Browse Source

AMBARI-4173. HDFS on HDP1. Using resource management lib (Eugene
Chekanskiy via aonishuk)

Andrew Onischuk 11 năm trước cách đây
mục cha
commit
2a48ee546e
36 tập tin đã thay đổi với 2829 bổ sung29 xóa
  1. 50 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-INSTALL/files/changeToSecureUid.sh
  2. 8 3
      ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-INSTALL/scripts/hook.py
  3. 81 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-INSTALL/scripts/params.py
  4. 102 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-INSTALL/scripts/shared_initialization.py
  5. 62 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/files/checkForFormat.sh
  6. 132 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/files/task-log4j.properties
  7. 10 3
      ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/scripts/hook.py
  8. 183 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/scripts/params.py
  9. 321 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/scripts/shared_initialization.py
  10. 25 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/templates/commons-logging.properties.j2
  11. 3 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/templates/exclude_hosts_list.j2
  12. 121 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/templates/hadoop-env.sh.j2
  13. 45 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/templates/hadoop-metrics2.properties.j2
  14. 17 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/templates/hdfs.conf.j2
  15. 91 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/templates/health_check-v2.j2
  16. 118 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/templates/health_check.j2
  17. 3 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/templates/include_hosts_list.j2
  18. 200 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/templates/log4j.properties.j2
  19. 3 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/templates/slaves.j2
  20. 48 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/templates/snmpd.conf.j2
  21. 20 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/templates/taskcontroller.cfg.j2
  22. 113 19
      ambari-server/src/main/resources/stacks/HDP/1.3._/services/HDFS/metainfo.xml
  23. 62 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/services/HDFS/package/files/checkForFormat.sh
  24. 53 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/services/HDFS/package/files/checkWebUI.py
  25. 57 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/services/HDFS/package/scripts/datanode.py
  26. 49 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/services/HDFS/package/scripts/hdfs_client.py
  27. 59 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/services/HDFS/package/scripts/hdfs_datanode.py
  28. 179 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/services/HDFS/package/scripts/hdfs_namenode.py
  29. 53 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/services/HDFS/package/scripts/hdfs_snamenode.py
  30. 59 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/services/HDFS/package/scripts/namenode.py
  31. 163 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/services/HDFS/package/scripts/params.py
  32. 106 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/services/HDFS/package/scripts/service_check.py
  33. 64 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/services/HDFS/package/scripts/snamenode.py
  34. 31 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/services/HDFS/package/scripts/status_params.py
  35. 133 0
      ambari-server/src/main/resources/stacks/HDP/1.3._/services/HDFS/package/scripts/utils.py
  36. 5 4
      ambari-server/src/main/resources/stacks/HDP/2.0.8/hooks/before-START/scripts/shared_initialization.py

+ 50 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-INSTALL/files/changeToSecureUid.sh

@@ -0,0 +1,50 @@
+#!/bin/sh
+#
+#
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+#
+
+username=$1
+directories=$2
+
+function find_available_uid() {
+ for ((i=1001; i<=2000; i++))
+ do
+   grep -q $i /etc/passwd
+   if [ "$?" -ne 0 ]
+   then
+    newUid=$i
+    break
+   fi
+ done
+}
+
+find_available_uid
+
+if [ $newUid -eq 0 ]
+then
+  echo "Failed to find Uid between 1000 and 2000"
+  exit 1
+fi
+
+dir_array=($(echo $directories | sed 's/,/\n/g'))
+old_uid=$(id -u $username)
+echo "Changing uid of $username from $old_uid to $newUid"
+echo "Changing directory permisions for ${dir_array[@]}"
+usermod -u $newUid $username && for dir in ${dir_array[@]} ; do chown -Rh $newUid $dir ; done
+exit 0

+ 8 - 3
ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START.py → ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-INSTALL/scripts/hook.py

@@ -20,11 +20,16 @@ limitations under the License.
 
 import sys
 from resource_management import *
+from shared_initialization import *
 
-class BeforeStartHook(Hook):
+#TODO this must be "CONFIGURE" hook when CONFIGURE command will be implemented
+class BeforeConfigureHook(Hook):
 
   def hook(self, env):
-    Execute(("touch", "/tmp/hook-test"))
+    import params
+
+    env.set_params(params)
+    setup_users()
 
 if __name__ == "__main__":
-  BeforeStartHook().execute()
+  BeforeConfigureHook().execute()

+ 81 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-INSTALL/scripts/params.py

@@ -0,0 +1,81 @@
+"""
+Licensed to the Apache Software Foundation (ASF) under one
+or more contributor license agreements.  See the NOTICE file
+distributed with this work for additional information
+regarding copyright ownership.  The ASF licenses this file
+to you under the Apache License, Version 2.0 (the
+"License"); you may not use this file except in compliance
+with the License.  You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+
+"""
+
+from resource_management import *
+from resource_management.core.system import System
+import os
+
+config = Script.get_config()
+
+#users and groups
+yarn_user = config['configurations']['global']['yarn_user']
+hbase_user = config['configurations']['global']['hbase_user']
+nagios_user = config['configurations']['global']['nagios_user']
+oozie_user = config['configurations']['global']['oozie_user']
+webhcat_user = config['configurations']['global']['hcat_user']
+hcat_user = config['configurations']['global']['hcat_user']
+hive_user = config['configurations']['global']['hive_user']
+smoke_user =  config['configurations']['global']['smokeuser']
+mapred_user = config['configurations']['global']['mapred_user']
+hdfs_user = config['configurations']['global']['hdfs_user']
+zk_user = config['configurations']['global']['zk_user']
+gmetad_user = config['configurations']['global']["gmetad_user"]
+gmond_user = config['configurations']['global']["gmond_user"]
+
+user_group = config['configurations']['global']['user_group']
+proxyuser_group =  config['configurations']['global']['proxyuser_group']
+nagios_group = config['configurations']['global']['nagios_group']
+smoke_user_group =  "users"
+mapred_tt_group = default("/configurations/mapred-site/mapreduce.tasktracker.group", user_group)
+
+#hosts
+hostname = config["hostname"]
+rm_host = default("/clusterHostInfo/rm_host", [])
+slave_hosts = default("/clusterHostInfo/slave_hosts", [])
+hagios_server_hosts = default("/clusterHostInfo/nagios_server_host", [])
+oozie_servers = default("/clusterHostInfo/oozie_server", [])
+hcat_server_hosts = default("/clusterHostInfo/webhcat_server_host", [])
+hive_server_host =  default("/clusterHostInfo/hive_server_host", [])
+hbase_master_hosts = default("/clusterHostInfo/hbase_master_hosts", [])
+hs_host = default("/clusterHostInfo/hs_host", [])
+jtnode_host = default("/clusterHostInfo/jtnode_host", [])
+namenode_host = default("/clusterHostInfo/namenode_host", [])
+zk_hosts = default("/clusterHostInfo/zookeeper_hosts", [])
+ganglia_server_hosts = default("/clusterHostInfo/ganglia_server_host", [])
+
+has_resourcemanager = not len(rm_host) == 0
+has_slaves = not len(slave_hosts) == 0
+has_nagios = not len(hagios_server_hosts) == 0
+has_oozie_server = not len(oozie_servers)  == 0
+has_hcat_server_host = not len(hcat_server_hosts)  == 0
+has_hive_server_host = not len(hive_server_host)  == 0
+has_hbase_masters = not len(hbase_master_hosts) == 0
+has_zk_host = not len(zk_hosts) == 0
+has_ganglia_server = not len(ganglia_server_hosts) == 0
+
+is_namenode_master = hostname in namenode_host
+is_jtnode_master = hostname in jtnode_host
+is_rmnode_master = hostname in rm_host
+is_hsnode_master = hostname in hs_host
+is_hbase_master = hostname in hbase_master_hosts
+is_slave = hostname in slave_hosts
+if has_ganglia_server:
+  ganglia_server_host = ganglia_server_hosts[0]
+
+hbase_tmp_dir = config['configurations']['hbase-site']['hbase.tmp.dir']

+ 102 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-INSTALL/scripts/shared_initialization.py

@@ -0,0 +1,102 @@
+"""
+Licensed to the Apache Software Foundation (ASF) under one
+or more contributor license agreements.  See the NOTICE file
+distributed with this work for additional information
+regarding copyright ownership.  The ASF licenses this file
+to you under the Apache License, Version 2.0 (the
+"License"); you may not use this file except in compliance
+with the License.  You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+
+"""
+
+import os
+
+from resource_management import *
+
+def setup_users():
+  """
+  Creates users before cluster installation
+  """
+  import params
+
+  Group(params.user_group)
+  Group(params.smoke_user_group)
+  Group(params.proxyuser_group)
+  User(params.smoke_user,
+       gid=params.user_group,
+       groups=[params.proxyuser_group]
+  )
+  smoke_user_dirs = format(
+    "/tmp/hadoop-{smoke_user},/tmp/hsperfdata_{smoke_user},/home/{smoke_user},/tmp/{smoke_user},/tmp/sqoop-{smoke_user}")
+  set_uid(params.smoke_user, smoke_user_dirs)
+
+  if params.has_hbase_masters:
+    User(params.hbase_user,
+         gid = params.user_group,
+         groups=[params.user_group])
+    hbase_user_dirs = format(
+      "/home/{hbase_user},/tmp/{hbase_user},/usr/bin/{hbase_user},/var/log/{hbase_user},{hbase_tmp_dir}")
+    set_uid(params.hbase_user, hbase_user_dirs)
+
+  if params.has_nagios:
+    Group(params.nagios_group)
+    User(params.nagios_user,
+         gid=params.nagios_group)
+
+  if params.has_oozie_server:
+    User(params.oozie_user,
+         gid = params.user_group)
+
+  if params.has_hcat_server_host:
+    User(params.webhcat_user,
+         gid = params.user_group)
+    User(params.hcat_user,
+         gid = params.user_group)
+
+  if params.has_hive_server_host:
+    User(params.hive_user,
+         gid = params.user_group)
+
+  if params.has_resourcemanager:
+    User(params.yarn_user,
+         gid = params.user_group)
+
+  if params.has_ganglia_server:
+    Group(params.gmetad_user)
+    Group(params.gmond_user)
+    User(params.gmond_user,
+         gid=params.user_group,
+        groups=[params.gmond_user])
+    User(params.gmetad_user,
+         gid=params.user_group,
+        groups=[params.gmetad_user])
+
+  User(params.hdfs_user,
+        gid=params.user_group,
+        groups=[params.user_group]
+  )
+  User(params.mapred_user,
+       gid=params.user_group,
+       groups=[params.user_group]
+  )
+  if params.has_zk_host:
+    User(params.zk_user,
+         gid=params.user_group)
+
+def set_uid(user, user_dirs):
+  """
+  user_dirs - comma separated directories
+  """
+  File("/tmp/changeUid.sh",
+       content=StaticFile("changeToSecureUid.sh"),
+       mode=0555)
+  Execute(format("/tmp/changeUid.sh {user} {user_dirs} 2>/dev/null"),
+          not_if = format("test $(id -u {user}) -gt 1000"))

+ 62 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/files/checkForFormat.sh

@@ -0,0 +1,62 @@
+#!/bin/sh
+#
+#
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+#
+#
+
+export hdfs_user=$1
+shift
+export conf_dir=$1
+shift
+export mark_dir=$1
+shift
+export name_dirs=$*
+
+export EXIT_CODE=0
+export command="namenode -format"
+export list_of_non_empty_dirs=""
+
+mark_file=/var/run/hadoop/hdfs/namenode-formatted
+if [[ -f ${mark_file} ]] ; then
+  rm -f ${mark_file}
+  mkdir -p ${mark_dir}
+fi
+
+if [[ ! -d $mark_dir ]] ; then
+  for dir in `echo $name_dirs | tr ',' ' '` ; do
+    echo "NameNode Dirname = $dir"
+    cmd="ls $dir | wc -l  | grep -q ^0$"
+    eval $cmd
+    if [[ $? -ne 0 ]] ; then
+      (( EXIT_CODE = $EXIT_CODE + 1 ))
+      list_of_non_empty_dirs="$list_of_non_empty_dirs $dir"
+    fi
+  done
+
+  if [[ $EXIT_CODE == 0 ]] ; then
+    su - ${hdfs_user} -c "yes Y | hadoop --config ${conf_dir} ${command}"
+  else
+    echo "ERROR: Namenode directory(s) is non empty. Will not format the namenode. List of non-empty namenode dirs ${list_of_non_empty_dirs}"
+  fi
+else
+  echo "${mark_dir} exists. Namenode DFS already formatted"
+fi
+
+exit $EXIT_CODE
+

+ 132 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/files/task-log4j.properties

