* Scrubber now uses registry client to communicate with registry

* glance-api writes out to a scrubber "queue" dir on delete
* Scrubber determines images to deleted from "queue" dir not db

Change-Id: Ia5574fc75f1a9c763bdef0f5773c2c182932b68a

etc/glance-api.conf

@@ -131,6 +131,13 @@ image_cache_stall_timeout = 86400
 # Turn on/off delayed delete
 delayed_delete = False
 
+# Delayed delete time in seconds
+scrub_time = 43200
+
+# Directory that the scrubber will use to remind itself of what to delete
+# Make sure this is also set in glance-scrubber.conf
+scrubber_datadir = /var/lib/glance/scrubber
+
 [pipeline:glance-api]
 pipeline = versionnegotiation context apiv1app
 # NOTE: use the following pipeline for keystone

etc/glance-scrubber.conf

@@ -12,28 +12,27 @@ log_file = /var/log/glance/scrubber.log
 # Send logs to syslog (/dev/log) instead of to file specified by `log_file`
 use_syslog = False
 
-# Delayed delete time in seconds
-scrub_time = 43200
-
 # Should we run our own loop or rely on cron/scheduler to run us
 daemon = False
 
-# Loop time between checking the db for new items to schedule for delete
+# Loop time between checking for new items to schedule for delete
 wakeup_time = 300
 
-# SQLAlchemy connection string for the reference implementation
-# registry server. Any valid SQLAlchemy connection string is fine.
-# See: http://www.sqlalchemy.org/docs/05/reference/sqlalchemy/connections.html#sqlalchemy.create_engine
-sql_connection = sqlite:///glance.sqlite
-
-# Period in seconds after which SQLAlchemy should reestablish its connection
-# to the database.
-#
-# MySQL uses a default `wait_timeout` of 8 hours, after which it will drop
-# idle connections. This can result in 'MySQL Gone Away' exceptions. If you
-# notice this, you can lower this value to ensure that SQLAlchemy reconnects
-# before MySQL can drop the connection.
-sql_idle_timeout = 3600
+# Directory that the scrubber will use to remind itself of what to delete
+# Make sure this is also set in glance-api.conf
+scrubber_datadir = /var/lib/glance/scrubber
+
+# Only one server in your deployment should be designated the cleanup host
+cleanup_scrubber = False
+
+# pending_delete items older than this time are candidates for cleanup
+cleanup_scrubber_time = 86400
+
+# Address to find the registry server for cleanups
+registry_host = 0.0.0.0
+
+# Port the registry server is listening on
+registry_port = 9191
 
 [app:glance-scrubber]
 paste.app_factory = glance.store.scrubber:app_factory

glance/common/context.py

@@ -36,14 +36,21 @@ def __init__(self, auth_tok=None, user=None, tenant=None, roles=None,
         self.roles = roles or []
         self.is_admin = is_admin
         self.read_only = read_only
-        self.show_deleted = show_deleted
+        self._show_deleted = show_deleted
         self.owner_is_tenant = owner_is_tenant
 
     @property
     def owner(self):
         """Return the owner to correlate with an image."""
         return self.tenant if self.owner_is_tenant else self.user
 
+    @property
+    def show_deleted(self):
+        """Admins can see deleted by default"""
+        if self._show_deleted or self.is_admin:
+            return True
+        return False
+
 
 class ContextMiddleware(wsgi.Middleware):
     def __init__(self, app, options):

glance/common/utils.py

@@ -21,6 +21,7 @@
 """
 
 import datetime
+import errno
 import inspect
 import logging
 import os
@@ -133,6 +134,22 @@ def parse_isotime(timestr):
     return datetime.datetime.strptime(timestr, TIME_FORMAT)
 
 
+def safe_mkdirs(path):
+    try:
+        os.makedirs(path)
+    except OSError, e:
+        if e.errno != errno.EEXIST:
+            raise
+
+
+def safe_remove(path):
+    try:
+        os.remove(path)
+    except OSError, e:
+        if e.errno != errno.ENOENT:
+            raise
+
+
 class LazyPluggable(object):
     """A pluggable backend loaded lazily based on some value."""
 

glance/registry/db/api.py

@@ -145,12 +145,15 @@ def image_get(context, image_id, session=None):
         raise exception.NotFound("No image found")
 
     try:
-        image = session.query(models.Image).\
-                       options(joinedload(models.Image.properties)).\
-                       options(joinedload(models.Image.members)).\
-                       filter_by(deleted=_deleted(context)).\
-                       filter_by(id=image_id).\
-                       one()
+        query = session.query(models.Image).\
+                        options(joinedload(models.Image.properties)).\
+                        options(joinedload(models.Image.members)).\
+                        filter_by(id=image_id)
+
+        if not can_show_deleted(context):
+            query = query.filter_by(deleted=False)
+
+        image = query.one()
     except exc.NoResultFound:
         raise exception.NotFound("No image found with ID %s" % image_id)
 
@@ -161,30 +164,6 @@ def image_get(context, image_id, session=None):
     return image
 
 
-def image_get_all_pending_delete(context, delete_time=None, limit=None):
-    """Get all images that are pending deletion
-
-    :param limit: maximum number of images to return
-    """
-    session = get_session()
-    query = session.query(models.Image).\
-                   options(joinedload(models.Image.properties)).\
-                   options(joinedload(models.Image.members)).\
-                   filter_by(deleted=True).\
-                   filter(models.Image.status == 'pending_delete')
-
-    if delete_time:
-        query = query.filter(models.Image.deleted_at <= delete_time)
-
-    query = query.order_by(desc(models.Image.deleted_at)).\
-                  order_by(desc(models.Image.id))
-
-    if limit:
-        query = query.limit(limit)
-
-    return query.all()
-
-
 def image_get_all(context, filters=None, marker=None, limit=None,
                   sort_key='created_at', sort_dir='desc'):
     """
@@ -204,9 +183,16 @@ def image_get_all(context, filters=None, marker=None, limit=None,
     query = session.query(models.Image).\
                    options(joinedload(models.Image.properties)).\
                    options(joinedload(models.Image.members)).\
-                   filter_by(deleted=_deleted(context)).\
                    filter(models.Image.status != 'killed')
 
