X-Git-Url: https://git.openstreetmap.org./nominatim.git/blobdiff_plain/b9517c99ae6297c2ab908d7fa324efd2d1b2f43a..2cdbcac353805767df011edc494f8067f9409f63:/nominatim/clicmd/replication.py diff --git a/nominatim/clicmd/replication.py b/nominatim/clicmd/replication.py index 4852c8b1..7ad82c4f 100644 --- a/nominatim/clicmd/replication.py +++ b/nominatim/clicmd/replication.py @@ -6,9 +6,9 @@ import logging import socket import time -from ..db import status -from ..db.connection import connect -from ..errors import UsageError +from nominatim.db import status +from nominatim.db.connection import connect +from nominatim.errors import UsageError LOG = logging.getLogger() @@ -17,20 +17,22 @@ LOG = logging.getLogger() # Using non-top-level imports to make pyosmium optional for replication only. # pylint: disable=E0012,C0415 -def _osm2pgsql_options_from_args(args, default_cache, default_threads): - """ Set up the standard osm2pgsql from the command line arguments. - """ - return dict(osm2pgsql=args.osm2pgsql_path, - osm2pgsql_cache=args.osm2pgsql_cache or default_cache, - osm2pgsql_style=args.config.get_import_style_file(), - threads=args.threads or default_threads, - dsn=args.config.get_libpq_dsn(), - flatnode_file=args.config.FLATNODE_FILE) - - class UpdateReplication: """\ Update the database using an online replication service. + + An OSM replication service is an online service that provides regular + updates (OSM diff files) for the planet or update they provide. The OSMF + provides the primary replication service for the full planet at + https://planet.osm.org/replication/ but there are other providers of + extracts of OSM data who provide such a service as well. + + This sub-command allows to set up such a replication service and download + and import updates at regular intervals. You need to call '--init' once to + set up the process or whenever you change the replication configuration + parameters. Without any arguments, the sub-command will go into a loop and + continuously apply updates as they become available. Giving `--once` just + downloads and imports the next batch of updates. """ @staticmethod @@ -40,35 +42,36 @@ 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 applicable - together with --once""") + help=("Do not index the new data. Only usable " + "together with --once")) group.add_argument('--osm2pgsql-cache', metavar='SIZE', type=int, help='Size of cache to be used by osm2pgsql (in MB)') group = parser.add_argument_group('Download parameters') group.add_argument('--socket-timeout', dest='socket_timeout', type=int, default=60, - help='Set timeout for file downloads.') + help='Set timeout for file downloads') @staticmethod def _init_replication(args): from ..tools import replication, refresh LOG.warning("Initialising replication updates") - conn = connect(args.config.get_libpq_dsn()) - replication.init_replication(conn, base_url=args.config.REPLICATION_URL) - if args.update_functions: - LOG.warning("Create functions") - refresh.create_functions(conn, args.config, args.sqllib_dir, - True, False) - conn.close() + with connect(args.config.get_libpq_dsn()) as conn: + replication.init_replication(conn, base_url=args.config.REPLICATION_URL) + if args.update_functions: + LOG.warning("Create functions") + refresh.create_functions(conn, args.config, True, False) return 0 @@ -76,10 +79,8 @@ class UpdateReplication: def _check_for_updates(args): from ..tools import replication - conn = connect(args.config.get_libpq_dsn()) - ret = replication.check_for_updates(conn, base_url=args.config.REPLICATION_URL) - conn.close() - return ret + 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): @@ -94,68 +95,84 @@ 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 = _osm2pgsql_options_from_args(args, 2000, 1) + 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.") raise UsageError("Bad argument '--no-index'.") 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: - conn = connect(args.config.get_libpq_dsn()) - start = dt.datetime.now(dt.timezone.utc) - state = replication.update(conn, params) - if state is not replication.UpdateState.NO_CHANGES: - status.log_status(conn, start, 'import') - batchdate, _, _ = status.get_status(conn) - conn.close() + with connect(args.config.get_libpq_dsn()) as conn: + start = dt.datetime.now(dt.timezone.utc) + state = replication.update(conn, params) + if state is not replication.UpdateState.NO_CHANGES: + status.log_status(conn, start, 'import') + batchdate, _, _ = status.get_status(conn) + conn.commit() 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(), - args.threads or 1) - indexer.index_boundaries(0, 30) - indexer.index_by_rank(0, 30) - - conn = connect(args.config.get_libpq_dsn()) - status.set_indexed(conn, True) - status.log_status(conn, index_start, 'index') - conn.close() + indexer.index_full(analyse=False) + + with connect(args.config.get_libpq_dsn()) as conn: + status.set_indexed(conn, True) + status.log_status(conn, index_start, 'index') + conn.commit() 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: LOG.warning("No new changes. Sleeping for %d sec.", recheck_interval) time.sleep(recheck_interval) - return state.value - @staticmethod def run(args): @@ -167,4 +184,5 @@ class UpdateReplication: if args.check_for_updates: return UpdateReplication._check_for_updates(args) - return UpdateReplication._update(args) + UpdateReplication._update(args) + return 0