-#! /usr/bin/env python
+#! /usr/bin/env python3
#-----------------------------------------------------------------------------
# nominatim - [description]
#-----------------------------------------------------------------------------
from psycopg2.extras import wait_select
import select
+from indexer.progress import ProgressLogger
+
log = logging.getLogger()
def make_connection(options, asynchronous=False):
- return psycopg2.connect(dbname=options.dbname, user=options.user,
- password=options.password, host=options.host,
- port=options.port, async_=asynchronous)
+ params = {'dbname' : options.dbname,
+ 'user' : options.user,
+ 'password' : options.password,
+ 'host' : options.host,
+ 'port' : options.port,
+ 'async' : asynchronous}
+
+ return psycopg2.connect(**params)
class RankRunner(object):
def name(self):
return "rank {}".format(self.rank)
- def sql_index_sectors(self):
- return """SELECT geometry_sector, count(*) FROM placex
+ def sql_count_objects(self):
+ return """SELECT count(*) FROM placex
WHERE rank_search = {} and indexed_status > 0
- GROUP BY geometry_sector
- ORDER BY geometry_sector""".format(self.rank)
+ """.format(self.rank)
- def sql_nosector_places(self):
+ def sql_get_objects(self):
return """SELECT place_id FROM placex
WHERE indexed_status > 0 and rank_search = {}
ORDER BY geometry_sector""".format(self.rank)
- def sql_sector_places(self):
- return """SELECT place_id FROM placex
- WHERE indexed_status > 0 and rank_search = {}
- and geometry_sector = %s""".format(self.rank)
-
def sql_index_place(self):
return "UPDATE placex SET indexed_status = 0 WHERE place_id = %s"
def name(self):
return "interpolation lines (location_property_osmline)"
- def sql_index_sectors(self):
- return """SELECT geometry_sector, count(*) FROM location_property_osmline
- WHERE indexed_status > 0
- GROUP BY geometry_sector
- ORDER BY geometry_sector"""
+ def sql_count_objects(self):
+ return """SELECT count(*) FROM location_property_osmline
+ WHERE indexed_status > 0"""
- def sql_nosector_places(self):
+ def sql_get_objects(self):
return """SELECT place_id FROM location_property_osmline
WHERE indexed_status > 0
ORDER BY geometry_sector"""
- def sql_sector_places(self):
- return """SELECT place_id FROM location_property_osmline
- WHERE indexed_status > 0 and geometry_sector = %s
- ORDER BY geometry_sector"""
-
def sql_index_place(self):
return """UPDATE location_property_osmline
SET indexed_status = 0 WHERE place_id = %s"""
class DBConnection(object):
- """ A signle non-blocking database connection.
+ """ A single non-blocking database connection.
"""
def __init__(self, options):
+ self.current_query = None
+ self.current_params = None
+
+ self.conn = None
+ self.connect()
+
+ def connect(self):
+ if self.conn is not None:
+ self.cursor.close()
+ self.conn.close()
+
self.conn = make_connection(options, asynchronous=True)
self.wait()
self.cursor = self.conn.cursor()
-
- self.current_query = None
- self.current_params = None
+ # Disable JIT and parallel workers as they are known to cause problems.
+ # Update pg_settings instead of using SET because it does not yield
+ # errors on older versions of Postgres where the settings are not
+ # implemented.
+ self.perform(
+ """ UPDATE pg_settings SET setting = -1 WHERE name = 'jit_above_cost';
+ UPDATE pg_settings SET setting = 0
+ WHERE name = 'max_parallel_workers_per_gather';""")
+ self.wait()
def wait(self):
""" Block until any pending operation is done.
"""
- wait_select(self.conn)
- self.current_query = None
+ while True:
+ try:
+ wait_select(self.conn)
+ self.current_query = None
+ return
+ except psycopg2.extensions.TransactionRollbackError as e:
+ if e.pgcode == '40P01':
+ log.info("Deadlock detected (params = {}), retry."
+ .format(self.current_params))
+ self.cursor.execute(self.current_query, self.current_params)
+ else:
+ raise
+ except psycopg2.errors.DeadlockDetected:
+ self.cursor.execute(self.current_query, self.current_params)
def perform(self, sql, args=None):
""" Send SQL query to the server. Returns immediately without
return True
except psycopg2.extensions.TransactionRollbackError as e:
if e.pgcode == '40P01':
- log.debug("Deadlock detected, retry.")
