Repository: eagle Updated Branches: refs/heads/master aa136afa9 -> 39ab83e62
Docker updates for eagle 0.5 This docker image is for eagle 0.5 There is still an issue where namenode process dies sometimes. creating this PR to get the review started.... Author: Jay <jhsonl...@gmail.com> Closes #914 from jhsenjaliya/EAGLE-925. Project: http://git-wip-us.apache.org/repos/asf/eagle/repo Commit: http://git-wip-us.apache.org/repos/asf/eagle/commit/39ab83e6 Tree: http://git-wip-us.apache.org/repos/asf/eagle/tree/39ab83e6 Diff: http://git-wip-us.apache.org/repos/asf/eagle/diff/39ab83e6 Branch: refs/heads/master Commit: 39ab83e625a271a2f3d55a9395c60a43c61f09da Parents: aa136af Author: Jay <jhsonl...@gmail.com> Authored: Wed Jun 28 15:05:58 2017 -0700 Committer: Jay <jhsonl...@gmail.com> Committed: Wed Jun 28 15:05:58 2017 -0700 ---------------------------------------------------------------------- .../src/main/initdata/eagle-topology-init.sh | 2 +- .../src/main/initdata/sample-policy-create.sh | 2 +- eagle-external/eagle-docker/Dockerfile | 18 +++++-- eagle-external/eagle-docker/README.md | 4 +- eagle-external/eagle-docker/bin/eagle-docker.sh | 57 +++++++++++--------- eagle-external/eagle-docker/bin/eagle-lib.sh | 12 ++--- .../eagle-docker/resource/deploy-eagle.sh | 46 ++++++---------- .../eagle-docker/resource/eagle-multinode.json | 4 +- .../eagle-docker/resource/eagle-singlenode.json | 27 +++++++--- .../eagle-docker/resource/install-cluster.sh | 8 +-- .../resource/serf/bin/start-serf-agent.sh | 49 +++++++++++++++++ .../eagle-docker/resource/wait-for-eagle.sh | 14 +++-- .../src/main/resources/application.conf | 3 ++ 13 files changed, 156 insertions(+), 90 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/eagle/blob/39ab83e6/eagle-core/eagle-embed/eagle-embed-hbase/src/main/initdata/eagle-topology-init.sh ---------------------------------------------------------------------- diff --git a/eagle-core/eagle-embed/eagle-embed-hbase/src/main/initdata/eagle-topology-init.sh b/eagle-core/eagle-embed/eagle-embed-hbase/src/main/initdata/eagle-topology-init.sh index 62b1e83..d3e553a 100755 --- a/eagle-core/eagle-embed/eagle-embed-hbase/src/main/initdata/eagle-topology-init.sh +++ b/eagle-core/eagle-embed/eagle-embed-hbase/src/main/initdata/eagle-topology-init.sh @@ -18,7 +18,7 @@ export EAGLE_SERVICE_USER=admin export EAGLE_SERVICE_PASSWD=secret export EAGLE_SERVICE_HOST=localhost -export EAGLE_SERVICE_PORT=38080 +export EAGLE_SERVICE_PORT=9090 ##################################################################### # Import stream metadata for HDFS http://git-wip-us.apache.org/repos/asf/eagle/blob/39ab83e6/eagle-core/eagle-embed/eagle-embed-hbase/src/main/initdata/sample-policy-create.sh ---------------------------------------------------------------------- diff --git a/eagle-core/eagle-embed/eagle-embed-hbase/src/main/initdata/sample-policy-create.sh b/eagle-core/eagle-embed/eagle-embed-hbase/src/main/initdata/sample-policy-create.sh index 307c542..6e66dc7 100755 --- a/eagle-core/eagle-embed/eagle-embed-hbase/src/main/initdata/sample-policy-create.sh +++ b/eagle-core/eagle-embed/eagle-embed-hbase/src/main/initdata/sample-policy-create.sh @@ -22,7 +22,7 @@ export EAGLE_SERVICE_PORT=38080 #### create hdfs policy sample in sandbox echo "create hdfs policy sample in sandbox... " -curl -u ${EAGLE_SERVICE_USER}:${EAGLE_SERVICE_PASSWD} -X POST -H 'Content-Type:application/json' "http://${EAGLE_SERVICE_HOST}:${EAGLE_SERVICE_PORT}/eagle-service/rest/entities?serviceName=AlertDefinitionService"; -d \ +curl -u ${EAGLE_SERVICE_USER}:${EAGLE_SERVICE_PASSWD} -X POST -H 'Content-Type:application/json' "http://${EAGLE_SERVICE_HOST}:${EAGLE_SERVICE_PORT}/rest/entities?serviceName=AlertDefinitionService"; -d \ '[{"tags":{"site":"sandbox","dataSource":"hdfsAuditLog","alertExecutorId":"hdfsAuditLogAlertExecutor","policyId":"viewPrivate","policyType":"siddhiCEPEngine"},"desc":"view private file","policyDef":"{\"type\":\"siddhiCEPEngine\",\"expression\":\"from hdfsAuditLogEventStream[(cmd=='\'open\'') and (src=='\'/tmp/private\'')] select * insert into outputStream\"}","dedupeDef": "{\"alertDedupIntervalMin\":0,\"emailDedupIntervalMin\":1440}","notificationDef": "[{\"subject\":\"just for test\",\"sender\":\"nob...@test.com\",\"recipients\":\"nob...@test.com\",\"flavor\":\"email\",\"id\":\"email_1\",\"tplFileName\":\"\"}]","remediationDef":"","enabled":true}]' #### create hive policy sample in sandbox http://git-wip-us.apache.org/repos/asf/eagle/blob/39ab83e6/eagle-external/eagle-docker/Dockerfile ---------------------------------------------------------------------- diff --git a/eagle-external/eagle-docker/Dockerfile b/eagle-external/eagle-docker/Dockerfile index 4aa3dec..de06bbc 100644 --- a/eagle-external/eagle-docker/Dockerfile +++ b/eagle-external/eagle-docker/Dockerfile @@ -15,11 +15,17 @@ # NOTICE: This docker image is built based sequenceiq/ambari which is open sourced under github: https://github.com/sequenceiq/docker-ambari FROM sequenceiq/ambari:1.7.0 - -MAINTAINER d...@eagle.incubator.apache.org +MAINTAINER d...@eagle.apache.org # Eagle environment ENV EAGLE_HOME=/usr/hdp/current/eagle +ENV JDK_VERSION 8u121 +ENV JDK_BUILD_VERSION b13 +# for local development +#ADD resource/jdk-8u121-linux-x64.rpm /tmp/ +#RUN rpm -i /tmp/jdk-8u121-linux-x64.rpm +RUN curl -LO "http://download.oracle.com/otn-pub/java/jdk/8u121-b13/e9e7ea248e2c4826b92b3f075a80e441/jdk-8u121-linux-x64.rpm"; -H 'Cookie: oraclelicense=accept-securebackup-cookie' && rpm -i jdk-$JDK_VERSION-linux-x64.rpm; +ENV JAVA_HOME /usr/java/default # Install Eagle Package # @@ -33,15 +39,19 @@ ENV EAGLE_HOME=/usr/hdp/current/eagle # `docker build` directly, to prepare the eagle package into build/eagle ADD target/eagle-current /usr/hdp/current/eagle + # Load External Packages RUN yum install -y kafka zookeeper storm hbase tez hadoop snappy snappy-devel hadoop-libhdfs ambari-log4j hive hive-hcatalog hive-webhcat webhcat-tar-hive webhcat-tar-pig mysql-connector-java mysql-server -# Load Static Resources +ENV SERF_HOME /usr/local/serf + ADD resource/serf /usr/local/serf + +# Load Static Resources ADD resource/install-cluster.sh /tmp/ ADD resource/eagle-singlenode.json /tmp/ ADD resource/eagle-multinode.json /tmp/ ADD resource/wait-for-eagle.sh /tmp/ ADD resource/deploy-eagle.sh /usr/hdp/current/eagle/deploy.sh -EXPOSE 9099 8744 8080 2181 2888 6667 60020 60030 60010 +EXPOSE 8744 8080 2181 2888 6667 60020 60030 60010 9090 http://git-wip-us.apache.org/repos/asf/eagle/blob/39ab83e6/eagle-external/eagle-docker/README.md ---------------------------------------------------------------------- diff --git a/eagle-external/eagle-docker/README.md b/eagle-external/eagle-docker/README.md index 105fee0..37253c7 100644 --- a/eagle-external/eagle-docker/README.md +++ b/eagle-external/eagle-docker/README.md @@ -43,8 +43,8 @@ The fastest way to get started with Eagle is to run with [docker](https://github docker run -p 9099:9099 -p 8080:8080 -p 8744:8744 -p 2181:2181 -p 2888:2888 -p 6667:6667 -p 60020:60020 \ -p 60030:60030 -p 60010:60010 -d --dns 127.0.0.1 --entrypoint /usr/local/serf/bin/start-serf-agent.sh \ - -e KEYCHAIN= --env EAGLE_SERVER_HOST=sandbox.eagle.incubator.apache.org --name sandbox \ - -h sandbox.eagle.incubator.apache.org --privileged=true apacheeagle/sandbox:latest \ + -e KEYCHAIN= --env EAGLE_SERVER_HOST=server.eagle.incubator.apache.org --name sandbox \ + -h server.eagle.incubator.apache.org --privileged=true apacheeagle/sandbox:latest \ --tag ambari-server=true docker run -it --rm -e EXPECTED_HOST_COUNT=1 -e BLUEPRINT=hdp-singlenode-eagle --link sandbox:ambariserver\ --entrypoint /bin/sh apacheeagle/sandbox:latest -c /tmp/install-cluster.sh http://git-wip-us.apache.org/repos/asf/eagle/blob/39ab83e6/eagle-external/eagle-docker/bin/eagle-docker.sh ---------------------------------------------------------------------- diff --git a/eagle-external/eagle-docker/bin/eagle-docker.sh b/eagle-external/eagle-docker/bin/eagle-docker.sh index d490d21..ea05c49 100755 --- a/eagle-external/eagle-docker/bin/eagle-docker.sh +++ b/eagle-external/eagle-docker/bin/eagle-docker.sh @@ -18,13 +18,13 @@ # NOTICE: This script is developed and maintained by Apache Eagle community under Apache Softwarw Foundation but not from official Docker product or community. EAGLE_DOCKER_VERSION=latest -EAGLE_DOCKER_NAME=apacheeagle/sandbox EAGLE_DOCKER_PREFIX=sandbox +EAGLE_DOCKER_NAME=apacheeagle/$EAGLE_DOCKER_PREFIX export NODE_NUM=1 cd `dirname $0`/../ -source bin/eagle-lib.sh +source bin/eagle-lib.sh function check_env(){ which docker 1>/dev/null 2>&1 @@ -66,56 +66,57 @@ function usage() { function build(){ check_env + + # bringing it to a parent level + DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )" + cd $DIR/../../../ + # ========================================== # Check Eagle Docker Image # ========================================== - echo "[1/3] Validate Environment" - # echo "Checking eagle docker image ..." + echo "[1/3] Validating Environment" docker images | grep $EAGLE_DOCKER_NAME 1>/dev/null 2>&1 if [ $? == 0 ];then echo "Eagle docker image already exists:" echo "" docker images | grep $EAGLE_DOCKER_NAME echo "" - echo "Rebuild it now [Y/N]? " + echo "do you want to re-build it [Y/N]? " read rebuild if [ $rebuild == "Y" ] || [ $rebuild == "y" ];then echo "Clean eagle image" clean else - echo "Quit now" + echo "exiting now, since eagle docker image exists already" exit 1 fi else - echo "No existing eagle docker images, environment is ready" + echo "Building new eagle docker images, environment is also ready" fi # ========================================== # Build Eagle Binary Package # ========================================== - echo "[2/3] Build Eagle Binary Package" - # echo "Checking eagle binary package" - cd ../../ + echo "[2/3] Building Eagle Binary Package" ls eagle-assembly/target/eagle-*-bin.tar.gz 