You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@ambari.apache.org by rl...@apache.org on 2015/04/24 17:12:50 UTC
[2/2] ambari git commit: AMBARI-10562. Summary:Issues when log/pid
dirs are customized - Kafka and Knox (Emil Anca via rlevas)
AMBARI-10562. Summary:Issues when log/pid dirs are customized - Kafka and Knox (Emil Anca via rlevas)
Project: http://git-wip-us.apache.org/repos/asf/ambari/repo
Commit: http://git-wip-us.apache.org/repos/asf/ambari/commit/239d3ac7
Tree: http://git-wip-us.apache.org/repos/asf/ambari/tree/239d3ac7
Diff: http://git-wip-us.apache.org/repos/asf/ambari/diff/239d3ac7
Branch: refs/heads/trunk
Commit: 239d3ac7541ab3642c1031191e4bbafd5fd9a9e6
Parents: b971804
Author: Emil Anca <ea...@hortonworks.com>
Authored: Fri Apr 24 11:12:38 2015 -0400
Committer: Robert Levas <rl...@hortonworks.com>
Committed: Fri Apr 24 11:12:38 2015 -0400
----------------------------------------------------------------------
.../KAFKA/0.8.1.2.2/package/scripts/kafka.py | 75 +++-
.../KAFKA/0.8.1.2.2/package/scripts/params.py | 5 +-
.../0.5.0.2.2/package/scripts/knox_gateway.py | 5 +
.../KNOX/0.5.0.2.2/package/scripts/params.py | 2 +
.../stacks/2.2/KAFKA/test_kafka_broker.py | 43 +-
.../python/stacks/2.2/KNOX/test_knox_gateway.py | 96 +++++
.../2.2/configs/default_custom_path_config.json | 391 +++++++++++++++++++
7 files changed, 613 insertions(+), 4 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/ambari/blob/239d3ac7/ambari-server/src/main/resources/common-services/KAFKA/0.8.1.2.2/package/scripts/kafka.py
----------------------------------------------------------------------
diff --git a/ambari-server/src/main/resources/common-services/KAFKA/0.8.1.2.2/package/scripts/kafka.py b/ambari-server/src/main/resources/common-services/KAFKA/0.8.1.2.2/package/scripts/kafka.py
index 0170116..6668c4e 100644
--- a/ambari-server/src/main/resources/common-services/KAFKA/0.8.1.2.2/package/scripts/kafka.py
+++ b/ambari-server/src/main/resources/common-services/KAFKA/0.8.1.2.2/package/scripts/kafka.py
@@ -20,7 +20,7 @@ limitations under the License.
from resource_management import *
from properties_config import properties_config
-import sys
+import sys, os
from copy import deepcopy
def kafka():
@@ -71,9 +71,82 @@ def kafka():
content=params.log4j_props
)
+ setup_symlink(params.kafka_managed_pid_dir, params.kafka_pid_dir)
+ setup_symlink(params.kafka_managed_log_dir, params.kafka_log_dir)
+
def mutable_config_dict(kafka_broker_config):
kafka_server_config = {}
for key, value in kafka_broker_config.iteritems():
kafka_server_config[key] = value
return kafka_server_config
+
+# Used to workaround the hardcoded pid/log dir used on the kafka bash process launcher
+def setup_symlink(kafka_managed_dir, kafka_ambari_managed_dir):
+ import params
+ backup_folder_path = None
+ backup_folder_suffix = "_tmp"
+ if kafka_ambari_managed_dir != kafka_managed_dir:
+ if os.path.exists(kafka_managed_dir) and not os.path.islink(kafka_managed_dir):
+
+ # Backup existing data before delete if config is changed repeatedly to/from default location at any point in time time, as there may be relevant contents (historic logs)
+ backup_folder_path = backup_dir_contents(kafka_managed_dir, backup_folder_suffix)
+
+ Directory(kafka_managed_dir,
+ action="delete",
+ recursive=True)
+
+ elif os.path.islink(kafka_managed_dir) and os.path.realpath(kafka_managed_dir) != kafka_ambari_managed_dir:
+ Link(kafka_managed_dir,
+ action="delete")
+
+ if not os.path.islink(kafka_managed_dir):
+ Link(kafka_managed_dir,
+ to=kafka_ambari_managed_dir)
+
+ elif os.path.islink(kafka_managed_dir): # If config is changed and coincides with the kafka managed dir, remove the symlink and physically create the folder
+ Link(kafka_managed_dir,
+ action="delete")
+
+ Directory(kafka_managed_dir,
+ mode=0755,
+ cd_access='a',
+ owner=params.kafka_user,
+ group=params.user_group,
+ recursive=True
+ )
+
+ if backup_folder_path:
+ # Restore backed up files to current relevant dirs if needed - will be triggered only when changing to/from default path;
+ for file in os.listdir(backup_folder_path):
+ File(os.path.join(kafka_managed_dir,file),
+ owner=params.kafka_user,
+ content = StaticFile(os.path.join(backup_folder_path,file)))
+
+ # Clean up backed up folder
+ Directory(backup_folder_path,
+ action="delete",
+ recursive=True)
+
+
+# Uses agent temp dir to store backup files
+def backup_dir_contents(dir_path, backup_folder_suffix):
+ import params
+ backup_destination_path = params.tmp_dir + os.path.normpath(dir_path)+backup_folder_suffix
+ Directory(backup_destination_path,
+ mode=0755,
+ cd_access='a',
+ owner=params.kafka_user,
+ group=params.user_group,
+ recursive=True
+ )
+ # Safely copy top-level contents to backup folder
+ for file in os.listdir(dir_path):
+ File(os.path.join(backup_destination_path, file),
+ owner=params.kafka_user,
+ content = StaticFile(os.path.join(dir_path,file)))
+
+ return backup_destination_path
+
+
+
http://git-wip-us.apache.org/repos/asf/ambari/blob/239d3ac7/ambari-server/src/main/resources/common-services/KAFKA/0.8.1.2.2/package/scripts/params.py
----------------------------------------------------------------------
diff --git a/ambari-server/src/main/resources/common-services/KAFKA/0.8.1.2.2/package/scripts/params.py b/ambari-server/src/main/resources/common-services/KAFKA/0.8.1.2.2/package/scripts/params.py
index 74c189e..e9f8f56 100644
--- a/ambari-server/src/main/resources/common-services/KAFKA/0.8.1.2.2/package/scripts/params.py
+++ b/ambari-server/src/main/resources/common-services/KAFKA/0.8.1.2.2/package/scripts/params.py
@@ -26,7 +26,7 @@ import status_params
# server configurations
config = Script.get_config()
-
+tmp_dir = Script.get_tmp_dir()
stack_name = default("/hostLevelParams/stack_name", None)
version = default("/commandParams/version", None)
@@ -48,6 +48,9 @@ kafka_user = config['configurations']['kafka-env']['kafka_user']
kafka_log_dir = config['configurations']['kafka-env']['kafka_log_dir']
kafka_pid_dir = status_params.kafka_pid_dir
kafka_pid_file = kafka_pid_dir+"/kafka.pid"
+# This is hardcoded on the kafka bash process lifecycle on which we have no control over
+kafka_managed_pid_dir = "/var/run/kafka"
+kafka_managed_log_dir = "/var/log/kafka"
hostname = config['hostname']
user_group = config['configurations']['cluster-env']['user_group']
java64_home = config['hostLevelParams']['java_home']
http://git-wip-us.apache.org/repos/asf/ambari/blob/239d3ac7/ambari-server/src/main/resources/common-services/KNOX/0.5.0.2.2/package/scripts/knox_gateway.py
----------------------------------------------------------------------
diff --git a/ambari-server/src/main/resources/common-services/KNOX/0.5.0.2.2/package/scripts/knox_gateway.py b/ambari-server/src/main/resources/common-services/KNOX/0.5.0.2.2/package/scripts/knox_gateway.py
index 9e20499..27a302f 100644
--- a/ambari-server/src/main/resources/common-services/KNOX/0.5.0.2.2/package/scripts/knox_gateway.py
+++ b/ambari-server/src/main/resources/common-services/KNOX/0.5.0.2.2/package/scripts/knox_gateway.py
@@ -81,6 +81,11 @@ class KnoxGateway(Script):
daemon_cmd = format('{knox_bin} start')
no_op_test = format('ls {knox_pid_file} >/dev/null 2>&1 && ps -p `cat {knox_pid_file}` >/dev/null 2>&1')
setup_ranger_knox()
+ # Used to setup symlink, needed to update the knox managed symlink, in case of custom locations
+ if os.path.islink(params.knox_managed_pid_symlink) and os.path.realpath(params.knox_managed_pid_symlink) != params.knox_pid_dir:
+ os.unlink(params.knox_managed_pid_symlink)
+ os.symlink(params.knox_pid_dir, params.knox_managed_pid_symlink)
+
Execute(daemon_cmd,
user=params.knox_user,
environment={'JAVA_HOME': params.java_home},
http://git-wip-us.apache.org/repos/asf/ambari/blob/239d3ac7/ambari-server/src/main/resources/common-services/KNOX/0.5.0.2.2/package/scripts/params.py
----------------------------------------------------------------------
diff --git a/ambari-server/src/main/resources/common-services/KNOX/0.5.0.2.2/package/scripts/params.py b/ambari-server/src/main/resources/common-services/KNOX/0.5.0.2.2/package/scripts/params.py
index a04842e..344dae9 100644
--- a/ambari-server/src/main/resources/common-services/KNOX/0.5.0.2.2/package/scripts/params.py
+++ b/ambari-server/src/main/resources/common-services/KNOX/0.5.0.2.2/package/scripts/params.py
@@ -110,6 +110,8 @@ if has_oozie:
if 'oozie.base.url' in config['configurations']['oozie-site']:
oozie_server_port = get_port_from_url(config['configurations']['oozie-site']['oozie.base.url'])
+# Knox managed properties
+knox_managed_pid_symlink= "/usr/hdp/current/knox-server/pids"
# server configurations
knox_pid_dir = status_params.knox_pid_dir
http://git-wip-us.apache.org/repos/asf/ambari/blob/239d3ac7/ambari-server/src/test/python/stacks/2.2/KAFKA/test_kafka_broker.py
----------------------------------------------------------------------
diff --git a/ambari-server/src/test/python/stacks/2.2/KAFKA/test_kafka_broker.py b/ambari-server/src/test/python/stacks/2.2/KAFKA/test_kafka_broker.py
index 2b6f7e4..151335c 100644
--- a/ambari-server/src/test/python/stacks/2.2/KAFKA/test_kafka_broker.py
+++ b/ambari-server/src/test/python/stacks/2.2/KAFKA/test_kafka_broker.py
@@ -19,7 +19,7 @@ limitations under the License.
