Quickly set up a Greenplum environment on GCP

# Create the Greenplum GCE instance gcloud compute instances create greenplum \ --zone=us-central1-c \ --machine-type=n1-standard-1 \ --image-project=debian-cloud --boot-disk-size=10GB \ --image=debian-9-stretch-v20190916 \ --boot-disk-type=pd-standard \ --boot-disk-device-name=greenplum \ --scopes=cloud-platform 

# Connect to the greenplum VM gcloud compute ssh --zone=us-central1-c greenplum # Login as super user sudo -s # Install Docker curl -sSL https://get.docker.com/ | sh # Install Git apt-get install git # Install postgresl client apt-get install postgresql-client # Clone greenplum official repo git clone https://github.com/greenplum-db/gpdb # Go to to the docker directory cd gpdb/src/tools/docker/ubuntu16_ppa-persistent # Build and run docker build -t local/gpdb . mkdir -p /tmp/gpdata/ docker run -d -p 5432:5432 -h dwgpdb -v /tmp/gpdata:/data local/gpdb 

# Verify GPDB is installed and started up successfully docker ps -a docker logs --follow <GPDB_CONTAINDER_ID> # Wait for the message to appear: # ===> GPDB starting process has completed, check the result above # or try to connect # Leave the logs command, by pressing CTRL + C # Log into the GPDB container docker ps docker exec -it <GPDB_CONTAINER_ID> bash # Log as the gpadmin user su gpadmin # Verify that the GDPB instance is running gpstate # Create a DB called messages_db createdb messages_db # Log into the new DB psql messages_db # Create tables and populate with Data CREATE TABLE Users (uid INTEGER PRIMARY KEY, name VARCHAR); INSERT INTO Users SELECT generate_series, random() FROM generate_series(1, 100000); CREATE TABLE Messages (mid INTEGER PRIMARY KEY, uid INTEGER REFERENCES Users(uid), ptime DATE, message VARCHAR); INSERT INTO Messages SELECT generate_series, round(random()*100000), date(now() - '1 hour'::INTERVAL * round(random()*24*30)), random()::text FROM generate_series(1, 100000);