Merge lp:~stub/launchpad/db-deploy into lp:launchpad

[Stuart Bishop]

[r=stub][bug=777559] Connections to databases not subscribed to the main Launchpad replication set should not block Launchpad database updates.

Connections to the SSO database should not block production rollouts.

The SSO database is not subscribed to the main Launchpad replications set. This is the only set of tables that is locked during a database update, so connections to the SSO database do not affect rollouts (this is by design).

[Stuart Bishop (stub)]

In the name of the Senate and Peoples of Rome.

review: Approve

=== modified file 'database/schema/preflight.py'
--- database/schema/preflight.py	2011-04-27 09:13:48 +0000
+++ database/schema/preflight.py	2011-05-10 11:33:17 +0000
@@ -26,7 +26,7 @@
 
 
 # Ignore connections by these users.
-SYSTEM_USERS = frozenset(['postgres', 'slony', 'nagios'])
+SYSTEM_USERS = frozenset(['postgres', 'slony', 'nagios', 'lagmon'])
 
 # How lagged the cluster can be before failing the preflight check.
 MAX_LAG = timedelta(seconds=45)
@@ -37,14 +37,32 @@
         self.log = log
         self.is_replicated = replication.helpers.slony_installed(master_con)
         if self.is_replicated:
-            self.nodes = replication.helpers.get_all_cluster_nodes(master_con)
+            self.nodes = set(
+                replication.helpers.get_all_cluster_nodes(master_con))
             for node in self.nodes:
                 node.con = psycopg2.connect(node.connection_string)
                 node.con.set_isolation_level(ISOLATION_LEVEL_AUTOCOMMIT)
         else:
             node = replication.helpers.Node(None, None, None, True)
             node.con = master_con
-            self.nodes = [node]
+            self.nodes = set([node])
+
+        # Create a list of nodes subscribed to the replicated sets we
+        # are modifying.
+        cur = master_con.cursor()
+        cur.execute("""
+            WITH subscriptions AS (
+                SELECT *
+                FROM _sl.sl_subscribe
+                WHERE sub_set = 1 AND sub_active IS TRUE)
+            SELECT sub_provider FROM subscriptions
+            UNION
+            SELECT sub_receiver FROM subscriptions
+            """)
+        lpmain_node_ids = set(row[0] for row in cur.fetchall())
+        self.lpmain_nodes = set(
+            node for node in self.nodes
+            if node.node_id in lpmain_node_ids)
 
     def check_is_superuser(self):
         """Return True if all the node connections are as superusers."""
@@ -65,12 +83,16 @@
         return success
 
     def check_open_connections(self):
-        """Return False if any nodes have connections from non-system users.
+        """False if any lpmain nodes have connections from non-system users.
+
+        We only check on subscribed nodes, as there will be active systems
+        connected to other nodes in the replication cluster (such as the
+        SSO servers).
 
         System users are defined by SYSTEM_USERS.
         """
         success = True
-        for node in self.nodes:
+        for node in self.lpmain_nodes:
             cur = node.con.cursor()
             cur.execute("""
                 SELECT datname, usename, COUNT(*) AS num_connections