def FetchTimeseriesData(args):
def _MatchesAllFilters(test_path):
return all(f in test_path for f in args.filters)
api = dashboard_api.PerfDashboardCommunicator(args)
with tables.DbSession(args.database_file) as con:
# Get test_paths.
if args.benchmark is not None:
api = dashboard_api.PerfDashboardCommunicator(args)
test_paths = api.dashboard.ListTestPaths(args.benchmark,
sheriff=args.sheriff)
elif args.input_file is not None:
test_paths = list(_ReadTestPathsFromFile(args.input_file))
elif args.study is not None:
test_paths = list(args.study.IterTestPaths(api))
else:
raise ValueError('No source for test paths specified')
# Apply --filter's to test_paths.
if args.filters:
test_paths = filter(_MatchesAllFilters, test_paths)
num_found = len(test_paths)
print '%d test paths found!' % num_found
# Filter out test_paths already in cache.
if args.use_cache:
test_paths = list(_IterStaleTestPaths(con, test_paths))
num_skipped = num_found - len(test_paths)
if num_skipped:
print '(skipping %d test paths already in the database)' % num_skipped
# Use worker pool to fetch test path data.
total_seconds = worker_pool.Run(
'Fetching data of %d timeseries: ' % len(test_paths),
_FetchTimeseriesWorker, args, test_paths)
print '[%.1f test paths per second]' % (len(test_paths) / total_seconds)
if args.output_csv is not None:
print
print 'Post-processing data for study ...'
dfs = []
with tables.DbSession(args.database_file) as con:
for test_path in test_paths:
df = tables.timeseries.GetTimeSeries(con, test_path)
dfs.append(df)
df = studies.PostProcess(pandas.concat(dfs, ignore_index=True))
with utils.OpenWrite(args.output_csv) as f:
df.to_csv(f, index=False)
print 'Wrote timeseries data to:', args.output_csv
def testGetMostRecentPoint_empty(self):
test_path = ('ChromiumPerf/android-nexus5/loading.mobile'
'/timeToFirstInteractive/PageSet/Google')
with tables.DbSession(':memory:') as con:
point = tables.timeseries.GetMostRecentPoint(con, test_path)
self.assertIsNone(point)
def FetchAlertsData(args):
api = dashboard_api.PerfDashboardCommunicator(args)
with tables.DbSession(args.database_file) as con:
# Get alerts.
num_alerts = 0
bug_ids = set()
# TODO: This loop may be slow when fetching thousands of alerts, needs a
# better progress indicator.
for data in api.IterAlertData(args.benchmark, args.sheriff, args.days):
alerts = tables.alerts.DataFrameFromJson(data)
pandas_sqlite.InsertOrReplaceRecords(con, 'alerts', alerts)
num_alerts += len(alerts)
bug_ids.update(alerts['bug_id'].unique())
print '%d alerts found!' % num_alerts
# Get set of bugs associated with those alerts.
bug_ids.discard(0) # A bug_id of 0 means untriaged.
print '%d bugs found!' % len(bug_ids)
# Filter out bugs already in cache.
if args.use_cache:
known_bugs = set(b for b in bug_ids
if tables.bugs.Get(con, b) is not None)
if known_bugs:
print '(skipping %d bugs already in the database)' % len(
known_bugs)
bug_ids.difference_update(known_bugs)
