Merge branch 'master' of https://github.com/cubedro/eth-netstats

merged with ansible commit

.gitignore

@@ -1,4 +1,8 @@
 .DS_Store
 */**/.DS_Store
 node_modules
-npm-debug.log
+npm-debug.log
+ansible/venv
+*~
+*.swp
+*.pem

ansible/ec2-setup.yml

@@ -0,0 +1,9 @@
+---
+- name: Provision EC2 instances
+  hosts: local
+  gather_facts: false
+  roles:
+    - ec2 
+
+  tasks:
+    - include: roles/ec2/tasks/setup.yml

ansible/ec2-terminate.yml

@@ -0,0 +1,10 @@
+---
+- name: Terminate all ec2 instances 
+  hosts: security_group_eth-netstat
+  remote_user: ubuntu 
+  gather_facts: false
+  roles:
+      - ec2
+
+  tasks:
+      - include: roles/ec2/tasks/terminate.yml

ansible/ec2.ini

@@ -0,0 +1,95 @@
+# Ansible EC2 external inventory script settings
+#
+
+[ec2]
+
+# to talk to a private eucalyptus instance uncomment these lines
+# and edit edit eucalyptus_host to be the host name of your cloud controller
+#eucalyptus = True
+#eucalyptus_host = clc.cloud.domain.org
+
+# AWS regions to make calls to. Set this to 'all' to make request to all regions
+# in AWS and merge the results together. Alternatively, set this to a comma
+# separated list of regions. E.g. 'us-east-1,us-west-1,us-west-2'
+regions = us-east-1
+regions_exclude = us-gov-west-1,cn-north-1
+
+# When generating inventory, Ansible needs to know how to address a server.
+# Each EC2 instance has a lot of variables associated with it. Here is the list:
+#   http://docs.pythonboto.org/en/latest/ref/ec2.html#module-boto.ec2.instance
+# Below are 2 variables that are used as the address of a server:
+#   - destination_variable
+#   - vpc_destination_variable
+
+# This is the normal destination variable to use. If you are running Ansible
+# from outside EC2, then 'public_dns_name' makes the most sense. If you are
+# running Ansible from within EC2, then perhaps you want to use the internal
+# address, and should set this to 'private_dns_name'.
+destination_variable = public_dns_name
+
+# For server inside a VPC, using DNS names may not make sense. When an instance
+# has 'subnet_id' set, this variable is used. If the subnet is public, setting
+# this to 'ip_address' will return the public IP address. For instances in a
+# private subnet, this should be set to 'private_ip_address', and Ansible must
+# be run from with EC2.
+vpc_destination_variable = ip_address
+
+# To tag instances on EC2 with the resource records that point to them from
+# Route53, uncomment and set 'route53' to True.
+route53 = False
+
+# To exclude RDS instances from the inventory, uncomment and set to False.
+#rds = False
+
+# Additionally, you can specify the list of zones to exclude looking up in
+# 'route53_excluded_zones' as a comma-separated list.
+# route53_excluded_zones = samplezone1.com, samplezone2.com
+
+# By default, only EC2 instances in the 'running' state are returned. Set
+# 'all_instances' to True to return all instances regardless of state.
+all_instances = False
+
+# By default, only RDS instances in the 'available' state are returned.  Set
+# 'all_rds_instances' to True return all RDS instances regardless of state.
+all_rds_instances = False
+
+# API calls to EC2 are slow. For this reason, we cache the results of an API
+# call. Set this to the path you want cache files to be written to. Two files
+# will be written to this directory:
+#   - ansible-ec2.cache
+#   - ansible-ec2.index
+cache_path = ~/.ansible/tmp
+
+# The number of seconds a cache file is considered valid. After this many
+# seconds, a new API call will be made, and the cache file will be updated.
+# To disable the cache, set this value to 0
+cache_max_age = 300
+
+# Organize groups into a nested/hierarchy instead of a flat namespace.
+nested_groups = False
+
+# If you only want to include hosts that match a certain regular expression
+# pattern_include = stage-*
+
+# If you want to exclude any hosts that match a certain regular expression
+# pattern_exclude = stage-*
+
+# Instance filters can be used to control which instances are retrieved for
+# inventory. For the full list of possible filters, please read the EC2 API
+# docs: http://docs.aws.amazon.com/AWSEC2/latest/APIReference/ApiReference-query-DescribeInstances.html#query-DescribeInstances-filters
+# Filters are key/value pairs separated by '=', to list multiple filters use
+# a list separated by commas. See examples below.
+
+# Retrieve only instances with (key=value) env=stage tag
+# instance_filters = tag:env=stage
+
+# Retrieve only instances with role=webservers OR role=dbservers tag
+# instance_filters = tag:role=webservers,tag:role=dbservers
+
+# Retrieve only t1.micro instances OR instances with tag env=stage
+# instance_filters = instance-type=t1.micro,tag:env=stage
+
+# You can use wildcards in filter values also. Below will list instances which
+# tag Name value matches webservers1*
+# (ex. webservers15, webservers1a, webservers123 etc) 
+# instance_filters = tag:Name=webservers1*

