summaryrefslogtreecommitdiff
path: root/cloud/amazon/elasticache.py
blob: 5a3a60c005fec0684eccf832e6f05090c25bbfcb (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
#!/usr/bin/python
# 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/>.

DOCUMENTATION = """
---
module: elasticache
short_description: Manage cache clusters in Amazon Elasticache.
description:
  - Manage cache clusters in Amazon Elasticache.
  - Returns information about the specified cache cluster.
version_added: "1.4"
author: "Jim Dalton (@jsdalton)"
options:
  state:
    description:
      - C(absent) or C(present) are idempotent actions that will create or destroy a cache cluster as needed. C(rebooted) will reboot the cluster, resulting in a momentary outage.
    choices: ['present', 'absent', 'rebooted']
    required: true
  name:
    description:
      - The cache cluster identifier
    required: true
  engine:
    description:
      - Name of the cache engine to be used.
    required: false
    default: memcached
    choices: ['redis', 'memcached']
  cache_engine_version:
    description:
      - The version number of the cache engine
    required: false
    default: None
  node_type:
    description:
      - The compute and memory capacity of the nodes in the cache cluster
    required: false
    default: cache.m1.small
  num_nodes:
    description:
      - The initial number of cache nodes that the cache cluster will have. Required when state=present.
    required: false
  cache_port:
    description:
      - The port number on which each of the cache nodes will accept connections
    required: false
    default: None
  cache_parameter_group:
    description:
      - The name of the cache parameter group to associate with this cache cluster. If this argument is omitted, the default cache parameter group for the specified engine will be used.
    required: false
    default: None
    version_added: "2.0"
    aliases: [ 'parameter_group' ]
  cache_subnet_group:
    description:
      - The subnet group name to associate with. Only use if inside a vpc. Required if inside a vpc
    required: false
    default: None
    version_added: "2.0"
  security_group_ids:
    description:
      - A list of vpc security group names to associate with this cache cluster. Only use if inside a vpc
    required: false
    default: None
    version_added: "1.6"
  cache_security_groups:
    description:
      - A list of cache security group names to associate with this cache cluster. Must be an empty list if inside a vpc
    required: false
    default: None
  zone:
    description:
      - The EC2 Availability Zone in which the cache cluster will be created
    required: false
    default: None
  wait:
    description:
      - Wait for cache cluster result before returning
    required: false
    default: yes
    choices: [ "yes", "no" ]
  hard_modify:
    description:
      - Whether to destroy and recreate an existing cache cluster if necessary in order to modify its state
    required: false
    default: no
    choices: [ "yes", "no" ]
extends_documentation_fragment:
    - aws
    - ec2
"""

EXAMPLES = """
# Note: None of these examples set aws_access_key, aws_secret_key, or region.
# It is assumed that their matching environment variables are set.

# Basic example
- elasticache:
    name: "test-please-delete"
    state: present
    engine: memcached
    cache_engine_version: 1.4.14
    node_type: cache.m1.small
    num_nodes: 1
    cache_port: 11211
    cache_security_groups:
      - default
    zone: us-east-1d


# Ensure cache cluster is gone
- elasticache:
    name: "test-please-delete"
    state: absent

# Reboot cache cluster
- elasticache:
    name: "test-please-delete"
    state: rebooted

"""

import sys
import time

try:
    import boto
    from boto.elasticache.layer1 import ElastiCacheConnection
    from boto.regioninfo import RegionInfo
    HAS_BOTO = True
except ImportError:
    HAS_BOTO = False


class ElastiCacheManager(object):
    """Handles elasticache creation and destruction"""

    EXIST_STATUSES = ['available', 'creating', 'rebooting', 'modifying']

    def __init__(self, module, name, engine, cache_engine_version, node_type,
                 num_nodes, cache_port, cache_parameter_group, cache_subnet_group,
                 cache_security_groups, security_group_ids, zone, wait,
                 hard_modify, region, **aws_connect_kwargs):
        self.module = module
        self.name = name
        self.engine = engine
        self.cache_engine_version = cache_engine_version
        self.node_type = node_type
        self.num_nodes = num_nodes
        self.cache_port = cache_port
        self.cache_parameter_group = cache_parameter_group
        self.cache_subnet_group = cache_subnet_group
        self.cache_security_groups = cache_security_groups
        self.security_group_ids = security_group_ids
        self.zone = zone
        self.wait = wait
        self.hard_modify = hard_modify

