Hello list,
I'm trying to spin up Metron in EC2 for testing purposes. I made the
following changes in playbook.yml so that I'm left with 5 EC2 instances
instead of 10:
<-- SNIP -->
tasks:
- include: tasks/create-keypair.yml
- include: tasks/create-vpc.yml
- include: tasks/create-open-inbound-security-group.yml
- include: tasks/create-open-outbound-security-group.yml
- include: tasks/create-hosts.yml host_count=1
host_type=sensors,ambari_master,ec2,monit
# - include: tasks/create-hosts.yml host_count=4
host_type=ambari_slave,ec2
- include: tasks/create-hosts.yml host_count=1
host_type=pcap_server,monit,ec2
- include: tasks/create-hosts.yml host_count=1
host_type=ambari_slave,enrichment,metron,ec2,zeppelin
# - include: tasks/create-hosts.yml host_count=2
host_type=ambari_slave,search,ec2
- include: tasks/create-hosts.yml host_count=1
host_type=ambari_slave,search,ec2
- include: tasks/create-hosts.yml host_count=1
host_type=ambari_slave,web,ec2
<-- END SNIP -->
I also had to change the line "ansible-playbook -vvv -i ec2.py
playbook.yml \
--skip-tags="quick_dev,sensor-stubs" \
--extra-vars="env=$ENV" \
$EXTRA_ARGS"
to "ansible-playbook -vvv -i ec2.py playbook.yml \
--skip-tags="quick_dev,sensor-stubs" \
--extra-vars="env=$ENV" \
$EXTRA_ARGS -c paramiko"
in run.sh otherwise ssh would time out.
However, Ansible errors out with:
2017-05-16 18:02:50,615 p=5362 u=laurens | TASK [ambari_config : Deploy
cluster with Ambari;
http://ec2-35-164-26-255.us-west-2.compute.amazonaws.com:8080] ***
2017-05-16 18:02:50,615 p=5362 u=laurens | task path:
/home/laurens/SAPSource/metron/metron-deployment/roles/ambari_config/tasks/main.yml:36
2017-05-16 18:02:52,660 p=5362 u=laurens | fatal:
[ec2-35-164-26-255.us-west-2.compute.amazonaws.com]: FAILED! =>
{"changed": false, "failed": true, "invocation": {"module_args":
{"blueprint_name": "metron_blueprint", "blueprint_var": {"groups":
[{"cardinality": 1, "components": [{"name": "NAMENODE"}, {"name":
"SECONDARY_NAMENODE"}, {"name": "RESOURCEMANAGER"}, {"name":
"HISTORYSERVER"}, {"name": "HDFS_CLIENT"}, {"name": "YARN_CLIENT"},
{"name": "MAPREDUCE2_CLIENT"}, {"name": "SPARK_CLIENT"}, {"name":
"ZOOKEEPER_CLIENT"}, {"name": "HBASE_CLIENT"}, {"name": "ES_SLAVE"}],
"configuration": [], "name": "master_1"}, {"cardinality": 1,
"components": [{"name": "ZOOKEEPER_SERVER"}, {"name": "NIMBUS"},
{"name": "STORM_UI_SERVER"}, {"name": "DRPC_SERVER"}, {"name":
"SPARK_JOBHISTORYSERVER"}, {"name": "HBASE_MASTER"}, {"name":
"HDFS_CLIENT"}, {"name": "YARN_CLIENT"}, {"name": "MAPREDUCE2_CLIENT"},
{"name": "SPARK_CLIENT"}, {"name": "ZOOKEEPER_CLIENT"}, {"name":
"HBASE_CLIENT"}, {"name": "APP_TIMELINE_SERVER"}, {"name": "ES_SLAVE"}],
"configuration": [], "name": "master_2"}, {"cardinality": 1,
"components": [{"name": "METRON_INDEXING"}, {"name":
"METRON_ENRICHMENT_MASTER"}, {"name": "METRON_PARSERS"}, {"name":
"METRON_REST"}, {"name": "DATANODE"}, {"name": "NODEMANAGER"}, {"name":
"SUPERVISOR"}, {"name": "KAFKA_BROKER"}, {"name": "HBASE_REGIONSERVER"},
{"name": "HDFS_CLIENT"}, {"name": "YARN_CLIENT"}, {"name":
"MAPREDUCE2_CLIENT"}, {"name": "SPARK_CLIENT"}, {"name":
"ZOOKEEPER_CLIENT"}, {"name": "HBASE_CLIENT"}], "configuration": [],
"name": "metron"}, {"cardinality": 1, "components": [{"name":
"KIBANA_MASTER"}, {"name": "ES_MASTER"}], "configuration": [], "name":
"web"}, {"cardinality": "1+", "components": [{"name": "DATANODE"},
{"name": "NODEMANAGER"}, {"name": "SUPERVISOR"}, {"name":
"KAFKA_BROKER"}, {"name": "HBASE_REGIONSERVER"}, {"name":
"HDFS_CLIENT"}, {"name": "YARN_CLIENT"}, {"name": "MAPREDUCE2_CLIENT"},
{"name": "SPARK_CLIENT"}, {"name": "ZOOKEEPER_CLIENT"}, {"name":
"HBASE_CLIENT"}], "configuration": [], "name": "slaves"}],