ansible/ec2.py

@@ -0,0 +1,727 @@
+#!/usr/bin/env python
+
+'''
+EC2 external inventory script
+=================================
+
+Generates inventory that Ansible can understand by making API request to
+AWS EC2 using the Boto library.
+
+NOTE: This script assumes Ansible is being executed where the environment
+variables needed for Boto have already been set:
+    export AWS_ACCESS_KEY_ID='AK123'
+    export AWS_SECRET_ACCESS_KEY='abc123'
+
+This script also assumes there is an ec2.ini file alongside it.  To specify a
+different path to ec2.ini, define the EC2_INI_PATH environment variable:
+
+    export EC2_INI_PATH=/path/to/my_ec2.ini
+
+If you're using eucalyptus you need to set the above variables and
+you need to define:
+
+    export EC2_URL=http://hostname_of_your_cc:port/services/Eucalyptus
+
+For more details, see: http://docs.pythonboto.org/en/latest/boto_config_tut.html
+
+When run against a specific host, this script returns the following variables:
+ - ec2_ami_launch_index
+ - ec2_architecture
+ - ec2_association
+ - ec2_attachTime
+ - ec2_attachment
+ - ec2_attachmentId
+ - ec2_client_token
+ - ec2_deleteOnTermination
+ - ec2_description
+ - ec2_deviceIndex
+ - ec2_dns_name
+ - ec2_eventsSet
+ - ec2_group_name
+ - ec2_hypervisor
+ - ec2_id
+ - ec2_image_id
+ - ec2_instanceState
+ - ec2_instance_type
+ - ec2_ipOwnerId
+ - ec2_ip_address
+ - ec2_item
+ - ec2_kernel
+ - ec2_key_name
+ - ec2_launch_time
+ - ec2_monitored
+ - ec2_monitoring
+ - ec2_networkInterfaceId
+ - ec2_ownerId
+ - ec2_persistent
+ - ec2_placement
+ - ec2_platform
+ - ec2_previous_state
+ - ec2_private_dns_name
+ - ec2_private_ip_address
+ - ec2_publicIp
+ - ec2_public_dns_name
+ - ec2_ramdisk
+ - ec2_reason
+ - ec2_region
+ - ec2_requester_id
+ - ec2_root_device_name
+ - ec2_root_device_type
+ - ec2_security_group_ids
+ - ec2_security_group_names
+ - ec2_shutdown_state
+ - ec2_sourceDestCheck
+ - ec2_spot_instance_request_id
+ - ec2_state
+ - ec2_state_code
+ - ec2_state_reason
+ - ec2_status
+ - ec2_subnet_id
+ - ec2_tenancy
+ - ec2_virtualization_type
+ - ec2_vpc_id
+
+These variables are pulled out of a boto.ec2.instance object. There is a lack of
+consistency with variable spellings (camelCase and underscores) since this
+just loops through all variables the object exposes. It is preferred to use the
+ones with underscores when multiple exist.
+
+In addition, if an instance has AWS Tags associated with it, each tag is a new
+variable named:
+ - ec2_tag_[Key] = [Value]
+
+Security groups are comma-separated in 'ec2_security_group_ids' and
+'ec2_security_group_names'.
+'''
+
+# (c) 2012, Peter Sankauskas
+#
+# This file is part of Ansible,
+#
+# Ansible is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Ansible is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with Ansible.  If not, see <http://www.gnu.org/licenses/>.
+
+######################################################################
+
+import sys
+import os
+import argparse
+import re
+from time import time
+import boto
+from boto import ec2
+from boto import rds
+from boto import route53
+import ConfigParser
+from collections import defaultdict
+
+try:
+    import json
+except ImportError:
+    import simplejson as json
+
+
+class Ec2Inventory(object):
+    def _empty_inventory(self):
+        return {"_meta" : {"hostvars" : {}}}
+
+    def __init__(self):
+        ''' Main execution path '''
+
+        # Inventory grouped by instance IDs, tags, security groups, regions,
+        # and availability zones
+        self.inventory = self._empty_inventory()
+
+        # Index of hostname (address) to instance ID
+        self.index = {}
+
+        # Read settings and parse CLI arguments
+        self.read_settings()
+        self.parse_cli_args()
+
+        # Cache
+        if self.args.refresh_cache:
+            self.do_api_calls_update_cache()
+        elif not self.is_cache_valid():
+            self.do_api_calls_update_cache()
+
+        # Data to print
+        if self.args.host:
+            data_to_print = self.get_host_info()
+
+        elif self.args.list:
+            # Display list of instances for inventory
+            if self.inventory == self._empty_inventory():
+                data_to_print = self.get_inventory_from_cache()
+            else:
+                data_to_print = self.json_format_dict(self.inventory, True)
+
+        print data_to_print
+
+
+    def is_cache_valid(self):
+        ''' Determines if the cache files have expired, or if it is still valid '''
+
+        if os.path.isfile(self.cache_path_cache):
+            mod_time = os.path.getmtime(self.cache_path_cache)
+            current_time = time()
+            if (mod_time + self.cache_max_age) > current_time:
+                if os.path.isfile(self.cache_path_index):
+                    return True
+
+        return False
+
+
+    def read_settings(self):
+        ''' Reads the settings from the ec2.ini file '''
+
+        config = ConfigParser.SafeConfigParser()
+        ec2_default_ini_path = os.path.join(os.path.dirname(os.path.realpath(__file__)), 'ec2.ini')
+        ec2_ini_path = os.environ.get('EC2_INI_PATH', ec2_default_ini_path)
+        config.read(ec2_ini_path)
+
+        # is eucalyptus?
+        self.eucalyptus_host = None
+        self.eucalyptus = False
+        if config.has_option('ec2', 'eucalyptus'):
