Merge pull request #315 from edx/jarv/updates-for-int

Adding play for continuous integration, ora bug fix

playbooks/ec2.ini

+# Ansible EC2 external inventory script settings
+#
+
 [ec2]
-regions=all
-destination_variable=public_dns_name
-vpc_destination_variable=private_ip_address
-cache_path=/tmp
-cache_max_age=300
+
+# 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 = all
+regions_exclude = us-gov-west-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 = private_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
+
+# Additionally, you can specify the list of zones to exclude looking up in
+# 'route53_excluded_zones' as a comma-seperated list.
+# route53_excluded_zones = samplezone1.com, samplezone2.com
+
+# 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 = /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.
+cache_max_age = 300

playbooks/ec2.py

 #!/usr/bin/env python
 
-import sys
-import os
-
 '''
 EC2 external inventory script
 =================================
@@ -118,6 +115,8 @@ import re
 from time import time
 import boto
 from boto import ec2
+from boto import rds
+from boto import route53
 import ConfigParser
 
 try:
@@ -138,8 +137,8 @@ class Ec2Inventory(object):
         self.index = {}
 
         # Read settings and parse CLI arguments
-        self.parse_cli_args()
         self.read_settings()
+        self.parse_cli_args()
 
         # Cache
         if self.args.refresh_cache:
@@ -178,7 +177,7 @@ class Ec2Inventory(object):
         ''' Reads the settings from the ec2.ini file '''
 
         config = ConfigParser.SafeConfigParser()
-        config.read(self.args.inifile)
+        config.read(os.path.dirname(os.path.realpath(__file__)) + '/ec2.ini')
 
         # is eucalyptus?
         self.eucalyptus_host = None
@@ -191,11 +190,13 @@ class Ec2Inventory(object):
         # 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(",")
@@ -204,6 +205,13 @@ class Ec2Inventory(object):
         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(','))
+
         # Cache related
         cache_path = config.get('ec2', 'cache_path')
         self.cache_path_cache = cache_path + "/ansible-ec2.cache"
@@ -222,18 +230,18 @@ class Ec2Inventory(object):
                            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)')
-        
-        default_inifile = os.environ.get("ANSIBLE_EC2_INI", os.path.dirname(os.path.realpath(__file__))+'/ec2.ini')
-
-        parser.add_argument('--inifile', dest='inifile', help='Path to init script to use', default=default_inifile)
         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)
+            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)
@@ -250,6 +258,11 @@ class Ec2Inventory(object):
             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()
             for reservation in reservations:
                 for instance in reservation.instances:
@@ -261,6 +274,20 @@ class Ec2Inventory(object):
             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 as e:
+            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 '''
@@ -270,6 +297,11 @@ class Ec2Inventory(object):
         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:
@@ -328,6 +360,111 @@ class Ec2Inventory(object):
             key = self.to_safe("tag_" + k + "=" + v)
             self.push(self.inventory, key, dest)
 
+        # 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)
+
+
+    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
+        if 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]
+
+        # Inventory: Group by region
+        self.push(self.inventory, region, dest)
+
+        # Inventory: Group by availability zone
+        self.push(self.inventory, instance.availability_zone, dest)
+        
+        # Inventory: Group by instance type
+        self.push(self.inventory, self.to_safe('type_' + instance.instance_class), dest)
+        
+        # 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)
+        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)
+
+        # Inventory: Group by parameter group
+        self.push(self.inventory, self.to_safe("rds_parameter_group_" + instance.parameter_group.name), dest)
+
+
+    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(self):
         ''' Get variables about a specific host '''
@@ -387,7 +524,7 @@ class Ec2Inventory(object):
         the dict '''
 
         if key in my_dict:
-            my_dict[key].append(element)
+            my_dict[key].append(element);
         else:
             my_dict[key] = [element]
 
@@ -438,4 +575,3 @@ class Ec2Inventory(object):
 # Run the script
 Ec2Inventory()
 
-

playbooks/edx-east/continuous_integration.yml

+- name: Configure instance(s)
+  hosts: tag_Name_edx-continuous-integration
+  sudo: True
+  gather_facts: True
+  vars:
+    migrate_db: "yes"
+    openid_workaround: True
+  roles:
+    - common
+    - nginx
+    - edxlocal
+    - edxapp
+    - { role: 'rabbitmq', rabbitmq_ip: '127.0.0.1' }
+    - { role: 'edxapp', celery_worker: True }
+    - oraclejdk
+    - elasticsearch
+    - role: rbenv
+      rbenv_user: "{{ forum_user }}"
+      rbenv_user_home: "{{ forum_home }}"
+      rbenv_ruby_version: "{{ forum_ruby_version }}"
+    - forum
+    - role: virtualenv
+      virtualenv_user: "{{ xqueue_user }}"
+      virtualenv_user_home: "{{ xqueue_user_home }}"
+      virtualenv_name: "{{ xqueue_user }}"
+    - { role: "xqueue", update_users: True }
+    - xserver
+    - ora

playbooks/roles/ora/tasks/main.yml

@@ -3,6 +3,11 @@
 #  - common/tasks/main.yml
 #  - nginx/tasks/main.yml
 ---
+- name: ora | create the ora application user
+  user: name={{ ora_user }}
+  tags:
+  - ora
+
 - name: ora | Create ml_models directory
   file: path={{ora_code_dir}}/../ml_models state=directory owner={{ ora_user }} group={{ ora_user }}
   tags: