"default_value": "false",
"description": "enable or disable the hive client authorization",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive.security.authorization.enabled"
},
{
"default_value": "org.apache.hadoop.hive.ql.security.authorization.StorageBasedAuthorizationProvider",
"description": "the hive client authorization manager class name.\n The user defined authorization class should implement interface org.apache.hadoop.hive.ql.security.authorization.HiveAuthorizationProvider. ",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive.security.authorization.manager"
},
{
"default_value": "org.apache.hadoop.hive.ql.security.authorization.StorageBasedAuthorizationProvider",
"description": "The authorization manager class name to be used in the metastore for authorization. The user-defined authorization class should implement interface org.apache.hadoop.hive.ql.security.authorization.HiveMetastoreAuthorizationProvider. ",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive.security.metastore.authorization.manager"
},
{
"default_value": "org.apache.hivealog.cli.HCatSemanticAnalyzerFactory",
"description": "controls which SemanticAnalyzerFactory implemenation class is used by CLI",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive.semantic.analyzer.factory.impl"
},
{
"default_value": "true",
"description": "...",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive.server2.enable.doAs"
},
{
"default_value": "false",
"description": "...",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "hive.vectorized.execution.enabled"
},
{
"default_value": "com.mysql.jdbc.Driver",
"description": "Driver class name for a JDBC metastore",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "javax.jdo.option.ConnectionDriverName"
},
{
"default_value": " ",
"description": "password to use against metastore database",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "javax.jdo.option.ConnectionPassword"
},
{
"default_value": "jdbc",
"description": "JDBC connect string for a JDBC metastore",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "javax.jdo.option.ConnectionURL"
},
{
"default_value": "hive",
"description": "username to use against metastore database",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "javax.jdo.option.ConnectionUserName"
}
]
},
{
"tag": "mapred-queue-acls.xml",
"properties": [
{
"default_value": "*",
"description": "...",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapred.queue.default.acl-administer-jobs"
},
{
"default_value": "*",
"description": "...",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapred.queue.default.acl-submit-job"
}
]
},
{
"tag": "mapred-site.xml",
"properties": [
{
"default_value": "-Djava.net.preferIPv4Stack=true -Dhadoop.metrics.log.level=WARN",
"description": "...",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.admin.map.child.java.opts"
},
{
"default_value": "-Djava.net.preferIPv4Stack=true -Dhadoop.metrics.log.level=WARN",
"description": "...",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.admin.reduce.child.java.opts"
},
{
"default_value": "LD_LIBRARY_PATH=/usr/lib/hadoop/lib/native:/usr/lib/hadoop/lib/native/`$JAVA_HOME/bin/java -d32 -version &> /dev/null;if [ $? -eq 0 ]; then echo Linux-i386-32; else echo Linux-amd64-64;fi`",
"description": "\n Additional execution environment entries for map and reduce task processes.\n This is not an additive property. You must preserve the original value if\n you want your map and reduce tasks to have access to native libraries (compression,etc)\n ",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.admin.user.env"
},
{
"default_value": "2",
"description": "\n The maximum number of application attempts. It is a\n application-specific setting. It should not be larger than the global number\n set by resourcemanager. Otherwise,it will be override. The default number is\n set to 2,to allow at least one retry for AM.\n ",
"config_type": "int",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.am.max-attempts"
},
{
"default_value": "$HADOOP_MAPRED_HOME/share/hadoop/mapreduce/*,$HADOOP_MAPRED_HOME/share/hadoop/mapreduce/lib/*",
"description": "\n CLASSPATH for MR applications. A comma-separated list of CLASSPATH\n entries.\n ",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.application.classpath"
},
{
"default_value": " hadoop",
"description": "\n Administrators for MapReduce applications.\n ",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.cluster.administrators"
},
{
"default_value": "yarn",
"description": "\n The runtime framework for executing MapReduce jobs. Can be one of local,\n classic or yarn.\n ",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.framework.name"
},
{
"default_value": "0.05",
"description": "\n Fraction of the number of maps in the job which should be complete before\n reduces are scheduled for the job.\n ",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.job.reduce.slowstart.completedmaps"
},
{
"default_value": "localhost:10020",
"description": "Enter your JobHistoryServer hostname.",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.jobhistory.address"
},
{
"default_value": "/mr-history/done",