+            self.eucalyptus = config.getboolean('ec2', 'eucalyptus')
+        if self.eucalyptus and config.has_option('ec2', 'eucalyptus_host'):
+            self.eucalyptus_host = config.get('ec2', 'eucalyptus_host')
+
+        # Regions
+        self.regions = []
+        configRegions = config.get('ec2', 'regions')
+        configRegions_exclude = config.get('ec2', 'regions_exclude')
+        if (configRegions == 'all'):
+            if self.eucalyptus_host:
+                self.regions.append(boto.connect_euca(host=self.eucalyptus_host).region.name)
+            else:
+                for regionInfo in ec2.regions():
+                    if regionInfo.name not in configRegions_exclude:
+                        self.regions.append(regionInfo.name)
+        else:
+            self.regions = configRegions.split(",")
+
+        # Destination addresses
+        self.destination_variable = config.get('ec2', 'destination_variable')
+        self.vpc_destination_variable = config.get('ec2', 'vpc_destination_variable')
+
+        # Route53
+        self.route53_enabled = config.getboolean('ec2', 'route53')
+        self.route53_excluded_zones = []
+        if config.has_option('ec2', 'route53_excluded_zones'):
+            self.route53_excluded_zones.extend(
+                config.get('ec2', 'route53_excluded_zones', '').split(','))
+
+        # Include RDS instances?
+        self.rds_enabled = True
+        if config.has_option('ec2', 'rds'):
+            self.rds_enabled = config.getboolean('ec2', 'rds')
+
+        # Return all EC2 and RDS instances (if RDS is enabled)
+        if config.has_option('ec2', 'all_instances'):
+            self.all_instances = config.getboolean('ec2', 'all_instances')
+        else:
+            self.all_instances = False
+        if config.has_option('ec2', 'all_rds_instances') and self.rds_enabled:
+            self.all_rds_instances = config.getboolean('ec2', 'all_rds_instances')
+        else:
+            self.all_rds_instances = False
+
+        # Cache related
+        cache_dir = os.path.expanduser(config.get('ec2', 'cache_path'))
+        if not os.path.exists(cache_dir):
+            os.makedirs(cache_dir)
+
+        self.cache_path_cache = cache_dir + "/ansible-ec2.cache"
+        self.cache_path_index = cache_dir + "/ansible-ec2.index"
+        self.cache_max_age = config.getint('ec2', 'cache_max_age')
+
+        # Configure nested groups instead of flat namespace.
+        if config.has_option('ec2', 'nested_groups'):
+            self.nested_groups = config.getboolean('ec2', 'nested_groups')
+        else:
+            self.nested_groups = False
+
+        # Do we need to just include hosts that match a pattern?
+        try:
+            pattern_include = config.get('ec2', 'pattern_include')
+            if pattern_include and len(pattern_include) > 0:
+                self.pattern_include = re.compile(pattern_include)
+            else:
+                self.pattern_include = None
+        except ConfigParser.NoOptionError, e:
+            self.pattern_include = None
+
+        # Do we need to exclude hosts that match a pattern?
+        try:
+            pattern_exclude = config.get('ec2', 'pattern_exclude');
+            if pattern_exclude and len(pattern_exclude) > 0:
+                self.pattern_exclude = re.compile(pattern_exclude)
+            else:
+                self.pattern_exclude = None
+        except ConfigParser.NoOptionError, e:
+            self.pattern_exclude = None
+
+        # Instance filters (see boto and EC2 API docs)
+        self.ec2_instance_filters = defaultdict(list)
+        if config.has_option('ec2', 'instance_filters'):
+            for x in config.get('ec2', 'instance_filters', '').split(','):
+                filter_key, filter_value = x.split('=')
+                self.ec2_instance_filters[filter_key].append(filter_value)
+
+    def parse_cli_args(self):
+        ''' Command line argument processing '''
+
+        parser = argparse.ArgumentParser(description='Produce an Ansible Inventory file based on EC2')
+        parser.add_argument('--list', action='store_true', default=True,
+                           help='List instances (default: True)')
+        parser.add_argument('--host', action='store',
+                           help='Get all the variables about a specific instance')
+        parser.add_argument('--refresh-cache', action='store_true', default=False,
+                           help='Force refresh of cache by making API requests to EC2 (default: False - use cache files)')
+        self.args = parser.parse_args()
+
+
+    def do_api_calls_update_cache(self):
+        ''' Do API calls to each region, and save data in cache files '''
+
+        if self.route53_enabled:
+            self.get_route53_records()
+
+        for region in self.regions:
+            self.get_instances_by_region(region)
+            if self.rds_enabled:
+                self.get_rds_instances_by_region(region)
+
+        self.write_to_cache(self.inventory, self.cache_path_cache)
+        self.write_to_cache(self.index, self.cache_path_index)
+
+
+    def get_instances_by_region(self, region):
+        ''' Makes an AWS EC2 API call to the list of instances in a particular
+        region '''
+
+        try:
+            if self.eucalyptus:
+                conn = boto.connect_euca(host=self.eucalyptus_host)
+                conn.APIVersion = '2010-08-31'