'''
import json
from stacks.utils.RMFTestCase import *
-
+from mock.mock import patch
class TestKafkaBroker(RMFTestCase):
COMMON_SERVICES_PACKAGE_DIR = "KAFKA/0.8.1.2.2/package"
@@ -58,6 +58,45 @@ class TestKafkaBroker(RMFTestCase):
cd_access = 'a'
)
+ @patch("os.path.islink")
+ @patch("os.path.realpath")
+ def test_configure_custom_paths_default(self, realpath_mock, islink_mock):
+
+ self.executeScript(self.COMMON_SERVICES_PACKAGE_DIR + "/scripts/kafka_broker.py",
+ classname = "KafkaBroker",
+ command = "configure",
+ config_file="default_custom_path_config.json",
+ hdp_stack_version = self.STACK_VERSION,
+ target = RMFTestCase.TARGET_COMMON_SERVICES
+ )
+
+ self.assertResourceCalled('Directory', '/customdisk/var/log/kafka',
+ owner = 'kafka',
+ group = 'hadoop',
+ recursive = True,
+ mode = 0755,
+ cd_access = 'a'
+ )
+
+ self.assertResourceCalled('Directory', '/customdisk/var/run/kafka',
+ owner = 'kafka',
+ group = 'hadoop',
+ recursive = True,
+ mode = 0755,
+ cd_access = 'a'
+ )
+
+ self.assertResourceCalled('Directory', '/etc/kafka/conf',
+ owner = 'kafka',
+ group = 'hadoop',
+ recursive = True,
+ mode = 0755,
+ cd_access = 'a'
+ )
+
+ self.assertTrue(islink_mock.called)
+ self.assertTrue(realpath_mock.called)
+
def test_pre_rolling_restart(self):
config_file = self.get_src_folder()+"/test/python/stacks/2.2/configs/default.json"
with open(config_file, "r") as f:
@@ -72,4 +111,4 @@ class TestKafkaBroker(RMFTestCase):
target = RMFTestCase.TARGET_COMMON_SERVICES)
self.assertResourceCalled('Execute',
'hdp-select set kafka-broker %s' % version,)
- self.assertNoMoreResources()
+ self.assertNoMoreResources()
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/ambari/blob/239d3ac7/ambari-server/src/test/python/stacks/2.2/KNOX/test_knox_gateway.py
----------------------------------------------------------------------
diff --git a/ambari-server/src/test/python/stacks/2.2/KNOX/test_knox_gateway.py b/ambari-server/src/test/python/stacks/2.2/KNOX/test_knox_gateway.py
index 37bb66b..82bee2a 100644
--- a/ambari-server/src/test/python/stacks/2.2/KNOX/test_knox_gateway.py
+++ b/ambari-server/src/test/python/stacks/2.2/KNOX/test_knox_gateway.py
@@ -230,3 +230,99 @@ class TestKnoxGateway(RMFTestCase):
self.assertTrue(tarfile_open_mock.called)
self.assertResourceCalled("Execute", "hdp-select set knox-server %s" % version)
+
+ @patch("os.path.islink")
+ @patch("os.path.realpath")
+ @patch("os.unlink")
+ @patch("os.symlink")
+ def test_start_default(self, symlink_mock, unlink_mock, realpath_mock, islink_mock):
+
+
+ self.executeScript(self.COMMON_SERVICES_PACKAGE_DIR + "/scripts/knox_gateway.py",
+ classname = "KnoxGateway",
+ command = "start",
+ config_file="default.json",
+ hdp_stack_version = self.STACK_VERSION,
+ target = RMFTestCase.TARGET_COMMON_SERVICES)
+
+
+ self.assertResourceCalled('Directory', '/var/lib/knox/data',
+ owner = 'knox',
+ group = 'knox',
+ recursive = True
+ )
+ self.assertResourceCalled('Directory', '/var/log/knox',
+ owner = 'knox',
+ group = 'knox',
+ recursive = True
+ )
+ self.assertResourceCalled('Directory', '/var/run/knox',
+ owner = 'knox',
+ group = 'knox',
+ recursive = True
+ )
+ self.assertResourceCalled('Directory', '/etc/knox/conf',
+ owner = 'knox',
+ group = 'knox',
+ recursive = True
+ )
+
+ self.assertResourceCalled('XmlConfig', 'gateway-site.xml',
+ owner = 'knox',
+ group = 'knox',
+ conf_dir = '/etc/knox/conf',
+ configurations = self.getConfig()['configurations']['gateway-site'],
+ configuration_attributes = self.getConfig()['configuration_attributes']['gateway-site']
+ )
+
+ self.assertResourceCalled('File', '/etc/knox/conf/gateway-log4j.properties',
+ mode=0644,
+ group='knox',
+ owner = 'knox',
+ content = self.getConfig()['configurations']['gateway-log4j']['content']
+ )
+ self.assertResourceCalled('File', '/etc/knox/conf/topologies/default.xml',
+ group='knox',
+ owner = 'knox',
+ content = InlineTemplate(self.getConfig()['configurations']['topology']['content'])
+ )
+ self.assertResourceCalled('Execute', ('chown',
+ '-R',
+ 'knox:knox',
+ '/var/lib/knox/data',
+ '/var/log/knox',
+ '/var/run/knox',
+ '/etc/knox/conf'),
+ sudo = True,
+ )
+ self.assertResourceCalled('Execute', '/usr/hdp/current/knox-server/bin/knoxcli.sh create-master --master sa',
+ environment = {'JAVA_HOME': u'/usr/jdk64/jdk1.7.0_45'},
+ not_if = "ambari-sudo.sh su knox -l -s /bin/bash -c '[RMF_EXPORT_PLACEHOLDER]test -f /var/lib/knox/data/security/master'",
+ user = 'knox',
+ )
+ self.assertResourceCalled('Execute', '/usr/hdp/current/knox-server/bin/knoxcli.sh create-cert --hostname c6401.ambari.apache.org',
+ environment = {'JAVA_HOME': u'/usr/jdk64/jdk1.7.0_45'},
+ not_if = "ambari-sudo.sh su knox -l -s /bin/bash -c '[RMF_EXPORT_PLACEHOLDER]test -f /var/lib/knox/data/security/keystores/gateway.jks'",
+ user = 'knox',
+ )
+ self.assertResourceCalled('File', '/etc/knox/conf/ldap-log4j.properties',
+ mode=0644,
+ group='knox',
+ owner = 'knox',
+ content = self.getConfig()['configurations']['ldap-log4j']['content']
+ )
+ self.assertResourceCalled('File', '/etc/knox/conf/users.ldif',
+ mode=0644,
+ group='knox',
+ owner = 'knox',
+ content = self.getConfig()['configurations']['users-ldif']['content']
+ )
+
+ self.assertResourceCalled("Execute", "/usr/hdp/current/knox-server/bin/gateway.sh start",
+ environment = {'JAVA_HOME': u'/usr/jdk64/jdk1.7.0_45'},
+ not_if = u'ls /var/run/knox/gateway.pid >/dev/null 2>&1 && ps -p `cat /var/run/knox/gateway.pid` >/dev/null 2>&1',
+ user = u'knox',)
+ self.assertTrue(islink_mock.called)
+ self.assertTrue(realpath_mock.called)
+ self.assertNoMoreResources()
+
http://git-wip-us.apache.org/repos/asf/ambari/blob/239d3ac7/ambari-server/src/test/python/stacks/2.2/configs/default_custom_path_config.json
----------------------------------------------------------------------
diff --git a/ambari-server/src/test/python/stacks/2.2/configs/default_custom_path_config.json b/ambari-server/src/test/python/stacks/2.2/configs/default_custom_path_config.json
new file mode 100644
index 0000000..2c9c918
--- /dev/null
+++ b/ambari-server/src/test/python/stacks/2.2/configs/default_custom_path_config.json
@@ -0,0 +1,391 @@
+{
+ "roleCommand": "SERVICE_CHECK",
+ "clusterName": "c1",
+ "hostname": "c6401.ambari.apache.org",
+ "hostLevelParams": {
+ "jdk_location": "http://c6401.ambari.apache.org:8080/resources/",
+ "ambari_db_rca_password": "mapred",
+ "ambari_db_rca_url": "jdbc:postgresql://c6401.ambari.apache.org/ambarirca",
+ "jce_name": "UnlimitedJCEPolicyJDK7.zip",
+ "stack_version": "2.2",
+ "stack_name": "HDP",
+ "ambari_db_rca_driver": "org.postgresql.Driver",
+ "jdk_name": "jdk-7u67-linux-x64.tar.gz",
+ "ambari_db_rca_username": "mapred",
+ "java_home": "/usr/jdk64/jdk1.7.0_45",
+ "java_version": "8",
+ "db_name": "ambari"
+ },
+ "commandType": "EXECUTION_COMMAND",
+ "roleParams": {},
+ "serviceName": "SLIDER",
+ "role": "SLIDER",
+ "commandParams": {
+ "version": "2.2.1.0-2067",
+ "command_timeout": "300",