@@ -0,0 +1,132 @@
+#
+#
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+#
+#
+
+
+# Define some default values that can be overridden by system properties
+hadoop.root.logger=INFO,console
+hadoop.log.dir=.
+hadoop.log.file=hadoop.log
+
+#
+# Job Summary Appender 
+#
+# Use following logger to send summary to separate file defined by 
+# hadoop.mapreduce.jobsummary.log.file rolled daily:
+# hadoop.mapreduce.jobsummary.logger=INFO,JSA
+# 
+hadoop.mapreduce.jobsummary.logger=${hadoop.root.logger}
+hadoop.mapreduce.jobsummary.log.file=hadoop-mapreduce.jobsummary.log
+
+# Define the root logger to the system property "hadoop.root.logger".
+log4j.rootLogger=${hadoop.root.logger}, EventCounter
+
+# Logging Threshold
+log4j.threshhold=ALL
+
+#
+# Daily Rolling File Appender
+#
+
+log4j.appender.DRFA=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.DRFA.File=${hadoop.log.dir}/${hadoop.log.file}
+
+# Rollver at midnight
+log4j.appender.DRFA.DatePattern=.yyyy-MM-dd
+
+# 30-day backup
+#log4j.appender.DRFA.MaxBackupIndex=30
+log4j.appender.DRFA.layout=org.apache.log4j.PatternLayout
+
+# Pattern format: Date LogLevel LoggerName LogMessage
+log4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
+# Debugging Pattern format
+#log4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n
+
+
+#
+# console
+# Add "console" to rootlogger above if you want to use this 
+#
+
+log4j.appender.console=org.apache.log4j.ConsoleAppender
+log4j.appender.console.target=System.err
+log4j.appender.console.layout=org.apache.log4j.PatternLayout
+log4j.appender.console.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{2}: %m%n
+
+#
+# TaskLog Appender
+#
+
+#Default values
+hadoop.tasklog.taskid=null
+hadoop.tasklog.iscleanup=false
+hadoop.tasklog.noKeepSplits=4
+hadoop.tasklog.totalLogFileSize=100
+hadoop.tasklog.purgeLogSplits=true
+hadoop.tasklog.logsRetainHours=12
+
+log4j.appender.TLA=org.apache.hadoop.mapred.TaskLogAppender
+log4j.appender.TLA.taskId=${hadoop.tasklog.taskid}
+log4j.appender.TLA.isCleanup=${hadoop.tasklog.iscleanup}
+log4j.appender.TLA.totalLogFileSize=${hadoop.tasklog.totalLogFileSize}
+
+log4j.appender.TLA.layout=org.apache.log4j.PatternLayout
+log4j.appender.TLA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
+
+#
+# Rolling File Appender
+#
+
+#log4j.appender.RFA=org.apache.log4j.RollingFileAppender
+#log4j.appender.RFA.File=${hadoop.log.dir}/${hadoop.log.file}
+
+# Logfile size and and 30-day backups
+#log4j.appender.RFA.MaxFileSize=1MB
+#log4j.appender.RFA.MaxBackupIndex=30
+
+#log4j.appender.RFA.layout=org.apache.log4j.PatternLayout
+#log4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} - %m%n
+#log4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n
+
+
+# Custom Logging levels
+
+hadoop.metrics.log.level=INFO
+#log4j.logger.org.apache.hadoop.mapred.JobTracker=DEBUG
+#log4j.logger.org.apache.hadoop.mapred.TaskTracker=DEBUG
+#log4j.logger.org.apache.hadoop.fs.FSNamesystem=DEBUG
+log4j.logger.org.apache.hadoop.metrics2=${hadoop.metrics.log.level}
+
+# Jets3t library
+log4j.logger.org.jets3t.service.impl.rest.httpclient.RestS3Service=ERROR
+
+#
+# Null Appender
+# Trap security logger on the hadoop client side
+#
+log4j.appender.NullAppender=org.apache.log4j.varia.NullAppender
+
+#
+# Event Counter Appender
+# Sends counts of logging messages at different severity levels to Hadoop Metrics.
+#
+log4j.appender.EventCounter=org.apache.hadoop.log.metrics.EventCounter
+

+ 10 - 3
ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/scripts/hook.py

@@ -20,11 +20,18 @@ limitations under the License.
 
 import sys
 from resource_management import *
+from shared_initialization import *
 
-class BeforeStartHook(Hook):
+#TODO this must be "CONFIGURE" hook when CONFIGURE command will be implemented
+class BeforeConfigureHook(Hook):
 
   def hook(self, env):
-    Execute(("touch", "/tmp/hook-test"))
+    import params
+
+    env.set_params(params)
+    setup_java()
+    setup_hadoop()
+    setup_configs()
 
 if __name__ == "__main__":
-  BeforeStartHook().execute()
+  BeforeConfigureHook().execute()

+ 183 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/scripts/params.py

@@ -0,0 +1,183 @@
+"""
+Licensed to the Apache Software Foundation (ASF) under one
+or more contributor license agreements.  See the NOTICE file
+distributed with this work for additional information
+regarding copyright ownership.  The ASF licenses this file
+to you under the Apache License, Version 2.0 (the
+"License"); you may not use this file except in compliance
+with the License.  You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+
+"""
+
+from resource_management import *
+from resource_management.core.system import System
+import os
+
+config = Script.get_config()
+
+#java params
+java_home = "/usr/jdk64/jdk1.6.0_31"
+artifact_dir = "/tmp/HDP-artifacts/"
+jdk_bin = "jdk-6u31-linux-x64.bin"
+jce_policy_zip = "jce_policy-6.zip"
+jce_location = config['hostLevelParams']['jdk_location']
+jdk_location = config['hostLevelParams']['jdk_location']
+#security params
+security_enabled = config['configurations']['global']['security_enabled']
+dfs_journalnode_keytab_file = config['configurations']['hdfs-site']['dfs.journalnode.keytab.file']
+dfs_web_authentication_kerberos_keytab = config['configurations']['hdfs-site']['dfs.journalnode.keytab.file']
+dfs_secondary_namenode_keytab_file =  config['configurations']['hdfs-site']['fs.secondary.namenode.keytab.file']
+dfs_datanode_keytab_file =  config['configurations']['hdfs-site']['dfs.datanode.keytab.file']
+dfs_namenode_keytab_file =  config['configurations']['hdfs-site']['dfs.namenode.keytab.file']
+
+dfs_datanode_kerberos_principal = config['configurations']['hdfs-site']['dfs.datanode.kerberos.principal']
+dfs_journalnode_kerberos_principal = config['configurations']['hdfs-site']['dfs.journalnode.kerberos.principal']
+dfs_secondary_namenode_kerberos_internal_spnego_principal = config['configurations']['hdfs-site']['dfs.secondary.namenode.kerberos.internal.spnego.principal']
+dfs_namenode_kerberos_principal = config['configurations']['hdfs-site']['dfs.namenode.kerberos.principal']
+dfs_web_authentication_kerberos_principal = config['configurations']['hdfs-site']['dfs.web.authentication.kerberos.principal']
+dfs_secondary_namenode_kerberos_principal = config['configurations']['hdfs-site']['dfs.secondary.namenode.kerberos.principal']
+dfs_journalnode_kerberos_internal_spnego_principal = config['configurations']['hdfs-site']['dfs.journalnode.kerberos.internal.spnego.principal']
+
+#users and groups
+mapred_user = config['configurations']['global']['mapred_user']
+hdfs_user = config['configurations']['global']['hdfs_user']
+yarn_user = config['configurations']['global']['yarn_user']
+
+user_group = config['configurations']['global']['user_group']
+mapred_tt_group = default("/configurations/mapred-site/mapreduce.tasktracker.group", user_group)
+
+#snmp
+snmp_conf_dir = "/etc/snmp/"
+snmp_source = "0.0.0.0/0"
+snmp_community = "hadoop"
+
+#hosts
+hostname = config["hostname"]
+rm_host = default("/clusterHostInfo/rm_host", [])
+slave_hosts = default("/clusterHostInfo/slave_hosts", [])
+hagios_server_hosts = default("/clusterHostInfo/nagios_server_host", [])
+oozie_servers = default("/clusterHostInfo/oozie_server", [])
+hcat_server_hosts = default("/clusterHostInfo/webhcat_server_host", [])
+hive_server_host =  default("/clusterHostInfo/hive_server_host", [])
+hbase_master_hosts = default("/clusterHostInfo/hbase_master_hosts", [])
+hs_host = default("/clusterHostInfo/hs_host", [])
+jtnode_host = default("/clusterHostInfo/jtnode_host", [])
+namenode_host = default("/clusterHostInfo/namenode_host", [])
+zk_hosts = default("/clusterHostInfo/zookeeper_hosts", [])
+ganglia_server_hosts = default("/clusterHostInfo/ganglia_server_host", [])
+
+has_resourcemanager = not len(rm_host) == 0
+has_slaves = not len(slave_hosts) == 0
+has_nagios = not len(hagios_server_hosts) == 0
+has_oozie_server = not len(oozie_servers)  == 0
+has_hcat_server_host = not len(hcat_server_hosts)  == 0
+has_hive_server_host = not len(hive_server_host)  == 0
+has_hbase_masters = not len(hbase_master_hosts) == 0
+has_zk_host = not len(zk_hosts) == 0
+has_ganglia_server = not len(ganglia_server_hosts) == 0
+
+is_namenode_master = hostname in namenode_host
+is_jtnode_master = hostname in jtnode_host
+is_rmnode_master = hostname in rm_host
+is_hsnode_master = hostname in hs_host
+is_hbase_master = hostname in hbase_master_hosts
+is_slave = hostname in slave_hosts
+if has_ganglia_server:
+  ganglia_server_host = ganglia_server_hosts[0]
+#hadoop params
+hadoop_tmp_dir = format("/tmp/hadoop-{hdfs_user}")
+hadoop_lib_home = "/usr/lib/hadoop/lib"
+hadoop_conf_dir = "/etc/hadoop/conf"
+hadoop_pid_dir_prefix = config['configurations']['global']['hadoop_pid_dir_prefix']
+hadoop_home = "/usr"
+hadoop_bin = "/usr/lib/hadoop/bin"
+
+task_log4j_properties_location = os.path.join(hadoop_conf_dir, "task-log4j.properties")
+limits_conf_dir = "/etc/security/limits.d"
+
+hdfs_log_dir_prefix = config['configurations']['global']['hdfs_log_dir_prefix']
+hbase_tmp_dir = config['configurations']['hbase-site']['hbase.tmp.dir']
+#db params
+server_db_name = config['hostLevelParams']['db_name']
+db_driver_filename = config['hostLevelParams']['db_driver_filename']
+oracle_driver_url = config['hostLevelParams']['oracle_jdbc_url']
+mysql_driver_url = config['hostLevelParams']['mysql_jdbc_url']
+
+ambari_db_rca_url = config['hostLevelParams']['ambari_db_rca_url']
+ambari_db_rca_driver = config['hostLevelParams']['ambari_db_rca_driver']
+ambari_db_rca_username = config['hostLevelParams']['ambari_db_rca_username']
+ambari_db_rca_password = config['hostLevelParams']['ambari_db_rca_password']
+
+rca_enabled = config['configurations']['global']['rca_enabled']
+rca_disabled_prefix = "###"
+if rca_enabled == True:
+  rca_prefix = ""
+else:
+  rca_prefix = rca_disabled_prefix
+
+#hadoop-env.sh
+java_home = config['configurations']['global']['java64_home']
+if System.get_instance().platform == "suse":
+  jsvc_path = "/usr/lib/bigtop-utils"
+else:
+  jsvc_path = "/usr/libexec/bigtop-utils"
+
+hadoop_heapsize = config['configurations']['global']['hadoop_heapsize']
+namenode_heapsize = config['configurations']['global']['namenode_heapsize']
+namenode_opt_newsize =  config['configurations']['global']['namenode_opt_newsize']
+namenode_opt_maxnewsize =  config['configurations']['global']['namenode_opt_maxnewsize']
+
+jtnode_opt_newsize = default("jtnode_opt_newsize","200m")
+jtnode_opt_maxnewsize = default("jtnode_opt_maxnewsize","200m")
+jtnode_heapsize =  default("jtnode_heapsize","1024m")
+ttnode_heapsize = "1024m"
+
+dtnode_heapsize = config['configurations']['global']['dtnode_heapsize']
+mapred_pid_dir_prefix = default("mapred_pid_dir_prefix","/var/run/hadoop-mapreduce")
+mapreduce_libs_path = "/usr/lib/hadoop-mapreduce/*"
+hadoop_libexec_dir = "/usr/lib/hadoop/libexec"
+mapred_log_dir_prefix = default("mapred_log_dir_prefix","/var/log/hadoop-mapreduce")
+
+#taskcontroller.cfg
+
+mapred_local_dir = "/tmp/hadoop-mapred/mapred/local"
+
+#log4j.properties
+
+yarn_log_dir_prefix = default("yarn_log_dir_prefix","/var/log/hadoop-yarn")
+
+#exclude file
+exlude_file_path = config['configurations']['hdfs-site']['dfs.hosts.exclude']
+if 'hdfs-exclude-file' in config['configurations']:
+  if 'datanodes' in config['configurations']['hdfs-exclude-file']:
+    hdfs_exclude_file = config['configurations']['hdfs-exclude-file']['datanodes'].split(",")
+  else:
+    hdfs_exclude_file = []
+else:
+  hdfs_exclude_file = []
+
+#hdfs ha properties
+dfs_ha_enabled = False
+dfs_ha_nameservices = default("/configurations/hdfs-site/dfs.nameservices", None)
+dfs_ha_namenode_ids = default(format("hdfs-site/dfs.ha.namenodes.{dfs_ha_nameservices}"), None)
+if dfs_ha_namenode_ids:
+  dfs_ha_namenode_ids_array_len = len(dfs_ha_namenode_ids.split(","))
+  if dfs_ha_namenode_ids_array_len > 1:
+    dfs_ha_enabled = True
+
+if dfs_ha_enabled:
+  for nn_id in dfs_ha_namenode_ids:
+    nn_host = config['configurations']['hdfs-site'][format('dfs.namenode.rpc-address.{dfs_ha_nameservices}.{nn_id}')]
+    if hostname in nn_host:
+      namenode_id = nn_id
+  namenode_id = None
+
+dfs_hosts = default('/configurations/hdfs-site/dfs.hosts', None)

+ 321 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/scripts/shared_initialization.py