+            else:
+                conn = ec2.connect_to_region(region)
+
+            # connect_to_region will fail "silently" by returning None if the region name is wrong or not supported
+            if conn is None:
+                print("region name: %s likely not supported, or AWS is down.  connection to region failed." % region)
+                sys.exit(1)
+
+            reservations = []
+            if self.ec2_instance_filters:
+                for filter_key, filter_values in self.ec2_instance_filters.iteritems():
+                    reservations.extend(conn.get_all_instances(filters = { filter_key : filter_values }))
+            else:
+                reservations = conn.get_all_instances()
+
+            for reservation in reservations:
+                for instance in reservation.instances:
+                    self.add_instance(instance, region)
+
+        except boto.exception.BotoServerError, e:
+            if  not self.eucalyptus:
+                print "Looks like AWS is down again:"
+            print e
+            sys.exit(1)
+
+    def get_rds_instances_by_region(self, region):
+        ''' Makes an AWS API call to the list of RDS instances in a particular
+        region '''
+
+        try:
+            conn = rds.connect_to_region(region)
+            if conn:
+                instances = conn.get_all_dbinstances()
+                for instance in instances:
+                    self.add_rds_instance(instance, region)
+        except boto.exception.BotoServerError, e:
+            if not e.reason == "Forbidden":
+                print "Looks like AWS RDS is down: "
+                print e
+                sys.exit(1)
+
+    def get_instance(self, region, instance_id):
+        ''' Gets details about a specific instance '''
+        if self.eucalyptus:
+            conn = boto.connect_euca(self.eucalyptus_host)
+            conn.APIVersion = '2010-08-31'
+        else:
+            conn = ec2.connect_to_region(region)
+
+        # connect_to_region will fail "silently" by returning None if the region name is wrong or not supported
+        if conn is None:
+            print("region name: %s likely not supported, or AWS is down.  connection to region failed." % region)
+            sys.exit(1)
+
+        reservations = conn.get_all_instances([instance_id])
+        for reservation in reservations:
+            for instance in reservation.instances:
+                return instance
+
+    def add_instance(self, instance, region):
+        ''' Adds an instance to the inventory and index, as long as it is
+        addressable '''
+
+        # Only want running instances unless all_instances is True
+        if not self.all_instances and instance.state != 'running':
+            return
+
+        # Select the best destination address
+        if instance.subnet_id:
+            dest = getattr(instance, self.vpc_destination_variable)
+        else:
+            dest =  getattr(instance, self.destination_variable)
+
+        if not dest:
+            # Skip instances we cannot address (e.g. private VPC subnet)
+            return
+
+        # if we only want to include hosts that match a pattern, skip those that don't
+        if self.pattern_include and not self.pattern_include.match(dest):
+            return
+
+        # if we need to exclude hosts that match a pattern, skip those
+        if self.pattern_exclude and self.pattern_exclude.match(dest):
+            return
+
+        # Add to index
+        self.index[dest] = [region, instance.id]
+
+        # Inventory: Group by instance ID (always a group of 1)
+        self.inventory[instance.id] = [dest]
+        if self.nested_groups:
+            self.push_group(self.inventory, 'instances', instance.id)
+
+        # Inventory: Group by region
+        if self.nested_groups:
+            self.push_group(self.inventory, 'regions', region)
+        else:
+            self.push(self.inventory, region, dest)
+
+        # Inventory: Group by availability zone
+        self.push(self.inventory, instance.placement, dest)
+        if self.nested_groups:
+            self.push_group(self.inventory, region, instance.placement)
+
+        # Inventory: Group by instance type
+        type_name = self.to_safe('type_' + instance.instance_type)
+        self.push(self.inventory, type_name, dest)
+        if self.nested_groups:
+            self.push_group(self.inventory, 'types', type_name)
+
+        # Inventory: Group by key pair
+        if instance.key_name:
+            key_name = self.to_safe('key_' + instance.key_name)
+            self.push(self.inventory, key_name, dest)
+            if self.nested_groups:
+                self.push_group(self.inventory, 'keys', key_name)
+
+        # Inventory: Group by VPC
+        if instance.vpc_id:
+            self.push(self.inventory, self.to_safe('vpc_id_' + instance.vpc_id), dest)
+
+        # Inventory: Group by security group
+        try:
+            for group in instance.groups:
+                key = self.to_safe("security_group_" + group.name)
+                self.push(self.inventory, key, dest)
+                if self.nested_groups:
+                    self.push_group(self.inventory, 'security_groups', key)
+        except AttributeError:
+            print 'Package boto seems a bit older.'
+            print 'Please upgrade boto >= 2.3.0.'