"description": "\n Directory where history files are managed by the MR JobHistory Server.\n ",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.jobhistory.done-dir"
},
{
"default_value": "/mr-history/tmp",
"description": "\n Directory where history files are written by MapReduce jobs.\n ",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.jobhistory.intermediate-done-dir"
},
{
"default_value": "localhost:19888",
"description": "Enter your JobHistoryServer hostname.",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.jobhistory.webapp.address"
},
{
"default_value": "-Xmx756m",
"description": "\n Larger heap-size for child jvms of maps.\n ",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.map.java.opts"
},
{
"default_value": "INFO",
"description": "\n The logging level for the map task. The allowed levels are:\n OFF,FATAL,ERROR,WARN,INFO,DEBUG,TRACE and ALL.\n ",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.map.log.level"
},
{
"default_value": "1024",
"description": "Virtual memory for single Map task",
"config_type": "int",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.map.memory.mb"
},
{
"default_value": "false",
"description": "...",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.map.output.compress"
},
{
"default_value": "0.7",
"description": "\n The soft limit in the serialization buffer. Once reached,a thread will\n begin to spill the contents to disk in the background. Note that\n collection will not block if this threshold is exceeded while a spill\n is already in progress,so spills may be larger than this threshold when\n it is set to less than .5\n ",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.map.sort.spill.percent"
},
{
"default_value": "false",
"description": "\n If true,then multiple instances of some map tasks\n may be executed in parallel.\n ",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.map.speculative"
},
{
"default_value": "false",
"description": "\n Should the job outputs be compressed?\n ",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.output.fileoutputformat.compress"
},
{
"default_value": "BLOCK",
"description": "\n If the job outputs are to compressed as SequenceFiles,how should\n they be compressed? Should be one of NONE,RECORD or BLOCK.\n ",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.output.fileoutputformat.compress.type"
},
{
"default_value": "0.0",
"description": "\n The percentage of memory- relative to the maximum heap size- to\n retain map outputs during the reduce. When the shuffle is concluded,any\n remaining map outputs in memory must consume less than this threshold before\n the reduce can begin.\n ",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.reduce.input.buffer.percent"
},
{
"default_value": "-Xmx756m",
"description": "\n Larger heap-size for child jvms of reduces.\n ",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.reduce.java.opts"
},
{
"default_value": "INFO",
"description": "\n The logging level for the reduce task. The allowed levels are:\n OFF,FATAL,ERROR,WARN,INFO,DEBUG,TRACE and ALL.\n ",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.reduce.log.level"
},
{
"default_value": "1024",
"description": "Virtual memory for single Reduce task",
"config_type": "int",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.reduce.memory.mb"
},
{
"default_value": "0.7",
"description": "\n The percentage of memory to be allocated from the maximum heap\n size to storing map outputs during the shuffle.\n ",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.reduce.shuffle.input.buffer.percent"
},
{
"default_value": "0.66",
"description": "\n The usage threshold at which an in-memory merge will be\n initiated,expressed as a percentage of the total memory allocated to\n storing in-memory map outputs,as defined by\n mapreduce.reduce.shuffle.input.buffer.percent.\n ",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.reduce.shuffle.merge.percent"
},
{
"default_value": "30",
"description": "\n The default number of parallel transfers run by reduce during\n the copy(shuffle) phase.\n ",
"config_type": "int",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.reduce.shuffle.parallelcopies"
},
{
"default_value": "false",
"description": "\n If true,then multiple instances of some reduce tasks may be\n executed in parallel.\n ",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.reduce.speculative"
},
{
"default_value": "13562",
"description": "\n Default port that the ShuffleHandler will run on.\n ShuffleHandler is a service run at the NodeManager to facilitate\n transfers of intermediate Map outputs to requesting Reducers.\n ",
"config_type": "int",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.shuffle.port"
},
{
"default_value": "100",
"description": "\n The number of streams to merge at once while sorting files.\n This determines the number of open file handles.\n ",
"config_type": "int",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.task.io.sort.factor"
},
{
"default_value": "200",
"description": "\n The total amount of buffer memory to use while sorting files,in megabytes.\n By default,gives each merge stream 1MB,which should minimize seeks.\n ",
