re-work vendor-data and smartos

This reduces how much cloud-init is explicitly involved in what "vendor-data"
could accomplish.  The goal of vendor-data was to provide the vendor with a
channel to run arbitrary code that accomodate for their specific platform.

Much of those accomodations are currently being done in cloud-init.
However, this now moves some of those things to default "vendor-data", instead
of cloud-init proper.

Basically, now we have an 'sdc:vendor-data' key in the metadata.
If that does not exist, then cloud-init will use the default.

The default, provides a boothook.  That boothook writes a file into
/var/lib/cloud/per-boot/ .  That file will be both written on every boot
and then executed at rc.local time frame (by 'scripts-per-boot').

It will then execute /var/lib/cloud/instance/data/user-script
and /var/lib/cloud/instance/data/operator-script if they exist.

So, the things that cloud-init is now doing outside of the default vendor-data
that I would rather be done in vendor-data is:
 * managing the population of instance/data/user-script and
   instance/data/operator-script.  These could very easily be done
   from the boothook, but doing them in cloud-init removes the necessity
   for having a 'mdata-get' command in the image (or some other way for
   the boothook script to query the datasource).
 * managing the LEGACY things.

cloudinit/sources/DataSourceSmartOS.py

@@ -50,7 +50,8 @@ SMARTOS_ATTRIB_MAP = {
     'iptables_disable': ('iptables_disable', True),
     'motd_sys_info': ('motd_sys_info', True),
     'availability_zone': ('sdc:datacenter_name', True),
-    'vendordata': ('sdc:operator-script', False),
+    'vendor-data': ('sdc:vendor-data', False),
+    'operator-script': ('sdc:operator-script', False),
 }
 
 DS_NAME = 'SmartOS'
@@ -95,33 +96,45 @@ BUILTIN_CLOUD_CONFIG = {
                   'device': 'ephemeral0'}],
 }
 
-BUILTIN_VENDOR_DATA = """
+## builtin vendor-data is a boothook that writes a script into
-#cloud-config:
+## /var/lib/cloud/scripts/per-boot.  *That* script then handles
-write_files:
+## executing the 'operator-script' and 'user-script' files
-  - encoding: b64
+## that cloud-init writes into /var/lib/cloud/instance/data/
-    owner: root:root
+## if they exist.
-    path: %(script_d)s/01_sdc-operator-script.sh
+##
-    permissions: '0755'
+## This is all very indirect, but its done like this so that at
-    content: |
+## some point in the future, perhaps cloud-init wouldn't do it at
-        """ + base64.b64encode("""#!/bin/sh
+## all, but rather the vendor actually provide vendor-data that accomplished
-# This file is written as part of the default vendor data for
+## their desires. (That is the point of vendor-data).
-# SmartOS. This script looks for the SmartDC operator script
+##
-# and then executes it. It will be run each boot.
+## cloud-init does cheat a bit, and write the operator-script and user-script
+## itself.  It could have the vendor-script do that, but it seems better
+## to not require the image to contain a tool (mdata-get) to read those
+## keys when we have a perfectly good one inside cloud-init.
+BUILTIN_VENDOR_DATA = """\
+#cloud-boothook
+#!/bin/sh
+fname="%(per_boot_d)s/01_smartos_vendor_data.sh"
+mkdir -p "${fname%%/*}"
+cat > "$fname" <<"END_SCRIPT"
+#!/bin/sh
+##
+# This file is written as part of the default vendor data for SmartOS.
+# The SmartOS datasource writes the listed file from the listed metadata key
+#   sdc:operator-script -> %(operator_script)s
+#   user-script -> %(user_script)s
 #
-# This requires the Joyent Metadata client to be installed.
+# You can view content with 'mdata-get <key>'
-# On Ubuntu, it is provided via the joyent-mdata-client package
+#
-# Or you can get it via https://github.com/joyent/mdata-client
+for script in "%(operator_script)s" "%(user_script)s"; do
+    [ -x "$script" ] || continue
+    echo "executing '$script'" 1>&2
+    "$script"
+done
+END_SCRIPT
+chmod +x "$fname"
+"""
 