+            sys.exit(1)
+
+        # Inventory: Group by tag keys
+        for k, v in instance.tags.iteritems():
+            key = self.to_safe("tag_" + k + "=" + v)
+            self.push(self.inventory, key, dest)
+            if self.nested_groups:
+                self.push_group(self.inventory, 'tags', self.to_safe("tag_" + k))
+                self.push_group(self.inventory, self.to_safe("tag_" + k), key)
+
+        # Inventory: Group by Route53 domain names if enabled
+        if self.route53_enabled:
+            route53_names = self.get_instance_route53_names(instance)
+            for name in route53_names:
+                self.push(self.inventory, name, dest)
+                if self.nested_groups:
+                    self.push_group(self.inventory, 'route53', name)
+
+        # Global Tag: instances without tags
+        if len(instance.tags) == 0:
+            self.push(self.inventory, 'tag_none', dest)
+            
+        # Global Tag: tag all EC2 instances
+        self.push(self.inventory, 'ec2', dest)
+
+        self.inventory["_meta"]["hostvars"][dest] = self.get_host_info_dict_from_instance(instance)
+
+
+    def add_rds_instance(self, instance, region):
+        ''' Adds an RDS instance to the inventory and index, as long as it is
+        addressable '''
+
+        # Only want available instances unless all_rds_instances is True
+        if not self.all_rds_instances and instance.status != 'available':
+            return
+
+        # Select the best destination address
+        #if instance.subnet_id:
+            #dest = getattr(instance, self.vpc_destination_variable)
+        #else:
+            #dest =  getattr(instance, self.destination_variable)
+        dest = instance.endpoint[0]
+
+        if not dest:
+            # Skip instances we cannot address (e.g. private VPC subnet)
+            return
+
+        # Add to index
+        self.index[dest] = [region, instance.id]
+
+        # Inventory: Group by instance ID (always a group of 1)
+        self.inventory[instance.id] = [dest]
+        if self.nested_groups:
+            self.push_group(self.inventory, 'instances', instance.id)
+
+        # Inventory: Group by region
+        if self.nested_groups:
+            self.push_group(self.inventory, 'regions', region)
+        else:
+            self.push(self.inventory, region, dest)
+
+        # Inventory: Group by availability zone
+        self.push(self.inventory, instance.availability_zone, dest)
+        if self.nested_groups:
+            self.push_group(self.inventory, region, instance.availability_zone)
+
+        # Inventory: Group by instance type
+        type_name = self.to_safe('type_' + instance.instance_class)
+        self.push(self.inventory, type_name, dest)
+        if self.nested_groups:
+            self.push_group(self.inventory, 'types', type_name)
+
+        # Inventory: Group by security group
+        try:
+            if instance.security_group:
+                key = self.to_safe("security_group_" + instance.security_group.name)
+                self.push(self.inventory, key, dest)
+                if self.nested_groups:
+                    self.push_group(self.inventory, 'security_groups', key)
+
+        except AttributeError:
+            print 'Package boto seems a bit older.'
+            print 'Please upgrade boto >= 2.3.0.'
+            sys.exit(1)
+
+        # Inventory: Group by engine
+        self.push(self.inventory, self.to_safe("rds_" + instance.engine), dest)
+        if self.nested_groups:
+            self.push_group(self.inventory, 'rds_engines', self.to_safe("rds_" + instance.engine))
+
+        # Inventory: Group by parameter group
+        self.push(self.inventory, self.to_safe("rds_parameter_group_" + instance.parameter_group.name), dest)
+        if self.nested_groups:
+            self.push_group(self.inventory, 'rds_parameter_groups', self.to_safe("rds_parameter_group_" + instance.parameter_group.name))
+
+        # Global Tag: all RDS instances
+        self.push(self.inventory, 'rds', dest)
+
+        self.inventory["_meta"]["hostvars"][dest] = self.get_host_info_dict_from_instance(instance)
+
+
+    def get_route53_records(self):
+        ''' Get and store the map of resource records to domain names that
+        point to them. '''
+
+        r53_conn = route53.Route53Connection()
+        all_zones = r53_conn.get_zones()
+
+        route53_zones = [ zone for zone in all_zones if zone.name[:-1]
+                          not in self.route53_excluded_zones ]
+
+        self.route53_records = {}
+
+        for zone in route53_zones:
+            rrsets = r53_conn.get_all_rrsets(zone.id)
+
+            for record_set in rrsets:
+                record_name = record_set.name
+
+                if record_name.endswith('.'):
+                    record_name = record_name[:-1]
+
+                for resource in record_set.resource_records:
+                    self.route53_records.setdefault(resource, set())
+                    self.route53_records[resource].add(record_name)
+
+
+    def get_instance_route53_names(self, instance):
+        ''' Check if an instance is referenced in the records we have from
+        Route53. If it is, return the list of domain names pointing to said
+        instance. If nothing points to it, return an empty list. '''
+
+        instance_attributes = [ 'public_dns_name', 'private_dns_name',
