Add install of vim on namenode creation. Copy custom log4j.properties…

… to namenode container

hadoop-spark-cluster/namenode/Dockerfile

@@ -7,6 +7,10 @@ ENV HDFS_CONF_dfs_namenode_name_dir=file:///hadoop/dfs/name
 RUN mkdir -p /hadoop/dfs/name
 VOLUME /hadoop/dfs/name
 
+RUN apt-get update && apt-get install vim
+
+COPY log4j.properties /etc/hadoop/log4j.properties
+
 ADD run.sh /run.sh
 RUN chmod a+x /run.sh
 

hadoop-spark-cluster/namenode/log4j.properties

@@ -0,0 +1,215 @@
+# 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=DEBUG,console
+hadoop.log.dir=.
+hadoop.log.file=hadoop.log
+
+# Define the root logger to the system property "hadoop.root.logger".
+log4j.rootLogger=${hadoop.root.logger}, EventCounter
+
+# Logging Threshold
+log4j.threshold=ALL
+
+# Null Appender
+log4j.appender.NullAppender=org.apache.log4j.varia.NullAppender
+
+#
+# Rolling File Appender - cap space usage at 5gb.
+#
+hadoop.log.maxfilesize=256MB
+hadoop.log.maxbackupindex=20
+log4j.appender.RFA=org.apache.log4j.RollingFileAppender
+log4j.appender.RFA.File=${hadoop.log.dir}/${hadoop.log.file}
+
+log4j.appender.RFA.MaxFileSize=${hadoop.log.maxfilesize}
+log4j.appender.RFA.MaxBackupIndex=${hadoop.log.maxbackupindex}
+
+log4j.appender.RFA.layout=org.apache.log4j.PatternLayout
+
+# Pattern format: Date LogLevel LoggerName LogMessage
+log4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
+# Debugging Pattern format
+#log4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n
+
+
+#
+# Daily Rolling File Appender
+#
+
+log4j.appender.DRFA=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.DRFA.File=${hadoop.log.dir}/${hadoop.log.file}
+
+# Rollover at midnight
+log4j.appender.DRFA.DatePattern=.yyyy-MM-dd
+
+log4j.appender.DRFA.layout=org.apache.log4j.PatternLayout
+
+# Pattern format: Date LogLevel LoggerName LogMessage
+log4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
+
+#
+# console
+# Add "console" to rootlogger above if you want to use this
+#
+
+log4j.appender.console=org.apache.log4j.ConsoleAppender
+log4j.appender.console.target=System.err
+log4j.appender.console.layout=org.apache.log4j.PatternLayout
+log4j.appender.console.layout.ConversionPattern=%d{ISO8601} %p %c{2}: %m%n
+
+#
+# TaskLog Appender
+#
+log4j.appender.TLA=org.apache.hadoop.mapred.TaskLogAppender
+
+log4j.appender.TLA.layout=org.apache.log4j.PatternLayout
+log4j.appender.TLA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
+
+#Security appender
+#
+hadoop.security.logger=INFO,NullAppender
+hadoop.security.log.maxfilesize=256MB
+hadoop.security.log.maxbackupindex=20
+log4j.category.SecurityLogger=${hadoop.security.logger}
+hadoop.security.log.file=SecurityAuth-${user.name}.audit
+log4j.appender.RFAS=org.apache.log4j.RollingFileAppender
+log4j.appender.RFAS.File=${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=${hadoop.security.log.maxbackupindex}
+
+#
+# Daily Rolling Security appender
+#
+log4j.appender.DRFAS=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.DRFAS.File=${hadoop.log.dir}/${hadoop.security.log.file}
+log4j.appender.DRFAS.layout=org.apache.log4j.PatternLayout
+log4j.appender.DRFAS.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
+log4j.appender.DRFAS.DatePattern=.yyyy-MM-dd
+
+#
+# hadoop configuration logging
+#
+
+#
+# hdfs audit logging
+#
+hdfs.audit.logger=INFO,NullAppender
+hdfs.audit.log.maxfilesize=256MB
+hdfs.audit.log.maxbackupindex=20
+log4j.logger.org.apache.hadoop.hdfs.server.namenode.FSNamesystem.audit=${hdfs.audit.logger}
+log4j.additivity.org.apache.hadoop.hdfs.server.namenode.FSNamesystem.audit=false
+log4j.appender.RFAAUDIT=org.apache.log4j.RollingFileAppender
+log4j.appender.RFAAUDIT.File=${hadoop.log.dir}/hdfs-audit.log
+log4j.appender.RFAAUDIT.layout=org.apache.log4j.PatternLayout
+log4j.appender.RFAAUDIT.layout.ConversionPattern=%d{ISO8601} %p %c{2}: %m%n
+log4j.appender.RFAAUDIT.MaxFileSize=${hdfs.audit.log.maxfilesize}
+log4j.appender.RFAAUDIT.MaxBackupIndex=${hdfs.audit.log.maxbackupindex}
+
+#
+# NameNode metrics logging.
+# The default is to retain two namenode-metrics.log files up to 64MB each.
+#
+namenode.metrics.logger=INFO,NullAppender
+log4j.logger.NameNodeMetricsLog=${namenode.metrics.logger}
