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
|
# vi: ts=4 expandtab
#
# Copyright (C) 2009-2010 Canonical Ltd.
# Copyright (C) 2012 Hewlett-Packard Development Company, L.P.
#
# Author: Scott Moser <scott.moser@canonical.com>
# Author: Juerg Hafliger <juerg.haefliger@hp.com>
# Author: Cosmin Luta <cosmin.luta@avira.com>
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License version 3, as
# published by the Free Software Foundation.
#
# This program 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 this program. If not, see <http://www.gnu.org/licenses/>.
import cloudinit.DataSource as DataSource
from cloudinit import seeddir as base_seeddir
from cloudinit import log
import cloudinit.util as util
import socket
import urllib2
import time
import boto.utils as boto_utils
from struct import pack
class DataSourceCS(DataSource.DataSource):
api_ver = 'latest'
seeddir = base_seeddir + '/cs'
metadata_address = None
def __init__(self, sys_cfg=None):
DataSource.DataSource.__init__(self, sys_cfg)
# Cloudstack has its metadata/userdata URLs located on http://<default-gateway-ip>/latest/
self.metadata_address = "http://" + self._get_default_gateway() + "/"
def _get_default_gateway(self):
f = None
try:
f = open("/proc/net/route", "r")
for line in f.readlines():
items = line.split("\t")
if items[1] == "00000000":
# found the default route, get the gateway
gw = int(items[2], 16)
log.debug("found default route, gateway %s" % items[2])
return socket.inet_ntoa(pack("<L", gw))
f.close()
except:
if f is not None:
f.close()
return "localhost"
def __str__(self):
return "DataSourceCS"
def get_data(self):
seedret = {}
if util.read_optional_seed(seedret, base=self.seeddir + "/"):
self.userdata_raw = seedret['user-data']
self.metadata = seedret['meta-data']
log.debug("using seeded cs data in %s" % self.seeddir)
return True
try:
if not self.wait_for_metadata_service():
return False
start = time.time()
self.userdata_raw = boto_utils.get_instance_userdata(self.api_ver,
None, self.metadata_address)
self.metadata = boto_utils.get_instance_metadata(self.api_ver,
self.metadata_address)
log.debug("crawl of metadata service took %ds" % (time.time() -
start))
return True
except Exception as e:
log.exception(e)
return False
def get_instance_id(self):
return self.metadata['instance-id']
def get_availability_zone(self):
return self.metadata['availability-zone']
def wait_for_metadata_service(self):
mcfg = self.ds_cfg
if not hasattr(mcfg, "get"):
mcfg = {}
max_wait = 120
try:
max_wait = int(mcfg.get("max_wait", max_wait))
except Exception:
util.logexc(log)
log.warn("Failed to get max wait. using %s" % max_wait)
if max_wait == 0:
return False
timeout = 50
try:
timeout = int(mcfg.get("timeout", timeout))
except Exception:
util.logexc(log)
log.warn("Failed to get timeout, using %s" % timeout)
def_mdurls = [self.metadata_address]
mdurls = mcfg.get("metadata_urls", def_mdurls)
# Remove addresses from the list that wont resolve.
filtered = [x for x in mdurls if util.is_resolvable_url(x)]
if set(filtered) != set(mdurls):
log.debug("removed the following from metadata urls: %s" %
list((set(mdurls) - set(filtered))))
if len(filtered):
mdurls = filtered
else:
log.warn("Empty metadata url list! using default list")
mdurls = def_mdurls
urls = []
url2base = {False: False}
for url in mdurls:
cur = "%s/%s/meta-data/instance-id" % (url, self.api_ver)
urls.append(cur)
url2base[cur] = url
starttime = time.time()
url = wait_for_metadata_service(urls=urls, max_wait=max_wait,
timeout=timeout, status_cb=log.warn)
if url:
log.debug("Using metadata source: '%s'" % url2base[url])
else:
log.critical("giving up on md after %i seconds\n" %
int(time.time() - starttime))
self.metadata_address = url2base[url]
return bool(url)
def wait_for_metadata_service(urls, max_wait=None, timeout=None,
status_cb=None):
"""
urls: a list of urls to try
max_wait: roughly the maximum time to wait before giving up
The max time is *actually* len(urls)*timeout as each url will
be tried once and given the timeout provided.
timeout: the timeout provided to urllib2.urlopen
status_cb: call method with string message when a url is not available
the idea of this routine is to wait for the EC2 metdata service to
come up. On both Eucalyptus and EC2 we have seen the case where
the instance hit the MD before the MD service was up. EC2 seems
to have permenantely fixed this, though.
In openstack, the metadata service might be painfully slow, and
unable to avoid hitting a timeout of even up to 10 seconds or more
(LP: #894279) for a simple GET.
Offset those needs with the need to not hang forever (and block boot)
on a system where cloud-init is configured to look for EC2 Metadata
service but is not going to find one. It is possible that the instance
data host (169.254.169.254) may be firewalled off Entirely for a sytem,
meaning that the connection will block forever unless a timeout is set.
"""
starttime = time.time()
sleeptime = 1
def nullstatus_cb(msg):
return
if status_cb == None:
status_cb = nullstatus_cb
def timeup(max_wait, starttime):
return((max_wait <= 0 or max_wait is None) or
(time.time() - starttime > max_wait))
loop_n = 0
while True:
sleeptime = int(loop_n / 5) + 1
for url in urls:
now = time.time()
if loop_n != 0:
if timeup(max_wait, starttime):
break
if timeout and (now + timeout > (starttime + max_wait)):
# shorten timeout to not run way over max_time
timeout = int((starttime + max_wait) - now)
try:
req = urllib2.Request(url)
resp = urllib2.urlopen(req, timeout=timeout)
if resp.read() != "":
return url
reason = "empty data [%s]" % resp.getcode()
except urllib2.HTTPError as e:
reason = "http error [%s]" % e.code
except urllib2.URLError as e:
reason = "url error [%s]" % e.reason
except socket.timeout as e:
reason = "socket timeout [%s]" % e
except Exception as e:
reason = "unexpected error [%s]" % e
if log:
status_cb("'%s' failed [%s/%ss]: %s" %
(url, int(time.time() - starttime), max_wait,
reason))
if timeup(max_wait, starttime):
break
loop_n += 1
time.sleep(sleeptime)
return False
datasources = [
(DataSourceCS, (DataSource.DEP_FILESYSTEM, DataSource.DEP_NETWORK)),
]
# return a list of data sources that match this set of dependencies
def get_datasource_list(depends):
return DataSource.list_from_depends(depends, datasources)
|