"config_type": "int",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.task.io.sort.mb"
},
{
"default_value": "300000",
"description": "\n The number of milliseconds before a task will be\n terminated if it neither reads an input,writes an output,nor\n updates its status string.\n ",
"config_type": "int",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "mapreduce.task.timeout"
},
{
"default_value": "-Djava.net.preferIPv4Stack=true -Dhadoop.metrics.log.level=WARN",
"description": "\n Java opts for the MR App Master processes for admin purposes.\n It will appears before the opts set by yarn.app.mapreduce.am.command-opts and\n thus its options can be overridden user.\n\n Usage of -Djava.library.path can cause programs to no longer function if\n hadoop native libraries are used. These values should instead be set as part\n of LD_LIBRARY_PATH in the map / reduce JVM env using the mapreduce.map.env and\n mapreduce.reduce.env config settings.\n ",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "yarn.app.mapreduce.am.admin-command-opts"
},
{
"default_value": "-Xmx312m",
"description": "\n Java opts for the MR App Master processes.\n The following symbol,if present,will be interpolated: @taskid@ is replaced\n by current TaskID. Any other occurrences of '@' will go unchanged.\n For example,to enable verbose gc logging to a file named for the taskid in\n /tmp and to set the heap maximum to be a gigabyte,pass a 'value' of:\n -Xmx1024m -verbose:gc -Xloggc:/tmp/@taskid@.gc\n\n Usage of -Djava.library.path can cause programs to no longer function if\n hadoop native libraries are used. These values should instead be set as part\n of LD_LIBRARY_PATH in the map / reduce JVM env using the mapreduce.map.env and\n mapreduce.reduce.env config settings.\n ",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "yarn.app.mapreduce.am.command-opts"
},
{
"default_value": "INFO",
"description": "MR App Master process log level.",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "yarn.app.mapreduce.am.log.level"
},
{
"default_value": "512",
"description": "The amount of memory the MR AppMaster needs.",
"config_type": "int",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "yarn.app.mapreduce.am.resource.mb"
},
{
"default_value": "/user",
"description": "\n The staging dir used while submitting jobs.\n ",
"config_type": "string",
"applicable_target": "MAPREDUCE2",
"is_optional": true,
"scope": "cluster",
"name": "yarn.app.mapreduce.am.staging-dir"
}
]
},
{
"tag": "oozie-site.xml",
"properties": [
{
"default_value": "\n RULE:[2:$1@$0]([jt]t@.*TODO-KERBEROS-DOMAIN)s/.*/TODO-MAPREDUSER/\n RULE:[2:$1@$0]([nd]n@.*TODO-KERBEROS-DOMAIN)s/.*/TODO-HDFSUSER/\n RULE:[2:$1@$0](hm@.*TODO-KERBEROS-DOMAIN)s/.*/TODO-HBASE-USER/\n RULE:[2:$1@$0](rs@.*TODO-KERBEROS-DOMAIN)s/.*/TODO-HBASE-USER/\n DEFAULT\n ",
"description": "The mapping from kerberos principal names to local OS user names.",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie.authentication.kerberos.name.rules"
},
{
"default_value": "simple",
"description": "\n ",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie.authentication.type"
},
{
"default_value": "http://localhost:11000/oozie",
"description": "Base Oozie URL.",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie.base.url"
},
{
"default_value": "hcat=org.apache.oozie.action.hadoop.HCatCredentials",
"description": "\n Credential Class to be used for HCat.\n ",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie.credentials.credentialclasses"
},
{
"default_value": "oozie",
"description": "\n Oozie DataBase Name\n ",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie.db.schema.name"
},
{
"default_value": "\n org.apache.oozie.action.email.EmailActionExecutor,\n org.apache.oozie.action.hadoop.HiveActionExecutor,\n org.apache.oozie.action.hadoop.ShellActionExecutor,\n org.apache.oozie.action.hadoop.SqoopActionExecutor,\n org.apache.oozie.action.hadoop.DistcpActionExecutor\n ",
"description": "...",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie.service.ActionService.executor.ext.classes"
},
{
"default_value": "true",
"description": "\n Specifies whether security (user name/admin role) is enabled or not.\n If disabled any user can manage Oozie system and manage any job.\n ",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie.service.AuthorizationService.security.enabled"
},
{
"default_value": "3",
"description": "\n Maximum concurrency for a given callable type.\n Each command is a callable type (submit,start,run,signal,job,jobs,suspend,resume,etc).\n Each action type is a callable type (Map-Reduce,Pig,SSH,FS,sub-workflow,etc).\n All commands that use action executors (action-start,action-end,action-kill and action-check) use\n the action type as the callable type.\n ",
"config_type": "int",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie.service.CallableQueueService.callable.concurrency"
},
{
"default_value": "1000",
"description": "Max callable queue size",
"config_type": "int",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie.service.CallableQueueService.queue.size"
},
{
"default_value": "10",
"description": "Number of threads used for executing callables",