        self.region = region
        self.aws_connect_kwargs = aws_connect_kwargs

        self.changed = False
        self.data = None
        self.status = 'gone'
        self.conn = self._get_elasticache_connection()
        self._refresh_data()

    def ensure_present(self):
        """Ensure cache cluster exists or create it if not"""
        if self.exists():
            self.sync()
        else:
            self.create()

    def ensure_absent(self):
        """Ensure cache cluster is gone or delete it if not"""
        self.delete()

    def ensure_rebooted(self):
        """Ensure cache cluster is gone or delete it if not"""
        self.reboot()

    def exists(self):
        """Check if cache cluster exists"""
        return self.status in self.EXIST_STATUSES

    def create(self):
        """Create an ElastiCache cluster"""
        if self.status == 'available':
            return
        if self.status in ['creating', 'rebooting', 'modifying']:
            if self.wait:
                self._wait_for_status('available')
            return
        if self.status == 'deleting':
            if self.wait:
                self._wait_for_status('gone')
            else:
                msg = "'%s' is currently deleting. Cannot create."
                self.module.fail_json(msg=msg % self.name)

        try:
            response = self.conn.create_cache_cluster(cache_cluster_id=self.name,
                                                      num_cache_nodes=self.num_nodes,
                                                      cache_node_type=self.node_type,
                                                      engine=self.engine,
                                                      engine_version=self.cache_engine_version,
                                                      cache_security_group_names=self.cache_security_groups,
                                                      security_group_ids=self.security_group_ids,
                                                      cache_parameter_group_name=self.cache_parameter_group,
                                                      cache_subnet_group_name=self.cache_subnet_group,
                                                      preferred_availability_zone=self.zone,
                                                      port=self.cache_port)
        except boto.exception.BotoServerError as e:
            self.module.fail_json(msg=e.message)

        self._refresh_data()

        self.changed = True
        if self.wait:
            self._wait_for_status('available')
        return True

    def delete(self):
        """Destroy an ElastiCache cluster"""
        if self.status == 'gone':
            return
        if self.status == 'deleting':
            if self.wait:
                self._wait_for_status('gone')
            return
        if self.status in ['creating', 'rebooting', 'modifying']:
            if self.wait:
                self._wait_for_status('available')
            else:
                msg = "'%s' is currently %s. Cannot delete."
                self.module.fail_json(msg=msg % (self.name, self.status))

        try:
            response = self.conn.delete_cache_cluster(cache_cluster_id=self.name)
        except boto.exception.BotoServerError as e:
            self.module.fail_json(msg=e.message)
        cache_cluster_data = response['DeleteCacheClusterResponse']['DeleteCacheClusterResult']['CacheCluster']
        self._refresh_data(cache_cluster_data)

        self.changed = True
        if self.wait:
            self._wait_for_status('gone')

    def sync(self):
        """Sync settings to cluster if required"""
        if not self.exists():
            msg = "'%s' is %s. Cannot sync."
            self.module.fail_json(msg=msg % (self.name, self.status))

        if self.status in ['creating', 'rebooting', 'modifying']:
            if self.wait:
                self._wait_for_status('available')
            else:
                # Cluster can only be synced if available. If we can't wait
                # for this, then just be done.
                return

        if self._requires_destroy_and_create():
            if not self.hard_modify:
                msg = "'%s' requires destructive modification. 'hard_modify' must be set to true to proceed."
                self.module.fail_json(msg=msg % self.name)
            if not self.wait:
                msg = "'%s' requires destructive modification. 'wait' must be set to true."
                self.module.fail_json(msg=msg % self.name)
            self.delete()
            self.create()
            return

        if self._requires_modification():
            self.modify()

    def modify(self):
        """Modify the cache cluster. Note it's only possible to modify a few select options."""
        nodes_to_remove = self._get_nodes_to_remove()
        try:
            response = self.conn.modify_cache_cluster(cache_cluster_id=self.name,
                                                  num_cache_nodes=self.num_nodes,
                                                  cache_node_ids_to_remove=nodes_to_remove,
                                                  cache_security_group_names=self.cache_security_groups,
                                                  cache_parameter_group_name=self.cache_parameter_group,
                                                  security_group_ids=self.security_group_ids,
                                                  apply_immediately=True,
                                                  engine_version=self.cache_engine_version)
        except boto.exception.BotoServerError as e:
            self.module.fail_json(msg=e.message)

        self._refresh_data()

        self.changed = True
        if self.wait:
            self._wait_for_status('available')

    def reboot(self):
        """Reboot the cache cluster"""
        if not self.exists():
            msg = "'%s' is %s. Cannot reboot."
            self.module.fail_json(msg=msg % (self.name, self.status))
        if self.status == 'rebooting':
            return
        if self.status in ['creating', 'modifying']:
            if self.wait:
                self._wait_for_status('available')
            else:
                msg = "'%s' is currently %s. Cannot reboot."
                self.module.fail_json(msg=msg % (self.name, self.status))