1>/dev/null 2>&1 if [ $? == 0 ];then - eagle_bin_pkg=`ls eagle-assembly/target/eagle-*-bin.tar.gz` - echo "Found eagle binary package at $eagle_bin_pkg" + eagle_pkg=`ls eagle-assembly/target/eagle-*-bin.tar.gz` + echo "Found eagle binary package at $eagle_pkg" else - echo "Eagle binary package is not found" - echo "Build eagle binary package now" - # ========================================== + # ========================================== # Build Eagle Binary Package with Maven # ========================================== + echo "Packaging eagle using CMD: mvn package -DskipTests" echo "" - echo "Execute: mvn package -DskipTests " mvn package -DskipTests if [ $? == 0 ];then - echo "Built successfully existing with 0" - ls eagle-assembly/target/eagle-*-bin.tar.gz 1>/dev/null 2>&1 + echo "Eagle built successfully." + eagle_pkg_file=$( (basename eagle-assembly/target/eagle-*-bin.tar.gz) 2>/dev/null ) if [ $? == 0 ];then - eagle_bin_pkg=`ls eagle-assembly/target/eagle-*-bin.tar.gz` + # getting path via ls command may not work in all env + eagle_pkg="eagle-assembly/target/$eagle_pkg_file" echo "" - echo "[SUCCESS] Successfully build eagle binary package at $eagle_bin_pkg" + echo "[SUCCESS] Successfully build eagle binary package at $eagle_pkg" else echo "" echo "[FAILED] Built eagle binary package exiting with 0, but package is not found" @@ -131,22 +132,24 @@ function build(){ # ===================================== # Build Eagle Docker Image # ===================================== - echo "[3/3] Build Eagle Docker Image: $EAGLE_DOCKER_NAME" - echo "Extracting $eagle_bin_pkg" + echo "[3/3] Building Eagle Docker Image: $EAGLE_DOCKER_NAME" + echo "Extracting $eagle_pkg" if [ -e eagle-external/eagle-docker/target ];then rm -rf eagle-external/eagle-docker/target fi mkdir -p eagle-external/eagle-docker/target/eagle-current - out=`tar -xzf $eagle_bin_pkg -C eagle-external/eagle-docker/target/` + out=`tar -xzf $eagle_pkg -C eagle-external/eagle-docker/target/` if [ $? != 0 ];then - echo "[ERROR] Failed to execute 'tar -xzf $eagle_bin_pkg -C eagle-external/eagle-docker/target/': $out" 1>&2 + echo "[ERROR] Failed to execute 'tar -xzf $eagle_pkg -C eagle-external/eagle-docker/target/': $out" 1>&2 exit 1 fi mv eagle-external/eagle-docker/target/eagle-*/* eagle-external/eagle-docker/target/eagle-current + mkdir eagle-external/eagle-docker/target/eagle-current/lib/common + cp eagle-external/eagle-log4jkafka/target/eagle-log4jkafka-*.jar eagle-external/eagle-docker/target/eagle-current/lib/common/ - echo "Execute: docker build -t $EAGLE_DOCKER_NAME ." - cd eagle-external/eagle-docker + echo "Executing: docker build -t $EAGLE_DOCKER_NAME ." + cd eagle-external/eagle-docker docker build -t $EAGLE_DOCKER_NAME . if [ $? == 0 ];then @@ -230,6 +233,8 @@ function clean(){ function deploy(){ check_env + # TODO: should check if all required ports are not already binded, + # so that it does not fail after creating first container. if [ "$NODE_NUM" == "" ];then export NODE_NUM=1 fi http://git-wip-us.apache.org/repos/asf/eagle/blob/39ab83e6/eagle-external/eagle-docker/bin/eagle-lib.sh ---------------------------------------------------------------------- diff --git a/eagle-external/eagle-docker/bin/eagle-lib.sh b/eagle-external/eagle-docker/bin/eagle-lib.sh old mode 100755 new mode 100644 index c988866..7cbdd3c --- a/eagle-external/eagle-docker/bin/eagle-lib.sh +++ b/eagle-external/eagle-docker/bin/eagle-lib.sh @@ -18,10 +18,10 @@ : ${VERSION:=latest} : ${IMAGE:="apacheeagle/sandbox:${VERSION}"} -: ${NODE_PREFIX:=sandbox} +: ${NODE_PREFIX:=server} : ${AMBARI_SERVER_NAME:=${NODE_PREFIX}} -: ${MYDOMAIN:=eagle.incubator.apache.org} -: ${DOCKER_OPTS:="--dns 127.0.0.1 --entrypoint /usr/local/serf/bin/start-serf-agent.sh -e KEYCHAIN=$KEYCHAIN --env EAGLE_SERVER_HOST=${AMBARI_SERVER_NAME}.${MYDOMAIN}"} +: ${MYDOMAIN:=eagle.apache.org} +: ${DOCKER_OPTS:="--dns 127.0.0.1 --entrypoint /usr/local/serf/bin/start-serf-agent.sh -e KEYCHAIN=$KEYCHAIN --env EAGLE_SERVER_HOST=${AMBARI_SERVER_NAME}.${MYDOMAIN} --env SERF_TAG_AMBARI_SERVER=true"} : ${CLUSTER_SIZE:=1} : ${DEBUG:=1} : ${SLEEP_TIME:=2} @@ -98,7 +98,7 @@ _amb_run_shell() { : ${COMMAND:? required} get-ambari-server-ip NODES=$(docker inspect --format="{{.Config.Image}} {{.Name}}" $(docker ps -q)|grep $IMAGE|grep $NODE_PREFIX|wc -l|xargs) - run-command docker run -it --rm -e EXPECTED_HOST_COUNT=$NODES -e BLUEPRINT=$BLUEPRINT --link ${AMBARI_SERVER_NAME}:ambariserver --entrypoint /bin/sh $IMAGE -c $COMMAND + run-command docker run -it --rm -e EXPECTED_HOST_COUNT=$NODES -e BLUEPRINT=$BLUEPRINT --env EAGLE_SERVER_HOST=${AMBARI_SERVER_NAME}.${MYDOMAIN} --link ${AMBARI_SERVER_NAME}:ambariserver --entrypoint /bin/sh $IMAGE -c $COMMAND } amb-shell() { @@ -122,7 +122,7 @@ eagle-deploy-cluster() { } amb-start-first() { - run-command docker run -p 9099:9099 -p 8080:8080 -p 8744:8744 -p 2181:2181 -p 2888:2888 -p 6667:6667 -p 60020:60020 -p 60030:60030 -p 60010:60010 -d $DOCKER_OPTS --name $AMBARI_SERVER_NAME -h $AMBARI_SERVER_NAME.$MYDOMAIN --privileged=true $IMAGE --tag ambari-server=true + run-command docker run -m 5g --cpus 0.000 --memory-swap -1 -p 9090:9090 -p 8080:8080 -p 8744:8744 -p 2181:2181 -p 2888:2888 -p 6667:6667 -p 60020:60020 -p 60030:60030 -p 60010:60010 -p 50070:50070 -d $DOCKER_OPTS --name $AMBARI_SERVER_NAME -h $AMBARI_SERVER_NAME.$MYDOMAIN --privileged=true $IMAGE --tag ambari-server=true } amb-copy-to-hdfs() { @@ -160,4 +160,4 @@ amb-start-node() { MORE_OPTIONS="$@" fi run-command docker run $MORE_OPTIONS -e SERF_JOIN_IP=$AMBARI_SERVER_IP $DOCKER_OPTS --name ${NODE_PREFIX}_$NUMBER -h ${NODE_PREFIX}_${NUMBER}.$MYDOMAIN $IMAGE --log-level debug -} +} \ No newline at end of file http://git-wip-us.apache.org/repos/asf/eagle/blob/39ab83e6/eagle-external/eagle-docker/resource/deploy-eagle.sh ---------------------------------------------------------------------- diff --git a/eagle-external/eagle-docker/resource/deploy-eagle.sh b/eagle-external/eagle-docker/resource/deploy-eagle.sh index a1e5a19..c0de256 100755 --- a/eagle-external/eagle-docker/resource/deploy-eagle.sh +++ b/eagle-external/eagle-docker/resource/deploy-eagle.sh @@ -35,51 +35,39 @@ echo "" echo "Eagle home folder path is $EAGLE_HOME" cd $EAGLE_HOME - +# hbase tables will be autocreated now #Initializing Eagle Service ... -sh ./bin/eagle-service-init.sh - -sleep 10 +#sh ./bin/eagle-service-init.sh +# +#sleep 10 #Starting Eagle Service ... -sh ./bin/eagle-service.sh start +sh ./bin/eagle-server.sh start sleep 10 echo "Creating kafka topics for eagle ... " KAFKA_HOME=/usr/hdp/current/kafka-broker EAGLE_ZOOKEEPER_QUORUM=$EAGLE_SERVER_HOST:2181 -topic=`${KAFKA_HOME}/bin/kafka-topics.sh --list --zookeeper $EAGLE_ZOOKEEPER_QUORUM --topic sandbox_hdfs_audit_log` +KAFKA_TOPIC_NAME=sandbox_hdfs_audit_log +topic=`${KAFKA_HOME}/bin/kafka-topics.sh --list --zookeeper $EAGLE_ZOOKEEPER_QUORUM --topic $KAFKA_TOPIC_NAME` if [ -z $topic ]; then - $KAFKA_HOME/bin/kafka-topics.sh --create --zookeeper $EAGLE_ZOOKEEPER_QUORUM --replication-factor 1 --partitions 1 --topic sandbox_hdfs_audit_log -fi - -if [ $? = 0 ]; then -echo "==> Create kafka topic successfully for eagle" + $KAFKA_HOME/bin/kafka-topics.sh --create --zookeeper $EAGLE_ZOOKEEPER_QUORUM --replication-factor 1 --partitions 1 --topic $KAFKA_TOPIC_NAME + if [ $? = 0 ]; then + echo "==> Created kafka topic: $KAFKA_TOPIC_NAME successfully for eagle" + else + echo "==> Failed to create required topic: $KAFKA_TOPIC_NAME, exiting" + exit 1 + fi else -echo "==> Failed, exiting" -exit 1 + echo "==> Kafka topic:$KAFKA_TOPIC_NAME already exists for eagl" fi EAGLE_NIMBUS_HOST=$EAGLE_SERVER_HOST EAGLE_SERVICE_HOST=$EAGLE_SERVER_HOST -EAGLE_TOPOLOGY_JAR=`ls ${EAGLE_HOME}/lib/topology/eagle-topology-*-assembly.jar` - -${EAGLE_HOME}/bin/eagle-topology-init.sh -[ $? != 0 ] && exit 1 -${EAGLE_HOME}/examples/sample-sensitivity-resource-create.sh -[ $? != 0 ] && exit 1 -${EAGLE_HOME}/examples/sample-policy-create.sh -[ $? != 0 ] && exit 1 -storm jar $EAGLE_TOPOLOGY_JAR org.apache.eagle.security.auditlog.HdfsAuditLogProcessorMain -D config.file=${EAGLE_HOME}/conf/sandbox-hdfsAuditLog-application.conf -D eagleProps.eagleService.host=$EAGLE_SERVICE_HOST -[ $? != 0 ] && exit 1 -storm jar $EAGLE_TOPOLOGY_JAR org.apache.eagle.security.hive.jobrunning.HiveJobRunningMonitoringMain -D config.file=${EAGLE_HOME}/conf/sandbox-hiveQueryLog-application.conf -D eagleProps.eagleService.host=$EAGLE_SERVICE_HOST -[ $? != 0 ] && exit 1 -storm jar $EAGLE_TOPOLOGY_JAR org.apache.eagle.security.userprofile.UserProfileDetectionMain -D config.file=${EAGLE_HOME}/conf/sandbox-userprofile-topology.conf -D eagleProps.eagleService.host=$EAGLE_SERVICE_HOST -[ $? != 0 ] && exit 1 +EAGLE_TOPOLOGY_JAR=`ls ${EAGLE_HOME}/lib/eagle-topology-*-assembly.jar` # TODO: More eagle start echo "Eagle is deployed successfully!" - -echo "Please visit http://<container_ip>:9099/eagle-service to play with Eagle!" +echo "Please visit http://$EAGLE_SERVER_HOST:9090 to play with Eagle!" http://git-wip-us.apache.org/repos/asf/eagle/blob/39ab83e6/eagle-external/eagle-docker/resource/eagle-multinode.json ---------------------------------------------------------------------- diff --git a/eagle-external/eagle-docker/resource/eagle-multinode.json b/eagle-external/eagle-docker/resource/eagle-multinode.json index 4c1071a..dfa5145 100644 --- a/eagle-external/eagle-docker/resource/eagle-multinode.json +++ b/eagle-external/eagle-docker/resource/eagle-multinode.json @@ -12,14 +12,14 @@ { "hadoop-env": { "properties": { - "content": "\r\n# Set Hadoop-specific environment variables here.\r\n\r\n# The only required environment variable is JAVA_HOME. All others are\r\n# optional. When running a distributed configuration it is best to\r\n# set JAVA_HOME in this file, so that it is correctly defined on\r\n# remote nodes.\r\n\r\n# The java implementation to use. Required.