+ "service_package_folder": "OOZIE",
+ "script_type": "PYTHON",
+ "script": "scripts/service_check.py",
+ "excluded_hosts": "host1,host2"
+ },
+ "taskId": 152,
+ "public_hostname": "c6401.ambari.apache.org",
+ "configurations": {
+ "admin-properties": {
+ "authentication_method": "UNIX",
+ "db_root_user": "root",
+ "xa_ldap_groupSearchBase": "\"ou=groups,dc=xasecure,dc=net\"",
+ "audit_db_name": "ranger_audit",
+ "xa_ldap_ad_domain": "\"xasecure.net\"",
+ "remoteLoginEnabled": "true",
+ "SQL_CONNECTOR_JAR": "/usr/share/java/mysql-connector-java.jar",
+ "xa_ldap_userDNpattern": "\"uid={0},ou=users,dc=xasecure,dc=net\"",
+ "SQL_COMMAND_INVOKER": "mysql",
+ "db_user": "rangeradmin",
+ "db_password": "aa",
+ "authServicePort": "5151",
+ "audit_db_password": "aa",
+ "DB_FLAVOR": "MYSQL",
+ "audit_db_user": "rangerlogger",
+ "db_root_password": "aa",
+ "xa_ldap_url": "\"ldap://71.127.43.33:389\"",
+ "db_name": "ranger",
+ "xa_ldap_groupSearchFilter": "\"(member=uid={0},ou=users,dc=xasecure,dc=net)\"",
+ "authServiceHostName": "localhost",
+ "xa_ldap_ad_url": "\"ldap://ad.xasecure.net:389\"",
+ "policymgr_external_url": "http://localhost:6080",
+ "policymgr_http_enabled": "true",
+ "db_host": "localhost",
+ "xa_ldap_groupRoleAttribute": "\"cn\""
+ },
+ "ranger-site": {
+ "http.enabled": "true",
+ "http.service.port": "6080",
+ "https.attrib.keystorePass": "ranger",
+ "https.attrib.clientAuth": "want",
+ "https.attrib.keystoreFile": "/etc/ranger/admin/keys/server.jks",
+ "https.service.port": "6182",
+ "https.attrib.keyAlias": "myKey"
+ },
+ "usersync-properties": {
+ "SYNC_INTERVAL": "1",
+ "SYNC_LDAP_USERNAME_CASE_CONVERSION": "lower",
+ "SYNC_LDAP_USER_SEARCH_FILTER": "-",
+ "SYNC_LDAP_URL": "ldap://localhost:389",
+ "SYNC_LDAP_GROUPNAME_CASE_CONVERSION": "lower",
+ "SYNC_LDAP_USER_SEARCH_SCOPE": "sub",
+ "SYNC_LDAP_BIND_PASSWORD": "admin321",
+ "SYNC_LDAP_USER_NAME_ATTRIBUTE": "cn",
+ "MIN_UNIX_USER_ID_TO_SYNC": "1000",
+ "SYNC_LDAP_USER_SEARCH_BASE": "ou=users,dc=xasecure,dc=net",
+ "SYNC_LDAP_USER_OBJECT_CLASS": "person",
+ "CRED_KEYSTORE_FILENAME": "/usr/lib/xausersync/.jceks/xausersync.jceks",
+ "SYNC_SOURCE": "unix",
+ "SYNC_LDAP_BIND_DN": "cn=admin,dc=xasecure,dc=net",
+ "SYNC_LDAP_USER_GROUP_NAME_ATTRIBUTE": "memberof,ismemberof",
+ "logdir": "logs"
+ },
+ "usersync-properties": {
+ "SYNC_INTERVAL": "1",
+ "SYNC_LDAP_USERNAME_CASE_CONVERSION": "lower",
+ "SYNC_LDAP_USER_SEARCH_FILTER": "-",
+ "SYNC_LDAP_URL": "ldap://localhost:389",
+ "SYNC_LDAP_GROUPNAME_CASE_CONVERSION": "lower",
+ "SYNC_LDAP_USER_SEARCH_SCOPE": "sub",
+ "SYNC_LDAP_BIND_PASSWORD": "admin321",
+ "SYNC_LDAP_USER_NAME_ATTRIBUTE": "cn",
+ "MIN_UNIX_USER_ID_TO_SYNC": "1000",
+ "SYNC_LDAP_USER_SEARCH_BASE": "ou=users,dc=xasecure,dc=net",
+ "SYNC_LDAP_USER_OBJECT_CLASS": "person",
+ "CRED_KEYSTORE_FILENAME": "/usr/lib/xausersync/.jceks/xausersync.jceks",
+ "SYNC_SOURCE": "unix",
+ "SYNC_LDAP_BIND_DN": "cn=admin,dc=xasecure,dc=net",
+ "SYNC_LDAP_USER_GROUP_NAME_ATTRIBUTE": "memberof,ismemberof",
+ "logdir": "logs"
+ },
+ "ranger-env": {
+ "ranger_group": "ranger",
+ "ranger_admin_log_dir": "/var/log/ranger/admin",
+ "oracle_home": "-",
+ "admin_username": "admin",
+ "ranger_user": "ranger",
+ "ranger_admin_username": "amb_ranger_admin",
+ "admin_password": "admin",
+ "ranger_admin_password": "aa",
+ "ranger_usersync_log_dir": "/var/log/ranger/usersync"
+ },
+ "spark-defaults": {
+ "spark.yarn.applicationMaster.waitTries": "10",
+ "spark.history.kerberos.keytab": "none",
+ "spark.yarn.preserve.staging.files": "false",
+ "spark.yarn.submit.file.replication": "3",
+ "spark.history.kerberos.principal": "none",
+ "spark.yarn.driver.memoryOverhead": "384",
+ "spark.yarn.queue": "default",
+ "spark.yarn.containerLauncherMaxThreads": "25",
+ "spark.yarn.scheduler.heartbeat.interval-ms": "5000",
+ "spark.history.ui.port": "18080",
+ "spark.yarn.max.executor.failures": "3",
+ "spark.driver.extraJavaOptions": "",
+ "spark.history.provider": "org.apache.spark.deploy.yarn.history.YarnHistoryProvider",
+ "spark.yarn.am.extraJavaOptions": "",
+ "spark.yarn.executor.memoryOverhead": "384"
+ },
+ "spark-javaopts-properties": {
+ "content": " "
+ },
+ "spark-log4j-properties": {
+ "content": "\n# Set everything to be logged to the console\nlog4j.rootCategory=INFO, console\nlog4j.appender.console=org.apache.log4j.ConsoleAppender\nlog4j.appender.console.target=System.err\nlog4j.appender.console.layout=org.apache.log4j.PatternLayout\nlog4j.appender.console.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{1}: %m%n\n\n# Settings to quiet third party logs that are too verbose\nlog4j.logger.org.eclipse.jetty=WARN\nlog4j.logger.org.eclipse.jetty.util.component.AbstractLifeCycle=ERROR\nlog4j.logger.org.apache.spark.repl.SparkIMain$exprTyper=INFO\nlog4j.logger.org.apache.spark.repl.SparkILoop$SparkILoopInterpreter=INFO"
+ },
+ "spark-env": {
+ "content": "\n#!/usr/bin/env bash\n\n# This file is sourced when running various Spark programs.\n# Copy it as spark-env.sh and edit that to configure Spark for your site.\n\n# Options read in YARN client mode\n#SPARK_EXECUTOR_INSTANCES=\"2\" #Number of workers to start (Default: 2)\n#SPARK_EXECUTOR_CORES=\"1\" #Number of cores for the workers (Default: 1).\n#SPARK_EXECUTOR_MEMORY=\"1G\" #Memory per Worker (e.g. 1000M, 2G) (Default: 1G)\n#SPARK_DRIVER_MEMORY=\"512 Mb\" #Memory for Master (e.g. 1000M, 2G) (Default: 512 Mb)\n#SPARK_YARN_APP_NAME=\"spark\" #The name of your application (Default: Spark)\n#SPARK_YARN_QUEUE=\"~@~Xdefault~@~Y\" #The hadoop queue to use for allocation requests (Default: @~Xdefault~@~Y)\n#SPARK_YARN_DIST_FILES=\"\" #Comma separated list of files to be distributed with the job.\n#SPARK_YARN_DIST_ARCHIVES=\"\" #Comma separated list of archives to be distributed with the job.\n\n# Generic options for the daemons used in the standalone deploy mode\n\
n# Alternate conf dir. (Default: ${SPARK_HOME}/conf)\nexport SPARK_CONF_DIR=${SPARK_HOME:-{{spark_home}}}/conf\n\n# Where log files are stored.(Default:${SPARK_HOME}/logs)\n#export SPARK_LOG_DIR=${SPARK_HOME:-{{spark_home}}}/logs\nexport SPARK_LOG_DIR={{spark_log_dir}}\n\n# Where the pid file is stored. (Default: /tmp)\nexport SPARK_PID_DIR={{spark_pid_dir}}\n\n# A string representing this instance of spark.(Default: $USER)\nSPARK_IDENT_STRING=$USER\n\n# The scheduling priority for daemons. (Default: 0)\nSPARK_NICENESS=0\n\nexport HADOOP_HOME=${HADOOP_HOME:-{{hadoop_home}}}\nexport HADOOP_CONF_DIR=${HADOOP_CONF_DIR:-{{hadoop_conf_dir}}}\n\n# The java implementation to use.\nexport JAVA_HOME={{java_home}}\n\nif [ -d \"/etc/tez/conf/\" ]; then\n export TEZ_CONF_DIR=/etc/tez/conf\nelse\n export TEZ_CONF_DIR=\nfi",
+ "spark_pid_dir": "/var/run/spark",
+ "spark_log_dir": "/var/log/spark",
+ "spark_group": "spark",
+ "spark_user": "spark"
+ },
+ "spark-metrics-properties": {
