nsabharwal

/usr/hdp/current/kafka-broker/bin/kafka-topics.sh --list --zookeeper localhost:2181

/usr/hdp/current/kafka-broker/bin/kafka-topics.sh --zookeeper localhost:2181 --create --topic test --replication-factor 1 --partitions 1

/usr/hdp/current/kafka-broker/bin/kafka-console-producer.sh --broker-list phdns01.cloud.hortonworks.com:6667 --topic test

 /usr/hdp/current/kafka-broker/bin/kafka-console-consumer.sh --zookeeper localhost:2181 --topic test --from-beginning

nsabharwal

##Create the vm
boot2docker init -m 8192 -s 30000 ( memory and size in GB)
###Start the vm 
boot2docker up
# Set the variables
`eval "$(boot2docker shellinit)"`
## Find the IP
boot2docker IP
##ssh into docker vm
boot2docker ssh

nsabharwal

boot2docker shellinit
docker run -d -p 8080:80 --name web nginx
docker exec -it web bash
echo myself for president > /usr/share/nginx/html/index.html
docker inspect web | grep IP
docker inspect -f '{{json .NetworkSettings.IPAddress}}' container

nsabharwal

#run mesos
#spin up zk instance
#start marathon 
MESOS_NATIVE_JAVA_LIBRARY=/Users/nsabharwal/mesos-0.28.1/build/src/.libs/libmesos.dylib ./bin/start --master local --zk zk://localhost:2181/marathon

nsabharwal

# start loacal zk
/var/root/zookeeper-3.4.8/bin/zkServer.sh  start
#start marathon
#marathon is connecting to the existing mesos instance instance connecting to it's own embeded instance
#--master 127.0.0.1:5050  and zk://localhost:2181/mesos 
 MESOS_NATIVE_JAVA_LIBRARY=/Users/nsabharwal/mesos-0.28.1/build/src/.libs/libmesos.dylib
/var/root/marathon-1.1.1/bin/start --master 127.0.0.1:5050 --zk zk://localhost:2181/mesos 


##########################################################

nsabharwal

 # install
 export MESOS_NATIVE_LIBRARY=/usr/local/lib/libmesos.dylib
 git clone https://github.com/mesos/chronos.git
cd chronos
#must have node installed
mvn package
#start on port 8081
java -cp target/chronos*.jar org.apache.mesos.chronos.scheduler.Main --master 127.0.0.1:5050 --zk_hosts localhost:2181 --http_port 8081
 #list jobs
 curl -L -X GET localhost:8081/scheduler/jobs

nsabharwal

## git clone https://github.com/Banno/druid-docker
## git clone  https://github.com/zcox/druid-pageviews
cd druid-docker
fig kill && fig rm --force
./build.sh
fig up -d druid
####  docker 
## `boot2docker shellinit`
## docker ps
## 

nsabharwal

su - hdfs
git clone https://github.com/pivotalsoftware/pivotal-samples.git

# I copied the files on /mnt
cd /mnt/pivotal-samples/sample-data   
# load data into HDFS
sh -x load_data_to_HDFS.sh   ## it will show you the output of the commands the script is running
 hdfs dfs -ls /retail_demo
####  Hive table  #####
https://github.com/pivotalsoftware/pivotal-samples/blob/master/hive/create_hive_tables.sql

nsabharwal

##Start cluster
/Users/neeraj/dse/bin/dse cassandra 
## - Stop cluster
/Users/neeraj/dse/bin/dse cassandra-stop
## enable advanced replication
vi /Users/neeraj/dse/resources/dse/conf/dse.yaml
./nodetool status
export CQLSH_HOST=192.168.1.185
 ./cqlsh
 # run this in edge and hub cluster

nsabharwal

#Install R and then following packages
#repr failed to create 
yum install R-*
install.packages("evaluate", dependencies = TRUE)
install.packages("base64enc", dependencies = TRUE)
install.packages("devtools", dependencies = TRUE)
install_github('IRkernel/repr')
install.packages("dplyr", dependencies = TRUE)
install.packages("caret", dependencies = TRUE)
install.packages("repr", dependencies = TRUE)