\r\nexport JAVA_HOME={{java_home}}\r\nexport HADOOP_HOME_WARN_SUPPRESS=1\r\n\r\n# Hadoop home directory\r\nexport HADOOP_HOME=${HADOOP_HOME:-{{hadoop_home}}}\r\n\r\n# Hadoop Configuration Directory\r\n\r\n{# this is different for HDP1 #}\r\n# Path to jsvc required by secure HDP 2.0 datanode\r\nexport JSVC_HOME={{jsvc_path}}\r\n\r\n\r\n# The maximum amount of heap to use, in MB. Default is 1000.\r\nexport HADOOP_HEAPSIZE=\"{{hadoop_heapsize}}\"\r\n\r\nexport HADOOP_NAMENODE_INIT_HEAPSIZE=\"-Xms{{namenode_heapsize}}\"\r\n\r\n# Extra Java runtime options. Empty by default.\r\nexport HADOOP_OPTS=\"-Djava.net.preferIPv4Stack=true ${HADOOP_OPTS}\"\r\n\r\n# Command specific options appended to HADOOP_OPTS when specified\r\nexport HADOOP_NAMENODE_OPTS=\"-server -XX:ParallelGCThreads=8 -XX:+UseConcMarkSweepGC -XX:ErrorFile={{hdfs_log_dir_prefix}}/$USER/hs_err_pid%p.log -XX:NewSize={{namenode_opt_newsize}} -XX:MaxNewSize={{namenode_opt_maxnewsize}} -XX:PermSize={{namenode_opt_permsize}} -XX:MaxPermSize={{namenode_opt_maxpermsize}} -Xloggc:{{hdfs_log_dir_prefix}}/$USER/gc.log-`date +'%Y%m%d%H%M'` -verbose:gc -XX:+PrintGCDetails -XX:+PrintGCTimeStamps -XX:+PrintGCDateStamps -Xms{{namenode_heapsize}} -Xmx{{namenode_heapsize}} -Dhadoop.security.logger=INFO,DRFAS -Dhdfs.audit.logger=INFO,DRFAAUDIT,KAFKA_HDFS_AUDIT ${HADOOP_NAMENODE_OPTS}\"\r\nHADOOP_JOBTRACKER_OPTS=\"-server -XX:ParallelGCThreads=8 -XX:+UseConcMarkSweepGC -XX:ErrorFile={{hdfs_log_dir_prefix}}/$USER/hs_err_pid%p.log -XX:NewSize={{jtnode_opt_newsize}} -XX:MaxNewSize={{jtnode_opt_maxnewsize}} -Xloggc:{{hdfs_log_dir_prefix}}/$USER/gc.log-`date +'%Y%m%d%H% M'` -verbose:gc -XX:+PrintGCDetails -XX:+PrintGCTimeStamps -XX:+PrintGCDateStamps -Xmx{{jtnode_heapsize}} -Dhadoop.security.logger=INFO,DRFAS -Dmapred.audit.logger=INFO,MRAUDIT -Dhadoop.mapreduce.jobsummary.logger=INFO,JSA ${HADOOP_JOBTRACKER_OPTS}\"\r\n\r\nHADOOP_TASKTRACKER_OPTS=\"-server -Xmx{{ttnode_heapsize}} -Dhadoop.security.logger=ERROR,console -Dmapred.audit.logger=ERROR,console ${HADOOP_TASKTRACKER_OPTS}\"\r\nexport HADOOP_DATANODE_OPTS=\"-server -XX:ParallelGCThreads=4 -XX:+UseConcMarkSweepGC -XX:ErrorFile=/var/log/hadoop/$USER/hs_err_pid%p.log -XX:NewSize=200m -XX:MaxNewSize=200m -XX:PermSize=128m -XX:MaxPermSize=256m -Xloggc:/var/log/hadoop/$USER/gc.log-`date +'%Y%m%d%H%M'` -verbose:gc -XX:+PrintGCDetails -XX:+PrintGCTimeStamps -XX:+PrintGCDateStamps -Xms{{dtnode_heapsize}} -Xmx{{dtnode_heapsize}} -Dhadoop.security.logger=INFO,DRFAS -Dhdfs.audit.logger=INFO,DRFAAUDIT ${HADOOP_DATANODE_OPTS}\"\r\nHADOOP_BALANCER_OPTS=\"-server -Xmx{{hadoop_heapsize}}m ${HADOOP_BALANCER_O PTS}\"\r\n\r\nexport HADOOP_SECONDARYNAMENODE_OPTS=$HADOOP_NAMENODE_OPTS\r\n\r\n# The following applies to multiple commands (fs, dfs, fsck, distcp etc)\r\nexport HADOOP_CLIENT_OPTS=\"-Xmx${HADOOP_HEAPSIZE}m -XX:MaxPermSize=512m $HADOOP_CLIENT_OPTS\"\r\n\r\n# On secure datanodes, user to run the datanode as after dropping privileges\r\nexport HADOOP_SECURE_DN_USER=${HADOOP_SECURE_DN_USER:-{{hadoop_secure_dn_user}}}\r\n\r\n# Extra ssh options. Empty by default.\r\nexport HADOOP_SSH_OPTS=\"-o ConnectTimeout=5 -o SendEnv=HADOOP_CONF_DIR\"\r\n\r\n# Where log files are stored. $HADOOP_HOME/logs by default.\r\nexport HADOOP_LOG_DIR={{hdfs_log_dir_prefix}}/$USER\r\n\r\n# History server logs\r\nexport HADOOP_MAPRED_LOG_DIR={{mapred_log_dir_prefix}}/$USER\r\n\r\n# Where log files are stored in the secure data environment.\r\nexport HADOOP_SECURE_DN_LOG_DIR={{hdfs_log_dir_prefix}}/$HADOOP_SECURE_DN_USER\r\n\r\n# File naming remote slave hosts. $HADOOP_HOME/conf/slaves by default.\r\n# expo rt HADOOP_SLAVES=${HADOOP_HOME}/conf/slaves\r\n\r\n# host:path where hadoop code should be rsync'd from. Unset by default.\r\n# export HADOOP_MASTER=master:/home/$USER/src/hadoop\r\n\r\n# Seconds to sleep between slave commands. Unset by default. This\r\n# can be useful in large clusters, where, e.g., slave rsyncs can\r\n# otherwise arrive faster than the master can service them.\r\n# export HADOOP_SLAVE_SLEEP=0.1\r\n\r\n# The directory where pid files are stored. /tmp by default.\r\nexport HADOOP_PID_DIR={{hadoop_pid_dir_prefix}}/$USER\r\nexport HADOOP_SECURE_DN_PID_DIR={{hadoop_pid_dir_prefix}}/$HADOOP_SECURE_DN_USER\r\n\r\n# History server pid\r\nexport HADOOP_MAPRED_PID_DIR={{mapred_pid_dir_prefix}}/$USER\r\n\r\nYARN_RESOURCEMANAGER_OPTS=\"-Dyarn.server.resourcemanager.appsummary.logger=INFO,RMSUMMARY\"\r\n\r\n# A string representing this instance of hadoop. $USER by default.\r\nexport HADOOP_IDENT_STRING=$USER\r\n\r\n# The scheduling priority for daemon processes. See 'man nice'.\r\n\r\n# export HADOOP_NICENESS=10\r\n\r\n# Use libraries from standard classpath\r\nJAVA_JDBC_LIBS=\"\"\r\n#Add libraries required by mysql connector\r\nfor jarFile in `ls /usr/share/java/*mysql* 2>/dev/null`\r\ndo\r\n JAVA_JDBC_LIBS=${JAVA_JDBC_LIBS}:$jarFile\r\ndone\r\n# Add libraries required by oracle connector\r\nfor jarFile in `ls /usr/share/java/*ojdbc* 2>/dev/null`\r\ndo\r\n JAVA_JDBC_LIBS=${JAVA_JDBC_LIBS}:$jarFile\r\ndone\r\n# Add libraries required by nodemanager\r\nMAPREDUCE_LIBS={{mapreduce_libs_path}}\r\nexport HADOOP_CLASSPATH=${HADOOP_CLASSPATH}${JAVA_JDBC_LIBS}:${MAPREDUCE_LIBS}:/usr/hdp/current/eagle/lib/log4jkafka/lib/*\r\n\r\n# added to the HADOOP_CLASSPATH\r\nif [ -d \"/usr/hdp/current/tez-client\" ]; then\r\n if [ -d \"/etc/tez/conf/\" ]; then\r\n # When using versioned RPMs, the tez-client will be a symlink to the current folder of tez in HDP.\r\n export HADOOP_CLASSPATH=${HADOOP_CLASSPATH}:/usr/hdp/current/tez-client/*:/usr/hdp/current/tez-cl ient/lib/*:/etc/tez/conf/\r\n fi\r\nfi\r\n\r\n# Setting path to hdfs command line\r\nexport HADOOP_LIBEXEC_DIR={{hadoop_libexec_dir}}\r\n\r\n# Mostly required for hadoop 2.0\r\nexport JAVA_LIBRARY_PATH=${JAVA_LIBRARY_PATH}\r\n\r\nexport HADOOP_OPTS=\"-Dhdp.version=$HDP_VERSION $HADOOP_OPTS\"\r\n" + "content": "\r\n# Set Hadoop-specific environment variables here.\r\n\r\n# The only required environment variable is JAVA_HOME. All others are\r\n# optional. When running a distributed configuration it is best to\r\n# set JAVA_HOME in this file, so that it is correctly defined on\r\n# remote nodes.\r\n\r\n# The java implementation to use. Required.\r\nexport JAVA_HOME=/usr/java/default\r\nexport HADOOP_HOME_WARN_SUPPRESS=1\r\n\r\n# Hadoop home directory\r\nexport HADOOP_HOME=${HADOOP_HOME:-{{hadoop_home}}}\r\n\r\n# Hadoop Configuration Directory\r\n\r\n{# this is different for HDP1 #}\r\n# Path to jsvc required by secure HDP 2.0 datanode\r\nexport JSVC_HOME={{jsvc_path}}\r\n\r\n\r\n# The maximum amount of heap to use, in MB. Default is 1000.\r\nexport HADOOP_HEAPSIZE=\"{{hadoop_heapsize}}\"\r\n\r\nexport HADOOP_NAMENODE_INIT_HEAPSIZE=\"-Xms{{namenode_heapsize}}\"\r\n\r\n# Extra Java runtime options. Empty by default.\r\nexport HADOOP_OPTS=\"-Djava.net.preferIPv4Stack=t rue ${HADOOP_OPTS}\"\r\n\r\n# Command specific options appended to HADOOP_OPTS when specified\r\nexport HADOOP_NAMENODE_OPTS=\"-server -XX:ParallelGCThreads=8 -XX:+UseConcMarkSweepGC -XX:ErrorFile={{hdfs_log_dir_prefix}}/$USER/hs_err_pid%p.log -XX:NewSize={{namenode_opt_newsize}} -XX:MaxNewSize={{namenode_opt_maxnewsize}} -XX:PermSize={{namenode_opt_permsize}} -XX:MaxPermSize={{namenode_opt_maxpermsize}} -Xloggc:{{hdfs_log_dir_prefix}}/$USER/gc.log-`date +'%Y%m%d%H%M'` -verbose:gc -XX:+PrintGCDetails -XX:+PrintGCTimeStamps -XX:+PrintGCDateStamps -Xms{{namenode_heapsize}} -Xmx{{namenode_heapsize}} -Dhadoop.security.logger=INFO,DRFAS -Dhdfs.audit.logger=INFO,DRFAAUDIT,KAFKA_HDFS_AUDIT ${HADOOP_NAMENODE_OPTS}\"\r\nHADOOP_JOBTRACKER_OPTS=\"-server -XX:ParallelGCThreads=8 -XX:+UseConcMarkSweepGC -XX:ErrorFile={{hdfs_log_dir_prefix}}/$USER/hs_err_pid%p.log -XX:NewSize={{jtnode_opt_newsize}} -XX:MaxNewSize={{jtnode_opt_maxnewsize}} -Xloggc:{{hdfs_log_dir_prefix}}/$USER/gc.log-`date +'%Y%m% d%H%M'` -verbose:gc -XX:+PrintGCDetails -XX:+PrintGCTimeStamps -XX:+PrintGCDateStamps -Xmx{{jtnode_heapsize}} -Dhadoop.security.logger=INFO,DRFAS -Dmapred.audit.logger=INFO,MRAUDIT -Dhadoop.mapreduce.jobsummary.logger=INFO,JSA ${HADOOP_JOBTRACKER_OPTS}\"\r\n\r\nHADOOP_TASKTRACKER_OPTS=\"-server -Xmx{{ttnode_heapsize}} -Dhadoop.security.logger=ERROR,console -Dmapred.audit.logger=ERROR,console ${HADOOP_TASKTRACKER_OPTS}\"\r\nexport HADOOP_DATANODE_OPTS=\"-server -XX:ParallelGCThreads=4 -XX:+UseConcMarkSweepGC -XX:ErrorFile=/var/log/hadoop/$USER/hs_err_pid%p.log -XX:NewSize=200m -XX:MaxNewSize=200m -XX:PermSize=128m -XX:MaxPermSize=256m -Xloggc:/var/log/hadoop/$USER/gc.log-`date +'%Y%m%d%H%M'` -verbose:gc -XX:+PrintGCDetails -XX:+PrintGCTimeStamps -XX:+PrintGCDateStamps -Xms{{dtnode_heapsize}} -Xmx{{dtnode_heapsize}} -Dhadoop.security.logger=INFO,DRFAS -Dhdfs.audit.logger=INFO,DRFAAUDIT ${HADOOP_DATANODE_OPTS}\"\r\nHADOOP_BALANCER_OPTS=\"-server -Xmx{{hadoop_heapsize}}m ${HADOOP_BALANC ER_OPTS}\"\r\n\r\nexport HADOOP_SECONDARYNAMENODE_OPTS=$HADOOP_NAMENODE_OPTS\r\n\r\n# The following applies to multiple commands (fs, dfs, fsck, distcp etc)\r\nexport HADOOP_CLIENT_OPTS=\"-Xmx${HADOOP_HEAPSIZE}m -XX:MaxPermSize=512m $HADOOP_CLIENT_OPTS\"\r\n\r\n# On secure datanodes, user to run the datanode as after dropping privileges\r\nexport HADOOP_SECURE_DN_USER=${HADOOP_SECURE_DN_USER:-{{hadoop_secure_dn_user}}}\r\n\r\n# Extra ssh options. Empty by default.\r\nexport HADOOP_SSH_OPTS=\"-o ConnectTimeout=5 -o SendEnv=HADOOP_CONF_DIR\"\r\n\r\n# Where log files are stored. $HADOOP_HOME/logs by default.\r\nexport HADOOP_LOG_DIR={{hdfs_log_dir_prefix}}/$USER\r\n\r\n# History server logs\r\nexport HADOOP_MAPRED_LOG_DIR={{mapred_log_dir_prefix}}/$USER\r\n\r\n# Where log files are stored in the secure data environment.\r\nexport HADOOP_SECURE_DN_LOG_DIR={{hdfs_log_dir_prefix}}/$HADOOP_SECURE_DN_USER\r\n\r\n# File naming remote slave hosts. $HADOOP_HOME/conf/slaves by default.