+                                'ip_address', 'private_ip_address' ]
+
+        name_list = set()
+
+        for attrib in instance_attributes:
+            try:
+                value = getattr(instance, attrib)
+            except AttributeError:
+                continue
+
+            if value in self.route53_records:
+                name_list.update(self.route53_records[value])
+
+        return list(name_list)
+
+
+    def get_host_info_dict_from_instance(self, instance):
+        instance_vars = {}
+        for key in vars(instance):
+            value = getattr(instance, key)
+            key = self.to_safe('ec2_' + key)
+
+            # Handle complex types
+            # state/previous_state changed to properties in boto in https://github.com/boto/boto/commit/a23c379837f698212252720d2af8dec0325c9518
+            if key == 'ec2__state':
+                instance_vars['ec2_state'] = instance.state or ''
+                instance_vars['ec2_state_code'] = instance.state_code
+            elif key == 'ec2__previous_state':
+                instance_vars['ec2_previous_state'] = instance.previous_state or ''
+                instance_vars['ec2_previous_state_code'] = instance.previous_state_code
+            elif type(value) in [int, bool]:
+                instance_vars[key] = value
+            elif type(value) in [str, unicode]:
+                instance_vars[key] = value.strip()
+            elif type(value) == type(None):
+                instance_vars[key] = ''
+            elif key == 'ec2_region':
+                instance_vars[key] = value.name
+            elif key == 'ec2__placement':
+                instance_vars['ec2_placement'] = value.zone
+            elif key == 'ec2_tags':
+                for k, v in value.iteritems():
+                    key = self.to_safe('ec2_tag_' + k)
+                    instance_vars[key] = v
+            elif key == 'ec2_groups':
+                group_ids = []
+                group_names = []
+                for group in value:
+                    group_ids.append(group.id)
+                    group_names.append(group.name)
+                instance_vars["ec2_security_group_ids"] = ','.join([str(i) for i in group_ids])
+                instance_vars["ec2_security_group_names"] = ','.join([str(i) for i in group_names])
+            else:
+                pass
+                # TODO Product codes if someone finds them useful
+                #print key
+                #print type(value)
+                #print value
+
+        return instance_vars
+
+    def get_host_info(self):
+        ''' Get variables about a specific host '''
+
+        if len(self.index) == 0:
+            # Need to load index from cache
+            self.load_index_from_cache()
+
+        if not self.args.host in self.index:
+            # try updating the cache
+            self.do_api_calls_update_cache()
+            if not self.args.host in self.index:
+                # host might not exist anymore
+                return self.json_format_dict({}, True)
+
+        (region, instance_id) = self.index[self.args.host]
+
+        instance = self.get_instance(region, instance_id)
+        return self.json_format_dict(self.get_host_info_dict_from_instance(instance), True)
+
+    def push(self, my_dict, key, element):
+        ''' Push an element onto an array that may not have been defined in
+        the dict '''
+        group_info = my_dict.setdefault(key, [])
+        if isinstance(group_info, dict):
+            host_list = group_info.setdefault('hosts', [])
+            host_list.append(element)
+        else:
+            group_info.append(element)
+
+    def push_group(self, my_dict, key, element):
+        ''' Push a group as a child of another group. '''
+        parent_group = my_dict.setdefault(key, {})
+        if not isinstance(parent_group, dict):
+            parent_group = my_dict[key] = {'hosts': parent_group}
+        child_groups = parent_group.setdefault('children', [])
+        if element not in child_groups:
+            child_groups.append(element)
+
+    def get_inventory_from_cache(self):
+        ''' Reads the inventory from the cache file and returns it as a JSON
+        object '''
+
+        cache = open(self.cache_path_cache, 'r')
+        json_inventory = cache.read()
+        return json_inventory
+
+
+    def load_index_from_cache(self):
+        ''' Reads the index from the cache file sets self.index '''
+
+        cache = open(self.cache_path_index, 'r')
+        json_index = cache.read()
+        self.index = json.loads(json_index)
+
+
+    def write_to_cache(self, data, filename):
+        ''' Writes data in JSON format to a file '''
+
+        json_data = self.json_format_dict(data, True)
+        cache = open(filename, 'w')
+        cache.write(json_data)
+        cache.close()
+
+
+    def to_safe(self, word):
+        ''' Converts 'bad' characters in a string to underscores so they can be
+        used as Ansible groups '''
+
+        return re.sub("[^A-Za-z0-9\-]", "_", word)
+
+
+    def json_format_dict(self, data, pretty=False):
+        ''' Converts a dict to a JSON object and dumps it as a formatted
+        string '''
+
+        if pretty:
+            return json.dumps(data, sort_keys=True, indent=2)
+        else:
+            return json.dumps(data)
+
+
+# Run the script
+Ec2Inventory()
+

