Page History

Python client can be used to create a cluster.
Below lines of code show how you can create a cluster from scratch.It is assumed that all nodes have the agents running and configured and as such there is no need to bootstrap the nodes.

Note
This feature is currently under work for 1.6.0+

Code Block

language	python
title	1. get the client object
firstline	1
linenumbers	true

client = AmbariClient("localhost", 8080, "admin", "admin", version=1)
print client.version
print client.host_url
print"\n"

Code Block

language	python
title	2. create the cluster
firstline	1
linenumbers	true

mycluster = client.create_cluster("test46", "HDP-1.3.0")
print mycluster

Code Block

language	python
title	check if cluster is created
firstline	1
linenumbers	true

mycluster = client.get_cluster('test46')
print mycluster
print mycluster.to_json_dict()
print"\n"

Note

We have not bootstrapped the nodes, It is assumed that the nodes are registered .
if not we can register them with below api

Code Block

language	python

client.bootstrap_hosts(self , hosts_list , ssh_key)

Code Block

language	python
title	3. create services
firstline	1
linenumbers	true

services_list = ["HDFS", "MAPREDUCE", "NAGIOS", "GANGLIA"]
s2 = mycluster.create_services(services_list)
print s2

Code Block

language	python
title	4. create configurations

prop_global__dict ={"dfs_name_dir":"/data/1/hadoop/hdfs/namenode,/data/2/hadoop/hdfs/namenode,/data/3/hadoop/hdfs/namenode,/data/4/hadoop/hdfs/namenode,/data/5/hadoop/hdfs/namenode,/data/6/hadoop/hdfs/namenode,/data/7/hadoop/hdfs/namenode,/data/8/hadoop/hdfs/namenode", "namenode_heapsize":"1024m", "namenode_opt_newsize":"200m", "fs_checkpoint_dir":"/data/1/hadoop/hdfs/namesecondary", "dfs_data_dir":"/data/1/hadoop/hdfs/data,/data/2/hadoop/hdfs/data,/data/3/hadoop/hdfs/data,/data/4/hadoop/hdfs/data,/data/5/hadoop/hdfs/data,/data/6/hadoop/hdfs/data,/data/7/hadoop/hdfs/data,/data/8/hadoop/hdfs/data,/data/9/hadoop/hdfs/data,/data/10/hadoop/hdfs/data", "dtnode_heapsize":"1024m", "dfs_datanode_failed_volume_tolerated":"0", "dfs_webhdfs_enabled":"true", "hadoop_heapsize":"1024", "datanode_du_reserved":"0", "fs_checkpoint_period":"21600", "fs_checkpoint_size":"67108864", "hdfs_log_dir_prefix":"/var/log/hadoop", "hadoop_pid_dir_prefix":"/var/run/hadoop", "namenode_opt_maxnewsize":"200m", "dfs_exclude":"dfs.exclude", "dfs_include":"dfs.include", "dfs_replication":"3", "dfs_block_local_path_access_user":"hbase", "dfs_datanode_data_dir_perm":"750", "security_enabled":"false", "namenode_formatted_mark_dir":"/var/run/hadoop/hdfs/namenode/formatted/", "hcat_conf_dir":"", "jtnode_opt_newsize":"200m", "jtnode_opt_maxnewsize":"200m", "jtnode_heapsize":"1024m", "mapred_local_dir":"/data/1/hadoop/mapred,/data/2/hadoop/mapred,/data/3/hadoop/mapred,/data/4/hadoop/mapred,/data/5/hadoop/mapred,/data/6/hadoop/mapred,/data/7/hadoop/mapred,/data/8/hadoop/mapred,/data/9/hadoop/mapred,/data/10/hadoop/mapred", "mapred_map_tasks_max":"4", "mapred_red_tasks_max":"2", "mapred_child_java_opts_sz":"768", "scheduler_name":"org.apache.hadoop.mapred.CapacityTaskScheduler", "mapred_cluster_map_mem_mb":"1536", "mapred_cluster_red_mem_mb":"2048", "mapred_cluster_max_map_mem_mb":"6144", "mapred_cluster_max_red_mem_mb":"4096", "mapred_job_map_mem_mb":"1536", "mapred_job_red_mem_mb":"2048", "io_sort_mb":"200", "io_sort_spill_percent":"0.9", "mapreduce_userlog_retainhours":"24", "maxtasks_per_job":"-1", "lzo_enabled":"true", "snappy_enabled":"true", "rca_enabled":"true", "mapred_system_dir":"/mapred/system", "mapred_hosts_exclude":"mapred.exclude", "mapred_hosts_include":"mapred.include", "mapred_jobstatus_dir":"file:////mapred/jobstatus", "nagios_web_login":"nagiosadmin", "nagios_web_password":"admin", "nagios_contact":"admin@admin.com", "nagios_group":"nagios", "hbase_conf_dir":"/etc/hbase", "proxyuser_group":"users", "dfs_datanode_address":"50010", "dfs_datanode_http_address":"50075", "gpl_artifacts_download_url":"", "apache_artifacts_download_url":"", "ganglia_runtime_dir":"/var/run/ganglia/hdp", "java64_home":"/usr/jdk/jdk1.6.0_31", "run_dir":"/var/run/hadoop", "hadoop_conf_dir":"/etc/hadoop", "hdfs_user":"hdfs", "mapred_user":"mapred", "hbase_user":"hbase", "hive_user":"hive", "hcat_user":"hcat", "webhcat_user":"hcat", "oozie_user":"oozie", "zk_user":"zookeeper", "gmetad_user":"nobody", "gmond_user":"nobody", "nagios_user":"nagios", "smokeuser":"ambari-qa", "user_group":"hadoop", "rrdcached_base_dir":"/var/lib/ganglia/rrds"}


s3 = mycluster.add_config("global", "version1" , prop_global__dict)
print s3

s3 = mycluster.add_config("core-site", "version1" , prop_core__dict)
print s3

s3 = mycluster.add_config("hdfs-site", "version1" , prop_hdfs__dict)
print s3

s3 = mycluster.add_config("mapred-site", "version1" , prop_mapred__dict)
print s3

Code Block

language	python
title	5. create service componenets
firstline	1
linenumbers	true

s2 = mycluster.create_service_components("1.3.0", "HDFS")
print s2
s2 = mycluster.create_service_components("1.3.0", "MAPREDUCE")
print s2
s2 = mycluster.create_service_components("1.3.0", "GANGLIA")
print s2
s2 = mycluster.create_service_components("1.3.0", "NAGIOS")
print s2

Code Block

language	python
title	6. create hosts
firstline	1
linenumbers	true

h_l = ['hostname1','hostname2']
print h_l
s3 = mycluster.create_hosts(h_l)
print s3
print"\n"

Code Block

language	python
title	7. add hosts roles
firstline	1
linenumbers	true

host1 = mycluster.get_host('hostname1')
print host1
s4 = host1.assign_role("NAMENODE")
print s4
print"\n"

Code Block

language	python
title	8. init all services
firstline	1
linenumbers	true

s4 = mycluster.install_all_services()
print s4
print"\n"

Code Block

language	python
title	9. Start all services and run smoke test
firstline	1
linenumbers	true

s4 = mycluster.start_all_services(run_smoke_test=True)
print s4
print"\n"

wait for some time and you can check http://localhost:8080/#/main/dashboard to see the cluster up and running

Space shortcuts

Child pages

Versions Compared

Old Version 9

New Version Current

Key