@@ -0,0 +1,321 @@
+"""
+Licensed to the Apache Software Foundation (ASF) under one
+or more contributor license agreements.  See the NOTICE file
+distributed with this work for additional information
+regarding copyright ownership.  The ASF licenses this file
+to you under the Apache License, Version 2.0 (the
+"License"); you may not use this file except in compliance
+with the License.  You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+
+"""
+
+import os
+
+from resource_management import *
+
+def setup_java():
+  """
+  Installs jdk using specific params, that comes from ambari-server
+  """
+  import params
+
+  jdk_curl_target = format("{artifact_dir}/{jdk_bin}")
+  java_dir = os.path.dirname(params.java_home)
+  java_exec = format("{java_home}/bin/java")
+  Execute(format("mkdir -p {artifact_dir} ; curl -kf --retry 10 {jdk_location}/{jdk_bin} -o {jdk_curl_target}"),
+          path = ["/bin","/usr/bin/"],
+          not_if = format("test -e {java_exec}"))
+  Execute(format("mkdir -p {java_dir} ; chmod +x {jdk_curl_target}; cd {java_dir} ; echo A | {jdk_curl_target} -noregister > /dev/null 2>&1"),
+          path = ["/bin","/usr/bin/"],
+          not_if = format("test -e {java_exec}")
+  )
+  jce_curl_target = format("{artifact_dir}/{jce_policy_zip}")
+  download_jce = format("mkdir -p {artifact_dir}; curl -kf --retry 10 {jce_location}/{jce_policy_zip} -o {jce_curl_target}")
+  Execute( download_jce,
+        path = ["/bin","/usr/bin/"],
+        not_if =format("test -e {jce_curl_target}"),
+        ignore_failures = True
+  )
+  security_dir = format("{java_home}/jre/lib/security")
+  extract_cmd = format("rm -f local_policy.jar; rm -f US_export_policy.jar; unzip -o -j -q {jce_curl_target}")
+  Execute(extract_cmd,
+        only_if = format("test -e {security_dir} && test -f {jce_curl_target}"),
+        cwd  = security_dir,
+        path = ['/bin/','/usr/bin']
+  )
+
+def setup_hadoop():
+  """
+  Setup hadoop files and directories
+  """
+  import params
+
+  File(os.path.join(params.snmp_conf_dir, 'snmpd.conf'),
+       content=Template("snmpd.conf.j2"))
+  Service("snmpd",
+          action = "restart")
+
+  Execute("/bin/echo 0 > /selinux/enforce",
+          only_if="test -f /selinux/enforce"
+  )
+
+  install_snappy()
+
+  #directories
+  Directory(params.hadoop_conf_dir,
+            recursive=True,
+            owner='root',
+            group='root'
+  )
+  Directory(params.hdfs_log_dir_prefix,
+            recursive=True,
+            owner='root',
+            group='root'
+  )
+  Directory(params.hadoop_pid_dir_prefix,
+            recursive=True,
+            owner='root',
+            group='root'
+  )
+
+  #files
+  File(os.path.join(params.limits_conf_dir, 'hdfs.conf'),
+       owner='root',
+       group='root',
+       mode=0644,
+       content=Template("hdfs.conf.j2")
+  )
+  if params.security_enabled:
+    File(os.path.join(params.hadoop_bin, "task-controller"),
+         owner="root",
+         group=params.mapred_tt_group,
+         mode=06050
+    )
+    tc_mode = 0644
+    tc_owner = "root"
+  else:
+    tc_mode = None
+    tc_owner = params.hdfs_user
+
+  if tc_mode:
+    File(os.path.join(params.hadoop_conf_dir, 'taskcontroller.cfg'),
+         owner = tc_owner,
+         mode = tc_mode,
+         group = params.mapred_tt_group,
+         content=Template("taskcontroller.cfg.j2")
+    )
+  else:
+    File(os.path.join(params.hadoop_conf_dir, 'taskcontroller.cfg'),
+         owner=tc_owner,
+         content=Template("taskcontroller.cfg.j2")
+    )
+  for file in ['hadoop-env.sh', 'commons-logging.properties', 'slaves']:
+    File(os.path.join(params.hadoop_conf_dir, file),
+         owner=tc_owner,
+         content=Template(file + ".j2")
+    )
+
+  health_check_template = "health_check" #for stack 1 use 'health_check'
+  File(os.path.join(params.hadoop_conf_dir, "health_check"),
+       owner=tc_owner,
+       content=Template(health_check_template + ".j2")
+  )
+
+  File(os.path.join(params.hadoop_conf_dir, "log4j.properties"),
+       owner=params.hdfs_user,
+       content=Template("log4j.properties.j2")
+  )
+
+  update_log4j_props(os.path.join(params.hadoop_conf_dir, "log4j.properties"))
+
+  File(os.path.join(params.hadoop_conf_dir, "hadoop-metrics2.properties"),
+       owner=params.hdfs_user,
+       content=Template("hadoop-metrics2.properties.j2")
+  )
+
+  db_driver_dload_cmd = ""
+  if params.server_db_name == 'oracle' and params.oracle_driver_url != "":
+    db_driver_dload_cmd = format(
+      "curl -kf --retry 5 {oracle_driver_url} -o {hadoop_lib_home}/{db_driver_filename}")
+  elif params.server_db_name == 'mysql' and params.mysql_driver_url != "":
+    db_driver_dload_cmd = format(
+      "curl -kf --retry 5 {mysql_driver_url} -o {hadoop_lib_home}/{db_driver_filename}")
+
+  if db_driver_dload_cmd:
+    Execute(db_driver_dload_cmd,
+            not_if =format("test -e {hadoop_lib_home}/{db_driver_filename}")
+    )
+
+
+def setup_configs():
+  """
+  Creates configs for services DHFS mapred
+  """
+  import params
+
+  if "mapred-queue-acls" in params.config['configurations']:
+    XmlConfig("mapred-queue-acls.xml",
+              conf_dir=params.hadoop_conf_dir,
+              configurations=params.config['configurations'][
+                'mapred-queue-acls'],
+              owner=params.mapred_user,
+              group=params.user_group
+    )
+  elif os.path.exists(
+      os.path.join(params.hadoop_conf_dir, "mapred-queue-acls.xml")):
+    File(os.path.join(params.hadoop_conf_dir, "mapred-queue-acls.xml"),
+         owner=params.mapred_user,
+         group=params.user_group
+    )
+
+  if "hadoop-policy" in params.config['configurations']:
+    XmlConfig("hadoop-policy.xml",
+              conf_dir=params.hadoop_conf_dir,
+              configurations=params.config['configurations']['hadoop-policy'],
+              owner=params.hdfs_user,
+              group=params.user_group
+    )
+
+  XmlConfig("core-site.xml",
+            conf_dir=params.hadoop_conf_dir,
+            configurations=params.config['configurations']['core-site'],
+            owner=params.hdfs_user,
+            group=params.user_group
+  )
+
+  if "mapred-site" in params.config['configurations']:
+    XmlConfig("mapred-site.xml",
+              conf_dir=params.hadoop_conf_dir,
+              configurations=params.config['configurations']['mapred-site'],
+              owner=params.mapred_user,
+              group=params.user_group
+    )
+
+  File(params.task_log4j_properties_location,
+       content=StaticFile("task-log4j.properties"),
+       mode=0755
+  )
+
+  if "capacity-scheduler" in params.config['configurations']:
+    XmlConfig("capacity-scheduler.xml",
+              conf_dir=params.hadoop_conf_dir,
+              configurations=params.config['configurations'][
+                'capacity-scheduler'],
+              owner=params.hdfs_user,
+              group=params.user_group
+    )
+
+  XmlConfig("hdfs-site.xml",
+            conf_dir=params.hadoop_conf_dir,
+            configurations=params.config['configurations']['hdfs-site'],
+            owner=params.hdfs_user,
+            group=params.user_group
+  )
+
+  # if params.stack_version[0] == "1":
+  Link('/usr/lib/hadoop/lib/hadoop-tools.jar',
+       to = '/usr/lib/hadoop/hadoop-tools.jar'
+  )
+
+  if os.path.exists(os.path.join(params.hadoop_conf_dir, 'configuration.xsl')):
+    File(os.path.join(params.hadoop_conf_dir, 'configuration.xsl'),
+         owner=params.hdfs_user,
+         group=params.user_group
+    )
+  if os.path.exists(os.path.join(params.hadoop_conf_dir, 'fair-scheduler.xml')):
+    File(os.path.join(params.hadoop_conf_dir, 'fair-scheduler.xml'),
+         owner=params.mapred_user,
+         group=params.user_group
+    )
+  if os.path.exists(os.path.join(params.hadoop_conf_dir, 'masters')):
+    File(os.path.join(params.hadoop_conf_dir, 'masters'),
+              owner=params.hdfs_user,
+              group=params.user_group
+    )
+  if os.path.exists(
+      os.path.join(params.hadoop_conf_dir, 'ssl-client.xml.example')):
+    File(os.path.join(params.hadoop_conf_dir, 'ssl-client.xml.example'),
+         owner=params.mapred_user,
+         group=params.user_group
+    )
+  if os.path.exists(
+      os.path.join(params.hadoop_conf_dir, 'ssl-server.xml.example')):
+    File(os.path.join(params.hadoop_conf_dir, 'ssl-server.xml.example'),
+         owner=params.mapred_user,
+         group=params.user_group
+    )
+
+  # generate_exlude_file()
+  # generate_include_file()
+
+def update_log4j_props(file):
+  import params
+
+  property_map = {
+    'ambari.jobhistory.database': params.ambari_db_rca_url,
+    'ambari.jobhistory.driver': params.ambari_db_rca_driver,
+    'ambari.jobhistory.user': params.ambari_db_rca_username,
+    'ambari.jobhistory.password': params.ambari_db_rca_password,
+    'ambari.jobhistory.logger': 'DEBUG,JHA',
+
+    'log4j.appender.JHA': 'org.apache.ambari.log4j.hadoop.mapreduce.jobhistory.JobHistoryAppender',
+    'log4j.appender.JHA.database': '${ambari.jobhistory.database}',
+    'log4j.appender.JHA.driver': '${ambari.jobhistory.driver}',
+    'log4j.appender.JHA.user': '${ambari.jobhistory.user}',
+    'log4j.appender.JHA.password': '${ambari.jobhistory.password}',
+
+    'log4j.logger.org.apache.hadoop.mapred.JobHistory$JobHistoryLogger': '${ambari.jobhistory.logger}',
+    'log4j.additivity.org.apache.hadoop.mapred.JobHistory$JobHistoryLogger': 'true'
+  }
+  for key in property_map:
+    value = property_map[key]
+    Execute(format(
+      "sed -i 's~\\({rca_disabled_prefix}\\)\\?{key}=.*~{rca_prefix}{key}={value}~' {file}"))
+
+
+def generate_exlude_file():
+  import params
+
+  File(params.exlude_file_path,
+       content=Template("exclude_hosts_list.j2"),
+       owner=params.hdfs_user,
+       group=params.user_group
+  )
+
+
+def generate_include_file():
+  import params
+
+  if params.dfs_hosts and params.has_slaves:
+    include_hosts_list = params.slave_hosts
+    File(params.dfs_hosts,
+         content=Template("include_hosts_list.j2"),
+         owner=params.hdfs_user,
+         group=params.user_group
+    )
+
+
+def install_snappy():
+  import params
+
+  snappy_so = "libsnappy.so"
+  so_target_dir_x86 = format("{hadoop_lib_home}/native/Linux-i386-32")
+  so_target_dir_x64 = format("{hadoop_lib_home}/native/Linux-amd64-64")
+  so_target_x86 = format("{so_target_dir_x86}/{snappy_so}")
+  so_target_x64 = format("{so_target_dir_x64}/{snappy_so}")
+  so_src_dir_x86 = format("{hadoop_home}/lib")
+  so_src_dir_x64 = format("{hadoop_home}/lib64")
+  so_src_x86 = format("{so_src_dir_x86}/{snappy_so}")
+  so_src_x64 = format("{so_src_dir_x64}/{snappy_so}")
+  Execute(
+    format("mkdir -p {so_target_dir_x86}; ln -sf {so_src_x86} {so_target_x86}"))
+  Execute(
+    format("mkdir -p {so_target_dir_x64}; ln -sf {so_src_x64} {so_target_x64}"))

+ 25 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/templates/commons-logging.properties.j2

@@ -0,0 +1,25 @@
+#/*
+# * Licensed to the Apache Software Foundation (ASF) under one
+# * or more contributor license agreements.  See the NOTICE file
+# * distributed with this work for additional information
+# * regarding copyright ownership.  The ASF licenses this file
+# * to you under the Apache License, Version 2.0 (the
+# * "License"); you may not use this file except in compliance
+# * with the License.  You may obtain a copy of the License at
+# *
+# *     http://www.apache.org/licenses/LICENSE-2.0
+# *
+# * Unless required by applicable law or agreed to in writing, software
+# * distributed under the License is distributed on an "AS IS" BASIS,
+# * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# * See the License for the specific language governing permissions and
+# * limitations under the License.
+# */
+
+#Logging Implementation
+
+#Log4J
+org.apache.commons.logging.Log=org.apache.commons.logging.impl.Log4JLogger
+
+#JDK Logger
+#org.apache.commons.logging.Log=org.apache.commons.logging.impl.Jdk14Logger

+ 3 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/templates/exclude_hosts_list.j2

@@ -0,0 +1,3 @@
+{% for host in hdfs_exclude_file %}
+{{host}}
+{% endfor %}

+ 121 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/templates/hadoop-env.sh.j2

