[CT] Update worker scripts to use new benchmarks and delete old benchmarks

ct/py/create_page_set.py

 #!/usr/bin/env python
 # Copyright (c) 2013 The Chromium Authors. All rights reserved.
 # Use of this source code is governed by a BSD-style license that can be
 # found in the LICENSE file.
 
 """Creates a Python telemetry page_set from the specified webpages CSV.
 
 This module does the following steps:
 * Downloads a ZIP from http://s3.amazonaws.com/alexa-static/top-1m.csv.zip
 * Unpacks it and reads its contents in memory.
 * Writes out multiple Python page sets from the CSV file for the specified
   number of webpages.
 
 Sample Usage:
   python create_page_set.py -s 1 -e 10000
 
 Running the above command will create 10000 different page sets.
 """
 
 __author__ = 'Ravi Mistry'
 
+import json
 import optparse
 import os
 import urllib
 import zipfile
 
 from StringIO import StringIO
 
 
 TOP1M_CSV_FILE_NAME = 'top-1m.csv'
 TOP1M_CSV_ZIP_LOCATION = (
@@ skipping 66 matching lines @@
       qualified_website = website
     else:
       qualified_website = 'http://www.%s' % website
     websites.append(qualified_website)
 
   archive_data_file = os.path.join(
       '/', 'b', 'storage', 'webpage_archives',
       options.pagesets_type,
       'alexa%s-%s.json' % (options.start_number, options.end_number))
 
-  page_set_content = """
-# Copyright 2015 The Chromium Authors. All rights reserved.
-# Use of this source code is governed by a BSD-style license that can be
-# found in the LICENSE file.
-# pylint: disable=W0401,W0614
-
-from telemetry import story
-from telemetry.page import page as page_module
-from telemetry.page import shared_page_state
-from page_sets import repaint_helpers
-
-
-class TypicalAlexaPage(page_module.Page):
-
-  def __init__(self, url, page_set):
-    super(TypicalAlexaPage, self).__init__(
-        url=url,
-        page_set=page_set,
-        shared_page_state_class=shared_page_state.Shared%(user_agent)sPageState)
-    self.archive_data_file = '%(archive_data_file)s'
-
-  def RunNavigateSteps(self, action_runner):
-    action_runner.Navigate(self.url)
-    action_runner.Wait(2)
-
-  def RunPageInteractions(self, action_runner):
-    repaint_helpers.Repaint(action_runner)
-
-
-class Alexa%(start)s_%(end)sPageSet(story.StorySet):
-
-  def __init__(self):
-    super(Alexa%(start)s_%(end)sPageSet, self).__init__(
-      archive_data_file='%(archive_data_file)s')
-
-    urls_list = %(urls_list)s
-
-    for url in urls_list:
-      self.AddStory(TypicalAlexaPage(url, self))
-""" % {
-      "user_agent": options.useragent_type.capitalize(),
-      "archive_data_file": archive_data_file,
-      "start": options.start_number,
-      "end": options.end_number,
-      "urls_list": str(websites),
+  page_set_content = {
+    'user_agent': options.useragent_type,
+    'archive_data_file': archive_data_file,
+    'urls_list': ','.join(websites),
   }
 
   # Output the pageset to a file.
   with open(os.path.join(options.pagesets_output_dir, 'alexa%s_%s.py' % (
                 options.start_number, options.end_number)),
             'w') as outfile:
-    outfile.write(page_set_content)
-
+    json.dump(page_set_content, outfile)

[dogben, 2015/10/14 18:25:50]

Any potential issues with changing the format of the pageset files? The only
thing I can think of is that we'll need to recreate pagesets before any other
tasks can run.

[rmistry, 2015/10/15 12:23:21]

Right, all pagesets will need to be recreated and then tested through all tasks
using Dummy1k.