Stats processing: don`t send data back to the main process, save it directly in the worker process

sitescripts/stats/bin/logprocessor.py

 # coding: utf-8
 
 # This file is part of the Adblock Plus web scripts,
 # Copyright (C) 2006-2013 Eyeo GmbH
 #
 # Adblock Plus is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License version 3 as
 # published by the Free Software Foundation.
 #
 # Adblock Plus is distributed in the hope that it will be useful,
 # but WITHOUT ANY WARRANTY; without even the implied warranty of
 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 # GNU General Public License for more details.
 #
 # You should have received a copy of the GNU General Public License
 # along with Adblock Plus.  If not, see <http://www.gnu.org/licenses/>.
 
 import argparse
 import codecs
 from collections import OrderedDict
 from datetime import datetime, timedelta
 import errno
+import functools
 import gzip
 import json
 import math
 import multiprocessing
 import numbers
 import os
 import re
 import pygeoip
 import socket
 import subprocess
@@ skipping 466 matching lines @@
       dir = os.path.dirname(path)
       try:
         os.makedirs(dir)
       except OSError, e:
         if e.errno != errno.EEXIST:
           raise
 
       with codecs.open(path, "wb", encoding="utf-8") as fileobj:
         json.dump(existing, fileobj, indent=2, sort_keys=True)
 
-def parse_source((mirror_name, server_type, log_file)):
+def parse_source(factor, lock, (mirror_name, server_type, log_file)):
   try:
     geo = pygeoip.GeoIP(get_config().get("stats", "geoip_db"), pygeoip.MEMORY_CACHE)
     geov6 = pygeoip.GeoIP(get_config().get("stats", "geoipv6_db"), pygeoip.MEMORY_CACHE)
 
     ignored = set()
     fileobj = open_stats_file(log_file)
     try:
       data = parse_fileobj(mirror_name, fileobj, geo, geov6, ignored)
     finally:
       fileobj.close()
-    return server_type, log_file, data, ignored
+
+    lock.acquire()
+    try:
+      save_stats(server_type, data, factor)
+    finally:
+      lock.release()
+    return log_file, ignored
   except:
     print >>sys.stderr, "Unable to process log file '%s'" % log_file
     traceback.print_exc()
     return None, None, None, None
 
 def parse_sources(sources, factor=1, verbose=False):
   pool = multiprocessing.Pool()
+  lock = multiprocessing.Manager().Lock()
+  callback = functools.partial(parse_source, factor, lock)
   try:
-    for server_type, log_file, data, ignored in pool.imap(parse_source, sources, chunksize=1):
-      if server_type == None:
-        continue
-
-      save_stats(server_type, data, factor)
-      if verbose:
+    for log_file, ignored in pool.imap_unordered(callback, sources, chunksize=1):
+      if verbose and ignored:
         print "Ignored files for %s" % log_file
         print "============================================================"
         print "\n".join(sorted(ignored))
   finally:
     pool.close()
 
 if __name__ == "__main__":
   setupStderr()
 
   parser = argparse.ArgumentParser(description="Processes log files and merges them into the stats database")
   parser.add_argument("--verbose", dest="verbose", action="store_const", const=True, default=False, help="Verbose mode, ignored requests will be listed")
   parser.add_argument("--revert", dest="factor", action="store_const", const=-1, default=1, help="Remove log data from the database")
   parser.add_argument("mirror_name", nargs="?", help="Name of the mirror server that the file belongs to")
   parser.add_argument("server_type", nargs="?", help="Server type like download, update or subscription")
   parser.add_argument("log_file", nargs="?", help="Log file path, can be a local file path, http:// or ssh:// URL")
   args = parser.parse_args()
 
   if args.mirror_name and args.server_type and args.log_file:
     sources = [(args.mirror_name, args.server_type, args.log_file)]
   else:
     sources = get_stats_files()
   parse_sources(sources, args.factor, args.verbose)