@@ -0,0 +1,121 @@
+#/*
+# * Licensed to the Apache Software Foundation (ASF) under one
+# * or more contributor license agreements.  See the NOTICE file
+# * distributed with this work for additional information
+# * regarding copyright ownership.  The ASF licenses this file
+# * to you under the Apache License, Version 2.0 (the
+# * "License"); you may not use this file except in compliance
+# * with the License.  You may obtain a copy of the License at
+# *
+# *     http://www.apache.org/licenses/LICENSE-2.0
+# *
+# * Unless required by applicable law or agreed to in writing, software
+# * distributed under the License is distributed on an "AS IS" BASIS,
+# * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# * See the License for the specific language governing permissions and
+# * limitations under the License.
+# */
+
+# Set Hadoop-specific environment variables here.
+
+# The only required environment variable is JAVA_HOME.  All others are
+# optional.  When running a distributed configuration it is best to
+# set JAVA_HOME in this file, so that it is correctly defined on
+# remote nodes.
+
+# The java implementation to use.  Required.
+export JAVA_HOME={{java_home}}
+export HADOOP_HOME_WARN_SUPPRESS=1
+
+# Hadoop Configuration Directory
+#TODO: if env var set that can cause problems
+export HADOOP_CONF_DIR=${HADOOP_CONF_DIR:-{{hadoop_conf_dir}}}
+
+# this is different for HDP1 #
+# Path to jsvc required by secure HDP 2.0 datanode
+# export JSVC_HOME={{jsvc_path}}
+
+
+# The maximum amount of heap to use, in MB. Default is 1000.
+export HADOOP_HEAPSIZE="{{hadoop_heapsize}}"
+
+export HADOOP_NAMENODE_INIT_HEAPSIZE="-Xms{{namenode_heapsize}}"
+
+# Extra Java runtime options.  Empty by default.
+export HADOOP_OPTS="-Djava.net.preferIPv4Stack=true ${HADOOP_OPTS}"
+
+# Command specific options appended to HADOOP_OPTS when specified
+export HADOOP_NAMENODE_OPTS="-server -XX:ParallelGCThreads=8 -XX:+UseConcMarkSweepGC -XX:ErrorFile={{hdfs_log_dir_prefix}}/$USER/hs_err_pid%p.log -XX:NewSize={{namenode_opt_newsize}} -XX:MaxNewSize={{namenode_opt_maxnewsize}} -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 ${HADOOP_NAMENODE_OPTS}"
+HADOOP_JOBTRACKER_OPTS="-server -XX:ParallelGCThreads=8 -XX:+UseConcMarkSweepGC -XX:ErrorFile={{hdfs_log_dir_prefix}}/$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:+PrintGCDateStamps -Xmx{{jtnode_heapsize}} -Dhadoop.security.logger=INFO,DRFAS -Dmapred.audit.logger=INFO,MRAUDIT -Dhadoop.mapreduce.jobsummary.logger=INFO,JSA ${HADOOP_JOBTRACKER_OPTS}"
+
+HADOOP_TASKTRACKER_OPTS="-server -Xmx{{ttnode_heapsize}} -Dhadoop.security.logger=ERROR,console -Dmapred.audit.logger=ERROR,console ${HADOOP_TASKTRACKER_OPTS}"
+HADOOP_DATANODE_OPTS="-Xmx{{dtnode_heapsize}} -Dhadoop.security.logger=ERROR,DRFAS ${HADOOP_DATANODE_OPTS}"
+HADOOP_BALANCER_OPTS="-server -Xmx{{hadoop_heapsize}}m ${HADOOP_BALANCER_OPTS}"
+
+export HADOOP_SECONDARYNAMENODE_OPTS="-server -XX:ParallelGCThreads=8 -XX:+UseConcMarkSweepGC -XX:ErrorFile={{hdfs_log_dir_prefix}}/$USER/hs_err_pid%p.log -XX:NewSize={{namenode_opt_newsize}} -XX:MaxNewSize={{namenode_opt_maxnewsize}} -Xloggc:{{hdfs_log_dir_prefix}}/$USER/gc.log-`date +'%Y%m%d%H%M'` -verbose:gc -XX:+PrintGCDetails -XX:+PrintGCTimeStamps -XX:+PrintGCDateStamps ${HADOOP_NAMENODE_INIT_HEAPSIZE} -Xmx{{namenode_heapsize}} -Dhadoop.security.logger=INFO,DRFAS -Dhdfs.audit.logger=INFO,DRFAAUDIT ${HADOOP_SECONDARYNAMENODE_OPTS}"
+
+# The following applies to multiple commands (fs, dfs, fsck, distcp etc)
+export HADOOP_CLIENT_OPTS="-Xmx${HADOOP_HEAPSIZE}m $HADOOP_CLIENT_OPTS"
+# On secure datanodes, user to run the datanode as after dropping privileges
+export HADOOP_SECURE_DN_USER={{hdfs_user}}
+
+# Extra ssh options.  Empty by default.
+export HADOOP_SSH_OPTS="-o ConnectTimeout=5 -o SendEnv=HADOOP_CONF_DIR"
+
+# Where log files are stored.  $HADOOP_HOME/logs by default.
+export HADOOP_LOG_DIR={{hdfs_log_dir_prefix}}/$USER
+
+# History server logs
+export HADOOP_MAPRED_LOG_DIR={{mapred_log_dir_prefix}}/$USER
+
+# Where log files are stored in the secure data environment.
+export HADOOP_SECURE_DN_LOG_DIR={{hdfs_log_dir_prefix}}/$HADOOP_SECURE_DN_USER
+
+# File naming remote slave hosts.  $HADOOP_HOME/conf/slaves by default.
+# export HADOOP_SLAVES=${HADOOP_HOME}/conf/slaves
+
+# host:path where hadoop code should be rsync'd from.  Unset by default.
+# export HADOOP_MASTER=master:/home/$USER/src/hadoop
+
+# Seconds to sleep between slave commands.  Unset by default.  This
+# can be useful in large clusters, where, e.g., slave rsyncs can
+# otherwise arrive faster than the master can service them.
+# export HADOOP_SLAVE_SLEEP=0.1
+
+# The directory where pid files are stored. /tmp by default.
+export HADOOP_PID_DIR={{hadoop_pid_dir_prefix}}/$USER
+export HADOOP_SECURE_DN_PID_DIR={{hadoop_pid_dir_prefix}}/$HADOOP_SECURE_DN_USER
+
+# History server pid
+export HADOOP_MAPRED_PID_DIR={{mapred_pid_dir_prefix}}/$USER
+
+YARN_RESOURCEMANAGER_OPTS="-Dyarn.server.resourcemanager.appsummary.logger=INFO,RMSUMMARY"
+
+# A string representing this instance of hadoop. $USER by default.
+export HADOOP_IDENT_STRING=$USER
+
+# The scheduling priority for daemon processes.  See 'man nice'.
+
+# export HADOOP_NICENESS=10
+
+# Use libraries from standard classpath
+JAVA_JDBC_LIBS=""
+#Add libraries required by mysql connector
+for jarFile in `ls /usr/share/java/*mysql* 2>/dev/null`
+do
+  JAVA_JDBC_LIBS=${JAVA_JDBC_LIBS}:$jarFile
+done
+#Add libraries required by oracle connector
+for jarFile in `ls /usr/share/java/*ojdbc* 2>/dev/null`
+do
+  JAVA_JDBC_LIBS=${JAVA_JDBC_LIBS}:$jarFile
+done
+#Add libraries required by nodemanager
+MAPREDUCE_LIBS={{mapreduce_libs_path}}
+export HADOOP_CLASSPATH=${HADOOP_CLASSPATH}${JAVA_JDBC_LIBS}:${MAPREDUCE_LIBS}
+
+# Setting path to hdfs command line
+export HADOOP_LIBEXEC_DIR={{hadoop_libexec_dir}}
+
+#Mostly required for hadoop 2.0
+export JAVA_LIBRARY_PATH=${JAVA_LIBRARY_PATH}:/usr/lib/hadoop/lib/native/Linux-amd64-64

+ 45 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/templates/hadoop-metrics2.properties.j2

@@ -0,0 +1,45 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements. See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# syntax: [prefix].[source|sink|jmx].[instance].[options]
+# See package.html for org.apache.hadoop.metrics2 for details
+
+{% if has_ganglia_server %}
+*.period=60
+
+*.sink.ganglia.class=org.apache.hadoop.metrics2.sink.ganglia.GangliaSink31
+*.sink.ganglia.period=10
+
+# default for supportsparse is false
+*.sink.ganglia.supportsparse=true
+
+.sink.ganglia.slope=jvm.metrics.gcCount=zero,jvm.metrics.memHeapUsedM=both
+.sink.ganglia.dmax=jvm.metrics.threadsBlocked=70,jvm.metrics.memHeapUsedM=40
+
+# Hook up to the server
+namenode.sink.ganglia.servers={{ganglia_server_host}}:8661
+datanode.sink.ganglia.servers={{ganglia_server_host}}:8660
+jobtracker.sink.ganglia.servers={{ganglia_server_host}}:8662
+tasktracker.sink.ganglia.servers={{ganglia_server_host}}:8660
+maptask.sink.ganglia.servers={{ganglia_server_host}}:8660
+reducetask.sink.ganglia.servers={{ganglia_server_host}}:8660
+resourcemanager.sink.ganglia.servers={{ganglia_server_host}}:8664
+nodemanager.sink.ganglia.servers={{ganglia_server_host}}:8660
+historyserver.sink.ganglia.servers={{ganglia_server_host}}:8666
+journalnode.sink.ganglia.servers={{ganglia_server_host}}:8660
+
+resourcemanager.sink.ganglia.tagsForPrefix.yarn=Queue
+
+{% endif %}

+ 17 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/templates/hdfs.conf.j2

@@ -0,0 +1,17 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+{{hdfs_user}}   - nofile 32768
+{{hdfs_user}}   - nproc  65536

+ 91 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/templates/health_check-v2.j2

@@ -0,0 +1,91 @@
+#!/bin/bash
+#
+#/*
+# * Licensed to the Apache Software Foundation (ASF) under one
+# * or more contributor license agreements.  See the NOTICE file
+# * distributed with this work for additional information
+# * regarding copyright ownership.  The ASF licenses this file
+# * to you under the Apache License, Version 2.0 (the
+# * "License"); you may not use this file except in compliance
+# * with the License.  You may obtain a copy of the License at
+# *
+# *     http://www.apache.org/licenses/LICENSE-2.0
+# *
+# * Unless required by applicable law or agreed to in writing, software
+# * distributed under the License is distributed on an "AS IS" BASIS,
+# * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# * See the License for the specific language governing permissions and
+# * limitations under the License.
+# */
+
+err=0;
+
+function check_disks {
+
+  for m in `awk '$3~/ext3/ {printf" %s ",$2}' /etc/fstab` ; do
+    fsdev=""
+    fsdev=`awk -v m=$m '$2==m {print $1}' /proc/mounts`;
+    if [ -z "$fsdev" -a "$m" != "/mnt" ] ; then
+      msg_="$msg_ $m(u)"
+    else
+      msg_="$msg_`awk -v m=$m '$2==m { if ( $4 ~ /^ro,/ ) {printf"%s(ro)",$2 } ; }' /proc/mounts`"
+    fi
+  done
+
+  if [ -z "$msg_" ] ; then
+    echo "disks ok" ; exit 0
+  else
+    echo "$msg_" ; exit 2
+  fi
+
+}
+
+function check_link {
+  snmp=/usr/bin/snmpwalk
+  if [ -e $snmp ] ; then
+    $snmp -t 5 -Oe  -Oq  -Os -v 1 -c public localhost if | \
+    awk ' {
+      split($1,a,".") ;
+      if ( a[1] == "ifIndex" ) { ifIndex[a[2]] = $2 }
+      if ( a[1] == "ifDescr" ) { ifDescr[a[2]] = $2 }
+      if ( a[1] == "ifType" ) { ifType[a[2]] = $2 }
+      if ( a[1] == "ifSpeed" ) { ifSpeed[a[2]] = $2 }
+      if ( a[1] == "ifAdminStatus" ) { ifAdminStatus[a[2]] = $2 }
+      if ( a[1] == "ifOperStatus" ) { ifOperStatus[a[2]] = $2 }
+    }
+    END {
+      up=0;
+      for (i in ifIndex ) {
+      if ( ifType[i] == 6 && ifAdminStatus[i] == 1 && ifOperStatus[i] == 1 && ifSpeed[i] == 1000000000 ) {
+      up=i;
+      }
+      }
+      if ( up == 0 ) { print "check link" ; exit 2 }
+      else { print ifDescr[up],"ok" }
+    }'
+    exit $? ;
+  fi
+}
+
+# Run all checks
+# Disabled 'check_link' for now... 
+for check in disks ; do
+  msg=`check_${check}` ;
+  if [ $? -eq 0 ] ; then
+    ok_msg="$ok_msg$msg,"
+  else
+    err_msg="$err_msg$msg,"
+  fi
+done
+
+if [ ! -z "$err_msg" ] ; then
+  echo -n "ERROR $err_msg "
+fi
+if [ ! -z "$ok_msg" ] ; then
+  echo -n "OK: $ok_msg"
+fi
+
+echo
+
+# Success!
+exit 0

+ 118 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/templates/health_check.j2