# Use worker pool to fetch bug data.
total_seconds = worker_pool.Run(
'Fetching data of %d bugs: ' % len(bug_ids), _FetchBugsWorker, args,
bug_ids)
print '[%.1f bugs per second]' % (len(bug_ids) / total_seconds)
def testGetMostRecentPoint_success(self):
test_path = ('ChromiumPerf/android-nexus5/loading.mobile'
'/timeToFirstInteractive/PageSet/Google')
data = {
'test_path':
test_path,
'improvement_direction':
1,
'timeseries': [
[
'revision', 'value', 'timestamp', 'r_commit_pos',
'r_chromium'
],
[
547397, 2300.3, '2018-04-01T14:16:32.000', '547397',
'adb123'
],
[
547398, 2750.9, '2018-04-01T18:24:04.000', '547398',
'cde456'
],
[
547423, 2342.2, '2018-04-02T02:19:00.000', '547423',
'fab789'
],
]
}
timeseries = tables.timeseries.DataFrameFromJson(data)
with tables.DbSession(':memory:') as con:
pandas_sqlite.InsertOrReplaceRecords(con, 'timeseries', timeseries)
point = tables.timeseries.GetMostRecentPoint(con, test_path)
self.assertEqual(point['point_id'], 547423)
def testGetTimeSeries_withSummaryMetric(self):
test_path = tables.timeseries.Key(test_suite='loading.mobile',
measurement='timeToFirstInteractive',
bot='ChromiumPerf:android-nexus5',
test_case='')
data = {
'improvement_direction':
'down',
'units':
'ms',
'data': [
SamplePoint(547397, 2300.3),
SamplePoint(547398, 2750.9),
SamplePoint(547423, 2342.2),
]
}
timeseries_in = tables.timeseries.DataFrameFromJson(test_path, data)
with tables.DbSession(':memory:') as con:
pandas_sqlite.InsertOrReplaceRecords(con, 'timeseries',
timeseries_in)
timeseries_out = tables.timeseries.GetTimeSeries(con, test_path)
# Both DataFrame's should be equal, except the one we get out of the db
# does not have an index defined.
timeseries_in = timeseries_in.reset_index()
self.assertTrue(timeseries_in.equals(timeseries_out))
def testGetMostRecentPoint_empty(self):
test_path = tables.timeseries.Key(test_suite='loading.mobile',
measurement='timeToFirstInteractive',
bot='ChromiumPerf:android-nexus5',
test_case='Wikipedia')
with tables.DbSession(':memory:') as con:
point = tables.timeseries.GetMostRecentPoint(con, test_path)
self.assertIsNone(point)
def testGetTimeSeries_withSummaryMetric(self):
test_path = (
'ChromiumPerf/android-nexus5/loading.mobile/timeToFirstInteractive'
)
data = {
'test_path':
test_path,
'improvement_direction':
1,
'timeseries': [
[
'revision', 'value', 'timestamp', 'r_commit_pos',
'r_chromium'
],
[
547397, 2300.3, '2018-04-01T14:16:32.000', '547397',
'adb123'
],
[
547398, 2750.9, '2018-04-01T18:24:04.000', '547398',
'cde456'
],
[
547423, 2342.2, '2018-04-02T02:19:00.000', '547423',
'fab789'
],
]
}
timeseries_in = tables.timeseries.DataFrameFromJson(data)
with tables.DbSession(':memory:') as con:
pandas_sqlite.InsertOrReplaceRecords(con, 'timeseries',
timeseries_in)
timeseries_out = tables.timeseries.GetTimeSeries(con, test_path)
print timeseries_out
# Both DataFrame's should be equal, except the one we get out of the db
# does not have an index defined.
timeseries_in = timeseries_in.reset_index()
self.assertTrue(timeseries_in.equals(timeseries_out))
def testGetMostRecentPoint_success(self):
test_path = tables.timeseries.Key(test_suite='loading.mobile',
measurement='timeToFirstInteractive',
bot='ChromiumPerf:android-nexus5',
test_case='Wikipedia')
data = {
'improvement_direction':
'down',
'units':
'ms',
'data': [
SamplePoint(547397, 2300.3),
SamplePoint(547398, 2750.9),
SamplePoint(547423, 2342.2),
]
}
timeseries = tables.timeseries.DataFrameFromJson(test_path, data)
with tables.DbSession(':memory:') as con:
pandas_sqlite.InsertOrReplaceRecords(con, 'timeseries', timeseries)
point = tables.timeseries.GetMostRecentPoint(con, test_path)
self.assertEqual(point['point_id'], 547423)