add new replication mode catch-up

This mode gets updates until the server reports no new diffs
anymore.

Also adds additional indexing, when the main indexing step left
a couple of objects to process. This happens only when the
next update is expected to be more than 40min away.

diff --git a/nominatim/clicmd/replication.py b/nominatim/clicmd/replication.py
index a22cef478d7459edbbef7a7cb5536d016e1948f5..44eec5f185e9ad03accc0b2c55f27ba71678c9cb 100644 (file)
--- a/nominatim/clicmd/replication.py
+++ b/nominatim/clicmd/replication.py
@@ -42,14 +42,17 @@ class UpdateReplication:
                            help='Initialise the update process')
         group.add_argument('--no-update-functions', dest='update_functions',
                            action='store_false',
-                           help=("Do not update the trigger function to "
-                                 "support differential updates."))
+                           help="Do not update the trigger function to "
+                                "support differential updates (EXPERT)")
         group = parser.add_argument_group('Arguments for updates')
         group.add_argument('--check-for-updates', action='store_true',
                            help='Check if new updates are available and exit')
         group.add_argument('--once', action='store_true',
-                           help=("Download and apply updates only once. When "
-                                 "not set, updates are continuously applied"))
+                           help="Download and apply updates only once. When "
+                                "not set, updates are continuously applied")
+        group.add_argument('--catch-up', action='store_true',
+                           help="Download and apply updates until no new "
+                                "data is available on the server")
         group.add_argument('--no-index', action='store_false', dest='do_index',
                            help=("Do not index the new data. Only usable "
                                  "together with --once"))
@@ -92,28 +95,40 @@ class UpdateReplication:
                     round_time(end - start_import),
                     round_time(end - batchdate))
 
+
+    @staticmethod
+    def _compute_update_interval(args):
+        if args.catch_up:
+            return 0
+
+        update_interval = args.config.get_int('REPLICATION_UPDATE_INTERVAL')
+        # Sanity check to not overwhelm the Geofabrik servers.
+        if 'download.geofabrik.de' in args.config.REPLICATION_URL\
+           and update_interval < 86400:
+            LOG.fatal("Update interval too low for download.geofabrik.de.\n"
+                      "Please check install documentation "
+                      "(https://nominatim.org/release-docs/latest/admin/Import-and-Update#"
+                      "setting-up-the-update-process).")
+            raise UsageError("Invalid replication update interval setting.")
+
+        return update_interval
+
+
     @staticmethod
     def _update(args):
         from ..tools import replication
         from ..indexer.indexer import Indexer
         from ..tokenizer import factory as tokenizer_factory
 
+        update_interval = UpdateReplication._compute_update_interval(args)
+
         params = args.osm2pgsql_options(default_cache=2000, default_threads=1)
         params.update(base_url=args.config.REPLICATION_URL,
-                      update_interval=args.config.get_int('REPLICATION_UPDATE_INTERVAL'),
+                      update_interval=update_interval,
                       import_file=args.project_dir / 'osmosischange.osc',
                       max_diff_size=args.config.get_int('REPLICATION_MAX_DIFF'),
                       indexed_only=not args.once)
 
-        # Sanity check to not overwhelm the Geofabrik servers.
-        if 'download.geofabrik.de' in params['base_url']\
-           and params['update_interval'] < 86400:
-            LOG.fatal("Update interval too low for download.geofabrik.de.\n"
-                      "Please check install documentation "
-                      "(https://nominatim.org/release-docs/latest/admin/Import-and-Update#"
-                      "setting-up-the-update-process).")
-            raise UsageError("Invalid replication update interval setting.")
-
         if not args.once:
             if not args.do_index:
                 LOG.fatal("Indexing cannot be disabled when running updates continuously.")
@@ -135,8 +150,7 @@ class UpdateReplication:
                 index_start = dt.datetime.now(dt.timezone.utc)
                 indexer = Indexer(args.config.get_libpq_dsn(), tokenizer,
                                   args.threads or 1)
-                indexer.index_boundaries(0, 30)
-                indexer.index_by_rank(0, 30)
+                indexer.index_full(analyse=False)
 
                 with connect(args.config.get_libpq_dsn()) as conn:
                     status.set_indexed(conn, True)
@@ -145,10 +159,15 @@ class UpdateReplication:
             else:
                 index_start = None
 
+            if state is replication.UpdateState.NO_CHANGES and \
+               args.catch_up or update_interval > 40*60:
+                while indexer.has_pending():
+                    indexer.index_full(analyse=False)
+
             if LOG.isEnabledFor(logging.WARNING):
                 UpdateReplication._report_update(batchdate, start, index_start)
 
-            if args.once:
+            if args.once or (args.catch_up and state is replication.UpdateState.NO_CHANGES):
                 break
 
             if state is replication.UpdateState.NO_CHANGES:

diff --git a/nominatim/indexer/indexer.py b/nominatim/indexer/indexer.py
index d0cfb391c4dbdf7a63c875af6ec1b2d98ca88d0c..50bd232e30dc0c341c6d43bbf8cf70eb720d37d0 100644 (file)
--- a/nominatim/indexer/indexer.py
+++ b/nominatim/indexer/indexer.py
@@ -91,6 +91,17 @@ class Indexer:
         self.num_threads = num_threads
 
 
+    def has_pending(self):
+        """ Check if any data still needs indexing.
+            This function must only be used after the import has finished.
+            Otherwise it will be very expensive.
+        """
+        with connect(self.dsn) as conn:
+            with conn.cursor() as cur:
+                cur.execute("SELECT 'a' FROM placex WHERE indexed_status > 0 LIMIT 1")
+                return cur.rowcount > 0
+
+
     def index_full(self, analyse=True):
         """ Index the complete database. This will first index boundaries
             followed by all other objects. When `analyse` is True, then the

diff --git a/test/python/test_cli_replication.py b/test/python/test_cli_replication.py
index dcaeaf25fb8fff283f3228ac0fe2d12d56a99ad5..2dd35c0e532d246546d13e6e65863867644aa14d 100644 (file)
--- a/test/python/test_cli_replication.py
+++ b/test/python/test_cli_replication.py
@@ -53,8 +53,7 @@ def init_status(temp_db_conn, status_table):
 @pytest.fixture
 def index_mock(monkeypatch, tokenizer_mock, init_status):
     mock = MockParamCapture()
-    monkeypatch.setattr(nominatim.indexer.indexer.Indexer, 'index_boundaries', mock)
-    monkeypatch.setattr(nominatim.indexer.indexer.Indexer, 'index_by_rank', mock)
+    monkeypatch.setattr(nominatim.indexer.indexer.Indexer, 'index_full', mock)
 
     return mock
 
@@ -122,7 +121,7 @@ class TestCliReplication:
         with pytest.raises(IndexError):
             self.call_nominatim()
 
-        assert index_mock.called == 4
+        assert index_mock.called == 2
 
 
     def test_replication_update_continuous_no_change(self, monkeypatch, index_mock):
@@ -137,6 +136,6 @@ class TestCliReplication:
         with pytest.raises(IndexError):
             self.call_nominatim()
 
-        assert index_mock.called == 2
+        assert index_mock.called == 1
         assert sleep_mock.called == 1
         assert sleep_mock.last_args[0] == 60