"config_type": "int",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie.service.CallableQueueService.threads"
},
{
"default_value": "*=/etc/hadoop/conf",
"description": "\n Comma separated AUTHORITY=HADOOP_CONF_DIR,where AUTHORITY is the HOST:PORT of\n the Hadoop service (JobTracker,HDFS). The wildcard '*' configuration is\n used when there is no exact match for an authority. The HADOOP_CONF_DIR contains\n the relevant Hadoop *-site.xml files. If the path is relative is looked within\n the Oozie configuration directory; though the path can be absolute (i.e. to point\n to Hadoop client conf/ directories in the local filesystem.\n ",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie.service.HadoopAccessorService.hadoop.configurations"
},
{
"default_value": " ",
"description": "\n Whitelisted job tracker for Oozie service.\n ",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie.service.HadoopAccessorService.jobTracker.whitelist"
},
{
"default_value": " ",
"description": "\n ",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie.service.HadoopAccessorService.nameNode.whitelist"
},
{
"default_value": "false",
"description": "\n Creates Oozie DB.\n\n If set to true,it creates the DB schema if it does not exist. If the DB schema exists is a NOP.\n If set to false,it does not create the DB schema. If the DB schema does not exist it fails start up.\n ",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie.service.JPAService.create.db.schema"
},
{
"default_value": "org.apache.derby.jdbc.EmbeddedDriver",
"description": "\n JDBC driver class.\n ",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie.service.JPAService.jdbc.driver"
},
{
"default_value": " ",
"description": "\n DB user password.\n\n IMPORTANT: if password is emtpy leave a 1 space string,the service trims the value,\n if empty Configuration assumes it is NULL.\n ",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie.service.JPAService.jdbc.password"
},
{
"default_value": "jdbc:derby:${oozie.data.dir}/${oozie.db.schema.name}-db;create=true",
"description": "\n JDBC URL.\n ",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie.service.JPAService.jdbc.url"
},
{
"default_value": "oozie",
"description": "\n Database user name to use to connect to the database\n ",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie.service.JPAService.jdbc.username"
},
{
"default_value": "10",
"description": "\n Max number of connections.\n ",
"config_type": "int",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie.service.JPAService.pool.max.active.conn"
},
{
"default_value": "30",
"description": "\n Jobs older than this value,in days,will be purged by the PurgeService.\n ",
"config_type": "int",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie.service.PurgeService.older.than"
},
{
"default_value": "3600",
"description": "\n Interval at which the purge service will run,in seconds.\n ",
"config_type": "int",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie.service.PurgeService.purge.interval"
},
{
"default_value": "shell-action-0.1.xsd,email-action-0.1.xsd,hive-action-0.2.xsd,sqoop-action-0.2.xsd,ssh-action-0.1.xsd,distcp-action-0.1.xsd,shell-action-0.2.xsd,oozie-sla-0.1.xsd,oozie-sla-0.2.xsd",
"description": "...",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie.service.SchemaService.wf.ext.schemas"
},
{
"default_value": "org.apache.oozie.dependency.FSURIHandler,org.apache.oozie.dependency.HCatURIHandler",
"description": "\n Enlist the different uri handlers supported for data availability checks.\n ",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie.service.URIHandlerService.uri.handlers"
},
{
"default_value": "/user/${user.name}/share/lib",
"description": "\n System library path to use for workflow applications.\n This path is added to workflow application if their job properties sets\n the property 'oozie.use.system.libpath' to true.\n ",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie.service.WorkflowAppService.system.libpath"
},
{
"default_value": "120",
"description": "Default timeout for a coordinator action input check (in minutes) for normal job.\n -1 means infinite timeout",
"config_type": "int",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie.service.coord.normal.default.timeout"
},
{
"default_value": "30000",
"description": "\n Command re-queue interval for push dependencies (in millisecond).\n ",
"config_type": "int",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie.service.coord.push.check.requeue.interval"
},
{