        # Collect ALL nodes for reboot
        cache_node_ids = [cn['CacheNodeId'] for cn in self.data['CacheNodes']]
        try:
            response = self.conn.reboot_cache_cluster(cache_cluster_id=self.name,
                                                      cache_node_ids_to_reboot=cache_node_ids)
        except boto.exception.BotoServerError as e:
            self.module.fail_json(msg=e.message)

        self._refresh_data()

        self.changed = True
        if self.wait:
            self._wait_for_status('available')

    def get_info(self):
        """Return basic info about the cache cluster"""
        info = {
            'name': self.name,
            'status': self.status
        }
        if self.data:
            info['data'] = self.data
        return info


    def _wait_for_status(self, awaited_status):
        """Wait for status to change from present status to awaited_status"""
        status_map = {
            'creating': 'available',
            'rebooting': 'available',
            'modifying': 'available',
            'deleting': 'gone'
        }
        if self.status == awaited_status:
            # No need to wait, we're already done
            return
        if status_map[self.status] != awaited_status:
            msg = "Invalid awaited status. '%s' cannot transition to '%s'"
            self.module.fail_json(msg=msg % (self.status, awaited_status))

        if awaited_status not in set(status_map.values()):
            msg = "'%s' is not a valid awaited status."
            self.module.fail_json(msg=msg % awaited_status)

        while True:
            time.sleep(1)
            self._refresh_data()
            if self.status == awaited_status:
                break

    def _requires_modification(self):
        """Check if cluster requires (nondestructive) modification"""
        # Check modifiable data attributes
        modifiable_data = {
            'NumCacheNodes': self.num_nodes,
            'EngineVersion': self.cache_engine_version
        }
        for key, value in modifiable_data.iteritems():
            if value is not None and self.data[key] != value:
                return True

        # Check cache security groups
        cache_security_groups = []
        for sg in self.data['CacheSecurityGroups']:
            cache_security_groups.append(sg['CacheSecurityGroupName'])
        if set(cache_security_groups) != set(self.cache_security_groups):
            return True

        # check vpc security groups
        vpc_security_groups = []
        security_groups = self.data['SecurityGroups'] or []
        for sg in security_groups:
            vpc_security_groups.append(sg['SecurityGroupId'])
        if set(vpc_security_groups) != set(self.security_group_ids):
            return True

        return False

    def _requires_destroy_and_create(self):
        """
        Check whether a destroy and create is required to synchronize cluster.
        """
        unmodifiable_data = {
            'node_type': self.data['CacheNodeType'],
            'engine': self.data['Engine'],
            'cache_port': self._get_port()
        }
        # Only check for modifications if zone is specified
        if self.zone is not None:
            unmodifiable_data['zone'] = self.data['PreferredAvailabilityZone']
        for key, value in unmodifiable_data.iteritems():
            if getattr(self, key) is not None and getattr(self, key) != value:
                return True
        return False

    def _get_elasticache_connection(self):
        """Get an elasticache connection"""
        try:
            endpoint = "elasticache.%s.amazonaws.com" % self.region
            connect_region = RegionInfo(name=self.region, endpoint=endpoint)
            return ElastiCacheConnection(
                region=connect_region,
                **self.aws_connect_kwargs
            )
        except boto.exception.NoAuthHandlerFound as e:
            self.module.fail_json(msg=e.message)

    def _get_port(self):
        """Get the port. Where this information is retrieved from is engine dependent."""
        if self.data['Engine'] == 'memcached':
            return self.data['ConfigurationEndpoint']['Port']
        elif self.data['Engine'] == 'redis':
            # Redis only supports a single node (presently) so just use
            # the first and only
            return self.data['CacheNodes'][0]['Endpoint']['Port']

    def _refresh_data(self, cache_cluster_data=None):
        """Refresh data about this cache cluster"""

        if cache_cluster_data is None:
            try:
                response = self.conn.describe_cache_clusters(cache_cluster_id=self.name,
                                                             show_cache_node_info=True)
            except boto.exception.BotoServerError:
                self.data = None
                self.status = 'gone'
                return
            cache_cluster_data = response['DescribeCacheClustersResponse']['DescribeCacheClustersResult']['CacheClusters'][0]
        self.data = cache_cluster_data
        self.status = self.data['CacheClusterStatus']