@@ -0,0 +1,118 @@
+#!/bin/bash
+#
+#/*
+# * Licensed to the Apache Software Foundation (ASF) under one
+# * or more contributor license agreements.  See the NOTICE file
+# * distributed with this work for additional information
+# * regarding copyright ownership.  The ASF licenses this file
+# * to you under the Apache License, Version 2.0 (the
+# * "License"); you may not use this file except in compliance
+# * with the License.  You may obtain a copy of the License at
+# *
+# *     http://www.apache.org/licenses/LICENSE-2.0
+# *
+# * Unless required by applicable law or agreed to in writing, software
+# * distributed under the License is distributed on an "AS IS" BASIS,
+# * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# * See the License for the specific language governing permissions and
+# * limitations under the License.
+# */
+
+err=0;
+
+function check_disks {
+
+  for m in `awk '$3~/ext3/ {printf" %s ",$2}' /etc/fstab` ; do
+    fsdev=""
+    fsdev=`awk -v m=$m '$2==m {print $1}' /proc/mounts`;
+    if [ -z "$fsdev" ] ; then
+      msg_="$msg_ $m(u)"
+    else
+      msg_="$msg_`awk -v m=$m '$2==m { if ( $4 ~ /^ro,/ ) {printf"%s(ro)",$2 } ; }' /proc/mounts`"
+    fi
+  done
+
+  if [ -z "$msg_" ] ; then
+    echo "disks ok" ; exit 0
+  else
+    echo "$msg_" ; exit 2
+  fi
+
+}
+
+function check_taskcontroller {
+  if [ "<%=scope.function_hdp_template_var("::hdp::params::security_enabled")%>" == "true" ]; then
+    perm=`stat -c %a:%U:%G <%=scope.function_hdp_template_var("task_bin_exe")%> 2>/dev/null`
+    if [ $? -eq 0 ] && [ "$perm" == "6050:root:hadoop" ] ; then
+      echo "taskcontroller ok"
+    else
+      echo 'check taskcontroller' ; exit 1
+    fi
+  fi
+}
+
+function check_jetty {
+  hname=`hostname`
+  jmx=`curl -s -S -m 5 "http://$hname:<%=scope.function_hdp_template_var("::hdp::tasktracker_port")%>/jmx?qry=Hadoop:service=TaskTracker,name=ShuffleServerMetrics" 2>/dev/null` ;
+  if [ $? -eq 0 ] ; then
+    e=`echo $jmx | awk '/shuffle_exceptions_caught/ {printf"%d",$2}'` ;
+    e=${e:-0} # no jmx servlet ?
+    if [ $e -gt 10 ] ; then
+      echo "check jetty: shuffle_exceptions=$e" ; exit 1
+    else
+      echo "jetty ok"
+    fi
+  else
+    echo "check jetty: ping failed" ; exit 1
+  fi
+}
+
+function check_link {
+  snmp=/usr/bin/snmpwalk
+  if [ -e $snmp ] ; then
+    $snmp -t 5 -Oe  -Oq  -Os -v 1 -c public localhost if | \
+    awk ' {
+      split($1,a,".") ;
+      if ( a[1] == "ifIndex" ) { ifIndex[a[2]] = $2 }
+      if ( a[1] == "ifDescr" ) { ifDescr[a[2]] = $2 }
+      if ( a[1] == "ifType" ) { ifType[a[2]] = $2 }
+      if ( a[1] == "ifSpeed" ) { ifSpeed[a[2]] = $2 }
+      if ( a[1] == "ifAdminStatus" ) { ifAdminStatus[a[2]] = $2 }
+      if ( a[1] == "ifOperStatus" ) { ifOperStatus[a[2]] = $2 }
+    }
+    END {
+      up=0;
+      for (i in ifIndex ) {
+      if ( ifType[i] == 6 && ifAdminStatus[i] == 1 && ifOperStatus[i] == 1 && ifSpeed[i] == 1000000000 ) {
+      up=i;
+      }
+      }
+      if ( up == 0 ) { print "check link" ; exit 2 }
+      else { print ifDescr[up],"ok" }
+    }'
+    exit $? ;
+  fi
+}
+
+# Run all checks
+# Disabled 'check_link' for now... 
+for check in disks taskcontroller jetty; do
+  msg=`check_${check}` ;
+  if [ $? -eq 0 ] ; then
+    ok_msg="$ok_msg$msg,"
+  else
+    err_msg="$err_msg$msg,"
+  fi
+done
+
+if [ ! -z "$err_msg" ] ; then
+  echo -n "ERROR $err_msg "
+fi
+if [ ! -z "$ok_msg" ] ; then
+  echo -n "OK: $ok_msg"
+fi
+
+echo
+
+# Success!
+exit 0

+ 3 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/templates/include_hosts_list.j2

@@ -0,0 +1,3 @@
+{% for host in slave_hosts %}
+{{host}}
+{% endfor %}

+ 200 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/templates/log4j.properties.j2

@@ -0,0 +1,200 @@
+# Copyright 2011 The Apache Software Foundation
+# 
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# Define some default values that can be overridden by system properties
+hadoop.root.logger=INFO,console
+hadoop.log.dir=.
+hadoop.log.file=hadoop.log
+
+
+# Define the root logger to the system property "hadoop.root.logger".
+log4j.rootLogger=${hadoop.root.logger}, EventCounter
+
+# Logging Threshold
+log4j.threshhold=ALL
+
+#
+# Daily Rolling File Appender
+#
+
+log4j.appender.DRFA=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.DRFA.File=${hadoop.log.dir}/${hadoop.log.file}
+
+# Rollver at midnight
+log4j.appender.DRFA.DatePattern=.yyyy-MM-dd
+
+# 30-day backup
+#log4j.appender.DRFA.MaxBackupIndex=30
+log4j.appender.DRFA.layout=org.apache.log4j.PatternLayout
+
+# Pattern format: Date LogLevel LoggerName LogMessage
+log4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
+# Debugging Pattern format
+#log4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n
+
+
+#
+# console
+# Add "console" to rootlogger above if you want to use this 
+#
+
+log4j.appender.console=org.apache.log4j.ConsoleAppender
+log4j.appender.console.target=System.err
+log4j.appender.console.layout=org.apache.log4j.PatternLayout
+log4j.appender.console.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{2}: %m%n
+
+#
+# TaskLog Appender
+#
+
+#Default values
+hadoop.tasklog.taskid=null
+hadoop.tasklog.iscleanup=false
+hadoop.tasklog.noKeepSplits=4
+hadoop.tasklog.totalLogFileSize=100
+hadoop.tasklog.purgeLogSplits=true
+hadoop.tasklog.logsRetainHours=12
+
+log4j.appender.TLA=org.apache.hadoop.mapred.TaskLogAppender
+log4j.appender.TLA.taskId=${hadoop.tasklog.taskid}
+log4j.appender.TLA.isCleanup=${hadoop.tasklog.iscleanup}
+log4j.appender.TLA.totalLogFileSize=${hadoop.tasklog.totalLogFileSize}
+
+log4j.appender.TLA.layout=org.apache.log4j.PatternLayout
+log4j.appender.TLA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
+
+#
+#Security audit appender
+#
+hadoop.security.logger=INFO,console
+hadoop.security.log.maxfilesize=256MB
+hadoop.security.log.maxbackupindex=20
+log4j.category.SecurityLogger=${hadoop.security.logger}
+hadoop.security.log.file=SecurityAuth.audit
+log4j.appender.DRFAS=org.apache.log4j.DailyRollingFileAppender 
+log4j.appender.DRFAS.File=${hadoop.log.dir}/${hadoop.security.log.file}
+log4j.appender.DRFAS.layout=org.apache.log4j.PatternLayout
+log4j.appender.DRFAS.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
+log4j.appender.DRFAS.DatePattern=.yyyy-MM-dd
+
+log4j.appender.RFAS=org.apache.log4j.RollingFileAppender 
+log4j.appender.RFAS.File=${hadoop.log.dir}/${hadoop.security.log.file}
+log4j.appender.RFAS.layout=org.apache.log4j.PatternLayout
+log4j.appender.RFAS.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
+log4j.appender.RFAS.MaxFileSize=${hadoop.security.log.maxfilesize}
+log4j.appender.RFAS.MaxBackupIndex=${hadoop.security.log.maxbackupindex}
+
+#
+# hdfs audit logging
+#
+hdfs.audit.logger=INFO,console
+log4j.logger.org.apache.hadoop.hdfs.server.namenode.FSNamesystem.audit=${hdfs.audit.logger}
+log4j.additivity.org.apache.hadoop.hdfs.server.namenode.FSNamesystem.audit=false
+log4j.appender.DRFAAUDIT=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.DRFAAUDIT.File=${hadoop.log.dir}/hdfs-audit.log
+log4j.appender.DRFAAUDIT.layout=org.apache.log4j.PatternLayout
+log4j.appender.DRFAAUDIT.layout.ConversionPattern=%d{ISO8601} %p %c{2}: %m%n
+log4j.appender.DRFAAUDIT.DatePattern=.yyyy-MM-dd
+
+#
+# mapred audit logging
+#
+mapred.audit.logger=INFO,console
+log4j.logger.org.apache.hadoop.mapred.AuditLogger=${mapred.audit.logger}
+log4j.additivity.org.apache.hadoop.mapred.AuditLogger=false
+log4j.appender.MRAUDIT=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.MRAUDIT.File=${hadoop.log.dir}/mapred-audit.log
+log4j.appender.MRAUDIT.layout=org.apache.log4j.PatternLayout
+log4j.appender.MRAUDIT.layout.ConversionPattern=%d{ISO8601} %p %c{2}: %m%n
+log4j.appender.MRAUDIT.DatePattern=.yyyy-MM-dd
+
+#
+# Rolling File Appender
+#
+
+log4j.appender.RFA=org.apache.log4j.RollingFileAppender
+log4j.appender.RFA.File=${hadoop.log.dir}/${hadoop.log.file}
+
+# Logfile size and and 30-day backups
+log4j.appender.RFA.MaxFileSize=256MB
+log4j.appender.RFA.MaxBackupIndex=10
+
+log4j.appender.RFA.layout=org.apache.log4j.PatternLayout
+log4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} - %m%n
+log4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n
+
+
+# Custom Logging levels
+
+hadoop.metrics.log.level=INFO
+#log4j.logger.org.apache.hadoop.mapred.JobTracker=DEBUG
+#log4j.logger.org.apache.hadoop.mapred.TaskTracker=DEBUG
+#log4j.logger.org.apache.hadoop.fs.FSNamesystem=DEBUG
+log4j.logger.org.apache.hadoop.metrics2=${hadoop.metrics.log.level}
+
+# Jets3t library
+log4j.logger.org.jets3t.service.impl.rest.httpclient.RestS3Service=ERROR
+
+#
+# Null Appender
+# Trap security logger on the hadoop client side
+#
+log4j.appender.NullAppender=org.apache.log4j.varia.NullAppender
+
+#
+# Event Counter Appender
+# Sends counts of logging messages at different severity levels to Hadoop Metrics.
+#
+log4j.appender.EventCounter=org.apache.hadoop.log.metrics.EventCounter
+
+{% if is_jtnode_master or is_rmnode_master %}
+#
+# Job Summary Appender 
+#
+# Use following logger to send summary to separate file defined by 
+# hadoop.mapreduce.jobsummary.log.file rolled daily:
+# hadoop.mapreduce.jobsummary.logger=INFO,JSA
+# 
+hadoop.mapreduce.jobsummary.logger=${hadoop.root.logger}
+hadoop.mapreduce.jobsummary.log.file=hadoop-mapreduce.jobsummary.log
+log4j.appender.JSA=org.apache.log4j.DailyRollingFileAppender
+
+log4j.appender.JSA.File={{hdfs_log_dir_prefix}}/{{mapred_user}}/${hadoop.mapreduce.jobsummary.log.file}
+
+log4j.appender.JSA.layout=org.apache.log4j.PatternLayout
+log4j.appender.JSA.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{2}: %m%n
+log4j.appender.JSA.DatePattern=.yyyy-MM-dd
+log4j.appender.JSA.layout=org.apache.log4j.PatternLayout
+log4j.logger.org.apache.hadoop.mapred.JobInProgress$JobSummary=${hadoop.mapreduce.jobsummary.logger}
+log4j.additivity.org.apache.hadoop.mapred.JobInProgress$JobSummary=false
+{% endif %}
+
+{{rca_prefix}}ambari.jobhistory.database={{ambari_db_rca_url}}
+{{rca_prefix}}ambari.jobhistory.driver={{ambari_db_rca_driver}}
+{{rca_prefix}}ambari.jobhistory.user={{ambari_db_rca_username}}
+{{rca_prefix}}ambari.jobhistory.password={{ambari_db_rca_password}}
+{{rca_prefix}}ambari.jobhistory.logger=DEBUG,JHA
+
+{{rca_prefix}}log4j.appender.JHA=org.apache.ambari.log4j.hadoop.mapreduce.jobhistory.JobHistoryAppender
+{{rca_prefix}}log4j.appender.JHA.database=${ambari.jobhistory.database}
+{{rca_prefix}}log4j.appender.JHA.driver=${ambari.jobhistory.driver}
+{{rca_prefix}}log4j.appender.JHA.user=${ambari.jobhistory.user}
+{{rca_prefix}}log4j.appender.JHA.password=${ambari.jobhistory.password}
+
+{{rca_prefix}}log4j.logger.org.apache.hadoop.mapred.JobHistory$JobHistoryLogger=${ambari.jobhistory.logger}
+{{rca_prefix}}log4j.additivity.org.apache.hadoop.mapred.JobHistory$JobHistoryLogger=true

+ 3 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/templates/slaves.j2

@@ -0,0 +1,3 @@
+{% for host in slave_hosts %}
+{{host}}
+{% endfor %}

+ 48 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/templates/snmpd.conf.j2

@@ -0,0 +1,48 @@
+#/*
+# * Licensed to the Apache Software Foundation (ASF) under one
+# * or more contributor license agreements.  See the NOTICE file
+# * distributed with this work for additional information
+# * regarding copyright ownership.  The ASF licenses this file
+# * to you under the Apache License, Version 2.0 (the
+# * "License"); you may not use this file except in compliance
+# * with the License.  You may obtain a copy of the License at
+# *
+# *     http://www.apache.org/licenses/LICENSE-2.0
+# *
+# * Unless required by applicable law or agreed to in writing, software
+# * distributed under the License is distributed on an "AS IS" BASIS,
+# * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# * See the License for the specific language governing permissions and
+# * limitations under the License.
+# */
+
+com2sec notConfigUser  {{snmp_source}}   {{snmp_community}}
+group   notConfigGroup v1           notConfigUser
+group   notConfigGroup v2c           notConfigUser
+view    systemview    included   .1
+access  notConfigGroup ""      any       noauth    exact  systemview none none
+
+syslocation Hadoop 
+syscontact HadoopMaster 
+dontLogTCPWrappersConnects yes
+
+###############################################################################
+# disk checks
+
+disk / 10000
+
+
+###############################################################################
+# load average checks
+#
+
+# load [1MAX=12.0] [5MAX=12.0] [15MAX=12.0]
+#
+# 1MAX:   If the 1 minute load average is above this limit at query
+#         time, the errorFlag will be set.
+# 5MAX:   Similar, but for 5 min average.
+# 15MAX:  Similar, but for 15 min average.
+
+# Check for loads:
+#load 12 14 14
+

+ 20 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/hooks/before-START/templates/taskcontroller.cfg.j2

