X-Git-Url: https://git.openstreetmap.org./nominatim.git/blobdiff_plain/c86cfefc4813d275073fb5f2b196ddfcc7f26aef..66832cf0a51777cf9fb1c74459de9f46160ea15e:/nominatim/clicmd/replication.py diff --git a/nominatim/clicmd/replication.py b/nominatim/clicmd/replication.py index a22cef47..2d6396a1 100644 --- a/nominatim/clicmd/replication.py +++ b/nominatim/clicmd/replication.py @@ -1,6 +1,14 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# This file is part of Nominatim. (https://nominatim.org) +# +# Copyright (C) 2022 by the Nominatim developer community. +# For a full list of authors see the git log. """ Implementation of the 'replication' sub-command. """ +from typing import Optional +import argparse import datetime as dt import logging import socket @@ -9,13 +17,14 @@ import time from nominatim.db import status from nominatim.db.connection import connect from nominatim.errors import UsageError +from nominatim.clicmd.args import NominatimArgs LOG = logging.getLogger() # Do not repeat documentation of subcommand classes. # pylint: disable=C0111 # Using non-top-level imports to make pyosmium optional for replication only. -# pylint: disable=E0012,C0415 +# pylint: disable=C0415 class UpdateReplication: """\ @@ -35,21 +44,23 @@ class UpdateReplication: downloads and imports the next batch of updates. """ - @staticmethod - def add_args(parser): + def add_args(self, parser: argparse.ArgumentParser) -> None: group = parser.add_argument_group('Arguments for initialisation') group.add_argument('--init', action='store_true', 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")) @@ -59,8 +70,8 @@ class UpdateReplication: group.add_argument('--socket-timeout', dest='socket_timeout', type=int, default=60, help='Set timeout for file downloads') - @staticmethod - def _init_replication(args): + + def _init_replication(self, args: NominatimArgs) -> int: from ..tools import replication, refresh LOG.warning("Initialising replication updates") @@ -72,48 +83,59 @@ class UpdateReplication: return 0 - @staticmethod - def _check_for_updates(args): + def _check_for_updates(self, args: NominatimArgs) -> int: from ..tools import replication with connect(args.config.get_libpq_dsn()) as conn: return replication.check_for_updates(conn, base_url=args.config.REPLICATION_URL) - @staticmethod - def _report_update(batchdate, start_import, start_index): - def round_time(delta): + + def _report_update(self, batchdate: dt.datetime, + start_import: dt.datetime, + start_index: Optional[dt.datetime]) -> None: + def round_time(delta: dt.timedelta) -> dt.timedelta: return dt.timedelta(seconds=int(delta.total_seconds())) end = dt.datetime.now(dt.timezone.utc) LOG.warning("Update completed. Import: %s. %sTotal: %s. Remaining backlog: %s.", round_time((start_index or end) - start_import), - "Indexing: {} ".format(round_time(end - start_index)) - if start_index else '', + f"Indexing: {round_time(end - start_index)} " if start_index else '', round_time(end - start_import), round_time(end - batchdate)) - @staticmethod - def _update(args): + + def _compute_update_interval(self, args: NominatimArgs) -> int: + 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 + + + def _update(self, args: NominatimArgs) -> None: + # pylint: disable=too-many-locals from ..tools import replication from ..indexer.indexer import Indexer from ..tokenizer import factory as tokenizer_factory + update_interval = self._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.") @@ -121,6 +143,7 @@ class UpdateReplication: recheck_interval = args.config.get_int('REPLICATION_RECHECK_INTERVAL') tokenizer = tokenizer_factory.get_tokenizer_for_db(args.config) + indexer = Indexer(args.config.get_libpq_dsn(), tokenizer, args.threads or 1) while True: with connect(args.config.get_libpq_dsn()) as conn: @@ -133,10 +156,7 @@ class UpdateReplication: if state is not replication.UpdateState.NO_CHANGES and args.do_index: 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 +165,16 @@ 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) + assert batchdate is not None + self._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: @@ -156,15 +182,14 @@ class UpdateReplication: time.sleep(recheck_interval) - @staticmethod - def run(args): + def run(self, args: NominatimArgs) -> int: socket.setdefaulttimeout(args.socket_timeout) if args.init: - return UpdateReplication._init_replication(args) + return self._init_replication(args) if args.check_for_updates: - return UpdateReplication._check_for_updates(args) + return self._check_for_updates(args) - UpdateReplication._update(args) + self._update(args) return 0