"default_value": "\n org.apache.oozie.service.SchedulerService,\n org.apache.oozie.service.InstrumentationService,\n org.apache.oozie.service.CallableQueueService,\n org.apache.oozie.service.UUIDService,\n org.apache.oozie.service.ELService,\n org.apache.oozie.service.AuthorizationService,\n org.apache.oozie.service.UserGroupInformationService,\n org.apache.oozie.service.HadoopAccessorService,\n org.apache.oozie.service.URIHandlerService,\n org.apache.oozie.service.MemoryLocksService,\n org.apache.oozie.service.DagXLogInfoService,\n org.apache.oozie.service.SchemaService,\n org.apache.oozie.service.LiteWorkflowAppService,\n org.apache.oozie.service.JPAService,\n org.apache.oozie.service.StoreService,\n org.apache.oozie.service.CoordinatorStoreService,\n org.apache.oozie.service.SLAStoreService,\n org.apache.oozie.service.DBLiteWorkflowStoreService,\n org.apache.oozie.service.CallbackService,\n org.apache.oozie.service.ActionService,\n org.apache.oozie.service.ActionCheckerService,\n org.apache.oozie.service.RecoveryService,\n org.apache.oozie.service.PurgeService,\n org.apache.oozie.service.CoordinatorEngineService,\n org.apache.oozie.service.BundleEngineService,\n org.apache.oozie.service.DagEngineService,\n org.apache.oozie.service.CoordMaterializeTriggerService,\n org.apache.oozie.service.StatusTransitService,\n org.apache.oozie.service.PauseTransitService,\n org.apache.oozie.service.GroupsService,\n org.apache.oozie.service.ProxyUserService\n ",
"description": "List of Oozie services",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie.services"
},
{
"default_value": "org.apache.oozie.service.PartitionDependencyManagerService,org.apache.oozie.service.HCatAccessorService",
"description": "\n To add/replace services defined in 'oozie.services' with custom implementations.\n Class names must be separated by commas.\n ",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie.services.ext"
},
{
"default_value": "oozie-${user.name}",
"description": "\n The Oozie system ID.\n ",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie.system.id"
},
{
"default_value": "NORMAL",
"description": "\n System mode for Oozie at startup.\n ",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "oozie.systemmode"
},
{
"default_value": "false",
"description": "\n If set to true,submissions of MapReduce and Pig jobs will include\n automatically the system library path,thus not requiring users to\n specify where the Pig JAR files are. Instead,the ones from the system\n library path are used.\n ",
"config_type": "string",
"applicable_target": "OOZIE",
"is_optional": true,
"scope": "cluster",
"name": "use.system.libpath.for.mapreduce.and.pig.jobs"
}
]
},
{
"tag": "webhcat-site.xml",
"properties": [
{
"default_value": "60000",
"description": "Time out for templeton api",
"config_type": "int",
"applicable_target": "WEBHCAT",
"is_optional": true,
"scope": "cluster",
"name": "templeton.exec.timeout"
},
{
"default_value": "/usr/bin/hadoop",
"description": "The path to the Hadoop executable.",
"config_type": "string",
"applicable_target": "WEBHCAT",
"is_optional": true,
"scope": "cluster",
"name": "templeton.hadoop"
},
{
"default_value": "/etc/hadoop/conf",
"description": "The path to the Hadoop configuration.",
"config_type": "string",
"applicable_target": "WEBHCAT",
"is_optional": true,
"scope": "cluster",
"name": "templeton.hadoop.conf.dir"
},
{
"default_value": "/usr/bin/hcat",
"description": "The path to the hcatalog executable.",
"config_type": "string",
"applicable_target": "WEBHCAT",
"is_optional": true,
"scope": "cluster",
"name": "templeton.hcat"
},
{
"default_value": "hdfs:///apps/webhcat/hive.tar.gz",
"description": "The path to the Hive archive.",
"config_type": "string",
"applicable_target": "WEBHCAT",
"is_optional": true,
"scope": "cluster",
"name": "templeton.hive.archive"
},
{
"default_value": "hive.tar.gz/hive/bin/hive",
"description": "The path to the Hive executable.",
"config_type": "string",
"applicable_target": "WEBHCAT",
"is_optional": true,
"scope": "cluster",
"name": "templeton.hive.path"
},
{
"default_value": "/usr/lib/hcatalog/share/webhcat/svr/webhcat.jar",
"description": "The path to the Templeton jar file.",
"config_type": "string",
"applicable_target": "WEBHCAT",
"is_optional": true,
"scope": "cluster",
"name": "templeton.jar"
},
{
"default_value": "/usr/lib/zookeeper/zookeeper.jar",
"description": "Jars to add the the classpath.",
"config_type": "string",
"applicable_target": "WEBHCAT",
"is_optional": true,
"scope": "cluster",
"name": "templeton.libjars"
},
{
"default_value": "false",
"description": "\n Enable the override path in templeton.override.jars\n ",
"config_type": "string",
"applicable_target": "WEBHCAT",
"is_optional": true,
"scope": "cluster",
"name": "templeton.override.enabled"
},
{
"default_value": "hdfs:///apps/webhcat/pig.tar.gz",
"description": "The path to the Pig archive.",
"config_type": "string",
"applicable_target": "WEBHCAT",
"is_optional": true,
"scope": "cluster",
"name": "templeton.pig.archive"
},
{
"default_value": "pig.tar.gz/pig/bin/pig",
"description": "The path to the Pig executable.",
"config_type": "string",
"applicable_target": "WEBHCAT",
"is_optional": true,
"scope": "cluster",
"name": "templeton.pig.path"
},
{
"default_value": "50111",
"description": "The HTTP port for the main server.",
"config_type": "int",
"applicable_target": "WEBHCAT",
"is_optional": true,
"scope": "cluster",
"name": "templeton.port"
},
{
"default_value": "org.apache.hive.hcatalog.templeton.tool.ZooKeeperStorage",
"description": "The class to use as storage",
"config_type": "string",
"applicable_target": "WEBHCAT",
"is_optional": true,
"scope": "cluster",
"name": "templeton.storage.class"
},
{
"default_value": "hdfs:///apps/webhcat/hadoop-streaming.jar",