+ "content": "\n# syntax: [instance].sink|source.[name].[options]=[value]\n\n# This file configures Spark's internal metrics system. The metrics system is\n# divided into instances which correspond to internal components.\n# Each instance can be configured to report its metrics to one or more sinks.\n# Accepted values for [instance] are \"master\", \"worker\", \"executor\", \"driver\",\n# and \"applications\". A wild card \"*\" can be used as an instance name, in\n# which case all instances will inherit the supplied property.\n#\n# Within an instance, a \"source\" specifies a particular set of grouped metrics.\n# there are two kinds of sources:\n# 1. Spark internal sources, like MasterSource, WorkerSource, etc, which will\n# collect a Spark component's internal state. Each instance is paired with a\n# Spark source that is added automatically.\n# 2. Common sources, like JvmSource, which will collect low level state.\n# These can be added through configuration options and ar
e then loaded\n# using reflection.\n#\n# A \"sink\" specifies where metrics are delivered to. Each instance can be\n# assigned one or more sinks.\n#\n# The sink|source field specifies whether the property relates to a sink or\n# source.\n#\n# The [name] field specifies the name of source or sink.\n#\n# The [options] field is the specific property of this source or sink. The\n# source or sink is responsible for parsing this property.\n#\n# Notes:\n# 1. To add a new sink, set the \"class\" option to a fully qualified class\n# name (see examples below).\n# 2. Some sinks involve a polling period. The minimum allowed polling period\n# is 1 second.\n# 3. Wild card properties can be overridden by more specific properties.\n# For example, master.sink.console.period takes precedence over\n# *.sink.console.period.\n# 4. A metrics specific configuration\n# \"spark.metrics.conf=${SPARK_HOME}/conf/metrics.properties\" should be\n# added to Java properties using -Dspark.metrics.conf=xxx if you wa
nt to\n# customize metrics system. You can also put the file in ${SPARK_HOME}/conf\n# and it will be loaded automatically.\n# 5. MetricsServlet is added by default as a sink in master, worker and client\n# driver, you can send http request \"/metrics/json\" to get a snapshot of all the\n# registered metrics in json format. For master, requests \"/metrics/master/json\" and\n# \"/metrics/applications/json\" can be sent seperately to get metrics snapshot of\n# instance master and applications. MetricsServlet may not be configured by self.\n#\n\n## List of available sinks and their properties.\n\n# org.apache.spark.metrics.sink.ConsoleSink\n# Name: Default: Description:\n# period 10 Poll period\n# unit seconds Units of poll period\n\n# org.apache.spark.metrics.sink.CSVSink\n# Name: Default: Description:\n# period 10 Poll period\n# unit seconds Units of poll period\n# directory /tmp Where to store CSV files\n\n# org.apache.spark.metrics.sink.GangliaSink\n# Name: Default: Description:\n#
host NONE Hostname or multicast group of Ganglia server\n# port NONE Port of Ganglia server(s)\n# period 10 Poll period\n# unit seconds Units of poll period\n# ttl 1 TTL of messages sent by Ganglia\n# mode multicast Ganglia network mode ('unicast' or 'multicast')\n\n# org.apache.spark.metrics.sink.JmxSink\n\n# org.apache.spark.metrics.sink.MetricsServlet\n# Name: Default: Description:\n# path VARIES* Path prefix from the web server root\n# sample false Whether to show entire set of samples for histograms ('false' or 'true')\n#\n# * Default path is /metrics/json for all instances except the master. The master has two paths:\n# /metrics/aplications/json # App information\n# /metrics/master/json # Master information\n\n# org.apache.spark.metrics.sink.GraphiteSink\n# Name: Default: Description:\n# host NONE Hostname of Graphite server\n# port NONE Port of Graphite server\n# period 10 Poll period\n# unit seconds Units of poll period\n# prefix EMPTY STRING Prefix to prepend to metric name
\n\n## Examples\n# Enable JmxSink for all instances by class name\n#*.sink.jmx.class=org.apache.spark.metrics.sink.JmxSink\n\n# Enable ConsoleSink for all instances by class name\n#*.sink.console.class=org.apache.spark.metrics.sink.ConsoleSink\n\n# Polling period for ConsoleSink\n#*.sink.console.period=10\n\n#*.sink.console.unit=seconds\n\n# Master instance overlap polling period\n#master.sink.console.period=15\n\n#master.sink.console.unit=seconds\n\n# Enable CsvSink for all instances\n#*.sink.csv.class=org.apache.spark.metrics.sink.CsvSink\n\n# Polling period for CsvSink\n#*.sink.csv.period=1\n\n#*.sink.csv.unit=minutes\n\n# Polling directory for CsvSink\n#*.sink.csv.directory=/tmp/\n\n# Worker instance overlap polling period\n#worker.sink.csv.period=10\n\n#worker.sink.csv.unit=minutes\n\n# Enable jvm source for instance master, worker, driver and executor\n#master.source.jvm.class=org.apache.spark.metrics.source.JvmSource\n\n#worker.source.jvm.class=org.apache.spark.metrics.source
.JvmSource\n\n#driver.source.jvm.class=org.apache.spark.metrics.source.JvmSource\n\n#executor.source.jvm.class=org.apache.spark.metrics.source.JvmSource"
+ },
+ "hadoop-env": {
+ "dtnode_heapsize": "1024m",
+ "namenode_opt_maxnewsize": "256m",
+ "hdfs_log_dir_prefix": "/var/log/hadoop",
+ "namenode_heapsize": "1024m",
+ "proxyuser_group": "users",
+ "hadoop_pid_dir_prefix": "/var/run/hadoop",
+ "content": "\n# Set Hadoop-specific environment variables here.\n\n# The only required environment variable is JAVA_HOME. All others are\n# optional. When running a distributed configuration it is best to\n# set JAVA_HOME in this file, so that it is correctly defined on\n# remote nodes.\n\n# The java implementation to use. Required.\nexport JAVA_HOME={{java_home}}\nexport HADOOP_HOME_WARN_SUPPRESS=1\n\n# Hadoop home directory\nexport HADOOP_HOME=${HADOOP_HOME:-{{hadoop_home}}}\n\n# Hadoop Configuration Directory\n\n{# this is different for HDP1 #}\n# Path to jsvc required by secure HDP 2.0 datanode\nexport JSVC_HOME={{jsvc_path}}\n\n\n# The maximum amount of heap to use, in MB. Default is 1000.\nexport HADOOP_HEAPSIZE=\"{{hadoop_heapsize}}\"\n\nexport HADOOP_NAMENODE_INIT_HEAPSIZE=\"-Xms{{namenode_heapsize}}\"\n\n# Extra Java runtime options. Empty by default.\nexport HADOOP_OPTS=\"-Djava.net.preferIPv4Stack=true ${HADOOP_OPTS}\"\n\n# Command specific options appende
d to HADOOP_OPTS when specified\nexport HADOOP_NAMENODE_OPTS=\"-server -XX:ParallelGCThreads=8 -XX:+UseConcMarkSweepGC -XX:ErrorFile={{hdfs_log_dir_prefix}}/$USER/hs_err_pid%p.log -XX:NewSize={{namenode_opt_newsize}} -XX:MaxNewSize={{namenode_opt_maxnewsize}} -XX:PermSize={{namenode_opt_permsize}} -XX:MaxPermSize={{namenode_opt_maxpermsize}} -Xloggc:{{hdfs_log_dir_prefix}}/$USER/gc.log-`date +'%Y%m%d%H%M'` -verbose:gc -XX:+PrintGCDetails -XX:+PrintGCTimeStamps -XX:+PrintGCDateStamps -Xms{{namenode_heapsize}} -Xmx{{namenode_heapsize}} -Dhadoop.security.logger=INFO,DRFAS -Dhdfs.audit.logger=INFO,DRFAAUDIT ${HADOOP_NAMENODE_OPTS}\"\nHADOOP_JOBTRACKER_OPTS=\"-server -XX:ParallelGCThreads=8 -XX:+UseConcMarkSweepGC -XX:ErrorFile={{hdfs_log_dir_prefix}}/$USER/hs_err_pid%p.log -XX:NewSize={{jtnode_opt_newsize}} -XX:MaxNewSize={{jtnode_opt_maxnewsize}} -Xloggc:{{hdfs_log_dir_prefix}}/$USER/gc.log-`date +'%Y%m%d%H%M'` -verbose:gc -XX:+PrintGCDetails -XX:+PrintGCTimeStamps -XX:+PrintGCDateStam
