CT Perf recipe to run benchmarks on the top 1k sites using swarming

scripts/slave/recipes/perf/ct_top1k_rr_perf.py

Index: scripts/slave/recipes/perf/ct_top1k_rr_perf.py
diff --git a/scripts/slave/recipes/perf/ct_top1k_rr_perf.py b/scripts/slave/recipes/perf/ct_top1k_rr_perf.py
new file mode 100644
index 0000000000000000000000000000000000000000..cba3c7fa8ec9a823bc812b3390f5ae75e2d5f975
--- /dev/null
+++ b/scripts/slave/recipes/perf/ct_top1k_rr_perf.py
@@ -0,0 +1,109 @@
+# 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.
+
+
+DEPS = [
+  'archive',
+  'ct_swarming',
+  'file',
+  'properties',
+  'step',
+  'time',
+]
+
+
+CT_PAGE_TYPE = '1k'
+CT_BINARY = 'run_chromium_perf_swarming'
+CT_ISOLATE_TEMPLATE = 'ct_top1k.isolate.tmpl'
+
+# Number of slaves to shard CT runs to.
+# TODO(rmistry): Change the below to 100 when ready to run the full top 1k.
+CT_NUM_SLAVES = 2
+
+
+def _DownloadAndExtractBinary(api):
+  """Downloads the binary from the revision passed to the recipe."""
+  api.archive.download_and_unzip_build(
+      step_name='Download and Extract Binary',
+      target='Release',
+      build_url=None,  # This is a required parameter, but has no effect.
+      build_archive_url=api.properties['parent_build_archive_url'])
+
+
+def RunSteps(api):
+  # Figure out which benchmark to use.
+  buildername = api.properties['buildername']
+  if 'Repaint' in buildername:
+    benchmark = 'repaint'
+  elif 'RR' in buildername:
+    benchmark = 'rasterize_and_record_micro'
+  else:
+    raise Exception('Do not recognise the buildername %s.' % buildername)
+
+  # Checkout chromium and swarming.
+  api.ct_swarming.checkout_dependencies()
+
+  # Download the prebuilt chromium binary.
+  _DownloadAndExtractBinary(api)
+
+  # Download Cluster Telemetry binary.
+  api.ct_swarming.download_CT_binary(CT_BINARY)
+
+  # Record how long the step took in swarming tasks.
+  swarming_start_time = api.time.time()
+
+  for slave_num in range(1, CT_NUM_SLAVES + 1):
+    slave_dir = api.ct_swarming.downloads_dir.join('slave%s' % slave_num)
+
+    # Download page sets and archives.
+    api.ct_swarming.download_page_artifacts(CT_PAGE_TYPE, slave_num, slave_dir)

[M-A Ruel, 2015/11/12 17:33:41]

IMHO You shouldn't pass an arbitrary path, the path should be returned instead.

[rmistry, 2015/11/13 14:59:58]

Done. Not returning the path because the downloads_dir is already available.

+
+    # TODO(rmistry): Remove the entire below section after crrev.com/1410353007
+    #                is submitted.
+    api.file.copy(
+        'copy %s' % CT_ISOLATE_TEMPLATE,
+        '/repos/chromium/src/chrome/%s' % CT_ISOLATE_TEMPLATE,
+        api.ct_swarming.chromium_src_dir.join('chrome', CT_ISOLATE_TEMPLATE))
+    for f in ['run_ct_top1k.py', 'path_util.py']:
+      api.file.copy(
+          'copy %s' % f,
+          '/repos/chromium/src/content/test/ct/%s' % f,
+          api.ct_swarming.chromium_src_dir.join('content', 'test', 'ct', f))
+
+    # Create this slave's isolate file from the CT_ISOLATE_TEMPLATE.
+    isolate_dir = api.ct_swarming.chromium_src_dir.join('chrome')
+    isolate_template_path = isolate_dir.join(CT_ISOLATE_TEMPLATE)
+    generated_isolate_path = isolate_dir.join(
+        'slave%s.ct_top1k.isolate' % slave_num)
+    with open(str(generated_isolate_path), 'wb') as fout:
+      with open(str(isolate_template_path), 'rb') as fin:
+        for line in fin:
+          fout.write(line.replace('[[SLAVE_NUM]]', str(slave_num))
+                         .replace('[[MASTER]]', api.properties['mastername'])
+                         .replace('[[BUILDER]]', api.properties['buildername'])
+                         .replace('[[GIT_HASH]]',
+                                  api.properties['git_revision'])
+                         .replace('[[BENCHMARK]]', benchmark))
+
+    # Create the slave's isolated.gen.json file to use for batcharchiving.
+    api.ct_swarming.create_isolated_gen_json(
+        generated_isolate_path, isolate_dir, 'linux', slave_num)
+
+  # Batcharchive everything on the isolate server for efficiency.
+  api.ct_swarming.batcharchive(CT_NUM_SLAVES)
+  swarm_hashes = (
+      api.step.active_result.presentation.properties['swarm_hashes']).values()
+
+  # Trigger all swarming tasks.
+  api.ct_swarming.trigger_swarming_tasks(
+      swarm_hashes, task_name_prefix='ct-1k-task',
+      dimensions={'os': 'Ubuntu', 'gpu': '10de'})
+
+  # Now collect all tasks.
+  api.ct_swarming.collect_swarming_tasks()
+
+  api.ct_swarming.cleanup()
+
+  print ('Running isolating, triggering and collecting swarming tasks took a '
+         'total of %s seconds') % (api.time.time() - swarming_start_time)