\r\n# export HADOOP_SLAVES=${HADOOP_HOME}/conf/slaves\r\n\r\n# host:path where hadoop code should be rsync'd from. Unset by default.\r\n# export HADOOP_MASTER=master:/home/$USER/src/hadoop\r\n\r\n# Seconds to sleep between slave commands. Unset by default. This\r\n# can be useful in large clusters, where, e.g., slave rsyncs can\r\n# otherwise arrive faster than the master can service them.\r\n# export HADOOP_SLAVE_SLEEP=0.1\r\n\r\n# The directory where pid files are stored. /tmp by default.\r\nexport HADOOP_PID_DIR={{hadoop_pid_dir_prefix}}/$USER\r\nexport HADOOP_SECURE_DN_PID_DIR={{hadoop_pid_dir_prefix}}/$HADOOP_SECURE_DN_USER\r\n\r\n# History server pid\r\nexport HADOOP_MAPRED_PID_DIR={{mapred_pid_dir_prefix}}/$USER\r\n\r\nYARN_RESOURCEMANAGER_OPTS=\"-Dyarn.server.resourcemanager.appsummary.logger=INFO,RMSUMMARY\"\r\n\r\n# A string representing this instance of hadoop. $USER by default.\r\nexport HADOOP_IDENT_STRING=$USER\r\n\r\n# The scheduling priority for daemon processes. See ' man nice'.\r\n\r\n# export HADOOP_NICENESS=10\r\n\r\n# Use libraries from standard classpath\r\nJAVA_JDBC_LIBS=\"\"\r\n#Add libraries required by mysql connector\r\nfor jarFile in `ls /usr/share/java/*mysql* 2>/dev/null`\r\ndo\r\n JAVA_JDBC_LIBS=${JAVA_JDBC_LIBS}:$jarFile\r\ndone\r\n# Add libraries required by oracle connector\r\nfor jarFile in `ls /usr/share/java/*ojdbc* 2>/dev/null`\r\ndo\r\n JAVA_JDBC_LIBS=${JAVA_JDBC_LIBS}:$jarFile\r\ndone\r\n# Add libraries required by nodemanager\r\nMAPREDUCE_LIBS={{mapreduce_libs_path}}\r\nexport HADOOP_CLASSPATH=${HADOOP_CLASSPATH}${JAVA_JDBC_LIBS}:${MAPREDUCE_LIBS}:/usr/hdp/current/eagle/lib/common/*:/usr/hdp/current/kafka-broker/libs/*\r\n\r\n# added to the HADOOP_CLASSPATH\r\nif [ -d \"/usr/hdp/current/tez-client\" ]; then\r\n if [ -d \"/etc/tez/conf/\" ]; then\r\n # When using versioned RPMs, the tez-client will be a symlink to the current folder of tez in HDP.\r\n export HADOOP_CLASSPATH=${HADOOP_CLASSPATH}:/usr/hdp/current/tez -client/*:/usr/hdp/current/tez-client/lib/*:/etc/tez/conf/\r\n fi\r\nfi\r\n\r\n# Setting path to hdfs command line\r\nexport HADOOP_LIBEXEC_DIR={{hadoop_libexec_dir}}\r\n\r\n# Mostly required for hadoop 2.0\r\nexport JAVA_LIBRARY_PATH=${JAVA_LIBRARY_PATH}\r\n\r\nexport HADOOP_OPTS=\"-Dhdp.version=$HDP_VERSION $HADOOP_OPTS\"\r\n" } } }, { "hdfs-log4j": { "properties": { - "content": "\r\n#\r\n# Licensed to the Apache Software Foundation (ASF) under one\r\n# or more contributor license agreements. See the NOTICE file\r\n# distributed with this work for additional information\r\n# regarding copyright ownership. The ASF licenses this file\r\n# to you under the Apache License, Version 2.0 (the\r\n# \"License\"); you may not use this file except in compliance\r\n# with the License. You may obtain a copy of the License at\r\n#\r\n# http://www.apache.org/licenses/LICENSE-2.0\r\n#\r\n# Unless required by applicable law or agreed to in writing,\r\n# software distributed under the License is distributed on an\r\n# \"AS IS\" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY\r\n# KIND, either express or implied. See the License for the\r\n# specific language governing permissions and limitations\r\n# under the License.\r\n#\r\n\r\n\r\n# Define some default values that can be overridden by system properties\r\n# To change daemon root logger use hadoop _root_logger in hadoop-env\r\nhadoop.root.logger=INFO,console\r\nhadoop.log.dir=.\r\nhadoop.log.file=hadoop.log\r\n\r\n\r\n# Define the root logger to the system property \"hadoop.root.logger\".\r\nlog4j.rootLogger=${hadoop.root.logger}, EventCounter\r\n\r\n# Logging Threshold\r\nlog4j.threshhold=ALL\r\n\r\n#\r\n# Daily Rolling File Appender\r\n#\r\n\r\nlog4j.appender.DRFA=org.apache.log4j.DailyRollingFileAppender\r\nlog4j.appender.DRFA.File=${hadoop.log.dir}/${hadoop.log.file}\r\n\r\n# Rollver at midnight\r\nlog4j.appender.DRFA.DatePattern=.yyyy-MM-dd\r\n\r\n# 30-day backup\r\n#log4j.appender.DRFA.MaxBackupIndex=30\r\nlog4j.appender.DRFA.layout=org.apache.log4j.PatternLayout\r\n\r\n# Pattern format: Date LogLevel LoggerName LogMessage\r\nlog4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n\r\n# Debugging Pattern format\r\n#log4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n\r\n\r\n\r\n#\r\n# console\r\n# Add \"console\" to rootlogg er above if you want to use this\r\n#\r\n\r\nlog4j.appender.console=org.apache.log4j.ConsoleAppender\r\nlog4j.appender.console.target=System.err\r\nlog4j.appender.console.layout=org.apache.log4j.PatternLayout\r\nlog4j.appender.console.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{2}: %m%n\r\n\r\n#\r\n# TaskLog Appender\r\n#\r\n\r\n#Default values\r\nhadoop.tasklog.taskid=null\r\nhadoop.tasklog.iscleanup=false\r\nhadoop.tasklog.noKeepSplits=4\r\nhadoop.tasklog.totalLogFileSize=100\r\nhadoop.tasklog.purgeLogSplits=true\r\nhadoop.tasklog.logsRetainHours=12\r\n\r\nlog4j.appender.TLA=org.apache.hadoop.mapred.TaskLogAppender\r\nlog4j.appender.TLA.taskId=${hadoop.tasklog.taskid}\r\nlog4j.appender.TLA.isCleanup=${hadoop.tasklog.iscleanup}\r\nlog4j.appender.TLA.totalLogFileSize=${hadoop.tasklog.totalLogFileSize}\r\n\r\nlog4j.appender.TLA.layout=org.apache.log4j.PatternLayout\r\nlog4j.appender.TLA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n\r\n\r\n#\r\n#Security audit appender\r\n #\r\nhadoop.security.logger=INFO,console\r\nhadoop.security.log.maxfilesize=256MB\r\nhadoop.security.log.maxbackupindex=20\r\nlog4j.category.SecurityLogger=${hadoop.security.logger}\r\nhadoop.security.log.file=SecurityAuth.audit\r\nlog4j.appender.DRFAS=org.apache.log4j.DailyRollingFileAppender\r\nlog4j.appender.DRFAS.File=${hadoop.log.dir}/${hadoop.security.log.file}\r\nlog4j.appender.DRFAS.layout=org.apache.log4j.PatternLayout\r\nlog4j.appender.DRFAS.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n\r\nlog4j.appender.DRFAS.DatePattern=.yyyy-MM-dd\r\n\r\nlog4j.appender.RFAS=org.apache.log4j.RollingFileAppender\r\nlog4j.appender.RFAS.File=${hadoop.log.dir}/${hadoop.security.log.file}\r\nlog4j.appender.RFAS.layout=org.apache.log4j.PatternLayout\r\nlog4j.appender.RFAS.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n\r\nlog4j.appender.RFAS.MaxFileSize=${hadoop.security.log.maxfilesize}\r\nlog4j.appender.RFAS.MaxBackupIndex=${hadoop.security.log.maxbackupindex}\r\n\r\n#\r\n# hdfs audit lo gging\r\n#\r\nhdfs.audit.logger=INFO,console\r\nlog4j.logger.org.apache.hadoop.hdfs.server.namenode.FSNamesystem.audit=${hdfs.audit.logger}\r\nlog4j.additivity.org.apache.hadoop.hdfs.server.namenode.FSNamesystem.audit=false\r\nlog4j.appender.DRFAAUDIT=org.apache.log4j.DailyRollingFileAppender\r\nlog4j.appender.DRFAAUDIT.File=${hadoop.log.dir}/hdfs-audit.log\r\nlog4j.appender.DRFAAUDIT.layout=org.apache.log4j.PatternLayout\r\nlog4j.appender.DRFAAUDIT.layout.ConversionPattern=%d{ISO8601} %p %c{2}: %m%n\r\nlog4j.appender.DRFAAUDIT.DatePattern=.yyyy-MM-dd\r\n\r\nlog4j.appender.KAFKA_HDFS_AUDIT=org.apache.eagle.log4j.kafka.KafkaLog4jAppender\r\nlog4j.appender.KAFKA_HDFS_AUDIT.Topic=sandbox_hdfs_audit_log\r\nlog4j.appender.KAFKA_HDFS_AUDIT.BrokerList=sandbox.eagle.incubator.apache.org:6667\r\nlog4j.appender.KAFKA_HDFS_AUDIT.KeyClass=org.apache.eagle.log4j.kafka.hadoop.AuditLogKeyer\r\nlog4j.appender.KAFKA_HDFS_AUDIT.Layout=org.apache.log4j.PatternLayout\r\nlog4j.appender.KAFKA_HDFS_AUDIT. Layout.ConversionPattern=%d{ISO8601} %p %c{2}: %m%n\r\nlog4j.appender.KAFKA_HDFS_AUDIT.ProducerType=async\r\nlog4j.appender.KAFKA_HDFS_AUDIT.BatchSize=1\r\nlog4j.appender.KAFKA_HDFS_AUDIT.QueueSize=1\r\n\r\n#\r\n# mapred audit logging\r\n#\r\nmapred.audit.logger=INFO,console\r\nlog4j.logger.org.apache.hadoop.mapred.AuditLogger=${mapred.audit.logger}\r\nlog4j.additivity.org.apache.hadoop.mapred.AuditLogger=false\r\nlog4j.appender.MRAUDIT=org.apache.log4j.DailyRollingFileAppender\r\nlog4j.appender.MRAUDIT.File=${hadoop.log.dir}/mapred-audit.log\r\nlog4j.appender.MRAUDIT.layout=org.apache.log4j.PatternLayout\r\nlog4j.appender.MRAUDIT.layout.ConversionPattern=%d{ISO8601} %p %c{2}: %m%n\r\nlog4j.appender.MRAUDIT.DatePattern=.yyyy-MM-dd\r\n\r\n#\r\n# Rolling File Appender\r\n#\r\n\r\nlog4j.appender.RFA=org.apache.log4j.RollingFileAppender\r\nlog4j.appender.RFA.File=${hadoop.log.dir}/${hadoop.log.file}\r\n\r\n# Logfile size and and 30-day backups\r\nlog4j.appender.RFA.MaxFileSize=256MB\r\n log4j.appender.RFA.MaxBackupIndex=10\r\n\r\nlog4j.appender.RFA.layout=org.apache.log4j.PatternLayout\r\nlog4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} - %m%n\r\nlog4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n\r\n\r\n\r\n# Custom Logging levels\r\n\r\nhadoop.metrics.log.level=INFO\r\n#log4j.logger.org.apache.hadoop.mapred.JobTracker=DEBUG\r\n#log4j.logger.org.apache.hadoop.mapred.TaskTracker=DEBUG\r\n#log4j.logger.org.apache.hadoop.fs.FSNamesystem=DEBUG\r\nlog4j.logger.org.apache.hadoop.metrics2=${hadoop.metrics.log.level}\r\n\r\n# Jets3t library\r\nlog4j.logger.org.jets3t.service.impl.rest.httpclient.RestS3Service=ERROR\r\n\r\n#\r\n# Null Appender\r\n# Trap security logger on the hadoop client side\r\n#\r\nlog4j.appender.NullAppender=org.apache.log4j.varia.NullAppender\r\n\r\n#\r\n# Event Counter Appender\r\n# Sends counts of logging messages at different severity levels to Hadoop Metrics.\r\n#\r\nlog4j.appender.EventCounter= org.apache.hadoop.log.metrics.EventCounter\r\n\r\n# Removes \"deprecated\" messages\r\nlog4j.logger.org.apache.hadoop.conf.Configuration.deprecation=WARN\r\n\r\n#\r\n# HDFS block state change log from block manager\r\n#\r\n# Uncomment the following to suppress normal block state change\r\n# messages from BlockManager in NameNode.