ps -Xmx{{jtnode_heapsize}} -Dhadoop.security.logger=INFO,DRFAS -Dmapred.audit.logger=INFO,MRAUDIT -Dhadoop.mapreduce.jobsummary.logger=INFO,JSA ${HADOOP_JOBTRACKER_OPTS}\"\n\nHADOOP_TASKTRACKER_OPTS=\"-server -Xmx{{ttnode_heapsize}} -Dhadoop.security.logger=ERROR,console -Dmapred.audit.logger=ERROR,console ${HADOOP_TASKTRACKER_OPTS}\"\nexport HADOOP_DATANODE_OPTS=\"-server -XX:ParallelGCThreads=4 -XX:+UseConcMarkSweepGC -XX:ErrorFile=/var/log/hadoop/$USER/hs_err_pid%p.log -XX:NewSize=200m -XX:MaxNewSize=200m -XX:PermSize=128m -XX:MaxPermSize=256m -Xloggc:/var/log/hadoop/$USER/gc.log-`date +'%Y%m%d%H%M'` -verbose:gc -XX:+PrintGCDetails -XX:+PrintGCTimeStamps -XX:+PrintGCDateStamps -Xms{{dtnode_heapsize}} -Xmx{{dtnode_heapsize}} -Dhadoop.security.logger=INFO,DRFAS -Dhdfs.audit.logger=INFO,DRFAAUDIT ${HADOOP_DATANODE_OPTS}\"\nHADOOP_BALANCER_OPTS=\"-server -Xmx{{hadoop_heapsize}}m ${HADOOP_BALANCER_OPTS}\"\n\nexport HADOOP_SECONDARYNAMENODE_OPTS=$HADOOP_NAMENODE_OPTS\n\n# The following
applies to multiple commands (fs, dfs, fsck, distcp etc)\nexport HADOOP_CLIENT_OPTS=\"-Xmx${HADOOP_HEAPSIZE}m -XX:MaxPermSize=512m $HADOOP_CLIENT_OPTS\"\n\n# On secure datanodes, user to run the datanode as after dropping privileges\nexport HADOOP_SECURE_DN_USER=${HADOOP_SECURE_DN_USER:-{{hadoop_secure_dn_user}}}\n\n# Extra ssh options. Empty by default.\nexport HADOOP_SSH_OPTS=\"-o ConnectTimeout=5 -o SendEnv=HADOOP_CONF_DIR\"\n\n# Where log files are stored. $HADOOP_HOME/logs by default.\nexport HADOOP_LOG_DIR={{hdfs_log_dir_prefix}}/$USER\n\n# History server logs\nexport HADOOP_MAPRED_LOG_DIR={{mapred_log_dir_prefix}}/$USER\n\n# Where log files are stored in the secure data environment.\nexport HADOOP_SECURE_DN_LOG_DIR={{hdfs_log_dir_prefix}}/$HADOOP_SECURE_DN_USER\n\n# File naming remote slave hosts. $HADOOP_HOME/conf/slaves by default.\n# export HADOOP_SLAVES=${HADOOP_HOME}/conf/slaves\n\n# host:path where hadoop code should be rsync'd from. Unset by default.\n# export HAD
OOP_MASTER=master:/home/$USER/src/hadoop\n\n# Seconds to sleep between slave commands. Unset by default. This\n# can be useful in large clusters, where, e.g., slave rsyncs can\n# otherwise arrive faster than the master can service them.\n# export HADOOP_SLAVE_SLEEP=0.1\n\n# The directory where pid files are stored. /tmp by default.\nexport HADOOP_PID_DIR={{hadoop_pid_dir_prefix}}/$USER\nexport HADOOP_SECURE_DN_PID_DIR={{hadoop_pid_dir_prefix}}/$HADOOP_SECURE_DN_USER\n\n# History server pid\nexport HADOOP_MAPRED_PID_DIR={{mapred_pid_dir_prefix}}/$USER\n\nYARN_RESOURCEMANAGER_OPTS=\"-Dyarn.server.resourcemanager.appsummary.logger=INFO,RMSUMMARY\"\n\n# A string representing this instance of hadoop. $USER by default.\nexport HADOOP_IDENT_STRING=$USER\n\n# The scheduling priority for daemon processes. See 'man nice'.\n\n# export HADOOP_NICENESS=10\n\n# Use libraries from standard classpath\nJAVA_JDBC_LIBS=\"\"\n#Add libraries required by mysql connector\nfor jarFile in `ls /usr/share/
java/*mysql* 2>/dev/null`\ndo\n JAVA_JDBC_LIBS=${JAVA_JDBC_LIBS}:$jarFile\ndone\n# Add libraries required by oracle connector\nfor jarFile in `ls /usr/share/java/*ojdbc* 2>/dev/null`\ndo\n JAVA_JDBC_LIBS=${JAVA_JDBC_LIBS}:$jarFile\ndone\n# Add libraries required by nodemanager\nMAPREDUCE_LIBS={{mapreduce_libs_path}}\nexport HADOOP_CLASSPATH=${HADOOP_CLASSPATH}${JAVA_JDBC_LIBS}:${MAPREDUCE_LIBS}\n\n# added to the HADOOP_CLASSPATH\nif [ -d \"/usr/hdp/current/tez-client\" ]; then\n if [ -d \"/etc/tez/conf/\" ]; then\n # When using versioned RPMs, the tez-client will be a symlink to the current folder of tez in HDP.\n export HADOOP_CLASSPATH=${HADOOP_CLASSPATH}:/usr/hdp/current/tez-client/*:/usr/hdp/current/tez-client/lib/*:/etc/tez/conf/\n fi\nfi\n\n\n# Setting path to hdfs command line\nexport HADOOP_LIBEXEC_DIR={{hadoop_libexec_dir}}\n\n# Mostly required for hadoop 2.0\nexport JAVA_LIBRARY_PATH=${JAVA_LIBRARY_PATH}\n\nexport HADOOP_OPTS=\"-Dhdp.version=$HDP_VERSION $HADOOP_
OPTS\"",
+ "hdfs_user": "hdfs",
+ "namenode_opt_newsize": "256m",
+ "dfs.datanode.data.dir.mount.file": "/etc/hadoop/conf/dfs_data_dir_mount.hist",
+ "hadoop_root_logger": "INFO,RFA",
+ "hadoop_heapsize": "1024",
+ "namenode_opt_maxpermsize": "256m",
+ "namenode_opt_permsize": "128m"
+ },
+ "spark-metrics-properties": {
+ "content": "\n# syntax: [instance].sink|source.[name].[options]=[value]\n\n# This file configures Spark's internal metrics system. The metrics system is\n# divided into instances which correspond to internal components.\n# Each instance can be configured to report its metrics to one or more sinks.\n# Accepted values for [instance] are \"master\", \"worker\", \"executor\", \"driver\",\n# and \"applications\". A wild card \"*\" can be used as an instance name, in\n# which case all instances will inherit the supplied property.\n#\n# Within an instance, a \"source\" specifies a particular set of grouped metrics.\n# there are two kinds of sources:\n# 1. Spark internal sources, like MasterSource, WorkerSource, etc, which will\n# collect a Spark component's internal state. Each instance is paired with a\n# Spark source that is added automatically.\n# 2. Common sources, like JvmSource, which will collect low level state.\n# These can be added through configuration options and ar
e then loaded\n# using reflection.\n#\n# A \"sink\" specifies where metrics are delivered to. Each instance can be\n# assigned one or more sinks.\n#\n# The sink|source field specifies whether the property relates to a sink or\n# source.\n#\n# The [name] field specifies the name of source or sink.\n#\n# The [options] field is the specific property of this source or sink. The\n# source or sink is responsible for parsing this property.\n#\n# Notes:\n# 1. To add a new sink, set the \"class\" option to a fully qualified class\n# name (see examples below).\n# 2. Some sinks involve a polling period. The minimum allowed polling period\n# is 1 second.\n# 3. Wild card properties can be overridden by more specific properties.\n# For example, master.sink.console.period takes precedence over\n# *.sink.console.period.\n# 4. A metrics specific configuration\n# \"spark.metrics.conf=${SPARK_HOME}/conf/metrics.properties\" should be\n# added to Java properties using -Dspark.metrics.conf=xxx if you wa