+    if not can_show_deleted(context) or 'deleted' not in filters:
+        query = query.filter_by(deleted=False)
+    else:
+        query = query.filter_by(deleted=filters['deleted'])
+
+    if 'deleted' in filters:
+        del filters['deleted']
+
     sort_dir_func = {
         'asc': asc,
         'desc': desc,
@@ -469,11 +455,15 @@ def image_member_get(context, member_id, session=None):
     """Get an image member or raise if it does not exist."""
     session = session or get_session()
     try:
-        member = session.query(models.ImageMember).\
+        query = session.query(models.ImageMember).\
                         options(joinedload(models.ImageMember.image)).\
-                        filter_by(deleted=_deleted(context)).\
-                        filter_by(id=member_id).\
-                        one()
+                        filter_by(id=member_id)
+
+        if not can_show_deleted(context):
+            query = query.filter_by(deleted=False)
+
+        member = query.one()
+
     except exc.NoResultFound:
         raise exception.NotFound("No membership found with ID %s" % member_id)
 
@@ -490,11 +480,16 @@ def image_member_find(context, image_id, member, session=None):
     try:
         # Note lack of permissions check; this function is called from
         # RequestContext.is_image_visible(), so avoid recursive calls
-        return session.query(models.ImageMember).\
+        query = session.query(models.ImageMember).\
                         options(joinedload(models.ImageMember.image)).\
                         filter_by(image_id=image_id).\
-                        filter_by(member=member).\
-                        one()
+                        filter_by(member=member)
+
+        if not can_show_deleted(context):
+            query = query.filter_by(deleted=False)
+
+        return query.one()
+
     except exc.NoResultFound:
         raise exception.NotFound("No membership found for image %s member %s" %
                                  (image_id, member))
@@ -515,9 +510,11 @@ def image_member_get_memberships(context, member, marker=None, limit=None,
     session = get_session()
     query = session.query(models.ImageMember).\
                    options(joinedload(models.ImageMember.image)).\
-                   filter_by(deleted=_deleted(context)).\
                    filter_by(member=member)
 
+    if not can_show_deleted(context):
+        query = query.filter_by(deleted=False)
+
     sort_dir_func = {
         'asc': asc,
         'desc': desc,
@@ -551,7 +548,7 @@ def image_member_get_memberships(context, member, marker=None, limit=None,
 
 
 # pylint: disable-msg=C0111
-def _deleted(context):
+def can_show_deleted(context):
     """
     Calculates whether to include deleted objects based on context.
     Currently just looks for a flag called deleted in the context dict.

glance/registry/server.py

@@ -25,8 +25,9 @@
 import routes
 from webob import exc
 
-from glance.common import wsgi
 from glance.common import exception
+from glance.common import utils
+from glance.common import wsgi
 from glance.registry.db import api as db_api
 
 
@@ -147,8 +148,14 @@ def _get_filters(self, req):
         if req.context.is_admin:
             # Only admin gets to look for non-public images
             filters['is_public'] = self._get_is_public(req)
+            # The same for deleted
+            filters['deleted'] = self._parse_deleted_filter(req)
         else:
             filters['is_public'] = True
+            # NOTE(jkoelker): This is technically unnecessary since the db
+            #                 api will force deleted=False if its not an
+            #                 admin context. But explicit > implicit.
+            filters['deleted'] = False
         for param in req.str_params:
             if param in SUPPORTED_FILTERS:
                 filters[param] = req.str_params.get(param)
@@ -240,6 +247,13 @@ def _get_is_public(self, req):
             raise exc.HTTPBadRequest(_("is_public must be None, True, "
                                        "or False"))
 
+    def _parse_deleted_filter(self, req):
+        """Parse deleted into something usable."""
+        deleted = req.str_params.get('deleted', False)
+        if not deleted:
+            return False
+        return utils.bool_from_string(deleted)
+
     def show(self, req, id):
         """Return data about the given image id."""
         try:

glance/store/__init__.py

@@ -18,6 +18,7 @@
 import logging
 import optparse
 import os
+import time
 import urlparse
 
 from glance import registry
@@ -168,5 +169,22 @@ def schedule_delete_from_backend(uri, options, context, image_id, **kwargs):
             msg = _("Failed to delete image from store (%(uri)s).") % locals()
             logger.error(msg)
 
+    datadir = config.get_option(options, 'scrubber_datadir')
+    scrub_time = config.get_option(options, 'scrub_time', type='int',
+                                   default=0)
+    delete_time = time.time() + scrub_time
+    file_path = os.path.join(datadir, str(image_id))
+    utils.safe_mkdirs(datadir)
+
+    if os.path.exists(file_path):
+        msg = _("Image id %(image_id)s already queued for delete") % {
+                'image_id': image_id}
+        raise exception.Duplicate(msg)
+
+    with open(file_path, 'w') as f:
+        f.write('\n'.join([uri, str(int(delete_time))]))
+    os.chmod(file_path, 0600)
+    os.utime(file_path, (delete_time, delete_time))
+
     registry.update_image_metadata(options, context, image_id,
                                    {'status': 'pending_delete'})