add support index when continuing import at index phase

Indexing scans the placex table sequentially during indexing
on the initial import. That is okay because we know that all
rows need to be processed anywhere. When continuing the import,
however, a large part might already be indexed, so that the
process spends a lot of time going through rows that are no
longer of interest. Create a supporting index for all unindexed
rows to speed up the scan. This is the same index as used later
for updates.

diff --git a/nominatim/clicmd/setup.py b/nominatim/clicmd/setup.py
index 92d0694359e62ab48a58a255143b4733dfd316f6..32e788a3681ef60b407f918c96bbc808ffe4777c 100644 (file)
--- a/nominatim/clicmd/setup.py
+++ b/nominatim/clicmd/setup.py
@@ -105,11 +105,11 @@ class SetupAll:
                 LOG.error('Wikipedia importance dump file not found. '
                           'Will be using default importances.')
 
+        if args.continue_at is None or args.continue_at == 'load-data':
             LOG.warning('Initialise tables')
             with connect(args.config.get_libpq_dsn()) as conn:
                 database_import.truncate_data_tables(conn, args.config.MAX_WORD_FREQUENCY)
 
-        if args.continue_at is None or args.continue_at == 'load-data':
             LOG.warning('Load data into placex table')
             database_import.load_data(args.config.get_libpq_dsn(),
                                       args.data_dir,
@@ -120,6 +120,9 @@ class SetupAll:
                               nominatim_env=args, throw_on_fail=not args.ignore_errors)
 
         if args.continue_at is None or args.continue_at in ('load-data', 'indexing'):
+            if args.continue_at is not None and args.continue_at != 'load-data':
+                with connect(args.config.get_libpq_dsn()) as conn:
+                    SetupAll._create_pending_index(conn, args.config.TABLESPACE_ADDRESS_INDEX)
             LOG.warning('Indexing places')
             indexer = Indexer(args.config.get_libpq_dsn(),
                               args.threads or psutil.cpu_count() or 1)
@@ -149,3 +152,25 @@ class SetupAll:
                                     '{0[0]}.{0[1]}.{0[2]}-{0[3]}'.format(NOMINATIM_VERSION))
 
         return 0
+
+
+    @staticmethod
+    def _create_pending_index(conn, tablespace):
+        """ Add a supporting index for finding places still to be indexed.
+
+            This index is normally created at the end of the import process
+            for later updates. When indexing was partially done, then this
+            index can greatly improve speed going through already indexed data.
+        """
+        if conn.index_exists('idx_placex_pendingsector'):
+            return
+
+        with conn.cursor() as cur:
+            LOG.warning('Creating support index')
+            if tablespace:
+                tablespace = 'TABLESPACE ' + tablespace
+            cur.execute("""CREATE INDEX idx_placex_pendingsector
+                           ON placex USING BTREE (rank_address,geometry_sector)
+                           {} WHERE indexed_status > 0
+                        """.format(tablespace))
+        conn.commit()