nt to\n# customize metrics system. You can also put the file in ${SPARK_HOME}/conf\n# and it will be loaded automatically.\n# 5. MetricsServlet is added by default as a sink in master, worker and client\n# driver, you can send http request \"/metrics/json\" to get a snapshot of all the\n# registered metrics in json format. For master, requests \"/metrics/master/json\" and\n# \"/metrics/applications/json\" can be sent seperately to get metrics snapshot of\n# instance master and applications. MetricsServlet may not be configured by self.\n#\n\n## List of available sinks and their properties.\n\n# org.apache.spark.metrics.sink.ConsoleSink\n# Name: Default: Description:\n# period 10 Poll period\n# unit seconds Units of poll period\n\n# org.apache.spark.metrics.sink.CSVSink\n# Name: Default: Description:\n# period 10 Poll period\n# unit seconds Units of poll period\n# directory /tmp Where to store CSV files\n\n# org.apache.spark.metrics.sink.GangliaSink\n# Name: Default: Description:\n#
host NONE Hostname or multicast group of Ganglia server\n# port NONE Port of Ganglia server(s)\n# period 10 Poll period\n# unit seconds Units of poll period\n# ttl 1 TTL of messages sent by Ganglia\n# mode multicast Ganglia network mode ('unicast' or 'multicast')\n\n# org.apache.spark.metrics.sink.JmxSink\n\n# org.apache.spark.metrics.sink.MetricsServlet\n# Name: Default: Description:\n# path VARIES* Path prefix from the web server root\n# sample false Whether to show entire set of samples for histograms ('false' or 'true')\n#\n# * Default path is /metrics/json for all instances except the master. The master has two paths:\n# /metrics/aplications/json # App information\n# /metrics/master/json # Master information\n\n# org.apache.spark.metrics.sink.GraphiteSink\n# Name: Default: Description:\n# host NONE Hostname of Graphite server\n# port NONE Port of Graphite server\n# period 10 Poll period\n# unit seconds Units of poll period\n# prefix EMPTY STRING Prefix to prepend to metric name
\n\n## Examples\n# Enable JmxSink for all instances by class name\n#*.sink.jmx.class=org.apache.spark.metrics.sink.JmxSink\n\n# Enable ConsoleSink for all instances by class name\n#*.sink.console.class=org.apache.spark.metrics.sink.ConsoleSink\n\n# Polling period for ConsoleSink\n#*.sink.console.period=10\n\n#*.sink.console.unit=seconds\n\n# Master instance overlap polling period\n#master.sink.console.period=15\n\n#master.sink.console.unit=seconds\n\n# Enable CsvSink for all instances\n#*.sink.csv.class=org.apache.spark.metrics.sink.CsvSink\n\n# Polling period for CsvSink\n#*.sink.csv.period=1\n\n#*.sink.csv.unit=minutes\n\n# Polling directory for CsvSink\n#*.sink.csv.directory=/tmp/\n\n# Worker instance overlap polling period\n#worker.sink.csv.period=10\n\n#worker.sink.csv.unit=minutes\n\n# Enable jvm source for instance master, worker, driver and executor\n#master.source.jvm.class=org.apache.spark.metrics.source.JvmSource\n\n#worker.source.jvm.class=org.apache.spark.metrics.source
.JvmSource\n\n#driver.source.jvm.class=org.apache.spark.metrics.source.JvmSource\n\n#executor.source.jvm.class=org.apache.spark.metrics.source.JvmSource"
+ },
+ "slider-client": {
+ "slider.yarn.queue": "default"
+ },
+ "core-site": {
+ "fs.defaultFS": "hdfs://c6401.ambari.apache.org:8020"
+ },
+ "hdfs-site": {
+ "a": "b"
+ },
+ "yarn-site": {
+ "yarn.application.classpath": "/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/*",
+ "yarn.resourcemanager.address": "c6401.ambari.apache.org:8050",
+ "yarn.resourcemanager.scheduler.address": "c6401.ambari.apache.org:8030"
+ },
+ "cluster-env": {
+ "security_enabled": "false",
+ "ignore_groupsusers_create": "false",
+ "smokeuser": "ambari-qa",
+ "kerberos_domain": "EXAMPLE.COM",
+ "user_group": "hadoop"
+ },
+ "webhcat-site": {
+ "templeton.jar": "/usr/hdp/current/hive-webhcat/share/webhcat/svr/lib/hive-webhcat-*.jar",
+ "templeton.pig.archive": "hdfs:///hdp/apps/{{ hdp_stack_version }}/pig/pig.tar.gz",
+ "templeton.hive.archive": "hdfs:///hdp/apps/{{ hdp_stack_version }}/hive/hive.tar.gz",
+ "templeton.sqoop.archive": "hdfs:///hdp/apps/{{ hdp_stack_version }}/sqoop/sqoop.tar.gz",
+ "templeton.streaming.jar": "hdfs:///hdp/apps/{{ hdp_stack_version }}/mr/hadoop-streaming.jar"
+ },
+ "slider-log4j": {
+ "content": "log4jproperties\nline2"
+ },
+ "slider-env": {
+ "content": "envproperties\nline2"
+ },
+ "gateway-site": {
+ "java.security.auth.login.config": "/etc/knox/conf/krb5JAASLogin.conf",
+ "gateway.hadoop.kerberos.secured": "false",
+ "gateway.gateway.conf.dir": "deployments",
+ "gateway.path": "gateway",
+ "sun.security.krb5.debug": "true",
+ "java.security.krb5.conf": "/etc/knox/conf/krb5.conf",
+ "gateway.port": "8443"
+ },
+
+ "users-ldif": {
+ "content": "\n # Licensed to the Apache Software Foundation (ASF) under one\n # or more contributor license agreements. See the NOTICE file\n # distributed with this work for additional information\n # regarding copyright ownership. The ASF licenses this file\n # to you under the Apache License, Version 2.0 (the\n # \"License\"); you may not use this file except in compliance\n # with the License. You may obtain a copy of the License at\n #\n # http://www.apache.org/licenses/LICENSE-2.0\n #\n # Unless required by applicable law or agreed to in writing, software\n # distributed under the License is distributed on an \"AS IS\" BASIS,\n # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n # See the License for the specific language governing permissions and\n # limitations under th
e License.\n\n version: 1\n\n # Please replace with site specific values\n dn: dc=hadoop,dc=apache,dc=org\n objectclass: organization\n objectclass: dcObject\n o: Hadoop\n dc: hadoop\n\n # Entry for a sample people container\n # Please replace with site specific values\n dn: ou=people,dc=hadoop,dc=apache,dc=org\n objectclass:top\n objectclass:organizationalUnit\n ou: people\n\n # Entry for a sample end user\n # Please replace with site specific values\n dn: uid=guest,ou=people,dc=hadoop,dc=apache,dc=org\n objectclass:top\n objectclass:person\n objectclass:organizationalPerson\n objectclass:inetOrgPerson\n cn: Guest\n sn: User\n uid: guest\n userPassword:guest-password\n\n # entry for sample user admin\n
dn: uid=admin,ou=people,dc=hadoop,dc=apache,dc=org\n objectclass:top\n objectclass:person\n objectclass:organizationalPerson\n objectclass:inetOrgPerson\n cn: Admin\n sn: Admin\n uid: admin\n userPassword:admin-password\n\n # entry for sample user sam\n dn: uid=sam,ou=people,dc=hadoop,dc=apache,dc=org\n objectclass:top\n objectclass:person\n objectclass:organizationalPerson\n objectclass:inetOrgPerson\n cn: sam\n sn: sam\n uid: sam\n userPassword:sam-password\n\n # entry for sample user tom\n dn: uid=tom,ou=people,dc=hadoop,dc=apache,dc=org\n objectclass:top\n objectclass:person\n objectclass:organizationalPerson\n objectclass:inetOrgPerson\n cn: tom\n sn: tom\n uid: tom\n userP
assword:tom-password\n\n # create FIRST Level groups branch\n dn: ou=groups,dc=hadoop,dc=apache,dc=org\n objectclass:top\n objectclass:organizationalUnit\n ou: groups\n description: generic groups branch\n\n # create the analyst group under groups\n dn: cn=analyst,ou=groups,dc=hadoop,dc=apache,dc=org\n objectclass:top\n objectclass: groupofnames\n cn: analyst\n description:analyst group\n member: uid=sam,ou=people,dc=hadoop,dc=apache,dc=org\n member: uid=tom,ou=people,dc=hadoop,dc=apache,dc=org\n\n\n # create the scientist group under groups\n dn: cn=scientist,ou=groups,dc=hadoop,dc=apache,dc=org\n objectclass:top\n objectclass: groupofnames\n cn: scientist\n description: scientist group\n member: uid=sam,ou=people,dc=hadoop,dc=apache,dc=org"