-my_path=$(dirname $0)
-[ -x /usr/sbin/mdata-get ] || exit 1
-
-/usr/sbin/mdata-get sdc:operator-script > \
-    $my_path/operator-script || exit 0
-
-[ -e $my_path/operator-script ] || exit 0
-chmod 0700 $my_path/operator-script
-exec /run/sdc/operator-script
-""")
 
 # @datadictionary: this is legacy path for placing files from metadata
 #   per the SmartOS location. It is not preferable, but is done for
@@ -148,8 +161,7 @@ class DataSourceSmartOS(sources.DataSource):
         self.b64_keys = self.ds_cfg.get('base64_keys')
         self.b64_all = self.ds_cfg.get('base64_all')
         self.script_base_d = os.path.join(self.paths.get_cpath("scripts"))
-        self.user_script_d = os.path.join(self.paths.get_cpath("scripts"),
+        self.data_d = os.path.join(self.paths.instance_link, 'data')
-                                          'per-boot')
 
     def __str__(self):
         root = sources.DataSource.__str__(self)
@@ -168,7 +180,7 @@ class DataSourceSmartOS(sources.DataSource):
             LOG.debug("No dmidata utility found")
             return False
 
-        system_uuid, system_type = dmi_info
+        system_uuid, system_type = tuple(dmi_info)
         if 'smartdc' not in system_type.lower():
             LOG.debug("Host is not on SmartOS. system_type=%s", system_type)
             return False
@@ -191,11 +203,18 @@ class DataSourceSmartOS(sources.DataSource):
         # to a file in the filesystem of the guest on each boot and then
         # executed. It may be of any format that would be considered
         # executable in the guest instance.
-        u_script = md.get('user-script')
+        #
-        u_script_f = "%s/99_user_script" % self.user_script_d
+        # We write 'user-script' and 'operator-script' into the 
+        # instance/data directory. The default vendor-data then handles
+        # executing them later.
+        user_script = os.path.join(self.data_d, 'user-script')
         u_script_l = "%s/user-script" % LEGACY_USER_D
-        write_boot_content(u_script, u_script_f, link=u_script_l, shebang=True,
+        write_boot_content(md.get('user-script'), content_f=user_script,
-                           mode=0700)
+                           link=u_script_l, shebang=True, mode=0700)
+
+        operator_script = os.path.join(self.data_d, 'operator-script')
+        write_boot_content(md.get('operator-script'),
+                           content_f=operator_script, shebang=False, mode=0700)
 
         # @datadictionary:  This key has no defined format, but its value
         # is written to the file /var/db/mdata-user-data on each boot prior
@@ -214,14 +233,16 @@ class DataSourceSmartOS(sources.DataSource):
         if md['user-data']:
             ud = md['user-data']
 
-        if not md['vendordata']:
+        if not md['vendor-data']:
-            md['vendordata'] = BUILTIN_VENDOR_DATA % {
+            md['vendor-data'] = BUILTIN_VENDOR_DATA % {
-                                'script_d': self.user_script_d
+                'user_script': user_script,
-                               }
+                'operator_script': operator_script,
+                'per_boot_d': os.path.join(self.paths.get_cpath("scripts"), 'per-boot'),
+            }
 
         self.metadata = util.mergemanydict([md, self.metadata])
         self.userdata_raw = ud
-        self.vendordata_raw = md['vendordata']
+        self.vendordata_raw = md['vendor-data']
         return True
 
     def device_name_to_device(self, name):

tests/unittests/test_datasource/test_smartos.py

@@ -44,6 +44,7 @@ MOCK_RETURNS = {
     'cloud-init:user-data': '\n'.join(['#!/bin/sh', '/bin/true', '']),
     'sdc:datacenter_name': 'somewhere2',
     'sdc:operator-script': '\n'.join(['bin/true', '']),
+    'sdc:vendor-data': '\n'.join(['VENDOR_DATA', '']),
     'user-data': '\n'.join(['something', '']),
     'user-script': '\n'.join(['/bin/true', '']),
 }
@@ -107,7 +108,6 @@ class MockSerial(object):
             yield '\n'
 