ansible/query-nodes.yml

@@ -0,0 +1,7 @@
+---
+- name: Install eth nodes w/ json-rpc for query-testing
+  hosts: tag_Role_query_test_node 
+  remote_user: ubuntu
+  roles:
+    - docker
+    - client

ansible/roles/client/files/docker-cpp/Dockerfile

@@ -0,0 +1,30 @@
+FROM ubuntu:14.04
+
+ENV DEBIAN_FRONTEND noninteractive
+RUN apt-get update
+RUN apt-get upgrade -y
+
+# Ethereum dependencies
+RUN apt-get install -qy build-essential g++-4.8 git cmake libboost-all-dev libcurl4-openssl-dev wget
+RUN apt-get install -qy automake unzip libgmp-dev libtool libleveldb-dev yasm libminiupnpc-dev libreadline-dev scons
+RUN apt-get install -qy libjsoncpp-dev libargtable2-dev
+
+# NCurses based GUI (not optional though for a succesful compilation, see https://github.com/ethereum/cpp-ethereum/issues/452 )
+RUN apt-get install -qy libncurses5-dev
+
+# Qt-based GUI
+# RUN apt-get install -qy qtbase5-dev qt5-default qtdeclarative5-dev libqt5webkit5-dev
+
+# Ethereum PPA
+RUN apt-get install -qy software-properties-common
+RUN add-apt-repository ppa:ethereum/ethereum
+RUN apt-get update
+RUN apt-get install -qy libcryptopp-dev libjson-rpc-cpp-dev
+
+# Build Ethereum (HEADLESS)
+RUN git clone --depth=1 --branch master https://github.com/ethereum/cpp-ethereum
+RUN mkdir -p cpp-ethereum/build
+RUN cd cpp-ethereum/build && cmake .. -DCMAKE_BUILD_TYPE=Release -DHEADLESS=1 && make -j $(cat /proc/cpuinfo | grep processor | wc -l) && make install
+RUN ldconfig
+
+ENTRYPOINT ["/usr/local/bin/eth"]

