def setup_hive(vms, env):
setup_disks(vms, env)
setup_base(vms, env)
ce = Cloudera(vms)
ce.install('Hadoop')
ce.install('Hive')
return ce['Hive']
def setup_spark(vms, env):
setup_disks(vms, env)
setup_base(vms, env)
ce = Cloudera(vms)
ce.install('Hadoop')
ce.install('Spark')
# Make sure spark can be written by anyone
parallel(lambda vm: vm.script('chown -R ubuntu:ubuntu /var/lib/spark/work'), vms)
parallel(lambda vm: vm.script('sudo -u hdfs hdfs dfs -chmod 777 /user/spark'), vms)
return ce['Spark']
def setup_spark(env, vms):
setup_base(env, vms)
ce = Cloudera(vms)
ce.install('Hadoop')
ce.install('Spark')
return ce['Spark']
def setup_hadoop(env, vms):
setup_base(env, vms)
ce = Cloudera(vms)
ce.install('Hadoop')
return ce['Hadoop']
def setup_hive(env, vms):
setup_base(env, vms)
ce = Cloudera(vms)
ce.install('Hive')
return ce['Hive']