Allow uploading results to BigQuery

1 files changed, 162 insertions, 0 deletions

diff --git a/tools/profiling/microbenchmarks/bm2bq.py b/tools/profiling/microbenchmarks/bm2bq.py
new file mode 100755
index 0000000000..124dbdfec5
--- /dev/null
+++ b/tools/profiling/microbenchmarks/bm2bq.py
@@ -0,0 +1,162 @@
+#!/usr/bin/env python2.7
+#
+# Convert google-benchmark json output to something that can be uploaded to
+# BigQuery
+#
+#
+# Copyright 2017, Google Inc.
+# All rights reserved.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are
+# met:
+#
+#     * Redistributions of source code must retain the above copyright
+# notice, this list of conditions and the following disclaimer.
+#     * Redistributions in binary form must reproduce the above
+# copyright notice, this list of conditions and the following disclaimer
+# in the documentation and/or other materials provided with the
+# distribution.
+#     * Neither the name of Google Inc. nor the names of its
+# contributors may be used to endorse or promote products derived from
+# this software without specific prior written permission.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+import sys
+import json
+import csv
+import os
+
+columns = [
+  ('jenkins_build', 'integer'),
+  ('jenkins_job', 'string'),
+  ('date', 'timestamp'),
+  ('cpu_scaling_enabled', 'boolean'),
+  ('num_cpus', 'integer'),
+  ('mhz_per_cpu', 'integer'),
+  ('library_build_type', 'string'),
+  ('name', 'string'),
+  ('fixture', 'string'),
+  ('client_mutator', 'string'),
+  ('server_mutator', 'string'),
+  ('request_size', 'integer'),
+  ('response_size', 'integer'),
+  ('request_count', 'integer'),
+  ('iterations', 'integer'),
+  ('time_unit', 'string'),
+  ('real_time', 'integer'),
+  ('cpu_time', 'integer'),
+  ('bytes_per_second', 'float'),
+  ('allocs_per_iteration', 'float'),
+  ('locks_per_iteration', 'float'),
+  ('writes_per_iteration', 'float'),
+]
+
+if sys.argv[1] == '--schema':
+  print ',\n'.join('%s:%s' % (k, t.upper()) for k, t in columns)
+  sys.exit(0)
+
+with open(sys.argv[1]) as f:
+  js = json.loads(f.read())
+
+writer = csv.DictWriter(sys.stdout, [c for c,t in columns])
+
+bm_specs = {
+  'BM_UnaryPingPong': {
+    'tpl': ['fixture', 'client_mutator', 'server_mutator'],
+    'dyn': ['request_size', 'response_size'],
+  },
+  'BM_PumpStreamClientToServer': {
+    'tpl': ['fixture'],
+    'dyn': ['request_size'],
+  },
+  'BM_PumpStreamServerToClient': {
+    'tpl': ['fixture'],
+    'dyn': ['request_size'],
+  },
+  'BM_StreamingPingPong': {
+    'tpl': ['fixture', 'client_mutator', 'server_mutator'],
+    'dyn': ['request_size', 'request_count'],
+  },
+  'BM_StreamingPingPongMsgs': {
+    'tpl': ['fixture', 'client_mutator', 'server_mutator'],
+    'dyn': ['request_size'],
+  }
+}
+
+def numericalize(s):
+  if not s: return ''
+  if s[-1] == 'k':
+    return int(s[:-1]) * 1024
+  if s[-1] == 'M':
+    return int(s[:-1]) * 1024 * 1024
+  if 0 <= (ord(s[-1]) - ord('0')) <= 9:
+    return int(s)
+  assert 'not a number: %s' % s
+
+def parse_name(name):
+  rest = name
+  out = {}
+  tpl_args = []
+  dyn_args = []
+  if '<' in rest:
+    tpl_bit = rest[rest.find('<') + 1 : rest.rfind('>')]
+    arg = ''
+    nesting = 0
+    for c in tpl_bit:
+      if c == '<':
+        nesting += 1
+        arg += c
+      elif c == '>':
+        nesting -= 1
+        arg += c
+      elif c == ',':
+        if nesting == 0:
+          tpl_args.append(arg.strip())
+          arg = ''
+        else:
+          arg += c
+      else:
+        arg += c
+    tpl_args.append(arg.strip())
+    rest = rest[:rest.find('<')] + rest[rest.rfind('>') + 1:]
+  if '/' in rest:
+    s = rest.split('/')
+    rest = s[0]
+    dyn_args = s[1:]
+  name = rest
+  assert name in bm_specs
+  assert len(dyn_args) == len(bm_specs[name]['dyn'])
+  assert len(tpl_args) == len(bm_specs[name]['tpl'])
+  out['name'] = name
+  out.update(dict((k, numericalize(v)) for k, v in zip(bm_specs[name]['dyn'], dyn_args)))
+  out.update(dict(zip(bm_specs[name]['tpl'], tpl_args)))
+  return out
+
+for bm in js['benchmarks']:
+  context = js['context']
+  labels_list = [s.split(':') for s in bm.get('label', '').split(' ')]
+  for el in labels_list:
+    el[0] = el[0].replace('/iter', '_per_iteration')
+  labels = dict(labels_list)
+  row = {
+    'jenkins_build': os.environ.get('BUILD_NUMBER', ''),
+    'jenkins_job': os.environ.get('JOB_NAME', ''),
+  }
+  row.update(context)
+  row.update(bm)
+  row.update(parse_name(row['name']))
+  row.update(labels)
+  del row['label']
+  writer.writerow(row)