 
-#class TestSmartOSDataSource(MockerTestCase):
 class TestSmartOSDataSource(helpers.FilesystemMockingTestCase):
     def setUp(self):
         helpers.FilesystemMockingTestCase.setUp(self)
@@ -345,10 +345,10 @@ class TestSmartOSDataSource(helpers.FilesystemMockingTestCase):
             there is no script remaining.
         """
 
-        script_d = os.path.join(self.tmp, "scripts", "per-boot")
+        script_d = os.path.join(self.tmp, "instance", "data")
         os.makedirs(script_d)
 
-        test_script_f = "%s/99_user_script" % script_d
+        test_script_f = os.path.join(script_d, 'user-script')
         with open(test_script_f, 'w') as f:
             f.write("TEST DATA")
 
@@ -397,49 +397,20 @@ class TestSmartOSDataSource(helpers.FilesystemMockingTestCase):
         dsrc = self._get_ds(mockdata=MOCK_RETURNS)
         ret = dsrc.get_data()
         self.assertTrue(ret)
-        self.assertEquals(MOCK_RETURNS['sdc:operator-script'],
+        self.assertEquals(MOCK_RETURNS['sdc:vendor-data'],
-                          dsrc.metadata['vendordata'])
+                          dsrc.metadata['vendor-data'])
 
     def test_default_vendor_data(self):
         my_returns = MOCK_RETURNS.copy()
-        def_op_script = my_returns['sdc:operator-script']
+        def_op_script = my_returns['sdc:vendor-data']
-        del my_returns['sdc:operator-script']
+        del my_returns['sdc:vendor-data']
         dsrc = self._get_ds(mockdata=my_returns)
         ret = dsrc.get_data()
         self.assertTrue(ret)
-        self.assertNotEquals(def_op_script, dsrc.metadata['vendordata'])
+        self.assertNotEquals(def_op_script, dsrc.metadata['vendor-data'])
 
-        self.replicateTestRoot('simple_ubuntu', self.tmp)
+        # we expect default vendor-data is a boothook
-        cfg = {
+        self.assertTrue(dsrc.vendordata_raw.startswith("#cloud-boothook"))
-            'cloud_init_modules': ['write-files'],
-        }
-        cloud_cfg = util.yaml_dumps(cfg)
-        util.ensure_dir(os.path.join(self.tmp, 'etc', 'cloud'))
-        util.write_file(os.path.join(self.tmp, 'etc',
-                                     'cloud', 'cloud.cfg'), cloud_cfg)
-
-        self._patchIn(self.tmp)
-
-        initer = stages.Init()
-        initer.read_cfg()
-        initer.datasource = dsrc
-        initer.initialize()
-        initer.fetch()
-        _iid = initer.instancify()
-        initer.update()
-        initer.cloudify().run('consume_data',
-                              initer.consume_data,
-                              args=[PER_INSTANCE],
-                              freq=PER_INSTANCE)
-        mods = stages.Modules(initer)
-        (_which_ran, _failures) = mods.run_section('cloud_init_modules')
-        pb_script_fns = os.path.join(dsrc.paths.get_cpath('scripts'),
-                                     'per-boot', '01_sdc-operator-script.sh')
-        self.assertTrue(os.path.isfile(pb_script_fns))
-        self.assertTrue(os.access(pb_script_fns, os.X_OK))
-
-        with open(pb_script_fns, 'r') as fd:
-            self.assertIn("#!/bin/sh", fd.readlines()[0])
 
     def test_disable_iptables_flag(self):
         dsrc = self._get_ds(mockdata=MOCK_RETURNS)