"required_configurations": [{"metron-env": {"es_hosts":
"ec2-35-164-136-88.us-west-2.compute.amazonaws.com,ec2-34-208-94-45.us-west-2.compute.amazonaws.com",
"metron_jdbc_driver": "org.h2.Driver", "metron_jdbc_password": "root",
"metron_jdbc_platform": "h2", "metron_jdbc_url":
"jdbc:h2:file:~/metrondb", "metron_jdbc_username": "root",
"storm_rest_addr":
"ec2-34-208-94-45.us-west-2.compute.amazonaws.com:8744",
"zeppelin_server_url":
"ec2-34-210-151-29.us-west-2.compute.amazonaws.com"}}, {"kibana-env":
{"kibana_default_application": "dashboard/Metron-Dashboard",
"kibana_es_url":
"http://ec2-35-164-136-88.us-west-2.compute.amazonaws.com:9200",
"kibana_log_dir": "/var/log/kibana", "kibana_pid_dir":
"/var/run/kibana", "kibana_server_port": 5000}}], "stack_name": "HDP",
"stack_version": "2.5"}, "cluster_name": "metron", "cluster_state":
"present", "configurations": [{"zoo.cfg": {"dataDir":
"/data1/hadoop/zookeeper"}}, {"hadoop-env": {"dtnode_heapsize": 1024,
"namenode_heapsize": 2048}}, {"hbase-env": {"hbase_master_heapsize":
1024, "hbase_regionserver_heapsize": 1024}}, {"hdfs-site":
{"dfs.datanode.data.dir":
"/data1/hadoop/hdfs/data,/data2/hadoop/hdfs/data",
"dfs.journalnode.edits.dir": "/data1/hadoop/hdfs/journalnode",
"dfs.namenode.checkpoint.dir": "/data1/hadoop/hdfs/namesecondary",
"dfs.namenode.name.dir": "/data1/hadoop/hdfs/namenode"}},
{"mapred-site": {"mapreduce.jobhistory.recovery.store.leveldb.path":
"/data1/hadoop/mapreduce/jhs", "mapreduce.map.memory.mb": 1229,
"mapreduce.reduce.memory.mb": 1229}}, {"yarn-site":
{"yarn.nodemanager.local-dirs": "/data1/hadoop/yarn/local",
"yarn.nodemanager.log-dirs": "/data1/hadoop/yarn/log",
"yarn.nodemanager.resource.memory-mb": 4096,
"yarn.timeline-service.leveldb-state-store.path":
"/data1/hadoop/yarn/timeline",
"yarn.timeline-service.leveldb-timeline-store.path":
"/data1/hadoop/yarn/timeline"}}, {"storm-site": {"storm.local.dir":
"/data1/hadoop/storm", "supervisor.slots.ports": "[6700, 6701, 6702,
6703]", "topology.classpath": "/etc/hbase/conf:/etc/hadoop/conf"}},
{"kafka-broker": {"log.dirs": "/data2/kafka-log"}}, {"metron-env":
{"parsers": "bro,snort,yaf"}}, {"elastic-site":
{"gateway_recover_after_data_nodes": 1, "index_number_of_replicas": 1,
"index_number_of_shards": 2, "network_host": "[ _local_, _eth0_ ]",
"zen_discovery_ping_unicast_hosts": "[
ec2-35-164-136-88.us-west-2.compute.amazonaws.com,
ec2-34-208-94-45.us-west-2.compute.amazonaws.com ]"}}], "host":
"ec2-35-164-26-255.us-west-2.compute.amazonaws.com", "password":
"admin", "port": 8080, "username": "admin", "wait_for_complete": true},
"module_name": "ambari_cluster_state"}, "msg": "Ambari client exception
occurred: Could not create cluster: request code 400,
request message {\n \"status\" : 400,\n \"message\" : \"Invalid
Cluster Creation Template:
org.apache.ambari.server.topology.InvalidTopologyTemplateException: Host
group 'slaves' must contain at least one 'hosts/fqdn' or a 'host_count'
value\"\n}"}
PLAY RECAP
*********************************************************************
ec2-34-208-94-45.us-west-2.compute.amazonaws.com : ok=49 changed=27
unreachable=0 failed=0
ec2-34-209-224-190.us-west-2.compute.amazonaws.com : ok=23 changed=8
unreachable=0 failed=0
ec2-34-210-151-29.us-west-2.compute.amazonaws.com : ok=58 changed=31
unreachable=0 failed=0
ec2-35-164-136-88.us-west-2.compute.amazonaws.com : ok=49 changed=27
unreachable=0 failed=0
ec2-35-164-26-255.us-west-2.compute.amazonaws.com : ok=54 changed=28
unreachable=0 failed=1
localhost : ok=29 changed=12 unreachable=0
failed=0
Any idea what might be going on?
(Don't worry about the URLs, the instances have been terminated)