"description": "The hdfs path to the Hadoop streaming jar file.",
"config_type": "string",
"applicable_target": "WEBHCAT",
"is_optional": true,
"scope": "cluster",
"name": "templeton.streaming.jar"
},
{
"default_value": "localhost:2181",
"description": "ZooKeeper servers,as comma separated host:port pairs",
"config_type": "string",
"applicable_target": "WEBHCAT",
"is_optional": true,
"scope": "cluster",
"name": "templeton.zookeeper.hosts"
},
{
"default_value": "hive.metastore.local=false,hive.metastore.uris=thrift:///%HIVE_METASTORE_HOST%:9083,hive.metastore.sasl.enabled=yes,hive.metastore.execute.setugi=true,hive.metastore.warehouse.dir=/apps/hive/warehouse",
"description": "...",
"config_type": "string",
"applicable_target": "HIVE",
"is_optional": true,
"scope": "cluster",
"name": "templeton.hive.properties"
}
]
},
{
"tag": "yarn-site.xml",
"properties": [
{
"default_value": "true",
"description": "...",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.acl.enable"
},
{
"default_value": "*",
"description": "...",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.admin.acl"
},
{
"default_value": "/etc/hadoop/conf,/usr/lib/hadoop/*,/usr/lib/hadoop/lib/*,/usr/lib/hadoop-hdfs/*,/usr/lib/hadoop-hdfs/lib/*,/usr/lib/hadoop-yarn/*,/usr/lib/hadoop-yarn/lib/*,/usr/lib/hadoop-mapreduce/*,/usr/lib/hadoop-mapreduce/lib/*",
"description": "Classpath for typical applications.",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.application.classpath"
},
{
"default_value": "true",
"description": "Whether to enable log aggregation",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.log-aggregation-enable"
},
{
"default_value": "2592000",
"description": "\n How long to keep aggregation logs before deleting them. -1 disables.\n Be careful set this too small and you will spam the name node.\n ",
"config_type": "int",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.log-aggregation.retain-seconds"
},
{
"default_value": "0.0.0.0:45454",
"description": "The address of the container manager in the NM.",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.nodemanager.address"
},
{
"default_value": "MALLOC_ARENA_MAX=$MALLOC_ARENA_MAX",
"description": "\n Environment variables that should be forwarded from the NodeManager's\n environment to the container's.\n ",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.nodemanager.admin-env"
},
{
"default_value": "mapreduce_shuffle",
"description": "Auxilliary services of NodeManager. A valid service name should only contain a-zA-Z0-9_ and can\n not start with numbers",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.nodemanager.aux-services"
},
{
"default_value": "org.apache.hadoop.mapred.ShuffleHandler",
"description": "...",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.nodemanager.aux-services.mapreduce_shuffle.class"
},
{
"default_value": "org.apache.hadoop.yarn.server.nodemanager.DefaultContainerExecutor",
"description": "ContainerExecutor for launching containers",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.nodemanager.container-executor.class"
},
{
"default_value": "3000",
"description": "\n The interval,in milliseconds,for which the node manager\n waits between two cycles of monitoring its containers' memory usage.\n ",
"config_type": "int",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.nodemanager.container-monitor.interval-ms"
},
{
"default_value": "0",
"description": "\n Number of seconds after an application finishes before the nodemanager's\n DeletionService will delete the application's localized file directory\n and log directory.\n\n To diagnose Yarn application problems,set this property's value large\n enough (for example,to 600 = 10 minutes) to permit examination of these\n directories. After changing the property's value,you must restart the\n nodemanager in order for it to have an effect.\n\n The roots of Yarn applications' work directories is configurable with\n the yarn.nodemanager.local-dirs property (see below),and the roots\n of the Yarn applications' log directories is configurable with the\n yarn.nodemanager.log-dirs property (see also below).\n ",
"config_type": "int",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.nodemanager.delete.debug-delay-sec"
},
{
"default_value": "0.25",
"description": "\n The minimum fraction of number of disks to be healthy for the nodemanager\n to launch new containers. This correspond to both\n yarn-nodemanager.local-dirs and yarn.nodemanager.log-dirs. i.e.\n If there are less number of healthy local-dirs (or log-dirs) available,\n then new containers will not be launched on this node.\n ",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.nodemanager.disk-health-checker.min-healthy-disks"
},
{
"default_value": "135000",
"description": "Frequency of running node health script.",
"config_type": "int",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.nodemanager.health-checker.interval-ms"
},
{
"default_value": "60000",
"description": "Script time out period.",
"config_type": "int",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.nodemanager.health-checker.script.timeout-ms"
},
{
"default_value": "hadoop",