ansible/roles/client/tasks/main.yml

@@ -0,0 +1,22 @@
+---
+- name: copy Dockerfile to server
+  copy: src=docker-cpp dest=/home/{{ ansible_ssh_user }}
+
+- name: build C++ client
+  sudo: true  
+  docker_image:
+      path: /home/{{ ansible_ssh_user }}/docker-cpp
+      name: cpp
+      state: build
+  async: 1200
+  poll: 5
+
+- name: start ethereum client w/ JSON-RPC and bootstrapping  
+  sudo: true
+  docker: 
+      image:    cpp
+      expose:   ["8080", "30303"]
+      ports:    ["8080:8080", "30303:30303"] 
+      
+      # parameters given to client 
+      command: --bootstrap --json-rpc

ansible/roles/docker/handlers/main.yml

@@ -0,0 +1,17 @@
+---
+- name: restart sshd
+  sudo: true 
+  service: name=ssh state=restarted
+
+- name: restart server
+  sudo: true
+  command: shutdown -r now 
+  async: 0
+  poll: 0
+  ignore_errors: true
+  notify: wait for server restart
+
+- name: wait for server restart
+  local_action: wait_for host={{ inventory_hostname }} port=22
+                state=started
+  sudo: false

ansible/roles/docker/tasks/main.yml

@@ -0,0 +1,32 @@
+---
+- name: update package list
+  sudo: true
+  apt: update_cache=true
+
+- name: install docker dependencies
+  sudo: true
+  apt: name={{ item }} install_recommends=false
+  with_items:
+    # Docker has serious problems on EC2: http://www.danstutzman.com/2014/07/speed-up-docker-on-ec2
+    # and https://github.com/docker/docker/issues/4036
+    - linux-generic
+    - python-pip
+  notify: restart server
+
+# make sure resteart is done now, not at end of play
+- meta: flush_handlers
+
+- name: install docker
+  sudo: true
+  # install script from https://docs.docker.com/installation/ubuntulinux/
+  # TODO this is not idempotent
+  shell: curl -sSL https://get.docker.com/ubuntu/ | sudo sh  
+
+- name: install docker python API
+  sudo: true
+  pip: name=docker-py
+
+- name: enable docker for standard user
+  sudo: true
+  user: name={{ ansible_ssh_user }} groups=docker append=yes
+  notify: restart sshd

ansible/roles/ec2/tasks/setup.yml

@@ -0,0 +1,42 @@
+---
+- name: create default security group 
+  ec2_group:
+    name: "{{ security_group }}"
+    region: "{{ region }}"
+    description: "{{ project_description }}"
+    rules:
+        # ssh
+      - proto: tcp
+        from_port: 22
+        to_port: 22
+        cidr_ip: "{{ ip_access_range }}"
+        # ethereum incoming connection port
+      - proto: tcp
+        from_port: 30303
+        to_port: 30303
+        cidr_ip: "{{ ip_access_range }}"
+        # ethereum JSON-RPC server
+      - proto: tcp
+        from_port: 8080
+        to_port: 8080
+        cidr_ip: "{{ ip_access_range }}"
+    rules_egress:
+      - proto: all
+        cidr_ip: "{{ ip_access_range }}"
+
+
+- name: start ec2 instances
+  ec2:  
+    group: "{{ security_group }}"
+    instance_type: "{{ instance_type }}" 
+    image: "{{ image }}" 
+    wait: true 
+    region: "{{ region }}"
+    key_name: "{{ keypair }}"
+    instance_tags:
+      Name: "{{ item }}"
+      Role: query_test_node
+    count_tag: # exactly one instace with the given name
+      Name: "{{ item }}"
+    exact_count: 1
+  with_sequence: start=1 end={{ total_no_instances }} format=test-%02x

ansible/roles/ec2/tasks/terminate.yml

@@ -0,0 +1,8 @@
+---
+- name: Terminate ec2 instances 
+  local_action: ec2
+        state=absent
+        instance_ids={{ ec2_id }}
+        region={{ region }}
+        wait=true
+

ansible/roles/ec2/vars/main.yml

@@ -0,0 +1,20 @@
+---
+# default config for ec2 instances
+
+# cpp-compilation needs RAM
+instance_type:      t2.medium
+security_group:     eth-netstat
+
+# image:              ami-d6e7c084
+image:              ami-9eaa1cf6
+# region:             ap-southeast-1
+region:             us-east-1
+keypair:            eth-netstat
+
+# limit access to AWS to these clients in CDIR notation
+ip_access_range:    0.0.0.0/0
+
+
+project_description: https://github.com/cubedro/eth-netstats 
+
+total_no_instances: 3