+ },
+
+ "topology": {
+ "content": "\n <topology>\n\n <gateway>\n\n <provider>\n <role>authentication</role>\n <name>ShiroProvider</name>\n <enabled>true</enabled>\n <param>\n <name>sessionTimeout</name>\n <value>30</value>\n </param>\n <param>\n <name>main.ldapRealm</name>\n <value>org.apache.hadoop.gateway.shirorealm.KnoxLdapRealm</value>\n </param>\n <param>\n <name>main.ldapRealm.userDnTemplate</name>\n <value>uid={0},ou=people,dc=hadoop,dc=apache,dc=org</value>\n </param>\n <param>\n <name>main.ldapRealm.contextFactory.url</name>\n <value>ldap://{{knox_host_name}}:33389</value>\n
</param>\n <param>\n <name>main.ldapRealm.contextFactory.authenticationMechanism</name>\n <value>simple</value>\n </param>\n <param>\n <name>urls./**</name>\n <value>authcBasic</value>\n </param>\n </provider>\n\n <provider>\n <role>identity-assertion</role>\n <name>Default</name>\n <enabled>true</enabled>\n </provider>\n\n </gateway>\n\n <service>\n <role>NAMENODE</role>\n <url>hdfs://{{namenode_host}}:{{namenode_rpc_port}}</url>\n </service>\n\n <service>\n <role>JOBTRACKER</role>\n <url>rpc://{{rm_host}}:{{jt_rpc_port}}</url>\n </service>\n\n <service>\n <role>WEBHDFS
</role>\n <url>http://{{namenode_host}}:{{namenode_http_port}}/webhdfs</url>\n </service>\n\n <service>\n <role>WEBHCAT</role>\n <url>http://{{webhcat_server_host}}:{{templeton_port}}/templeton</url>\n </service>\n\n <service>\n <role>OOZIE</role>\n <url>http://{{oozie_server_host}}:{{oozie_server_port}}/oozie</url>\n </service>\n\n <service>\n <role>WEBHBASE</role>\n <url>http://{{hbase_master_host}}:{{hbase_master_port}}</url>\n </service>\n\n <service>\n <role>HIVE</role>\n <url>http://{{hive_server_host}}:{{hive_http_port}}/{{hive_http_path}}</url>\n </service>\n\n <service>\n <role>RESOURCEMANAGER</role>\n <url>http://{{rm_host}}:{{rm_port}}/ws</url>\n </service>\n </topology>"
+ },
+
+ "ldap-log4j": {
+ "content": "\n # Licensed to the Apache Software Foundation (ASF) under one\n # or more contributor license agreements. See the NOTICE file\n # distributed with this work for additional information\n # regarding copyright ownership. The ASF licenses this file\n # to you under the Apache License, Version 2.0 (the\n # \"License\"); you may not use this file except in compliance\n # with the License. You may obtain a copy of the License at\n #\n # http://www.apache.org/licenses/LICENSE-2.0\n #\n # Unless required by applicable law or agreed to in writing, software\n # distributed under the License is distributed on an \"AS IS\" BASIS,\n # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n # See the License for the specific language governing permissions and\n # limitations under the License.\n #testing\n\n app.log.dir=${launch
er.dir}/../logs\n app.log.file=${launcher.name}.log\n\n log4j.rootLogger=ERROR, drfa\n log4j.logger.org.apache.directory.server.ldap.LdapServer=INFO\n log4j.logger.org.apache.directory=WARN\n\n log4j.appender.stdout=org.apache.log4j.ConsoleAppender\n log4j.appender.stdout.layout=org.apache.log4j.PatternLayout\n log4j.appender.stdout.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{2}: %m%n\n\n log4j.appender.drfa=org.apache.log4j.DailyRollingFileAppender\n log4j.appender.drfa.File=${app.log.dir}/${app.log.file}\n log4j.appender.drfa.DatePattern=.yyyy-MM-dd\n log4j.appender.drfa.layout=org.apache.log4j.PatternLayout\n log4j.appender.drfa.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n"
+ },
+
+ "gateway-log4j": {
+ "content": "\n\n # Licensed to the Apache Software Foundation (ASF) under one\n # or more contributor license agreements. See the NOTICE file\n # distributed with this work for additional information\n # regarding copyright ownership. The ASF licenses this file\n # to you under the Apache License, Version 2.0 (the\n # \"License\"); you may not use this file except in compliance\n # with the License. You may obtain a copy of the License at\n #\n # http://www.apache.org/licenses/LICENSE-2.0\n #\n # Unless required by applicable law or agreed to in writing, software\n # distributed under the License is distributed on an \"AS IS\" BASIS,\n # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n # See the License for the specific language governing permissions and\n # limitations under the License.\n\n app.log.dir=${launcher.dir}/../logs\n app.log.file=${launcher.name}.lo
g\n app.audit.file=${launcher.name}-audit.log\n\n log4j.rootLogger=ERROR, drfa\n\n log4j.logger.org.apache.hadoop.gateway=INFO\n #log4j.logger.org.apache.hadoop.gateway=DEBUG\n\n #log4j.logger.org.eclipse.jetty=DEBUG\n #log4j.logger.org.apache.shiro=DEBUG\n #log4j.logger.org.apache.http=DEBUG\n #log4j.logger.org.apache.http.client=DEBUG\n #log4j.logger.org.apache.http.headers=DEBUG\n #log4j.logger.org.apache.http.wire=DEBUG\n\n log4j.appender.stdout=org.apache.log4j.ConsoleAppender\n log4j.appender.stdout.layout=org.apache.log4j.PatternLayout\n log4j.appender.stdout.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{2}: %m%n\n\n log4j.appender.drfa=org.apache.log4j.DailyRollingFileAppender\n log4j.appender.drfa.File=${app.log.dir}/${app.log.file}\n log4j.appender.drfa.DatePattern=.yyyy-MM-dd\n log4j.appender.drfa.layout=org.apache.log4j.PatternLayout\n log4j.appender.drfa.layout.ConversionPat
tern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n\n\n log4j.logger.audit=INFO, auditfile\n log4j.appender.auditfile=org.apache.log4j.DailyRollingFileAppender\n log4j.appender.auditfile.File=${app.log.dir}/${app.audit.file}\n log4j.appender.auditfile.Append = true\n log4j.appender.auditfile.DatePattern = '.'yyyy-MM-dd\n log4j.appender.auditfile.layout = org.apache.hadoop.gateway.audit.log4j.layout.AuditLayout"
+ },
+ "knox-env": {
+ "knox_master_secret": "sa",
+ "knox_group": "knox",
+ "knox_pid_dir": "/var/run/knox",
+ "knox_user": "knox"
+ },
+ "kafka-env": {
+ "content": "\n#!/bin/bash\n\n# Set KAFKA specific environment variables here.\n\n# The java implementation to use.\nexport JAVA_HOME={{java64_home}}\nexport PATH=$PATH:$JAVA_HOME/bin",
+ "kafka_user": "kafka",
+ "kafka_log_dir": "/customdisk/var/log/kafka",
+ "kafka_pid_dir": "/customdisk/var/run/kafka"
+ },
+ "kafka-log4j": {
+ "content": "\n#\n#\n# Licensed to the Apache Software Foundation (ASF) under one\n# or more contributor license agreements. See the NOTICE file\n# distributed with this work for additional information\n# regarding copyright ownership. The ASF licenses this file\n# to you under the Apache License, Version 2.0 (the\n# \"License\"); you may not use this file except in compliance\n# with the License. You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing,\n# software distributed under the License is distributed on an\n# \"AS IS\" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY\n# KIND, either express or implied. See the License for the\n# specific language governing permissions and limitations\n# under the License.\n#\n#\n#\nkafka.logs.dir=logs\n\nlog4j.rootLogger=INFO, stdout\n\nlog4j.appender.stdout=org.apache.log4j.ConsoleAppender\nlog4j.appender.stdout.layout=org.apache