\r\n#log4j.logger.BlockStateChange=WARN\r\n" + "content": "\r\n#\r\n# Licensed to the Apache Software Foundation (ASF) under one\r\n# or more contributor license agreements. See the NOTICE file\r\n# distributed with this work for additional information\r\n# regarding copyright ownership. The ASF licenses this file\r\n# to you under the Apache License, Version 2.0 (the\r\n# \"License\"); you may not use this file except in compliance\r\n# with the License. You may obtain a copy of the License at\r\n#\r\n# http://www.apache.org/licenses/LICENSE-2.0\r\n#\r\n# Unless required by applicable law or agreed to in writing,\r\n# software distributed under the License is distributed on an\r\n# \"AS IS\" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY\r\n# KIND, either express or implied. See the License for the\r\n# specific language governing permissions and limitations\r\n# under the License.\r\n#\r\n\r\n\r\n# Define some default values that can be overridden by system properties\r\n# To change daemon root logger use hadoop _root_logger in hadoop-env\r\nhadoop.root.logger=INFO,console\r\nhadoop.log.dir=.\r\nhadoop.log.file=hadoop.log\r\n\r\n\r\n# Define the root logger to the system property \"hadoop.root.logger\".\r\nlog4j.rootLogger=${hadoop.root.logger}, EventCounter\r\n\r\n# Logging Threshold\r\nlog4j.threshhold=ALL\r\n\r\n#\r\n# Daily Rolling File Appender\r\n#\r\n\r\nlog4j.appender.DRFA=org.apache.log4j.DailyRollingFileAppender\r\nlog4j.appender.DRFA.File=${hadoop.log.dir}/${hadoop.log.file}\r\n\r\n# Rollver at midnight\r\nlog4j.appender.DRFA.DatePattern=.yyyy-MM-dd\r\n\r\n# 30-day backup\r\n#log4j.appender.DRFA.MaxBackupIndex=30\r\nlog4j.appender.DRFA.layout=org.apache.log4j.PatternLayout\r\n\r\n# Pattern format: Date LogLevel LoggerName LogMessage\r\nlog4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n\r\n# Debugging Pattern format\r\n#log4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n\r\n\r\n\r\n#\r\n# console\r\n# Add \"console\" to rootlogg er above if you want to use this\r\n#\r\n\r\nlog4j.appender.console=org.apache.log4j.ConsoleAppender\r\nlog4j.appender.console.target=System.err\r\nlog4j.appender.console.layout=org.apache.log4j.PatternLayout\r\nlog4j.appender.console.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{2}: %m%n\r\n\r\n#\r\n# TaskLog Appender\r\n#\r\n\r\n#Default values\r\nhadoop.tasklog.taskid=null\r\nhadoop.tasklog.iscleanup=false\r\nhadoop.tasklog.noKeepSplits=4\r\nhadoop.tasklog.totalLogFileSize=100\r\nhadoop.tasklog.purgeLogSplits=true\r\nhadoop.tasklog.logsRetainHours=12\r\n\r\nlog4j.appender.TLA=org.apache.hadoop.mapred.TaskLogAppender\r\nlog4j.appender.TLA.taskId=${hadoop.tasklog.taskid}\r\nlog4j.appender.TLA.isCleanup=${hadoop.tasklog.iscleanup}\r\nlog4j.appender.TLA.totalLogFileSize=${hadoop.tasklog.totalLogFileSize}\r\n\r\nlog4j.appender.TLA.layout=org.apache.log4j.PatternLayout\r\nlog4j.appender.TLA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n\r\n\r\n#\r\n#Security audit appender\r\n #\r\nhadoop.security.logger=INFO,console\r\nhadoop.security.log.maxfilesize=256MB\r\nhadoop.security.log.maxbackupindex=20\r\nlog4j.category.SecurityLogger=${hadoop.security.logger}\r\nhadoop.security.log.file=SecurityAuth.audit\r\nlog4j.appender.DRFAS=org.apache.log4j.DailyRollingFileAppender\r\nlog4j.appender.DRFAS.File=${hadoop.log.dir}/${hadoop.security.log.file}\r\nlog4j.appender.DRFAS.layout=org.apache.log4j.PatternLayout\r\nlog4j.appender.DRFAS.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n\r\nlog4j.appender.DRFAS.DatePattern=.yyyy-MM-dd\r\n\r\nlog4j.appender.RFAS=org.apache.log4j.RollingFileAppender\r\nlog4j.appender.RFAS.File=${hadoop.log.dir}/${hadoop.security.log.file}\r\nlog4j.appender.RFAS.layout=org.apache.log4j.PatternLayout\r\nlog4j.appender.RFAS.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n\r\nlog4j.appender.RFAS.MaxFileSize=${hadoop.security.log.maxfilesize}\r\nlog4j.appender.RFAS.MaxBackupIndex=${hadoop.security.log.maxbackupindex}\r\n\r\n#\r\n# hdfs audit lo gging\r\n#\r\nhdfs.audit.logger=INFO,console\r\nlog4j.logger.org.apache.hadoop.hdfs.server.namenode.FSNamesystem.audit=${hdfs.audit.logger}\r\nlog4j.additivity.org.apache.hadoop.hdfs.server.namenode.FSNamesystem.audit=false\r\nlog4j.appender.DRFAAUDIT=org.apache.log4j.DailyRollingFileAppender\r\nlog4j.appender.DRFAAUDIT.File=${hadoop.log.dir}/hdfs-audit.log\r\nlog4j.appender.DRFAAUDIT.layout=org.apache.log4j.PatternLayout\r\nlog4j.appender.DRFAAUDIT.layout.ConversionPattern=%d{ISO8601} %p %c{2}: %m%n\r\nlog4j.appender.DRFAAUDIT.DatePattern=.yyyy-MM-dd\r\n\r\nlog4j.appender.KAFKA_HDFS_AUDIT=org.apache.eagle.log4j.kafka.KafkaLog4jAppender\r\nlog4j.appender.KAFKA_HDFS_AUDIT.Topic=sandbox_hdfs_audit_log\r\nlog4j.appender.KAFKA_HDFS_AUDIT.BrokerList=server.eagle.apache.org:6667\r\nlog4j.appender.KAFKA_HDFS_AUDIT.KeyClass=org.apache.eagle.log4j.kafka.hadoop.AuditLogKeyer\r\nlog4j.appender.KAFKA_HDFS_AUDIT.Layout=org.apache.log4j.PatternLayout\r\nlog4j.appender.KAFKA_HDFS_AUDIT.Layout.Conv ersionPattern=%d{ISO8601} %p %c{2}: %m%n\r\nlog4j.appender.KAFKA_HDFS_AUDIT.ProducerType=async\r\nlog4j.appender.KAFKA_HDFS_AUDIT.BatchSize=1\r\nlog4j.appender.KAFKA_HDFS_AUDIT.QueueSize=1\r\n\r\n#\r\n# mapred audit logging\r\n#\r\nmapred.audit.logger=INFO,console\r\nlog4j.logger.org.apache.hadoop.mapred.AuditLogger=${mapred.audit.logger}\r\nlog4j.additivity.org.apache.hadoop.mapred.AuditLogger=false\r\nlog4j.appender.MRAUDIT=org.apache.log4j.DailyRollingFileAppender\r\nlog4j.appender.MRAUDIT.File=${hadoop.log.dir}/mapred-audit.log\r\nlog4j.appender.MRAUDIT.layout=org.apache.log4j.PatternLayout\r\nlog4j.appender.MRAUDIT.layout.ConversionPattern=%d{ISO8601} %p %c{2}: %m%n\r\nlog4j.appender.MRAUDIT.DatePattern=.yyyy-MM-dd\r\n\r\n#\r\n# Rolling File Appender\r\n#\r\n\r\nlog4j.appender.RFA=org.apache.log4j.RollingFileAppender\r\nlog4j.appender.RFA.File=${hadoop.log.dir}/${hadoop.log.file}\r\n\r\n# Logfile size and and 30-day backups\r\nlog4j.appender.RFA.MaxFileSize=256MB\r\nlog4j.appen der.RFA.MaxBackupIndex=10\r\n\r\nlog4j.appender.RFA.layout=org.apache.log4j.PatternLayout\r\nlog4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} - %m%n\r\nlog4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n\r\n\r\n\r\n# Custom Logging levels\r\n\r\nhadoop.metrics.log.level=INFO\r\n#log4j.logger.org.apache.hadoop.mapred.JobTracker=DEBUG\r\n#log4j.logger.org.apache.hadoop.mapred.TaskTracker=DEBUG\r\n#log4j.logger.org.apache.hadoop.fs.FSNamesystem=DEBUG\r\nlog4j.logger.org.apache.hadoop.metrics2=${hadoop.metrics.log.level}\r\n\r\n# Jets3t library\r\nlog4j.logger.org.jets3t.service.impl.rest.httpclient.RestS3Service=ERROR\r\n\r\n#\r\n# Null Appender\r\n# Trap security logger on the hadoop client side\r\n#\r\nlog4j.appender.NullAppender=org.apache.log4j.varia.NullAppender\r\n\r\n#\r\n# Event Counter Appender\r\n# Sends counts of logging messages at different severity levels to Hadoop Metrics.\r\n#\r\nlog4j.appender.EventCounter=org.apache. hadoop.log.metrics.EventCounter\r\n\r\n# Removes \"deprecated\" messages\r\nlog4j.logger.org.apache.hadoop.conf.Configuration.deprecation=WARN\r\n\r\n#\r\n# HDFS block state change log from block manager\r\n#\r\n# Uncomment the following to suppress normal block state change\r\n# messages from BlockManager in NameNode.\r\n#log4j.logger.BlockStateChange=WARN\r\n" } } } http://git-wip-us.apache.org/repos/asf/eagle/blob/39ab83e6/eagle-external/eagle-docker/resource/eagle-singlenode.json ---------------------------------------------------------------------- diff --git a/eagle-external/eagle-docker/resource/eagle-singlenode.json b/eagle-external/eagle-docker/resource/eagle-singlenode.json index d070689..ac822fd 100644 --- a/eagle-external/eagle-docker/resource/eagle-singlenode.json +++ b/eagle-external/eagle-docker/resource/eagle-singlenode.json @@ -10,16 +10,26 @@ } }, { + "hbase-site": { + "properties" : { + "zookeeper.znode.parent" : "/hbase-unsecure", + "hbase.zookeeper.property.clientPort" : "2181", + "hbase.rootdir" : "hdfs://server.eagle.apache.org:8020/hbase", + "hbase.cluster.distributed" : "true" + } + } + }, + { "hadoop-env": { "properties": { - "content": "\r\n# Set Hadoop-specific environment variables here.\r\n\r\n# The only required environment variable is JAVA_HOME. All others are\r\n# optional. When running a distributed configuration it is best to\r\n# set JAVA_HOME in this file, so that it is correctly defined on\r\n# remote nodes.\r\n\r\n# The java implementation to use. Required.\r\nexport JAVA_HOME={{java_home}}\r\nexport HADOOP_HOME_WARN_SUPPRESS=1\r\n\r\n# Hadoop home directory\r\nexport HADOOP_HOME=${HADOOP_HOME:-{{hadoop_home}}}\r\n\r\n# Hadoop Configuration Directory\r\n\r\n{# this is different for HDP1 #}\r\n# Path to jsvc required by secure HDP 2.0 datanode\r\nexport JSVC_HOME={{jsvc_path}}\r\n\r\n\r\n# The maximum amount of heap to use, in MB. Default is 1000.\r\nexport HADOOP_HEAPSIZE=\"{{hadoop_heapsize}}\"\r\n\r\nexport HADOOP_NAMENODE_INIT_HEAPSIZE=\"-Xms{{namenode_heapsize}}\"\r\n\r\n# Extra Java runtime options. Empty by default.