        # The documentation for elasticache lies -- status on rebooting is set
        # to 'rebooting cache cluster nodes' instead of 'rebooting'. Fix it
        # here to make status checks etc. more sane.
        if self.status == 'rebooting cache cluster nodes':
            self.status = 'rebooting'

    def _get_nodes_to_remove(self):
        """If there are nodes to remove, it figures out which need to be removed"""
        num_nodes_to_remove = self.data['NumCacheNodes'] - self.num_nodes
        if num_nodes_to_remove <= 0:
            return None

        if not self.hard_modify:
            msg = "'%s' requires removal of cache nodes. 'hard_modify' must be set to true to proceed."
            self.module.fail_json(msg=msg % self.name)

        cache_node_ids = [cn['CacheNodeId'] for cn in self.data['CacheNodes']]
        return cache_node_ids[-num_nodes_to_remove:]


def main():
    argument_spec = ec2_argument_spec()
    argument_spec.update(dict(
            state                 ={'required': True, 'choices': ['present', 'absent', 'rebooted']},
            name                  ={'required': True},
            engine                ={'required': False, 'default': 'memcached'},
            cache_engine_version  ={'required': False},
            node_type             ={'required': False, 'default': 'cache.m1.small'},
            num_nodes             ={'required': False, 'default': None, 'type': 'int'},
            # alias for compat with the original PR 1950
            cache_parameter_group ={'required': False, 'default': None, 'aliases': ['parameter_group']},
            cache_port            ={'required': False, 'type': 'int'},
            cache_subnet_group    ={'required': False, 'default': None},
            cache_security_groups ={'required': False, 'default': [], 'type': 'list'},
            security_group_ids    ={'required': False, 'default': [], 'type': 'list'},
            zone                  ={'required': False, 'default': None},
            wait                  ={'required': False, 'type' : 'bool', 'default': True},
            hard_modify           ={'required': False, 'type': 'bool', 'default': False}
        )
    )

    module = AnsibleModule(
        argument_spec=argument_spec,
    )

    if not HAS_BOTO:
        module.fail_json(msg='boto required for this module')

    region, ec2_url, aws_connect_kwargs = get_aws_connection_info(module)

    name = module.params['name']
    state = module.params['state']
    engine = module.params['engine']
    cache_engine_version = module.params['cache_engine_version']
    node_type = module.params['node_type']
    num_nodes = module.params['num_nodes']
    cache_port = module.params['cache_port']
    cache_subnet_group = module.params['cache_subnet_group']
    cache_security_groups = module.params['cache_security_groups']
    security_group_ids = module.params['security_group_ids']
    zone = module.params['zone']
    wait = module.params['wait']
    hard_modify = module.params['hard_modify']
    cache_parameter_group = module.params['cache_parameter_group']

    if cache_subnet_group and cache_security_groups:
        module.fail_json(msg="Can't specify both cache_subnet_group and cache_security_groups")

    if state == 'present' and not num_nodes:
        module.fail_json(msg="'num_nodes' is a required parameter. Please specify num_nodes > 0")

    if not region:
        module.fail_json(msg=str("Either region or AWS_REGION or EC2_REGION environment variable or boto config aws_region or ec2_region must be set."))

    elasticache_manager = ElastiCacheManager(module, name, engine,
                                             cache_engine_version, node_type,
                                             num_nodes, cache_port,
                                             cache_parameter_group,
                                             cache_subnet_group,
                                             cache_security_groups,
                                             security_group_ids, zone, wait,
                                             hard_modify, region, **aws_connect_kwargs)

    if state == 'present':
        elasticache_manager.ensure_present()
    elif state == 'absent':
        elasticache_manager.ensure_absent()
    elif state == 'rebooted':
        elasticache_manager.ensure_rebooted()

    facts_result = dict(changed=elasticache_manager.changed,
                        elasticache=elasticache_manager.get_info())

    module.exit_json(**facts_result)

# import module snippets
from ansible.module_utils.basic import *
from ansible.module_utils.ec2 import *

main()