+log4j.additivity.NameNodeMetricsLog=false
+log4j.appender.NNMETRICSRFA=org.apache.log4j.RollingFileAppender
+log4j.appender.NNMETRICSRFA.File=${hadoop.log.dir}/namenode-metrics.log
+log4j.appender.NNMETRICSRFA.layout=org.apache.log4j.PatternLayout
+log4j.appender.NNMETRICSRFA.layout.ConversionPattern=%d{ISO8601} %m%n
+log4j.appender.NNMETRICSRFA.MaxBackupIndex=1
+log4j.appender.NNMETRICSRFA.MaxFileSize=64MB
+
+#
+# DataNode metrics logging.
+# The default is to retain two datanode-metrics.log files up to 64MB each.
+#
+datanode.metrics.logger=INFO,NullAppender
+log4j.logger.DataNodeMetricsLog=${datanode.metrics.logger}
+log4j.additivity.DataNodeMetricsLog=false
+log4j.appender.DNMETRICSRFA=org.apache.log4j.RollingFileAppender
+log4j.appender.DNMETRICSRFA.File=${hadoop.log.dir}/datanode-metrics.log
+log4j.appender.DNMETRICSRFA.layout=org.apache.log4j.PatternLayout
+log4j.appender.DNMETRICSRFA.layout.ConversionPattern=%d{ISO8601} %m%n
+log4j.appender.DNMETRICSRFA.MaxBackupIndex=1
+log4j.appender.DNMETRICSRFA.MaxFileSize=64MB
+
+# AWS SDK & S3A FileSystem
+#log4j.logger.com.amazonaws=ERROR
+log4j.logger.com.amazonaws.http.AmazonHttpClient=ERROR
+#log4j.logger.org.apache.hadoop.fs.s3a.S3AFileSystem=WARN
+
+log4j.appender.EventCounter=org.apache.hadoop.log.metrics.EventCounter
+
+#
+# Set the ResourceManager summary log filename
+yarn.server.resourcemanager.appsummary.log.file=rm-appsummary.log
+# Set the ResourceManager summary log level and appender
+yarn.server.resourcemanager.appsummary.logger=${hadoop.root.logger}
+
+log4j.logger.org.apache.hadoop.yarn.server.resourcemanager.RMAppManager$ApplicationSummary=${yarn.server.resourcemanager.appsummary.logger}
+log4j.additivity.org.apache.hadoop.yarn.server.resourcemanager.RMAppManager$ApplicationSummary=false
+log4j.appender.RMSUMMARY=org.apache.log4j.RollingFileAppender
+log4j.appender.RMSUMMARY.File=${hadoop.log.dir}/${yarn.server.resourcemanager.appsummary.log.file}
+log4j.appender.RMSUMMARY.MaxFileSize=256MB
+log4j.appender.RMSUMMARY.MaxBackupIndex=20
+log4j.appender.RMSUMMARY.layout=org.apache.log4j.PatternLayout
+log4j.appender.RMSUMMARY.layout.ConversionPattern=%d{ISO8601} %p %c{2}: %m%n
+
+#
+# YARN ResourceManager audit logging
+#
+rm.audit.logger=INFO,NullAppender
+rm.audit.log.maxfilesize=256MB
+rm.audit.log.maxbackupindex=20
+log4j.logger.org.apache.hadoop.yarn.server.resourcemanager.RMAuditLogger=${rm.audit.logger}
+log4j.additivity.org.apache.hadoop.yarn.server.resourcemanager.RMAuditLogger=false
+log4j.appender.RMAUDIT=org.apache.log4j.RollingFileAppender
+log4j.appender.RMAUDIT.File=${hadoop.log.dir}/rm-audit.log
+log4j.appender.RMAUDIT.layout=org.apache.log4j.PatternLayout
+log4j.appender.RMAUDIT.layout.ConversionPattern=%d{ISO8601} %p %c{2}: %m%n
+log4j.appender.RMAUDIT.MaxFileSize=${rm.audit.log.maxfilesize}
+log4j.appender.RMAUDIT.MaxBackupIndex=${rm.audit.log.maxbackupindex}
+
+#
+# YARN NodeManager audit logging
+#
+nm.audit.logger=INFO,NullAppender
+nm.audit.log.maxfilesize=256MB
+nm.audit.log.maxbackupindex=20
+log4j.logger.org.apache.hadoop.yarn.server.nodemanager.NMAuditLogger=${nm.audit.logger}
+log4j.additivity.org.apache.hadoop.yarn.server.nodemanager.NMAuditLogger=false
+log4j.appender.NMAUDIT=org.apache.log4j.RollingFileAppender
+log4j.appender.NMAUDIT.File=${hadoop.log.dir}/nm-audit.log
+log4j.appender.NMAUDIT.layout=org.apache.log4j.PatternLayout
+log4j.appender.NMAUDIT.layout.ConversionPattern=%d{ISO8601}%p %c{2}: %m%n
+log4j.appender.NMAUDIT.MaxFileSize=${nm.audit.log.maxfilesize}
+log4j.appender.NMAUDIT.MaxBackupIndex=${nm.audit.log.maxbackupindex}
+
+# Appender for viewing information for errors and warnings
+yarn.ewma.cleanupInterval=300
+yarn.ewma.messageAgeLimitSeconds=86400
+yarn.ewma.maxUniqueMessages=250
+log4j.appender.EWMA=org.apache.hadoop.yarn.util.Log4jWarningErrorMetricsAppender
+log4j.appender.EWMA.cleanupInterval=${yarn.ewma.cleanupInterval}
+log4j.appender.EWMA.messageAgeLimitSeconds=${yarn.ewma.messageAgeLimitSeconds}
+log4j.appender.EWMA.maxUniqueMessages=${yarn.ewma.maxUniqueMessages}
+
+# Log levels of third-party libraries
+log4j.logger.org.apache.commons.beanutils=WARN