\r\nexport HADOOP_OPTS=\"-Djava.net.preferIPv4Stack=true ${HADOOP_OPTS}\"\r\n\r\n# Command specific options appended to HADOOP_OPTS when specified\r\nexport HADOOP_NAMENODE_OPTS=\"-server -XX:ParallelGCThreads=8 -XX:+UseConcMarkSweepGC -XX:ErrorFile={{hdfs_log_dir_prefix}}/$USER/hs_err_pid%p.log -XX:NewSize={{namenode_opt_newsize}} -XX:MaxNewSize={{namenode_opt_maxnewsize}} -XX:PermSize={{namenode_opt_permsize}} -XX:MaxPermSize={{namenode_opt_maxpermsize}} -Xloggc:{{hdfs_log_dir_prefix}}/$USER/gc.log-`date +'%Y%m%d%H%M'` -verbose:gc -XX:+PrintGCDetails -XX:+PrintGCTimeStamps -XX:+PrintGCDateStamps -Xms{{namenode_heapsize}} -Xmx{{namenode_heapsize}} -Dhadoop.security.logger=INFO,DRFAS -Dhdfs.audit.logger=INFO,DRFAAUDIT,KAFKA_HDFS_AUDIT ${HADOOP_NAMENODE_OPTS}\"\r\nHADOOP_JOBTRACKER_OPTS=\"-server -XX:ParallelGCThreads=8 -XX:+UseConcMarkSweepGC -XX:ErrorFile={{hdfs_log_dir_prefix}}/$USER/hs_err_pid%p.log -XX:NewSize={{jtnode_opt_newsize}} -XX:MaxNewSize={{jtnode_opt_maxnewsize}} -Xloggc:{{hdfs_log_dir_prefix}}/$USER/gc.log-`date +'%Y%m%d%H% M'` -verbose:gc -XX:+PrintGCDetails -XX:+PrintGCTimeStamps -XX:+PrintGCDateStamps -Xmx{{jtnode_heapsize}} -Dhadoop.security.logger=INFO,DRFAS -Dmapred.audit.logger=INFO,MRAUDIT -Dhadoop.mapreduce.jobsummary.logger=INFO,JSA ${HADOOP_JOBTRACKER_OPTS}\"\r\n\r\nHADOOP_TASKTRACKER_OPTS=\"-server -Xmx{{ttnode_heapsize}} -Dhadoop.security.logger=ERROR,console -Dmapred.audit.logger=ERROR,console ${HADOOP_TASKTRACKER_OPTS}\"\r\nexport HADOOP_DATANODE_OPTS=\"-server -XX:ParallelGCThreads=4 -XX:+UseConcMarkSweepGC -XX:ErrorFile=/var/log/hadoop/$USER/hs_err_pid%p.log -XX:NewSize=200m -XX:MaxNewSize=200m -XX:PermSize=128m -XX:MaxPermSize=256m -Xloggc:/var/log/hadoop/$USER/gc.log-`date +'%Y%m%d%H%M'` -verbose:gc -XX:+PrintGCDetails -XX:+PrintGCTimeStamps -XX:+PrintGCDateStamps -Xms{{dtnode_heapsize}} -Xmx{{dtnode_heapsize}} -Dhadoop.security.logger=INFO,DRFAS -Dhdfs.audit.logger=INFO,DRFAAUDIT ${HADOOP_DATANODE_OPTS}\"\r\nHADOOP_BALANCER_OPTS=\"-server -Xmx{{hadoop_heapsize}}m ${HADOOP_BALANCER_O PTS}\"\r\n\r\nexport HADOOP_SECONDARYNAMENODE_OPTS=$HADOOP_NAMENODE_OPTS\r\n\r\n# The following applies to multiple commands (fs, dfs, fsck, distcp etc)\r\nexport HADOOP_CLIENT_OPTS=\"-Xmx${HADOOP_HEAPSIZE}m -XX:MaxPermSize=512m $HADOOP_CLIENT_OPTS\"\r\n\r\n# On secure datanodes, user to run the datanode as after dropping privileges\r\nexport HADOOP_SECURE_DN_USER=${HADOOP_SECURE_DN_USER:-{{hadoop_secure_dn_user}}}\r\n\r\n# Extra ssh options. Empty by default.\r\nexport HADOOP_SSH_OPTS=\"-o ConnectTimeout=5 -o SendEnv=HADOOP_CONF_DIR\"\r\n\r\n# Where log files are stored. $HADOOP_HOME/logs by default.\r\nexport HADOOP_LOG_DIR={{hdfs_log_dir_prefix}}/$USER\r\n\r\n# History server logs\r\nexport HADOOP_MAPRED_LOG_DIR={{mapred_log_dir_prefix}}/$USER\r\n\r\n# Where log files are stored in the secure data environment.\r\nexport HADOOP_SECURE_DN_LOG_DIR={{hdfs_log_dir_prefix}}/$HADOOP_SECURE_DN_USER\r\n\r\n# File naming remote slave hosts. $HADOOP_HOME/conf/slaves by default.\r\n# expo rt HADOOP_SLAVES=${HADOOP_HOME}/conf/slaves\r\n\r\n# host:path where hadoop code should be rsync'd from. Unset by default.\r\n# export HADOOP_MASTER=master:/home/$USER/src/hadoop\r\n\r\n# Seconds to sleep between slave commands. Unset by default. This\r\n# can be useful in large clusters, where, e.g., slave rsyncs can\r\n# otherwise arrive faster than the master can service them.\r\n# export HADOOP_SLAVE_SLEEP=0.1\r\n\r\n# The directory where pid files are stored. /tmp by default.\r\nexport HADOOP_PID_DIR={{hadoop_pid_dir_prefix}}/$USER\r\nexport HADOOP_SECURE_DN_PID_DIR={{hadoop_pid_dir_prefix}}/$HADOOP_SECURE_DN_USER\r\n\r\n# History server pid\r\nexport HADOOP_MAPRED_PID_DIR={{mapred_pid_dir_prefix}}/$USER\r\n\r\nYARN_RESOURCEMANAGER_OPTS=\"-Dyarn.server.resourcemanager.appsummary.logger=INFO,RMSUMMARY\"\r\n\r\n# A string representing this instance of hadoop. $USER by default.\r\nexport HADOOP_IDENT_STRING=$USER\r\n\r\n# The scheduling priority for daemon processes. See 'man nice'.\r\n\r\n# export HADOOP_NICENESS=10\r\n\r\n# Use libraries from standard classpath\r\nJAVA_JDBC_LIBS=\"\"\r\n#Add libraries required by mysql connector\r\nfor jarFile in `ls /usr/share/java/*mysql* 2>/dev/null`\r\ndo\r\n JAVA_JDBC_LIBS=${JAVA_JDBC_LIBS}:$jarFile\r\ndone\r\n# Add libraries required by oracle connector\r\nfor jarFile in `ls /usr/share/java/*ojdbc* 2>/dev/null`\r\ndo\r\n JAVA_JDBC_LIBS=${JAVA_JDBC_LIBS}:$jarFile\r\ndone\r\n# Add libraries required by nodemanager\r\nMAPREDUCE_LIBS={{mapreduce_libs_path}}\r\nexport HADOOP_CLASSPATH=${HADOOP_CLASSPATH}${JAVA_JDBC_LIBS}:${MAPREDUCE_LIBS}:/usr/hdp/current/eagle/lib/log4jkafka/lib/*\r\n\r\n# added to the HADOOP_CLASSPATH\r\nif [ -d \"/usr/hdp/current/tez-client\" ]; then\r\n if [ -d \"/etc/tez/conf/\" ]; then\r\n # When using versioned RPMs, the tez-client will be a symlink to the current folder of tez in HDP.\r\n export HADOOP_CLASSPATH=${HADOOP_CLASSPATH}:/usr/hdp/current/tez-client/*:/usr/hdp/current/tez-cl ient/lib/*:/etc/tez/conf/\r\n fi\r\nfi\r\n\r\n# Setting path to hdfs command line\r\nexport HADOOP_LIBEXEC_DIR={{hadoop_libexec_dir}}\r\n\r\n# Mostly required for hadoop 2.0\r\nexport JAVA_LIBRARY_PATH=${JAVA_LIBRARY_PATH}\r\n\r\nexport HADOOP_OPTS=\"-Dhdp.version=$HDP_VERSION $HADOOP_OPTS\"\r\n" + "content": "\n# Set Hadoop-specific environment variables here.\n\n# The only required environment variable is JAVA_HOME. All others are\n# optional. When running a distributed configuration it is best to\n# set JAVA_HOME in this file, so that it is correctly defined on\n# remote nodes.\n\n# The java implementation to use. Required.\nexport JAVA_HOME=/usr/java/default\nexport HADOOP_HOME_WARN_SUPPRESS=1\n\n# Hadoop home directory\nexport HADOOP_HOME=${HADOOP_HOME:-{{hadoop_home}}}\n\n# Hadoop Configuration Directory\n\n{# this is different for HDP1 #}\n# Path to jsvc required by secure HDP 2.0 datanode\nexport JSVC_HOME={{jsvc_path}}\n\n\n# The maximum amount of heap to use, in MB. Default is 1000.\nexport HADOOP_HEAPSIZE=\"{{hadoop_heapsize}}\"\n\nexport HADOOP_NAMENODE_INIT_HEAPSIZE=\"-Xms{{namenode_heapsize}}\"\n\n# Extra Java runtime options. Empty by default.\nexport HADOOP_OPTS=\"-Djava.net.preferIPv4Stack=true ${HADOOP_OPTS}\"\n\n# Command specific options appen ded to HADOOP_OPTS when specified\nexport HADOOP_NAMENODE_OPTS=\"-server -XX:ParallelGCThreads=8 -XX:+UseConcMarkSweepGC -XX:ErrorFile={{hdfs_log_dir_prefix}}/$USER/hs_err_pid%p.log -XX:NewSize={{namenode_opt_newsize}} -XX:MaxNewSize={{namenode_opt_maxnewsize}} -XX:PermSize={{namenode_opt_permsize}} -XX:MaxPermSize={{namenode_opt_maxpermsize}} -Xloggc:{{hdfs_log_dir_prefix}}/$USER/gc.log-`date +'%Y%m%d%H%M'` -verbose:gc -XX:+PrintGCDetails -XX:+PrintGCTimeStamps -XX:+PrintGCDateStamps -Xms{{namenode_heapsize}} -Xmx{{namenode_heapsize}} -Dhadoop.security.logger=INFO,DRFAS -Dhdfs.audit.logger=INFO,DRFAAUDIT,KAFKA_HDFS_AUDIT ${HADOOP_NAMENODE_OPTS}\"\nHADOOP_JOBTRACKER_OPTS=\"-server -XX:ParallelGCThreads=8 -XX:+UseConcMarkSweepGC -XX:ErrorFile={{hdfs_log_dir_prefix}}/$USER/hs_err_pid%p.log -XX:NewSize={{jtnode_opt_newsize}} -XX:MaxNewSize={{jtnode_opt_maxnewsize}} -Xloggc:{{hdfs_log_dir_prefix}}/$USER/gc.log-`date +'%Y%m%d%H%M'` -verbose:gc -XX:+PrintGCDetails -XX:+PrintGCTimeStamps - XX:+PrintGCDateStamps -Xmx{{jtnode_heapsize}} -Dhadoop.security.logger=INFO,DRFAS -Dmapred.audit.logger=INFO,MRAUDIT -Dhadoop.mapreduce.jobsummary.logger=INFO,JSA ${HADOOP_JOBTRACKER_OPTS}\"\n\nHADOOP_TASKTRACKER_OPTS=\"-server -Xmx{{ttnode_heapsize}} -Dhadoop.security.logger=ERROR,console -Dmapred.audit.logger=ERROR,console ${HADOOP_TASKTRACKER_OPTS}\"\nexport HADOOP_DATANODE_OPTS=\"-server -XX:ParallelGCThreads=4 -XX:+UseConcMarkSweepGC -XX:ErrorFile=/var/log/hadoop/$USER/hs_err_pid%p.log -XX:NewSize=200m -XX:MaxNewSize=200m -XX:PermSize=128m -XX:MaxPermSize=256m -Xloggc:/var/log/hadoop/$USER/gc.log-`date +'%Y%m%d%H%M'` -verbose:gc -XX:+PrintGCDetails -XX:+PrintGCTimeStamps -XX:+PrintGCDateStamps -Xms{{dtnode_heapsize}} -Xmx{{dtnode_heapsize}} -Dhadoop.security.logger=INFO,DRFAS -Dhdfs.audit.logger=INFO,DRFAAUDIT ${HADOOP_DATANODE_OPTS}\"\nHADOOP_BALANCER_OPTS=\"-server -Xmx{{hadoop_heapsize}}m ${HADOOP_BALANCER_OPTS}\"\n\nexport HADOOP_SECONDARYNAMENODE_OPTS=$HADOOP_NAMENODE_OPTS \n\n# The following applies to multiple commands (fs, dfs, fsck, distcp etc)\nexport HADOOP_CLIENT_OPTS=\"-Xmx${HADOOP_HEAPSIZE}m -XX:MaxPermSize=512m $HADOOP_CLIENT_OPTS\"\n\n# On secure datanodes, user to run the datanode as after dropping privileges\nexport HADOOP_SECURE_DN_USER=${HADOOP_SECURE_DN_USER:-{{hadoop_secure_dn_user}}}\n\n# Extra ssh options. Empty by default.\nexport HADOOP_SSH_OPTS=\"-o ConnectTimeout=5 -o SendEnv=HADOOP_CONF_DIR\"\n\n# Where log files are stored. $HADOOP_HOME/logs by default.\nexport HADOOP_LOG_DIR={{hdfs_log_dir_prefix}}/$USER\n\n# History server logs\nexport HADOOP_MAPRED_LOG_DIR={{mapred_log_dir_prefix}}/$USER\n\n# Where log files are stored in the secure data environment.\nexport HADOOP_SECURE_DN_LOG_DIR={{hdfs_log_dir_prefix}}/$HADOOP_SECURE_DN_USER\n\n# File naming remote slave hosts. $HADOOP_HOME/conf/slaves by default.\n# export HADOOP_SLAVES=${HADOOP_HOME}/conf/slaves\n\n# host:path where hadoop code should be rsync'd from. Unset by def ault.\n# export HADOOP_MASTER=master:/home/$USER/src/hadoop\n\n# Seconds to sleep between slave commands. Unset by default. This\n# can be useful in large clusters, where, e.g., slave rsyncs can\n# otherwise arrive faster than the master can service them.\n# export HADOOP_SLAVE_SLEEP=0.1\n\n# The directory where pid files are stored. /tmp by default.\nexport HADOOP_PID_DIR={{hadoop_pid_dir_prefix}}/$USER\nexport HADOOP_SECURE_DN_PID_DIR={{hadoop_pid_dir_prefix}}/$HADOOP_SECURE_DN_USER\n\n# History server pid\nexport HADOOP_MAPRED_PID_DIR={{mapred_pid_dir_prefix}}/$USER\n\nYARN_RESOURCEMANAGER_OPTS=\"-Dyarn.server.resourcemanager.appsummary.logger=INFO,RMSUMMARY\"\n\n# A string representing this instance of hadoop. $USER by default.\nexport HADOOP_IDENT_STRING=$USER\n\n# The scheduling priority for daemon processes. See 'man nice'.\n\n# export HADOOP_NICENESS=10\n\n# Use libraries from standard classpath\nJAVA_JDBC_LIBS=\"\"\n#Add libraries required by mysql connector\nfor jarFile in `ls /usr/share/java/*mysql* 2>/dev/null`\ndo\n JAVA_JDBC_LIBS=${JAVA_JDBC_LIBS}:$jarFile\ndone\n# Add libraries required by oracle connector\nfor jarFile in `ls /usr/share/java/*ojdbc* 2>/dev/null`\ndo\n JAVA_JDBC_LIBS=${JAVA_JDBC_LIBS}:$jarFile\ndone\n# Add libraries required by nodemanager\nMAPREDUCE_LIBS={{mapreduce_libs_path}}\nexport HADOOP_CLASSPATH=${HADOOP_CLASSPATH}${JAVA_JDBC_LIBS}:${MAPREDUCE_LIBS}:/usr/hdp/current/eagle/lib/common/*:/usr/hdp/current/kafka-broker/libs/*\n\n# added to the HADOOP_CLASSPATH\nif [ -d \"/usr/hdp/current/tez-client\" ]; then\n if [ -d \"/etc/tez/conf/\" ]; then\n # When using versioned RPMs, the tez-client will be a symlink to the current folder of tez in HDP.