@@ -0,0 +1,20 @@
+#/*
+# * Licensed to the Apache Software Foundation (ASF) under one
+# * or more contributor license agreements.  See the NOTICE file
+# * distributed with this work for additional information
+# * regarding copyright ownership.  The ASF licenses this file
+# * to you under the Apache License, Version 2.0 (the
+# * "License"); you may not use this file except in compliance
+# * with the License.  You may obtain a copy of the License at
+# *
+# *     http://www.apache.org/licenses/LICENSE-2.0
+# *
+# * Unless required by applicable law or agreed to in writing, software
+# * distributed under the License is distributed on an "AS IS" BASIS,
+# * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# * See the License for the specific language governing permissions and
+# * limitations under the License.
+# */
+mapred.local.dir={{mapred_local_dir}}
+mapreduce.tasktracker.group={{mapred_tt_group}}
+hadoop.log.dir={{hdfs_log_dir_prefix}}/{{mapred_user}}

+ 113 - 19
ambari-server/src/main/resources/stacks/HDP/1.3._/services/HDFS/metainfo.xml

@@ -16,35 +16,129 @@
    limitations under the License.
 -->
 <metainfo>
-    <user>root</user>
-    <comment>Apache Hadoop Distributed File System</comment>
-    <version>1.2.0.1.3.3.0</version>
+  <schemaVersion>2.0</schemaVersion>
+  <services>
+    <service>
+      <name>HDFS</name>
+      <comment>Apache Hadoop Distributed File System</comment>
+      <version>1.2.0.1.3.3.0</version>
 
-    <components>
+      <components>
         <component>
-            <name>NAMENODE</name>
-            <category>MASTER</category>
+          <name>NAMENODE</name>
+          <category>MASTER</category>
+          <commandScript>
+            <script>scripts/namenode.py</script>
+            <scriptType>PYTHON</scriptType>
+            <timeout>600</timeout>
+          </commandScript>
         </component>
 
         <component>
-            <name>DATANODE</name>
-            <category>SLAVE</category>
+          <name>DATANODE</name>
+          <category>SLAVE</category>
+          <commandScript>
+            <script>scripts/datanode.py</script>
+            <scriptType>PYTHON</scriptType>
+            <timeout>600</timeout>
+          </commandScript>
         </component>
 
         <component>
-            <name>SECONDARY_NAMENODE</name>
-            <category>MASTER</category>
+          <name>SECONDARY_NAMENODE</name>
+          <category>MASTER</category>
+          <commandScript>
+            <script>scripts/snamenode.py</script>
+            <scriptType>PYTHON</scriptType>
+            <timeout>600</timeout>
+          </commandScript>
         </component>
 
         <component>
-            <name>HDFS_CLIENT</name>
-            <category>CLIENT</category>
+          <name>HDFS_CLIENT</name>
+          <category>CLIENT</category>
+          <commandScript>
+            <script>scripts/hdfs_client.py</script>
+            <scriptType>PYTHON</scriptType>
+            <timeout>600</timeout>
+          </commandScript>
         </component>
-    </components>
-    <configuration-dependencies>
-      <config-type>core-site</config-type>
-      <config-type>global</config-type>
-      <config-type>hdfs-site</config-type>
-      <config-type>hadoop-policy</config-type>
-    </configuration-dependencies>
+      </components>
+      <osSpecifics>
+        <osSpecific>
+          <osType>any</osType>
+          <packages>
+            <package>
+              <type>rpm</type>
+              <name>net-snmp</name>
+            </package>
+            <package>
+              <type>rpm</type>
+              <name>net-snmp-utils</name>
+            </package>
+            <package>
+              <type>rpm</type>
+              <name>lzo</name>
+            </package>
+            <package>
+              <type>rpm</type>
+              <name>unzip</name>
+            </package>
+            <package>
+              <type>rpm</type>
+              <name>hadoop</name>
+            </package>
+            <package>
+              <type>rpm</type>
+              <name>hadoop-libhdfs</name>
+            </package>
+            <package>
+              <type>rpm</type>
+              <name>hadoop-native</name>
+            </package>
+            <package>
+              <type>rpm</type>
+              <name>hadoop-pipes</name>
+            </package>
+            <package>
+              <type>rpm</type>
+              <name>hadoop-sbin</name>
+            </package>
+            <package>
+              <type>rpm</type>
+              <name>hadoop-lzo</name>
+            </package>
+            <package>
+              <type>rpm</type>
+              <name>hadoop-lzo-native</name>
+            </package>
+            <package>
+              <type>rpm</type>
+              <name>snappy</name>
+            </package>
+            <package>
+              <type>rpm</type>
+              <name>snappy-devel</name>
+            </package>
+            <package>
+              <type>rpm</type>
+              <name>ambari-log4j</name>
+            </package>
+          </packages>
+        </osSpecific>
+      </osSpecifics>
+      <commandScript>
+        <script>scripts/service_check.py</script>
+        <scriptType>PYTHON</scriptType>
+        <timeout>300</timeout>
+      </commandScript>
+
+      <configuration-dependencies>
+        <config-type>core-site</config-type>
+        <config-type>global</config-type>
+        <config-type>hdfs-site</config-type>
+        <config-type>hadoop-policy</config-type>
+      </configuration-dependencies>
+    </service>
+  </services>
 </metainfo>

+ 62 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/services/HDFS/package/files/checkForFormat.sh

@@ -0,0 +1,62 @@
+#!/bin/sh
+#
+#
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+#
+#
+
+export hdfs_user=$1
+shift
+export conf_dir=$1
+shift
+export mark_dir=$1
+shift
+export name_dirs=$*
+
+export EXIT_CODE=0
+export command="namenode -format"
+export list_of_non_empty_dirs=""
+
+mark_file=/var/run/hadoop/hdfs/namenode-formatted
+if [[ -f ${mark_file} ]] ; then
+  rm -f ${mark_file}
+  mkdir -p ${mark_dir}
+fi
+
+if [[ ! -d $mark_dir ]] ; then
+  for dir in `echo $name_dirs | tr ',' ' '` ; do
+    echo "NameNode Dirname = $dir"
+    cmd="ls $dir | wc -l  | grep -q ^0$"
+    eval $cmd
+    if [[ $? -ne 0 ]] ; then
+      (( EXIT_CODE = $EXIT_CODE + 1 ))
+      list_of_non_empty_dirs="$list_of_non_empty_dirs $dir"
+    fi
+  done
+
+  if [[ $EXIT_CODE == 0 ]] ; then
+    su - ${hdfs_user} -c "yes Y | hadoop --config ${conf_dir} ${command}"
+  else
+    echo "ERROR: Namenode directory(s) is non empty. Will not format the namenode. List of non-empty namenode dirs ${list_of_non_empty_dirs}"
+  fi
+else
+  echo "${mark_dir} exists. Namenode DFS already formatted"
+fi
+
+exit $EXIT_CODE
+

+ 53 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/services/HDFS/package/files/checkWebUI.py

@@ -0,0 +1,53 @@
+#!/usr/bin/env python
+
+'''
+Licensed to the Apache Software Foundation (ASF) under one
+or more contributor license agreements.  See the NOTICE file
+distributed with this work for additional information
+regarding copyright ownership.  The ASF licenses this file
+to you under the Apache License, Version 2.0 (the
+"License"); you may not use this file except in compliance
+with the License.  You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+'''
+
+import optparse
+import httplib
+
+#
+# Main.
+#
+def main():
+  parser = optparse.OptionParser(usage="usage: %prog [options] component ")
+  parser.add_option("-m", "--hosts", dest="hosts", help="Comma separated hosts list for WEB UI to check it availability")
+  parser.add_option("-p", "--port", dest="port", help="Port of WEB UI to check it availability")
+
+  (options, args) = parser.parse_args()
+  
+  hosts = options.hosts.split(',')
+  port = options.port
+
+  for host in hosts:
+    try:
+      conn = httplib.HTTPConnection(host, port)
+      # This can be modified to get a partial url part to be sent with request
+      conn.request("GET", "/")
+      httpCode = conn.getresponse().status
+      conn.close()
+    except Exception:
+      httpCode = 404
+
+    if httpCode != 200:
+      print "Cannot access WEB UI on: http://" + host + ":" + port
+      exit(1)
+      
+
+if __name__ == "__main__":
+  main()

+ 57 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/services/HDFS/package/scripts/datanode.py

@@ -0,0 +1,57 @@
+"""
+Licensed to the Apache Software Foundation (ASF) under one
+or more contributor license agreements.  See the NOTICE file
+distributed with this work for additional information
+regarding copyright ownership.  The ASF licenses this file
+to you under the Apache License, Version 2.0 (the
+"License"); you may not use this file except in compliance
+with the License.  You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+
+"""
+
+from resource_management import *
+from hdfs_datanode import datanode
+
+
+class DataNode(Script):
+  def install(self, env):
+    import params
+
+    self.install_packages(env)
+    env.set_params(params)
+
+  def start(self, env):
+    import params
+
+    env.set_params(params)
+    self.config(env)
+    datanode(action="start")
+
+  def stop(self, env):
+    import params
+
+    env.set_params(params)
+    datanode(action="stop")
+
+  def config(self, env):
+    import params
+
+    datanode(action="configure")
+
+  def status(self, env):
+    import status_params
+
+    env.set_params(status_params)
+    check_process_status(status_params.datanode_pid_file)
+
+
+if __name__ == "__main__":
+  DataNode().execute()

+ 49 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/services/HDFS/package/scripts/hdfs_client.py

@@ -0,0 +1,49 @@
+"""
+Licensed to the Apache Software Foundation (ASF) under one
+or more contributor license agreements.  See the NOTICE file
+distributed with this work for additional information
+regarding copyright ownership.  The ASF licenses this file
+to you under the Apache License, Version 2.0 (the
+"License"); you may not use this file except in compliance
+with the License.  You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+
+"""
+
+from resource_management import *
+from utils import service
+
+
+class HdfsClient(Script):
+  def install(self, env):
+    import params
+
+    self.install_packages(env)
+    env.set_params(params)
+    self.config(env)
+
+  def start(self, env):
+    import params
+
+    env.set_params(params)
+
+  def stop(self, env):
+    import params
+
+    env.set_params(params)
+
+  def config(self, env):
+    import params
+
+    pass
+
+
+if __name__ == "__main__":
+  HdfsClient().execute()

+ 59 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/services/HDFS/package/scripts/hdfs_datanode.py

@@ -0,0 +1,59 @@
+"""
+Licensed to the Apache Software Foundation (ASF) under one
+or more contributor license agreements.  See the NOTICE file
+distributed with this work for additional information
+regarding copyright ownership.  The ASF licenses this file
+to you under the Apache License, Version 2.0 (the
+"License"); you may not use this file except in compliance
+with the License.  You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+
+"""
+
+from resource_management import *
+from utils import service
+import os
+
+def datanode(action=None):
+  import params
+
+  if action == "configure":
+    Directory(params.dfs_domain_socket_dir,
+              recursive=True,
+              mode=0750,
+              owner=params.hdfs_user,
+              group=params.user_group)
+    Directory(os.path.dirname(params.dfs_data_dir),
+              recursive=True,
+              mode=0755)
+    Directory(params.dfs_data_dir,
+              recursive=False,
+              mode=0750,
+              owner=params.hdfs_user,
+              group=params.user_group)
+
+  if action == "start":
+    service(
+      action=action, name="datanode",
+      user=params.hdfs_user,
+      create_pid_dir=True,
+      create_log_dir=True,
+      keytab=params.dfs_datanode_keytab_file,
+      principal=params.dfs_datanode_kerberos_principal
+    )
+  if action == "stop":
+    service(
+      action=action, name="datanode",
+      user=params.hdfs_user,
+      create_pid_dir=True,
+      create_log_dir=True,
+      keytab=params.dfs_datanode_keytab_file,
+      principal=params.dfs_datanode_kerberos_principal
+    )

+ 179 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/services/HDFS/package/scripts/hdfs_namenode.py