.log4j.PatternLayout\nlog4j.appender.stdout.layout.ConversionPattern=[%d] %p %m (%c)%n\n\nlog4j.appender.kafkaAppender=org.apache.log4j.DailyRollingFileAppender\nlog4j.appender.kafkaAppender.DatePattern='.'yyyy-MM-dd-HH\nlog4j.appender.kafkaAppender.File=${kafka.logs.dir}/server.log\nlog4j.appender.kafkaAppender.layout=org.apache.log4j.PatternLayout\nlog4j.appender.kafkaAppender.layout.ConversionPattern=[%d] %p %m (%c)%n\n\nlog4j.appender.stateChangeAppender=org.apache.log4j.DailyRollingFileAppender\nlog4j.appender.stateChangeAppender.DatePattern='.'yyyy-MM-dd-HH\nlog4j.appender.stateChangeAppender.File=${kafka.logs.dir}/state-change.log\nlog4j.appender.stateChangeAppender.layout=org.apache.log4j.PatternLayout\nlog4j.appender.stateChangeAppender.layout.ConversionPattern=[%d] %p %m (%c)%n\n\nlog4j.appender.requestAppender=org.apache.log4j.DailyRollingFileAppender\nlog4j.appender.requestAppender.DatePattern='.'yyyy-MM-dd-HH\nlog4j.appender.requestAppender.File=${kafka.logs.dir}/kafka-
request.log\nlog4j.appender.requestAppender.layout=org.apache.log4j.PatternLayout\nlog4j.appender.requestAppender.layout.ConversionPattern=[%d] %p %m (%c)%n\n\nlog4j.appender.cleanerAppender=org.apache.log4j.DailyRollingFileAppender\nlog4j.appender.cleanerAppender.DatePattern='.'yyyy-MM-dd-HH\nlog4j.appender.cleanerAppender.File=${kafka.logs.dir}/log-cleaner.log\nlog4j.appender.cleanerAppender.layout=org.apache.log4j.PatternLayout\nlog4j.appender.cleanerAppender.layout.ConversionPattern=[%d] %p %m (%c)%n\n\nlog4j.appender.controllerAppender=org.apache.log4j.DailyRollingFileAppender\nlog4j.appender.controllerAppender.DatePattern='.'yyyy-MM-dd-HH\nlog4j.appender.controllerAppender.File=${kafka.logs.dir}/controller.log\nlog4j.appender.controllerAppender.layout=org.apache.log4j.PatternLayout\nlog4j.appender.controllerAppender.layout.ConversionPattern=[%d] %p %m (%c)%n\n\n# Turn on all our debugging info\n#log4j.logger.kafka.producer.async.DefaultEventHandler=DEBUG, kafkaAppender\n#log4j
.logger.kafka.client.ClientUtils=DEBUG, kafkaAppender\n#log4j.logger.kafka.perf=DEBUG, kafkaAppender\n#log4j.logger.kafka.perf.ProducerPerformance$ProducerThread=DEBUG, kafkaAppender\n#log4j.logger.org.I0Itec.zkclient.ZkClient=DEBUG\nlog4j.logger.kafka=INFO, kafkaAppender\nlog4j.logger.kafka.network.RequestChannel$=WARN, requestAppender\nlog4j.additivity.kafka.network.RequestChannel$=false\n\n#log4j.logger.kafka.network.Processor=TRACE, requestAppender\n#log4j.logger.kafka.server.KafkaApis=TRACE, requestAppender\n#log4j.additivity.kafka.server.KafkaApis=false\nlog4j.logger.kafka.request.logger=WARN, requestAppender\nlog4j.additivity.kafka.request.logger=false\n\nlog4j.logger.kafka.controller=TRACE, controllerAppender\nlog4j.additivity.kafka.controller=false\n\nlog4j.logger.kafka.log.LogCleaner=INFO, cleanerAppender\nlog4j.additivity.kafka.log.LogCleaner=false\n\nlog4j.logger.state.change.logger=TRACE, stateChangeAppender\nlog4j.additivity.state.change.logger=false"
+ },
+ "kafka-broker": {
+ "log.segment.bytes": "1073741824",
+ "socket.send.buffer.bytes": "102400",
+ "num.network.threads": "3",
+ "log.flush.scheduler.interval.ms": "3000",
+ "kafka.ganglia.metrics.host": "localhost",
+ "zookeeper.session.timeout.ms": "6000",
+ "replica.lag.time.max.ms": "10000",
+ "num.io.threads": "8",
+ "kafka.ganglia.metrics.group": "kafka",
+ "replica.lag.max.messages": "4000",
+ "port": "6667",
+ "log.retention.bytes": "-1",
+ "fetch.purgatory.purge.interval.requests": "10000",
+ "producer.purgatory.purge.interval.requests": "10000",
+ "default.replication.factor": "1",
+ "replica.high.watermark.checkpoint.interval.ms": "5000",
+ "zookeeper.connect": "c6402.ambari.apache.org:2181",
+ "controlled.shutdown.retry.backoff.ms": "5000",
+ "num.partitions": "1",
+ "log.flush.interval.messages": "10000",
+ "replica.fetch.min.bytes": "1",
+ "queued.max.requests": "500",
+ "controlled.shutdown.max.retries": "3",
+ "replica.fetch.wait.max.ms": "500",
+ "controlled.shutdown.enable": "false",
+ "log.roll.hours": "168",
+ "log.cleanup.interval.mins": "10",
+ "replica.socket.receive.buffer.bytes": "65536",
+ "zookeeper.connection.timeout.ms": "6000",
+ "replica.fetch.max.bytes": "1048576",
+ "num.replica.fetchers": "1",
+ "socket.request.max.bytes": "104857600",
+ "message.max.bytes": "1000000",
+ "zookeeper.sync.time.ms": "2000",
+ "socket.receive.buffer.bytes": "102400",
+ "controller.message.queue.size": "10",
+ "log.flush.interval.ms": "3000",
+ "log.dirs": "/tmp/log/dir",
+ "controller.socket.timeout.ms": "30000",
+ "replica.socket.timeout.ms": "30000",
+ "auto.create.topics.enable": "true",
+ "log.index.size.max.bytes": "10485760",
+ "kafka.ganglia.metrics.port": "8649",
+ "log.index.interval.bytes": "4096",
+ "log.retention.hours": "168"
+ },
+ "ranger-hbase-plugin-properties": {
+ "ranger-hbase-plugin-enabled":"yes"
+ },
+ "ranger-hive-plugin-properties": {
+ "ranger-hive-plugin-enabled":"yes"
+ }
+ },
+ "configuration_attributes": {
+ "yarn-site": {
+ "final": {
+ "yarn.nodemanager.disk-health-checker.min-healthy-disks": "true",
+ "yarn.nodemanager.container-executor.class": "true",
+ "yarn.nodemanager.local-dirs": "true"
+ }
+ },
+ "hdfs-site": {
+ "final": {
+ "dfs.web.ugi": "true",
+ "dfs.support.append": "true",
+ "dfs.cluster.administrators": "true"
+ }
+ },
+ "core-site": {
+ "final": {
+ "hadoop.proxyuser.hive.groups": "true",
+ "webinterface.private.actions": "true",
+ "hadoop.proxyuser.oozie.hosts": "true"
+ }
+ },
+ "knox-env": {},
+ "gateway-site": {},
+ "users-ldif": {},
+ "kafka-env": {},
+ "kafka-log4j": {},
+ "kafka-broker": {}
+ },
+ "configurationTags": {
+ "slider-client": {
+ "tag": "version1"
+ },
+ "slider-log4j": {
+ "tag": "version1"
+ },
+ "slider-env": {
+ "tag": "version1"
+ },
+ "core-site": {
+ "tag": "version1"
+ },
+ "hdfs-site": {
+ "tag": "version1"
+ },
+ "yarn-site": {
+ "tag": "version1"
+ },
+ "gateway-site": {
+ "tag": "version1"
+ },
+ "topology": {
+ "tag": "version1"
+ },
+ "users-ldif": {
+ "tag": "version1"
+ },
+ "kafka-env": {
+ "tag": "version1"
+ },
+ "kafka-log4j": {
+ "tag": "version1"
+ },
+ "kafka-broker": {
+ "tag": "version1"
+ }
+ },
+ "commandId": "7-1",
+ "clusterHostInfo": {
+ "ambari_server_host": [
+ "c6401.ambari.apache.org"
+ ],
+ "all_ping_ports": [
+ "8670",
+ "8670"
+ ],
+ "rm_host": [
+ "c6402.ambari.apache.org"
+ ],
+ "all_hosts": [
+ "c6401.ambari.apache.org",
+ "c6402.ambari.apache.org"
+ ],
+ "knox_gateway_hosts": [
+ "jaimin-knox-1.c.pramod-thangali.internal"
+ ],
+ "kafka_broker_hosts": [
+ "c6401.ambari.apache.org"
+ ],
+ "zookeeper_hosts": [
+ "c6401.ambari.apache.org"
+ ]
+
+ }
+}