\n export HADOOP_CLASSPATH=${HADOOP_CLASSPATH}:/usr/hdp/current/tez-client/*:/usr/hdp/current/tez-client/lib/*:/etc/tez/conf/\n fi\nfi\n\n# Setting path to hdfs command line\nexport HADOOP_LIBEXEC_DIR={{hadoop_libexec_dir}}\n\n# Mostly required for hadoop 2.0\nexport JAVA_LIB RARY_PATH=${JAVA_LIBRARY_PATH}\n\nexport HADOOP_OPTS=\"-Dhdp.version=$HDP_VERSION $HADOOP_OPTS\"\n" } } }, { "hdfs-log4j": { "properties": { - "content": "\r\n#\r\n# Licensed to the Apache Software Foundation (ASF) under one\r\n# or more contributor license agreements. See the NOTICE file\r\n# distributed with this work for additional information\r\n# regarding copyright ownership. The ASF licenses this file\r\n# to you under the Apache License, Version 2.0 (the\r\n# \"License\"); you may not use this file except in compliance\r\n# with the License. You may obtain a copy of the License at\r\n#\r\n# http://www.apache.org/licenses/LICENSE-2.0\r\n#\r\n# Unless required by applicable law or agreed to in writing,\r\n# software distributed under the License is distributed on an\r\n# \"AS IS\" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY\r\n# KIND, either express or implied. See the License for the\r\n# specific language governing permissions and limitations\r\n# under the License.\r\n#\r\n\r\n\r\n# Define some default values that can be overridden by system properties\r\n# To change daemon root logger use hadoop _root_logger in hadoop-env\r\nhadoop.root.logger=INFO,console\r\nhadoop.log.dir=.\r\nhadoop.log.file=hadoop.log\r\n\r\n\r\n# Define the root logger to the system property \"hadoop.root.logger\".\r\nlog4j.rootLogger=${hadoop.root.logger}, EventCounter\r\n\r\n# Logging Threshold\r\nlog4j.threshhold=ALL\r\n\r\n#\r\n# Daily Rolling File Appender\r\n#\r\n\r\nlog4j.appender.DRFA=org.apache.log4j.DailyRollingFileAppender\r\nlog4j.appender.DRFA.File=${hadoop.log.dir}/${hadoop.log.file}\r\n\r\n# Rollver at midnight\r\nlog4j.appender.DRFA.DatePattern=.yyyy-MM-dd\r\n\r\n# 30-day backup\r\n#log4j.appender.DRFA.MaxBackupIndex=30\r\nlog4j.appender.DRFA.layout=org.apache.log4j.PatternLayout\r\n\r\n# Pattern format: Date LogLevel LoggerName LogMessage\r\nlog4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n\r\n# Debugging Pattern format\r\n#log4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n\r\n\r\n\r\n#\r\n# console\r\n# Add \"console\" to rootlogg er above if you want to use this\r\n#\r\n\r\nlog4j.appender.console=org.apache.log4j.ConsoleAppender\r\nlog4j.appender.console.target=System.err\r\nlog4j.appender.console.layout=org.apache.log4j.PatternLayout\r\nlog4j.appender.console.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{2}: %m%n\r\n\r\n#\r\n# TaskLog Appender\r\n#\r\n\r\n#Default values\r\nhadoop.tasklog.taskid=null\r\nhadoop.tasklog.iscleanup=false\r\nhadoop.tasklog.noKeepSplits=4\r\nhadoop.tasklog.totalLogFileSize=100\r\nhadoop.tasklog.purgeLogSplits=true\r\nhadoop.tasklog.logsRetainHours=12\r\n\r\nlog4j.appender.TLA=org.apache.hadoop.mapred.TaskLogAppender\r\nlog4j.appender.TLA.taskId=${hadoop.tasklog.taskid}\r\nlog4j.appender.TLA.isCleanup=${hadoop.tasklog.iscleanup}\r\nlog4j.appender.TLA.totalLogFileSize=${hadoop.tasklog.totalLogFileSize}\r\n\r\nlog4j.appender.TLA.layout=org.apache.log4j.PatternLayout\r\nlog4j.appender.TLA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n\r\n\r\n#\r\n#Security audit appender\r\n #\r\nhadoop.security.logger=INFO,console\r\nhadoop.security.log.maxfilesize=256MB\r\nhadoop.security.log.maxbackupindex=20\r\nlog4j.category.SecurityLogger=${hadoop.security.logger}\r\nhadoop.security.log.file=SecurityAuth.audit\r\nlog4j.appender.DRFAS=org.apache.log4j.DailyRollingFileAppender\r\nlog4j.appender.DRFAS.File=${hadoop.log.dir}/${hadoop.security.log.file}\r\nlog4j.appender.DRFAS.layout=org.apache.log4j.PatternLayout\r\nlog4j.appender.DRFAS.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n\r\nlog4j.appender.DRFAS.DatePattern=.yyyy-MM-dd\r\n\r\nlog4j.appender.RFAS=org.apache.log4j.RollingFileAppender\r\nlog4j.appender.RFAS.File=${hadoop.log.dir}/${hadoop.security.log.file}\r\nlog4j.appender.RFAS.layout=org.apache.log4j.PatternLayout\r\nlog4j.appender.RFAS.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n\r\nlog4j.appender.RFAS.MaxFileSize=${hadoop.security.log.maxfilesize}\r\nlog4j.appender.RFAS.MaxBackupIndex=${hadoop.security.log.maxbackupindex}\r\n\r\n#\r\n# hdfs audit lo gging\r\n#\r\nhdfs.audit.logger=INFO,console\r\nlog4j.logger.org.apache.hadoop.hdfs.server.namenode.FSNamesystem.audit=${hdfs.audit.logger}\r\nlog4j.additivity.org.apache.hadoop.hdfs.server.namenode.FSNamesystem.audit=false\r\nlog4j.appender.DRFAAUDIT=org.apache.log4j.DailyRollingFileAppender\r\nlog4j.appender.DRFAAUDIT.File=${hadoop.log.dir}/hdfs-audit.log\r\nlog4j.appender.DRFAAUDIT.layout=org.apache.log4j.PatternLayout\r\nlog4j.appender.DRFAAUDIT.layout.ConversionPattern=%d{ISO8601} %p %c{2}: %m%n\r\nlog4j.appender.DRFAAUDIT.DatePattern=.yyyy-MM-dd\r\n\r\nlog4j.appender.KAFKA_HDFS_AUDIT=org.apache.eagle.log4j.kafka.KafkaLog4jAppender\r\nlog4j.appender.KAFKA_HDFS_AUDIT.Topic=sandbox_hdfs_audit_log\r\nlog4j.appender.KAFKA_HDFS_AUDIT.BrokerList=sandbox.eagle.incubator.apache.org:6667\r\nlog4j.appender.KAFKA_HDFS_AUDIT.KeyClass=org.apache.eagle.log4j.kafka.hadoop.AuditLogKeyer\r\nlog4j.appender.KAFKA_HDFS_AUDIT.Layout=org.apache.log4j.PatternLayout\r\nlog4j.appender.KAFKA_HDFS_AUDIT. Layout.ConversionPattern=%d{ISO8601} %p %c{2}: %m%n\r\nlog4j.appender.KAFKA_HDFS_AUDIT.ProducerType=async\r\nlog4j.appender.KAFKA_HDFS_AUDIT.BatchSize=1\r\nlog4j.appender.KAFKA_HDFS_AUDIT.QueueSize=1\r\n\r\n#\r\n# mapred audit logging\r\n#\r\nmapred.audit.logger=INFO,console\r\nlog4j.logger.org.apache.hadoop.mapred.AuditLogger=${mapred.audit.logger}\r\nlog4j.additivity.org.apache.hadoop.mapred.AuditLogger=false\r\nlog4j.appender.MRAUDIT=org.apache.log4j.DailyRollingFileAppender\r\nlog4j.appender.MRAUDIT.File=${hadoop.log.dir}/mapred-audit.log\r\nlog4j.appender.MRAUDIT.layout=org.apache.log4j.PatternLayout\r\nlog4j.appender.MRAUDIT.layout.ConversionPattern=%d{ISO8601} %p %c{2}: %m%n\r\nlog4j.appender.MRAUDIT.DatePattern=.yyyy-MM-dd\r\n\r\n#\r\n# Rolling File Appender\r\n#\r\n\r\nlog4j.appender.RFA=org.apache.log4j.RollingFileAppender\r\nlog4j.appender.RFA.File=${hadoop.log.dir}/${hadoop.log.file}\r\n\r\n# Logfile size and and 30-day backups\r\nlog4j.appender.RFA.MaxFileSize=256MB\r\n log4j.appender.RFA.MaxBackupIndex=10\r\n\r\nlog4j.appender.RFA.layout=org.apache.log4j.PatternLayout\r\nlog4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} - %m%n\r\nlog4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n\r\n\r\n\r\n# Custom Logging levels\r\n\r\nhadoop.metrics.log.level=INFO\r\n#log4j.logger.org.apache.hadoop.mapred.JobTracker=DEBUG\r\n#log4j.logger.org.apache.hadoop.mapred.TaskTracker=DEBUG\r\n#log4j.logger.org.apache.hadoop.fs.FSNamesystem=DEBUG\r\nlog4j.logger.org.apache.hadoop.metrics2=${hadoop.metrics.log.level}\r\n\r\n# Jets3t library\r\nlog4j.logger.org.jets3t.service.impl.rest.httpclient.RestS3Service=ERROR\r\n\r\n#\r\n# Null Appender\r\n# Trap security logger on the hadoop client side\r\n#\r\nlog4j.appender.NullAppender=org.apache.log4j.varia.NullAppender\r\n\r\n#\r\n# Event Counter Appender\r\n# Sends counts of logging messages at different severity levels to Hadoop Metrics.\r\n#\r\nlog4j.appender.EventCounter= org.apache.hadoop.log.metrics.EventCounter\r\n\r\n# Removes \"deprecated\" messages\r\nlog4j.logger.org.apache.hadoop.conf.Configuration.deprecation=WARN\r\n\r\n#\r\n# HDFS block state change log from block manager\r\n#\r\n# Uncomment the following to suppress normal block state change\r\n# messages from BlockManager in NameNode.\r\n#log4j.logger.BlockStateChange=WARN\r\n" + "content": "\n#\n# Licensed to the Apache Software Foundation (ASF) under one\n# or more contributor license agreements. See the NOTICE file\n# distributed with this work for additional information\n# regarding copyright ownership. The ASF licenses this file\n# to you under the Apache License, Version 2.0 (the\n# \"License\"); you may not use this file except in compliance\n# with the License. You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing,\n# software distributed under the License is distributed on an\n# \"AS IS\" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY\n# KIND, either express or implied. See the License for the\n# specific language governing permissions and limitations\n# under the License.\n#\n\n\n# Define some default values that can be overridden by system properties\n# To change daemon root logger use hadoop_root_logger in hadoop-env\nhadoop.root.logg er=INFO,console\nhadoop.log.dir=.\nhadoop.log.file=hadoop.log\n\n\n# Define the root logger to the system property \"hadoop.root.logger\".\nlog4j.rootLogger=${hadoop.root.logger}, EventCounter\n\n# Logging Threshold\nlog4j.threshhold=ALL\n\n#\n# Daily Rolling File Appender\n#\n\nlog4j.appender.DRFA=org.apache.log4j.DailyRollingFileAppender\nlog4j.appender.DRFA.File=${hadoop.log.dir}/${hadoop.log.file}\n\n# Rollver at midnight\nlog4j.appender.DRFA.DatePattern=.yyyy-MM-dd\n\n# 30-day backup\n#log4j.appender.DRFA.MaxBackupIndex=30\nlog4j.appender.DRFA.layout=org.apache.log4j.PatternLayout\n\n# Pattern format: Date LogLevel LoggerName LogMessage\nlog4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n\n# Debugging Pattern format\n#log4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n\n\n\n#\n# console\n# Add \"console\" to rootlogger above if you want to use this\n#\n\nlog4j.appender.console=org.apache.log4j.ConsoleAppender\nlog4j.appender.c onsole.target=System.err\nlog4j.appender.console.layout=org.apache.log4j.PatternLayout\nlog4j.appender.console.