@@ -0,0 +1,179 @@
+"""
+Licensed to the Apache Software Foundation (ASF) under one
+or more contributor license agreements.  See the NOTICE file
+distributed with this work for additional information
+regarding copyright ownership.  The ASF licenses this file
+to you under the Apache License, Version 2.0 (the
+"License"); you may not use this file except in compliance
+with the License.  You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+
+"""
+
+from resource_management import *
+from utils import service
+from utils import hdfs_directory
+import urlparse
+
+
+def namenode(action=None, format=True):
+  import params
+
+  if action == "configure":
+    create_name_dirs(params.dfs_name_dir)
+
+  if action == "start":
+    if format:
+      format_namenode()
+      pass
+    service(
+      action="start", name="namenode", user=params.hdfs_user,
+      keytab=params.dfs_namenode_keytab_file,
+      create_pid_dir=True,
+      create_log_dir=True,
+      principal=params.dfs_namenode_kerberos_principal
+    )
+
+    # TODO: extract creating of dirs to different services
+    create_app_directories()
+    create_user_directories()
+
+  if action == "stop":
+    service(
+      action="stop", name="namenode", user=params.hdfs_user,
+      keytab=params.dfs_namenode_keytab_file,
+      principal=params.dfs_namenode_kerberos_principal
+    )
+
+
+def create_name_dirs(directories):
+  import params
+
+  dirs = directories.split(",")
+  Directory(dirs,
+            mode=0755,
+            owner=params.hdfs_user,
+            group=params.user_group,
+            recursive=True
+  )
+
+
+def create_app_directories():
+  import params
+
+  hdfs_directory(name="/tmp",
+                 owner=params.hdfs_user,
+                 mode="777"
+  )
+  #mapred directories
+  if params.has_jobtracker:
+    hdfs_directory(name="/mapred",
+                   owner=params.mapred_user
+    )
+    hdfs_directory(name="/mapred/system",
+                   owner=params.mapred_user
+    )
+    #hbase directories
+  if len(params.hbase_master_hosts) != 0:
+    hdfs_directory(name=params.hbase_hdfs_root_dir,
+                   owner=params.hbase_user
+    )
+    hdfs_directory(name=params.hbase_staging_dir,
+                   owner=params.hbase_user,
+                   mode="711"
+    )
+    #hive directories
+  if len(params.hive_server_host) != 0:
+    hdfs_directory(name=params.hive_apps_whs_dir,
+                   owner=params.hive_user,
+                   mode="777"
+    )
+  if len(params.hcat_server_hosts) != 0:
+    hdfs_directory(name=params.webhcat_apps_dir,
+                   owner=params.webhcat_user,
+                   mode="755"
+    )
+  if len(params.hs_host) != 0:
+    if params.yarn_log_aggregation_enabled:
+      hdfs_directory(name=params.yarn_nm_app_log_dir,
+                     owner=params.yarn_user,
+                     group=params.user_group,
+                     mode="1777",
+                     recursive_chmod=True
+      )
+    hdfs_directory(name=params.mapreduce_jobhistory_intermediate_done_dir,
+                   owner=params.mapred_user,
+                   group=params.user_group,
+                   mode="1777"
+    )
+
+    hdfs_directory(name=params.mapreduce_jobhistory_done_dir,
+                   owner=params.mapred_user,
+                   group=params.user_group,
+                   mode="1777"
+    )
+
+  pass
+
+
+def create_user_directories():
+  import params
+
+  hdfs_directory(name=params.smoke_hdfs_user_dir,
+                 owner=params.smoke_user,
+                 mode=params.smoke_hdfs_user_mode
+  )
+
+  if params.has_hive_server_host:
+    hdfs_directory(name=params.hive_hdfs_user_dir,
+                   owner=params.hive_user,
+                   mode=params.hive_hdfs_user_mode
+    )
+
+  if params.has_hcat_server_host:
+    if params.hcat_hdfs_user_dir != params.webhcat_hdfs_user_dir:
+      hdfs_directory(name=params.hcat_hdfs_user_dir,
+                     owner=params.hcat_user,
+                     mode=params.hcat_hdfs_user_mode
+      )
+    hdfs_directory(name=params.webhcat_hdfs_user_dir,
+                   owner=params.webhcat_user,
+                   mode=params.webhcat_hdfs_user_mode
+    )
+
+  if params.has_oozie_server:
+    hdfs_directory(name=params.oozie_hdfs_user_dir,
+                   owner=params.oozie_user,
+                   mode=params.oozie_hdfs_user_mode
+    )
+
+
+def format_namenode(force=None):
+  import params
+
+  mark_dir = params.namenode_formatted_mark_dir
+  dfs_name_dir = params.dfs_name_dir
+  hdfs_user = params.hdfs_user
+  hadoop_conf_dir = params.hadoop_conf_dir
+
+  if True:
+    if force:
+      ExecuteHadoop('namenode -format',
+                    kinit_override=True)
+    else:
+      File('/tmp/checkForFormat.sh',
+           content=StaticFile("checkForFormat.sh"),
+           mode=0755)
+      Execute(format(
+        "sh /tmp/checkForFormat.sh {hdfs_user} {hadoop_conf_dir} {mark_dir} "
+        "{dfs_name_dir}"),
+              not_if=format("test -d {mark_dir}"),
+              path="/usr/sbin:/sbin:/usr/local/bin:/bin:/usr/bin")
+    Execute(format("mkdir -p {mark_dir}"))

+ 53 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/services/HDFS/package/scripts/hdfs_snamenode.py

@@ -0,0 +1,53 @@
+"""
+Licensed to the Apache Software Foundation (ASF) under one
+or more contributor license agreements.  See the NOTICE file
+distributed with this work for additional information
+regarding copyright ownership.  The ASF licenses this file
+to you under the Apache License, Version 2.0 (the
+"License"); you may not use this file except in compliance
+with the License.  You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+
+"""
+
+from resource_management import *
+from utils import service
+from utils import hdfs_directory
+
+
+def snamenode(action=None, format=False):
+  import params
+
+  if action == "configure":
+    Directory(params.fs_checkpoint_dir,
+              recursive=True,
+              mode=0755,
+              owner=params.hdfs_user,
+              group=params.user_group)
+  elif action == "start":
+    service(
+      action=action,
+      name="secondarynamenode",
+      user=params.hdfs_user,
+      create_pid_dir=True,
+      create_log_dir=True,
+      keytab=params.dfs_secondary_namenode_keytab_file,
+      principal=params.dfs_secondary_namenode_kerberos_principal
+    )
+  elif action == "stop":
+    service(
+      action=action,
+      name="secondarynamenode",
+      user=params.hdfs_user,
+      create_pid_dir=True,
+      create_log_dir=True,
+      keytab=params.dfs_secondary_namenode_keytab_file,
+      principal=params.dfs_secondary_namenode_kerberos_principal
+    )

+ 59 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/services/HDFS/package/scripts/namenode.py

@@ -0,0 +1,59 @@
+"""
+Licensed to the Apache Software Foundation (ASF) under one
+or more contributor license agreements.  See the NOTICE file
+distributed with this work for additional information
+regarding copyright ownership.  The ASF licenses this file
+to you under the Apache License, Version 2.0 (the
+"License"); you may not use this file except in compliance
+with the License.  You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+
+"""
+
+from resource_management import *
+from hdfs_namenode import namenode
+
+
+class NameNode(Script):
+  def install(self, env):
+    import params
+
+    self.install_packages(env)
+    env.set_params(params)
+
+  def start(self, env):
+    import params
+
+    env.set_params(params)
+    self.config(env)
+    namenode(action="start")
+
+  def stop(self, env):
+    import params
+
+    env.set_params(params)
+    namenode(action="stop")
+
+  def config(self, env):
+    import params
+
+    env.set_params(params)
+    namenode(action="configure")
+    pass
+
+  def status(self, env):
+    import status_params
+
+    env.set_params(status_params)
+    check_process_status(status_params.namenode_pid_file)
+
+
+if __name__ == "__main__":
+  NameNode().execute()

+ 163 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/services/HDFS/package/scripts/params.py

@@ -0,0 +1,163 @@
+"""
+Licensed to the Apache Software Foundation (ASF) under one
+or more contributor license agreements.  See the NOTICE file
+distributed with this work for additional information
+regarding copyright ownership.  The ASF licenses this file
+to you under the Apache License, Version 2.0 (the
+"License"); you may not use this file except in compliance
+with the License.  You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+
+"""
+
+from resource_management import *
+import status_params
+import os
+
+config = Script.get_config()
+
+#security params
+security_enabled = config['configurations']['global']['security_enabled']
+dfs_journalnode_keytab_file = config['configurations']['hdfs-site']['dfs.journalnode.keytab.file']
+dfs_web_authentication_kerberos_keytab = config['configurations']['hdfs-site']['dfs.journalnode.keytab.file']
+dfs_secondary_namenode_keytab_file =  config['configurations']['hdfs-site']['dfs.secondary.namenode.keytab.file']
+dfs_datanode_keytab_file =  config['configurations']['hdfs-site']['dfs.datanode.keytab.file']
+dfs_namenode_keytab_file =  config['configurations']['hdfs-site']['dfs.namenode.keytab.file']
+smoke_user_keytab = config['configurations']['global']['smokeuser_keytab']
+hdfs_user_keytab = config['configurations']['global']['hdfs_user_keytab']
+
+dfs_datanode_kerberos_principal = config['configurations']['hdfs-site']['dfs.datanode.kerberos.principal']
+dfs_journalnode_kerberos_principal = config['configurations']['hdfs-site']['dfs.journalnode.kerberos.principal']
+dfs_secondary_namenode_kerberos_internal_spnego_principal = config['configurations']['hdfs-site']['dfs.secondary.namenode.kerberos.internal.spnego.principal']
+dfs_namenode_kerberos_principal = config['configurations']['hdfs-site']['dfs.namenode.kerberos.principal']
+dfs_web_authentication_kerberos_principal = config['configurations']['hdfs-site']['dfs.web.authentication.kerberos.principal']
+dfs_secondary_namenode_kerberos_principal = config['configurations']['hdfs-site']['dfs.secondary.namenode.kerberos.principal']
+dfs_journalnode_kerberos_internal_spnego_principal = config['configurations']['hdfs-site']['dfs.journalnode.kerberos.internal.spnego.principal']
+
+kinit_path_local = get_kinit_path([default("kinit_path_local",None), "/usr/bin", "/usr/kerberos/bin", "/usr/sbin"])
+#hosts
+hostname = config["hostname"]
+rm_host = default("/clusterHostInfo/rm_host", [])
+slave_hosts = default("/clusterHostInfo/slave_hosts", [])
+hagios_server_hosts = default("/clusterHostInfo/nagios_server_host", [])
+oozie_servers = default("/clusterHostInfo/oozie_server", [])
+hcat_server_hosts = default("/clusterHostInfo/webhcat_server_host", [])
+hive_server_host =  default("/clusterHostInfo/hive_server_host", [])
+hbase_master_hosts = default("/clusterHostInfo/hbase_master_hosts", [])
+hs_host = default("/clusterHostInfo/hs_host", [])
+jtnode_host = default("/clusterHostInfo/jtnode_host", [])
+namenode_host = default("/clusterHostInfo/namenode_host", [])
+nm_host = default("/clusterHostInfo/nm_host", [])
+ganglia_server_hosts = default("/clusterHostInfo/ganglia_server_host", [])
+journalnode_hosts = default("/clusterHostInfo/journalnode_hosts", [])
+zkfc_hosts = default("/clusterHostInfo/zkfc_hosts", [])
+
+has_ganglia_server = not len(ganglia_server_hosts) == 0
+has_namenodes = not len(namenode_host) == 0
+has_jobtracker = not len(jtnode_host) == 0
+has_resourcemanager = not len(rm_host) == 0
+has_histroryserver = not len(hs_host) == 0
+has_hbase_masters = not len(hbase_master_hosts) == 0
+has_slaves = not len(slave_hosts) == 0
+has_nagios = not len(hagios_server_hosts) == 0
+has_oozie_server = not len(oozie_servers)  == 0
+has_hcat_server_host = not len(hcat_server_hosts)  == 0
+has_hive_server_host = not len(hive_server_host)  == 0
+has_journalnode_hosts = not len(journalnode_hosts)  == 0
+has_zkfc_hosts = not len(zkfc_hosts)  == 0
+
+
+is_namenode_master = hostname in namenode_host
+is_jtnode_master = hostname in jtnode_host
+is_rmnode_master = hostname in rm_host
+is_hsnode_master = hostname in hs_host
+is_hbase_master = hostname in hbase_master_hosts
+is_slave = hostname in slave_hosts
+
+if has_ganglia_server:
+  ganglia_server_host = ganglia_server_hosts[0]
+
+#users and groups
+yarn_user = config['configurations']['global']['yarn_user']
+hbase_user = config['configurations']['global']['hbase_user']
+nagios_user = config['configurations']['global']['nagios_user']
+oozie_user = config['configurations']['global']['oozie_user']
+webhcat_user = config['configurations']['global']['hcat_user']
+hcat_user = config['configurations']['global']['hcat_user']
+hive_user = config['configurations']['global']['hive_user']
+smoke_user =  config['configurations']['global']['smokeuser']
+mapred_user = config['configurations']['global']['mapred_user']
+hdfs_user = status_params.hdfs_user
+
+user_group = config['configurations']['global']['user_group']
+proxyuser_group =  config['configurations']['global']['proxyuser_group']
+nagios_group = config['configurations']['global']['nagios_group']
+smoke_user_group = "users"
+
+#hadoop params
+hadoop_conf_dir = "/etc/hadoop/conf"
+hadoop_pid_dir_prefix = status_params.hadoop_pid_dir_prefix
+hadoop_bin = "/usr/lib/hadoop/bin"
+
+hdfs_log_dir_prefix = config['configurations']['global']['hdfs_log_dir_prefix']
+
+dfs_domain_socket_path = "/var/lib/hadoop-hdfs/dn_socket"
+dfs_domain_socket_dir = os.path.dirname(dfs_domain_socket_path)
+
+hadoop_libexec_dir = "/usr/lib/hadoop/libexec"
+
+jn_edits_dir = config['configurations']['hdfs-site']['dfs.journalnode.edits.dir']#"/grid/0/hdfs/journal"
+
+# if stack_version[0] == "2":
+#dfs_name_dir = config['configurations']['hdfs-site']['dfs.namenode.name.dir']
+# else:
+dfs_name_dir = config['configurations']['hdfs-site']['dfs.name.dir']#","/tmp/hadoop-hdfs/dfs/name")
+
+namenode_dirs_created_stub_dir = format("{hdfs_log_dir_prefix}/{hdfs_user}")
+namenode_dirs_stub_filename = "namenode_dirs_created"
+
+hbase_hdfs_root_dir = config['configurations']['hbase-site']['hbase.rootdir']#","/apps/hbase/data")
+hbase_staging_dir = "/apps/hbase/staging"
+hive_apps_whs_dir = config['configurations']['hive-site']["hive.metastore.warehouse.dir"] #, "/apps/hive/warehouse")
+webhcat_apps_dir = "/apps/webhcat"
+yarn_log_aggregation_enabled = config['configurations']['yarn-site']['yarn.log-aggregation-enable']#","true")
+yarn_nm_app_log_dir =  config['configurations']['yarn-site']['yarn.nodemanager.remote-app-log-dir']#","/app-logs")
+mapreduce_jobhistory_intermediate_done_dir = config['configurations']['mapred-site']['mapreduce.jobhistory.intermediate-done-dir']#","/app-logs")
+mapreduce_jobhistory_done_dir = config['configurations']['mapred-site']['mapreduce.jobhistory.done-dir']#","/mr-history/done")
+
+if has_oozie_server:
+  oozie_hdfs_user_dir = format("/user/{oozie_user}")
+  oozie_hdfs_user_mode = 775
+if has_hcat_server_host:
+  hcat_hdfs_user_dir = format("/user/{hcat_user}")
+  hcat_hdfs_user_mode = 755
+  webhcat_hdfs_user_dir = format("/user/{webhcat_user}")
+  webhcat_hdfs_user_mode = 755
+if has_hive_server_host:
+  hive_hdfs_user_dir = format("/user/{hive_user}")
+  hive_hdfs_user_mode = 700
+smoke_hdfs_user_dir = format("/user/{smoke_user}")
+smoke_hdfs_user_mode = 770
+
+namenode_formatted_mark_dir = format("{hadoop_pid_dir_prefix}/hdfs/namenode/formatted/")
+
+# if stack_version[0] == "2":
+#fs_checkpoint_dir = config['configurations']['hdfs-site']['dfs.namenode.checkpoint.dir'] #","/tmp/hadoop-hdfs/dfs/namesecondary")
+# else:
+fs_checkpoint_dir = config['configurations']['core-site']['fs.checkpoint.dir']#","/tmp/hadoop-hdfs/dfs/namesecondary")
+
+# if stack_version[0] == "2":
+#dfs_data_dir = config['configurations']['hdfs-site']['dfs.datanode.data.dir']#,"/tmp/hadoop-hdfs/dfs/data")
+# else:
+dfs_data_dir = config['configurations']['hdfs-site']['dfs.data.dir']#,"/tmp/hadoop-hdfs/dfs/data")
+
+
+
+

