The spark-cluster from rsanchezavalos

spark-cluster's Introduction

export MACHINE_DRIVER=amazonec2
export AWS_ACCESS_KEY_ID=AKIAIRLNSTJUPRAPLISA
export AWS_SECRET_ACCESS_KEY=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
export AWS_DEFAULT_REGION=us-west-2
export AWS_INSTANCE_TYPE=t2.nano

for N in $(seq 1 5); do
     docker-machine create node$N
     docker-machine ssh node$N sudo usermod -aG docker ubuntu
done

aws ec2 authorize-security-group-ingress --group-name docker-machine --protocol -1 --cidr 0.0.0.0/0

docker-machine ssh node1


# Docker Compose
cd
sudo curl -L \
 https://github.com/docker/compose/releases/download/1.10.0/docker-compose-$(uname -s)-$(uname -m) \
-o /usr/local/bin/docker-compose

chmod +x /usr/local/bin/docker-compose
docker-compose --version

#Docker-machine

curl -L https://github.com/docker/machine/releases/download/v0.9.0/docker-machine-`uname -s`-`uname -m` \
> /usr/local/bin/docker-machine && \
chmod +x /usr/local/bin/docker-machine

docker-machine --version



# Crea un volumen de docker (para compartir storage en el cluster y el driver)

docker volume create --name dpa_store --opt type=none \
 --opt device=PATH_COMPLETO/spark-ejemplo --opt o=bind ; \

docker-compose up -d


docker run -it --name pyspark-ipython \ 
	--network sparkejemplo_dpa_net \ 
	--volume dpa_store:/spark-ejemplo \
	dpa/spark-client \ 
	/bin/bash


pip install ipython pandas click # Instala paquetes que usaremos
PYSPARK_DRIVER_PYTHON=/usr/local/bin/ipython pyspark --master spark://master:7077

Recommend Projects