"description": "Unix group of the NodeManager",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.nodemanager.linux-container-executor.group"
},
{
"default_value": "/hadoop/yarn/local",
"description": "\n List of directories to store localized files in. An\n application's localized file directory will be found in:\n ${yarn.nodemanager.local-dirs}/usercache/${user}/appcache/application_${appid}.\n Individual containers' work directories,called container_${contid},will\n be subdirectories of this.\n ",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.nodemanager.local-dirs"
},
{
"default_value": "gz",
"description": "\n T-file compression types used to compress aggregated logs.\n ",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.nodemanager.log-aggregation.compression-type"
},
{
"default_value": "/hadoop/yarn/log",
"description": "\n Where to store container logs. An application's localized log directory\n will be found in ${yarn.nodemanager.log-dirs}/application_${appid}.\n Individual containers' log directories will be below this,in directories\n named container_{$contid}. Each container directory will contain the files\n stderr,stdin,and syslog generated by that container.\n ",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.nodemanager.log-dirs"
},
{
"default_value": "604800",
"description": "\n Time in seconds to retain user logs. Only applicable if\n log aggregation is disabled.\n ",
"config_type": "int",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.nodemanager.log.retain-second"
},
{
"default_value": "/app-logs",
"description": "...",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.nodemanager.remote-app-log-dir"
},
{
"default_value": "logs",
"description": "\n The remote log dir will be created at\n {yarn.nodemanager.remote-app-log-dir}/${user}/{thisParam}.\n ",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.nodemanager.remote-app-log-dir-suffix"
},
{
"default_value": "5120",
"description": "Amount of physical memory,in MB,that can be allocated\n for containers.",
"config_type": "int",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.nodemanager.resource.memory-mb"
},
{
"default_value": "false",
"description": "\n Whether virtual memory limits will be enforced for containers.\n ",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.nodemanager.vmem-check-enabled"
},
{
"default_value": "2.1",
"description": "Ratio between virtual memory to physical memory when\n setting memory limits for containers. Container allocations are\n expressed in terms of physical memory,and virtual memory usage\n is allowed to exceed this allocation by this ratio.\n ",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.nodemanager.vmem-pmem-ratio"
},
{
"default_value": "localhost:8050",
"description": "\n The address of the applications manager interface in the\n RM.\n ",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.resourcemanager.address"
},
{
"default_value": "localhost:8141",
"description": "The address of the RM admin interface.",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.resourcemanager.admin.address"
},
{
"default_value": "2",
"description": "\n The maximum number of application attempts. It's a global\n setting for all application masters. Each application master can specify\n its individual maximum number of application attempts via the API,but the\n individual number cannot be more than the global upper bound. If it is,\n the resourcemanager will override it. The default number is set to 2,to\n allow at least one retry for AM.\n ",
"config_type": "int",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.resourcemanager.am.max-attempts"
},
{
"default_value": "localhost:8025",
"description": "...",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.resourcemanager.resource-tracker.address"
},
{
"default_value": "localhost:8030",
"description": "The address of the scheduler interface.",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.resourcemanager.scheduler.address"
},
{
"default_value": "org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler",
"description": "The class to use as the resource scheduler.",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.resourcemanager.scheduler.class"
},
{
"default_value": "localhost:8088",
"description": "\n The address of the RM web application.\n ",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.resourcemanager.webapp.address"
},
{
"default_value": "2048",
"description": "\n The maximum allocation for every container request at the RM,\n in MBs. Memory requests higher than this won't take effect,\n and will get capped to this value.\n ",
"config_type": "int",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.scheduler.maximum-allocation-mb"
},
{
"default_value": "512",
"description": "\n TThe minimum allocation for every container request at the RM,\n in MBs. Memory requests lower than this won't take effect,\n and the specified value will get allocated at minimum.\n ",
"config_type": "int",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.scheduler.minimum-allocation-mb"
},
{
"default_value": "localhost",
"description": "...",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.resourcemanager.hostname"