+ 106 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/services/HDFS/package/scripts/service_check.py

@@ -0,0 +1,106 @@
+"""
+Licensed to the Apache Software Foundation (ASF) under one
+or more contributor license agreements.  See the NOTICE file
+distributed with this work for additional information
+regarding copyright ownership.  The ASF licenses this file
+to you under the Apache License, Version 2.0 (the
+"License"); you may not use this file except in compliance
+with the License.  You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+
+"""
+
+from resource_management import *
+
+
+class HdfsServiceCheck(Script):
+  def service_check(self, env):
+    import params
+
+    env.set_params(params)
+    unique = get_unique_id_and_date()
+    dir = '/tmp'
+    tmp_file = format("{dir}/{unique}")
+
+    safemode_command = "dfsadmin -safemode get | grep OFF"
+
+    create_dir_cmd = format("fs -mkdir {dir} ; hadoop fs -chmod -R 777 {dir}")
+    test_dir_exists = format("hadoop fs -test -e {dir}")
+    cleanup_cmd = format("fs -rm {tmp_file}")
+    #cleanup put below to handle retries; if retrying there wil be a stale file
+    #that needs cleanup; exit code is fn of second command
+    create_file_cmd = format(
+      "{cleanup_cmd}; hadoop fs -put /etc/passwd {tmp_file}")
+    test_cmd = format("fs -test -e {tmp_file}")
+    if params.security_enabled:
+      Execute(format(
+        "su - {smoke_user} -c '{kinit_path_local} -kt {smoke_user_keytab} "
+        "{smoke_user}'"))
+    ExecuteHadoop(safemode_command,
+                  user=params.smoke_user,
+                  logoutput=True,
+                  conf_dir=params.hadoop_conf_dir,
+                  try_sleep=15,
+                  tries=20
+    )
+    ExecuteHadoop(create_dir_cmd,
+                  user=params.smoke_user,
+                  logoutput=True,
+                  not_if=test_dir_exists,
+                  conf_dir=params.hadoop_conf_dir,
+                  try_sleep=3,
+                  tries=5
+    )
+    ExecuteHadoop(create_file_cmd,
+                  user=params.smoke_user,
+                  logoutput=True,
+                  conf_dir=params.hadoop_conf_dir,
+                  try_sleep=3,
+                  tries=5
+    )
+    ExecuteHadoop(test_cmd,
+                  user=params.smoke_user,
+                  logoutput=True,
+                  conf_dir=params.hadoop_conf_dir,
+                  try_sleep=3,
+                  tries=5
+    )
+    if params.has_journalnode_hosts:
+      journalnode_port = params.journalnode_port
+      smoke_test_user = params.smoke_user
+      checkWebUIFileName = "checkWebUI.py"
+      checkWebUIFilePath = format("/tmp/{checkWebUIFileName}")
+      comma_sep_jn_hosts = ",".join(params.journalnode_hosts)
+      checkWebUICmd = format(
+        "su - {smoke_test_user} -c 'python {checkWebUIFilePath} -m "
+        "{comma_sep_jn_hosts} -p {journalnode_port}'")
+      File(checkWebUIFilePath,
+           content=StaticFile(checkWebUIFileName))
+
+      Execute(checkWebUICmd,
+              logoutput=True,
+              try_sleep=3,
+              tries=5
+      )
+
+    if params.has_zkfc_hosts:
+      pid_dir = format("{hadoop_pid_dir_prefix}/{hdfs_user}")
+      pid_file = format("{pid_dir}/hadoop-{hdfs_user}-zkfc.pid")
+      check_zkfc_process_cmd = format(
+        "ls {pid_file} >/dev/null 2>&1 && ps `cat {pid_file}` >/dev/null 2>&1")
+      Execute(check_zkfc_process_cmd,
+              logoutput=True,
+              try_sleep=3,
+              tries=5
+      )
+
+
+if __name__ == "__main__":
+  HdfsServiceCheck().execute()

+ 64 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/services/HDFS/package/scripts/snamenode.py

@@ -0,0 +1,64 @@
+"""
+Licensed to the Apache Software Foundation (ASF) under one
+or more contributor license agreements.  See the NOTICE file
+distributed with this work for additional information
+regarding copyright ownership.  The ASF licenses this file
+to you under the Apache License, Version 2.0 (the
+"License"); you may not use this file except in compliance
+with the License.  You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+
+"""
+
+from resource_management import *
+from hdfs_snamenode import snamenode
+
+
+class SNameNode(Script):
+  def install(self, env):
+    import params
+
+    env.set_params(params)
+
+    self.install_packages(env)
+
+
+  def start(self, env):
+    import params
+
+    env.set_params(params)
+
+    self.config(env)
+    snamenode(action="start")
+
+  def stop(self, env):
+    import params
+
+    env.set_params(params)
+
+    snamenode(action="stop")
+
+  def config(self, env):
+    import params
+
+    env.set_params(params)
+
+    snamenode(action="configure")
+
+  def status(self, env):
+    import status_params
+
+    env.set_params(status_params)
+
+    check_process_status(status_params.snamenode_pid_file)
+
+
+if __name__ == "__main__":
+  SNameNode().execute()

+ 31 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/services/HDFS/package/scripts/status_params.py

@@ -0,0 +1,31 @@
+"""
+Licensed to the Apache Software Foundation (ASF) under one
+or more contributor license agreements.  See the NOTICE file
+distributed with this work for additional information
+regarding copyright ownership.  The ASF licenses this file
+to you under the Apache License, Version 2.0 (the
+"License"); you may not use this file except in compliance
+with the License.  You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+
+"""
+
+from resource_management import *
+
+config = Script.get_config()
+
+hadoop_pid_dir_prefix = config['configurations']['global']['hadoop_pid_dir_prefix']
+hdfs_user = config['configurations']['global']['hdfs_user']
+hdp_pid_dir = format("{hadoop_pid_dir_prefix}/{hdfs_user}")
+datanode_pid_file = format("{hdp_pid_dir}/hadoop-{hdfs_user}-datanode.pid")
+namenode_pid_file = format("{hdp_pid_dir}/hadoop-{hdfs_user}-namenode.pid")
+snamenode_pid_file = format("{hdp_pid_dir}/hadoop-{hdfs_user}-secondarynamenode.pid")
+journalnode_pid_file = format("{hdp_pid_dir}/hadoop-{hdfs_user}-journalnode.pid")
+zkfc_pid_file = format("{hdp_pid_dir}/hadoop-{hdfs_user}-zkfc.pid")

+ 133 - 0
ambari-server/src/main/resources/stacks/HDP/1.3._/services/HDFS/package/scripts/utils.py

@@ -0,0 +1,133 @@
+"""
+Licensed to the Apache Software Foundation (ASF) under one
+or more contributor license agreements.  See the NOTICE file
+distributed with this work for additional information
+regarding copyright ownership.  The ASF licenses this file
+to you under the Apache License, Version 2.0 (the
+"License"); you may not use this file except in compliance
+with the License.  You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+
+"""
+
+from resource_management import *
+
+
+def service(action=None, name=None, user=None, create_pid_dir=False,
+            create_log_dir=False, keytab=None, principal=None):
+  import params
+
+  kinit_cmd = "true"
+  pid_dir = format("{hadoop_pid_dir_prefix}/{user}")
+  pid_file = format("{pid_dir}/hadoop-{user}-{name}.pid")
+  log_dir = format("{hdfs_log_dir_prefix}/{user}")
+  hadoop_daemon = format(
+    "export HADOOP_LIBEXEC_DIR={hadoop_libexec_dir} && "
+    "{hadoop_bin}/hadoop-daemon.sh")
+  cmd = format("{hadoop_daemon} --config {hadoop_conf_dir}")
+
+  if create_pid_dir:
+    Directory(pid_dir,
+              owner=user,
+              recursive=True)
+  if create_log_dir:
+    Directory(log_dir,
+              owner=user,
+              recursive=True)
+
+  if params.security_enabled:
+    principal_replaced = principal.replace("_HOST", params.hostname)
+    kinit_cmd = format("kinit -kt {keytab} {principal_replaced}")
+
+    if name == "datanode":
+      user = "root"
+      pid_file = format(
+        "{hadoop_pid_dir_prefix}/{hdfs_user}/hadoop-{hdfs_user}-{name}.pid")
+
+  daemon_cmd = format("{cmd} {action} {name}")
+
+  service_is_up = format(
+    "ls {pid_file} >/dev/null 2>&1 &&"
+    " ps `cat {pid_file}` >/dev/null 2>&1") if action == "start" else None
+
+  Execute(kinit_cmd)
+  Execute(daemon_cmd,
+          user = user,
+          not_if=service_is_up
+  )
+  if action == "stop":
+    File(pid_file,
+         action="delete",
+         ignore_failures=True
+    )
+
+
+def hdfs_directory(name=None, owner=None, group=None,
+                   mode=None, recursive_chown=False, recursive_chmod=False):
+  import params
+
+  dir_exists = format("hadoop fs -ls {name} >/dev/null 2>&1")
+  namenode_safe_mode_off = "hadoop dfsadmin -safemode get|grep 'Safe mode is OFF'"
+
+  stub_dir = params.namenode_dirs_created_stub_dir
+  stub_filename = params.namenode_dirs_stub_filename
+  dir_absent_in_stub = format(
+    "grep -q '^{name}$' {stub_dir}/{stub_filename} > /dev/null 2>&1; test $? -ne 0")
+  record_dir_in_stub = format("echo '{name}' >> {stub_dir}/{stub_filename}")
+  tries = 3
+  try_sleep = 10
+  dfs_check_nn_status_cmd = "true"
+
+  #if params.stack_version[0] == "2":
+  #mkdir_cmd = format("fs -mkdir -p {name}")
+  #else:
+  mkdir_cmd = format("fs -mkdir {name}")
+
+  if params.security_enabled:
+    Execute(format("kinit -kt {hdfs_user_keytab} {hdfs_user}"),
+            user = params.hdfs_user)
+  ExecuteHadoop(mkdir_cmd,
+                try_sleep=try_sleep,
+                tries=tries,
+                not_if=format(
+                  "{dir_absent_in_stub} && {dfs_check_nn_status_cmd} && "
+                  "{dir_exists} && ! {namenode_safe_mode_off}"),
+                only_if=format(
+                  "su - hdfs -c '{dir_absent_in_stub} && {dfs_check_nn_status_cmd} && "
+                  "! {dir_exists}'"),
+                conf_dir=params.hadoop_conf_dir,
+                user=params.hdfs_user
+  )
+  Execute(record_dir_in_stub,
+          user=params.hdfs_user,
+          only_if=format("! {dir_absent_in_stub}")
+  )
+
+  recursive = "-R" if recursive_chown else ""
+  perm_cmds = []
+
+  if owner:
+    chown = owner
+    if group:
+      chown = format("{owner}:{group}")
+    perm_cmds.append(format("fs -chown {recursive} {chown} {name}"))
+  if mode:
+    perm_cmds.append(format("fs -chmod {recursive} {mode} {name}"))
+  for cmd in perm_cmds:
+    ExecuteHadoop(cmd,
+                  user=params.hdfs_user,
+                  only_if=format("su - hdfs -c '{dir_absent_in_stub} && {dfs_check_nn_status_cmd} && {namenode_safe_mode_off} && {dir_exists}'"),
+                  try_sleep=try_sleep,
+                  tries=tries,
+                  conf_dir=params.hadoop_conf_dir
+    )
+
+
+

+ 5 - 4
ambari-server/src/main/resources/stacks/HDP/2.0.8/hooks/before-START/scripts/shared_initialization.py

@@ -101,7 +101,7 @@ def setup_hadoop():
     File(os.path.join(params.hadoop_bin, "task-controller"),
          owner="root",
          group=params.mapred_tt_group,
-         mode=6050
+         mode=06050
     )
     tc_mode = 0644
     tc_owner = "root"
@@ -111,8 +111,9 @@ def setup_hadoop():
 
   if tc_mode:
     File(os.path.join(params.hadoop_conf_dir, 'taskcontroller.cfg'),
-         owner=tc_owner,
-         mode=tc_mode,
+         owner = tc_owner,
+         mode = tc_mode,
+         group = params.mapred_tt_group,
          content=Template("taskcontroller.cfg.j2")
     )
   else:
@@ -240,7 +241,7 @@ def setup_configs():
          group=params.user_group
     )
   if os.path.exists(os.path.join(params.hadoop_conf_dir, 'masters')):
-    Directory(os.path.join(params.hadoop_conf_dir, 'masters'),
+    File(os.path.join(params.hadoop_conf_dir, 'masters'),
               owner=params.hdfs_user,
               group=params.user_group
     )