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{2}: %m%n\n\n#\n# TaskLog Appender\n#\n\n#Default values\nhadoop.tasklog.taskid=null\nhadoop.tasklog.iscleanup=false\nhadoop.tasklog.noKeepSplits=4\nhadoop.tasklog.totalLogFileSize=100\nhadoop.tasklog.purgeLogSplits=true\nhadoop.tasklog.logsRetainHours=12\n\nlog4j.appender.TLA=org.apache.hadoop.mapred.TaskLogAppender\nlog4j.appender.TLA.taskId=${hadoop.tasklog.taskid}\nlog4j.appender.TLA.isCleanup=${hadoop.tasklog.iscleanup}\nlog4j.appender.TLA.totalLogFileSize=${hadoop.tasklog.totalLogFileSize}\n\nlog4j.appender.TLA.layout=org.apache.log4j.PatternLayout\nlog4j.appender.TLA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n\n\n#\n#Security audit appender\n#\nhadoop.security.logger=INFO,console\nhadoop.security.log.maxfilesize=256MB\nhadoop.security.log.maxbackupindex=20\nlog4j.category.SecurityLogger=${hadoop.security.logger }\nhadoop.security.log.file=SecurityAuth.audit\nlog4j.appender.DRFAS=org.apache.log4j.DailyRollingFileAppender\nlog4j.appender.DRFAS.File=${hadoop.log.dir}/${hadoop.security.log.file}\nlog4j.appender.DRFAS.layout=org.apache.log4j.PatternLayout\nlog4j.appender.DRFAS.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n\nlog4j.appender.DRFAS.DatePattern=.yyyy-MM-dd\n\nlog4j.appender.RFAS=org.apache.log4j.RollingFileAppender\nlog4j.appender.RFAS.File=${hadoop.log.dir}/${hadoop.security.log.file}\nlog4j.appender.RFAS.layout=org.apache.log4j.PatternLayout\nlog4j.appender.RFAS.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n\nlog4j.appender.RFAS.MaxFileSize=${hadoop.security.log.maxfilesize}\nlog4j.appender.RFAS.MaxBackupIndex=${hadoop.security.log.maxbackupindex}\n\n#\n# hdfs audit logging\n#\nhdfs.audit.logger=INFO,console\nlog4j.logger.org.apache.hadoop.hdfs.server.namenode.FSNamesystem.audit=${hdfs.audit.logger}\nlog4j.additivity.org.apache.hadoop.hdfs.server.namenode.FSNamesystem.audit=fa lse\nlog4j.appender.DRFAAUDIT=org.apache.log4j.DailyRollingFileAppender\nlog4j.appender.DRFAAUDIT.File=${hadoop.log.dir}/hdfs-audit.log\nlog4j.appender.DRFAAUDIT.layout=org.apache.log4j.PatternLayout\nlog4j.appender.DRFAAUDIT.layout.ConversionPattern=%d{ISO8601} %p %c{2}: %m%n\nlog4j.appender.DRFAAUDIT.DatePattern=.yyyy-MM-dd\n\nlog4j.appender.KAFKA_HDFS_AUDIT=org.apache.eagle.log4j.kafka.KafkaLog4jAppender\nlog4j.appender.KAFKA_HDFS_AUDIT.Topic=sandbox_hdfs_audit_log\nlog4j.appender.KAFKA_HDFS_AUDIT.BrokerList=server.eagle.apache.org:6667\nlog4j.appender.KAFKA_HDFS_AUDIT.KeyClass=org.apache.eagle.log4j.kafka.hadoop.AuditLogKeyer\nlog4j.appender.KAFKA_HDFS_AUDIT.Layout=org.apache.log4j.PatternLayout\nlog4j.appender.KAFKA_HDFS_AUDIT.Layout.ConversionPattern=%d{ISO8601} %p %c{2}: %m%n\nlog4j.appender.KAFKA_HDFS_AUDIT.ProducerType=async\nlog4j.appender.KAFKA_HDFS_AUDIT.BatchSize=1\nlog4j.appender.KAFKA_HDFS_AUDIT.QueueSize=1\n\n#\n# mapred audit logging\n#\nmapred.audit.logger=INFO,con sole\nlog4j.logger.org.apache.hadoop.mapred.AuditLogger=${mapred.audit.logger}\nlog4j.additivity.org.apache.hadoop.mapred.AuditLogger=false\nlog4j.appender.MRAUDIT=org.apache.log4j.DailyRollingFileAppender\nlog4j.appender.MRAUDIT.File=${hadoop.log.dir}/mapred-audit.log\nlog4j.appender.MRAUDIT.layout=org.apache.log4j.PatternLayout\nlog4j.appender.MRAUDIT.layout.ConversionPattern=%d{ISO8601} %p %c{2}: %m%n\nlog4j.appender.MRAUDIT.DatePattern=.yyyy-MM-dd\n\n#\n# Rolling File Appender\n#\n\nlog4j.appender.RFA=org.apache.log4j.RollingFileAppender\nlog4j.appender.RFA.File=${hadoop.log.dir}/${hadoop.log.file}\n\n# Logfile size and and 30-day backups\nlog4j.appender.RFA.MaxFileSize=256MB\nlog4j.appender.RFA.MaxBackupIndex=10\n\nlog4j.appender.RFA.layout=org.apache.log4j.PatternLayout\nlog4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} - %m%n\nlog4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n\n\n\n# Custom Logging levels\n\nhadoop.metrics.l og.level=INFO\n#log4j.logger.org.apache.hadoop.mapred.JobTracker=DEBUG\n#log4j.logger.org.apache.hadoop.mapred.TaskTracker=DEBUG\n#log4j.logger.org.apache.hadoop.fs.FSNamesystem=DEBUG\nlog4j.logger.org.apache.hadoop.metrics2=${hadoop.metrics.log.level}\n\n# Jets3t library\nlog4j.logger.org.jets3t.service.impl.rest.httpclient.RestS3Service=ERROR\n\n#\n# Null Appender\n# Trap security logger on the hadoop client side\n#\nlog4j.appender.NullAppender=org.apache.log4j.varia.NullAppender\n\n#\n# Event Counter Appender\n# Sends counts of logging messages at different severity levels to Hadoop Metrics.\n#\nlog4j.appender.EventCounter=org.apache.hadoop.log.metrics.EventCounter\n\n# Removes \"deprecated\" messages\nlog4j.logger.org.apache.hadoop.conf.Configuration.deprecation=WARN\n\n#\n# HDFS block state change log from block manager\n#\n# Uncomment the following to suppress normal block state change\n# messages from BlockManager in NameNode.\n#log4j.logger.BlockStateChange=WARN\n" } } } @@ -29,6 +39,12 @@ "name": "master", "components": [ { + "name": "AMBARI_SERVER" + }, + { + "name": "KAFKA_BROKER" + }, + { "name": "APP_TIMELINE_SERVER" }, { @@ -50,9 +66,6 @@ "name": "NAMENODE" }, { - "name": "AMBARI_SERVER" - }, - { "name": "HDFS_CLIENT" }, { @@ -101,9 +114,6 @@ "name": "GANGLIA_MONITOR" }, { - "name": "KAFKA_BROKER" - }, - { "name": "DRPC_SERVER" }, { @@ -116,6 +126,7 @@ "name": "SUPERVISOR" } ], + "configurations" : [ ], "cardinality": "1" } ], http://git-wip-us.apache.org/repos/asf/eagle/blob/39ab83e6/eagle-external/eagle-docker/resource/install-cluster.sh ---------------------------------------------------------------------- diff --git a/eagle-external/eagle-docker/resource/install-cluster.sh b/eagle-external/eagle-docker/resource/install-cluster.sh index 4acd384..910a112 100755 --- a/eagle-external/eagle-docker/resource/install-cluster.sh +++ b/eagle-external/eagle-docker/resource/install-cluster.sh @@ -16,9 +16,9 @@ # limitations under the License. -export PATH=/usr/jdk64/jdk1.7.0_67/bin:$PATH - +export AMBARI_HOST=$EAGLE_SERVER_HOST +echo "installing hadoop cluster via ambari..." ./ambari-shell.sh << EOF blueprint add --file /tmp/eagle-singlenode.json blueprint add --file /tmp/eagle-multinode.json @@ -29,8 +29,4 @@ EOF clear -SERF_RPC_ADDR=${AMBARISERVER_PORT_7373_TCP##*/} -serf event --rpc-addr=$SERF_RPC_ADDR eagle - ./wait-for-eagle.sh - http://git-wip-us.apache.org/repos/asf/eagle/blob/39ab83e6/eagle-external/eagle-docker/resource/serf/bin/start-serf-agent.sh ---------------------------------------------------------------------- diff --git a/eagle-external/eagle-docker/resource/serf/bin/start-serf-agent.sh b/eagle-external/eagle-docker/resource/serf/bin/start-serf-agent.sh new file mode 100755 index 0000000..dbb8df0 --- /dev/null +++ b/eagle-external/eagle-docker/resource/serf/bin/start-serf-agent.sh @@ -0,0 +1,49 @@ +#!/bin/bash + +SERF_HOME=/usr/local/serf +SERF_BIN=$SERF_HOME/bin/serf +SERF_CONFIG_DIR=$SERF_HOME/etc +SERF_LOG_FILE=/var/log/serf.log +SERF_INIT_DIR=/usr/local/init + +set -x + +echo "Executing scripts from $SERF_INIT_DIR" | tee $SERF_LOG_FILE + +for file in $SERF_INIT_DIR/* +do + echo "Execute: $file" | tee -a $SERF_LOG_FILE + /bin/bash $file | tee -a $SERF_LOG_FILE +done + +# if SERF_JOIN_IP env variable set generate a config json for serf +[[ -n $SERF_JOIN_IP ]] && cat > $SERF_CONFIG_DIR/join.json <<EOF +{ + "retry_join" : ["$SERF_JOIN_IP"], + "retry_interval" : "5s" +} +EOF + +# by default only short hostname would be the nodename +# we need FQDN +# while loop for azure deployment +unset SERF_HOSTNAME +while [ -z "$SERF_HOSTNAME" ]; do + SERF_HOSTNAME=$(hostname -f 2>/dev/null) + sleep 5 +done; +cat > $SERF_CONFIG_DIR/node.json <<EOF +{ + "node_name" : "$SERF_HOSTNAME", + "bind" : "$SERF_HOSTNAME" +} +EOF + +# if SERF_ADVERTISE_IP env variable set generate a advertise.json for serf to advertise the given IP +[[ -n $SERF_ADVERTISE_IP ]] && cat > $SERF_CONFIG_DIR/advertise.json <<EOF +{ + "advertise" : "$SERF_ADVERTISE_IP" +} +EOF + +$SERF_BIN agent -config-dir $SERF_CONFIG_DIR $@ | tee -a $SERF_LOG_FILE \ No newline at end of file http://git-wip-us.apache.org/repos/asf/eagle/blob/39ab83e6/eagle-external/eagle-docker/resource/wait-for-eagle.sh ---------------------------------------------------------------------- diff --git a/eagle-external/eagle-docker/resource/wait-for-eagle.sh b/eagle-external/eagle-docker/resource/wait-for-eagle.sh index 3b6ab11..db614e6 100755 --- a/eagle-external/eagle-docker/resource/wait-for-eagle.sh +++ b/eagle-external/eagle-docker/resource/wait-for-eagle.sh @@ -15,24 +15,28 @@ # See the License for the specific language governing permissions and # limitations under the License. -: ${EAGLE_HOST:=$AMBARISERVER_PORT_9099_TCP_ADDR} +#: ${EAGLE_HOST:=$AMBARISERVER_PORT_9099_TCP_ADDR} +: ${EAGLE_HOST:=$EAGLE_SERVER_HOST} : ${SLEEP:=2} : ${DEBUG:=1} -: ${EAGLE_HOST:? eagle server address is mandatory, fallback is a linked containers exposed 9099} +: ${EAGLE_HOST:? eagle server address is mandatory, fallback is a linked containers exposed 9090} debug() { [ $DEBUG -gt 0 ] && echo [DEBUG] "$@" 1>&2 } get-server-state() { - curl -s -o /dev/null -w "%{http_code}" $AMBARISERVER_PORT_9099_TCP_ADDR:9099/eagle-service/index.html + curl -s -o /dev/null -w "%{http_code}" $EAGLE_HOST:9090 } -debug waits for eagle to start on: $EAGLE_HOST +SERF_RPC_ADDR=${EAGLE_SERVER_HOST}:7373 +serf event --rpc-addr=$SERF_RPC_ADDR eagle + +debug waiting for eagle to start on: $EAGLE_HOST while ! get-server-state | grep 200 &>/dev/null ; do [ $DEBUG -gt 0 ] && echo -n . sleep $SLEEP done [ $DEBUG -gt 0 ] && echo -debug eagle web started: $EAGLE_HOST:9099/eagle-service +debug eagle web started: $EAGLE_HOST:9090 http://git-wip-us.apache.org/repos/asf/eagle/blob/39ab83e6/eagle-server/src/main/resources/application.conf ---------------------------------------------------------------------- diff --git a/eagle-server/src/main/resources/application.conf b/eagle-server/src/main/resources/application.conf index d657f54..a1f13bb 100644 --- a/eagle-server/src/main/resources/application.conf +++ b/eagle-server/src/main/resources/application.conf @@ -65,6 +65,9 @@ storage { # eagle coprocessor enabled or not: [true, false] # default is false coprocessorEnabled = false + + # Autocreate hbase tables + autoCreateTable = true } }