},
{
"default_value": "http://master.novalocal:19888/jobhistory/logs",
"description": "...",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.log.server.url"
}
]
},
{
"tag": "capacity-scheduler.xml",
"properties": [
{
"default_value": "0.2",
"description": "\n Maximum percent of resources in the cluster which can be used to run \n application masters i.e. controls number of concurrent running\n applications.\n ",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.scheduler.capacity.maximum-am-resource-percent"
},
{
"default_value": "10000",
"description": "\n Maximum number of applications that can be pending and running.\n ",
"config_type": "int",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.scheduler.capacity.maximum-applications"
},
{
"default_value": "*",
"description": "\n The ACL for who can administer this queue i.e. change sub-queue \n allocations.\n ",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.scheduler.capacity.root.acl_administer_queues"
},
{
"default_value": "100",
"description": "\n The total capacity as a percentage out of 100 for this queue.\n If it has child queues then this includes their capacity as well.\n The child queues capacity should add up to their parent queue's capacity\n or less.\n ",
"config_type": "int",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.scheduler.capacity.root.capacity"
},
{
"default_value": "*",
"description": "\n The ACL of who can administer jobs on the default queue.\n ",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.scheduler.capacity.root.default.acl_administer_jobs"
},
{
"default_value": "*",
"description": "\n The ACL of who can submit jobs to the default queue.\n ",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.scheduler.capacity.root.default.acl_submit_jobs"
},
{
"default_value": "100",
"description": "Default queue target capacity.",
"config_type": "int",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.scheduler.capacity.root.default.capacity"
},
{
"default_value": "100",
"description": "\n The maximum capacity of the default queue. \n ",
"config_type": "int",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.scheduler.capacity.root.default.maximum-capacity"
},
{
"default_value": "RUNNING",
"description": "\n The state of the default queue. State can be one of RUNNING or STOPPED.\n ",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.scheduler.capacity.root.default.state"
},
{
"default_value": "1",
"description": "\n Default queue user limit a percentage from 0.0 to 1.0.\n ",
"config_type": "int",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.scheduler.capacity.root.default.user-limit-factor"
},
{
"default_value": "default",
"description": "\n The queues at the this level (root is the root queue).\n ",
"config_type": "string",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.scheduler.capacity.root.queues"
},
{
"default_value": "50",
"description": "\n No description\n ",
"config_type": "int",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.scheduler.capacity.root.unfunded.capacity"
},
{
"default_value": "40",
"description": "...",
"config_type": "int",
"applicable_target": "YARN",
"is_optional": true,
"scope": "cluster",
"name": "yarn.scheduler.capacity.node-locality-delay"
}
]
},
{
"tag": "ambari",
"properties": [
{
"applicable_target": "AMBARI",
"config_type": "string",
"default_value": "8080",
"description": "Ambari Server API port.",
"is_optional": true,
"name": "server.port",
"scope": "cluster"
}
]
},
{
"tag": "ambari-stack",
"properties": [
{
"applicable_target": "AMBARI",
"config_type": "string",
"default_value": "admin",
"description": "Ambari admin user name.",
"is_optional": true,
"name": "ambari.admin.user",
"scope": "cluster"
},
{
"applicable_target": "AMBARI",
"config_type": "string",
"default_value": "admin",
"description": "Ambari admin user password.",
"is_optional": true,
"name": "ambari.admin.password",
"scope": "cluster"
}
]
},
{
"tag": "hue-ini",
"properties": [
{
"applicable_target": "HUE",
"config_type": "int",
"default_value": "8000",
"description": "The HTTP port for the web-based user interface.",
"is_optional": true,
"name": "desktop/http_port",
"scope": "cluster"
},
{
"applicable_target": "HUE",
"config_type": "string",
"default_value": "admin",
"description": "The username of the initial administrative user.",
"is_optional": true,
"name": "useradmin/default_username",
"scope": "cluster"
},
{
"applicable_target": "HUE",
"config_type": "string",
"default_value": "admin",
"description": "The password for the initial administrative user.",
"is_optional": true,
"name": "useradmin/default_user_password",
"scope": "cluster"
},
{
"applicable_target": "HUE",
"config_type": "string",
"default_value": "hadoop",
"description": "The default group for hue users.",
"is_optional": true,
"name": "useradmin/default_user_group",
"scope": "cluster"
}
]
},
{
"tag": "hdfsha",
"properties": [
{
"applicable_target": "HDFSHA",
"config_type": "boolean",
"default_value": false,
"description": "Enable HDFS NameNode High Availability",
"is_optional": true,
"name": "hdfs.nnha",
"scope": "cluster"
}
]
}
]
}
View Git Blame Copy Permalink