+ log.info("Deadlock detected (params = {}), retry.".format(self.current_params))
self.cursor.execute(self.current_query, self.current_params)
else:
raise
+ except psycopg2.errors.DeadlockDetected:
+ self.cursor.execute(self.current_query, self.current_params)
return False
if self.maxrank == 30:
self.index(InterpolationRunner())
- self.index(RankRunner(30))
+
+ self.index(RankRunner(self.maxrank))
def index(self, obj):
""" Index a single rank or table. `obj` describes the SQL to use
"""
log.warning("Starting {}".format(obj.name()))
- cur = self.conn.cursor(name='main')
- cur.execute(obj.sql_index_sectors())
+ cur = self.conn.cursor()
+ cur.execute(obj.sql_count_objects())
- total_tuples = 0
- for r in cur:
- total_tuples += r[1]
- log.debug("Total number of rows; {}".format(total_tuples))
+ total_tuples = cur.fetchone()[0]
+ log.debug("Total number of rows: {}".format(total_tuples))
- cur.scroll(0, mode='absolute')
+ cur.close()
next_thread = self.find_free_thread()
- done_tuples = 0
- rank_start_time = datetime.now()
-
- sector_sql = obj.sql_sector_places()
- index_sql = obj.sql_index_place()
- min_grouped_tuples = total_tuples - len(self.threads) * 1000
-
- next_info = 100 if log.isEnabledFor(logging.INFO) else total_tuples + 1
+ progress = ProgressLogger(obj.name(), total_tuples)
- for r in cur:
- sector = r[0]
+ cur = self.conn.cursor(name='places')
+ cur.execute(obj.sql_get_objects())
- # Should we do the remaining ones together?
- do_all = done_tuples > min_grouped_tuples
+ for place in cur:
+ place_id = place[0]
+ log.debug("Processing place {}".format(place_id))
+ thread = next(next_thread)
- pcur = self.conn.cursor(name='places')
-
- if do_all:
- pcur.execute(obj.sql_nosector_places())
- else:
- pcur.execute(sector_sql, (sector, ))
-
- for place in pcur:
- place_id = place[0]
- log.debug("Processing place {}".format(place_id))
- thread = next(next_thread)
-
- thread.perform(index_sql, (place_id,))
- done_tuples += 1
-
- if done_tuples >= next_info:
- now = datetime.now()
- done_time = (now - rank_start_time).total_seconds()
- tuples_per_sec = done_tuples / done_time
- log.info("Done {} in {} @ {:.3f} per second - {} ETA (seconds): {:.2f}"
- .format(done_tuples, int(done_time),
- tuples_per_sec, obj.name(),
- (total_tuples - done_tuples)/tuples_per_sec))
- next_info += int(tuples_per_sec)
-
- pcur.close()
-
- if do_all:
- break
+ thread.perform(obj.sql_index_place(), (place_id,))
+ progress.add()
cur.close()
for t in self.threads:
t.wait()
- rank_end_time = datetime.now()
- diff_seconds = (rank_end_time-rank_start_time).total_seconds()
-
- log.warning("Done {}/{} in {} @ {:.3f} per second - FINISHED {}\n".format(
- done_tuples, total_tuples, int(diff_seconds),
- done_tuples/diff_seconds, obj.name()))
+ progress.done()
def find_free_thread(self):
""" Generator that returns the next connection that is free for
sending a query.
"""
ready = self.threads
+ command_stat = 0
while True:
for thread in ready:
if thread.is_done():
+ command_stat += 1
yield thread
- ready, _, _ = select.select(self.threads, [], [])
+ # refresh the connections occasionaly to avoid potential
+ # memory leaks in Postgresql.
+ if command_stat > 100000:
+ for t in self.threads:
+ while not t.is_done():
+ t.wait()
+ t.connect()
+ command_stat = 0
+ ready = self.threads
+ else:
+ ready, _, _ = select.select(self.threads, [], [])
- assert(False, "Unreachable code")
+ assert False, "Unreachable code"
def nominatim_arg_parser():
projects / nominatim.git / blobdiff