[Findit] Adding suspected CL to master flake analysis in preparation for try jobs

appengine/findit/model/flake/master_flake_analysis.py

 # Copyright 2016 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.
 
 import base64
+import logging
 
 from google.appengine.ext import ndb
 
+from gae_libs.gitiles.cached_gitiles_repository import CachedGitilesRepository
 from gae_libs.model.versioned_model import VersionedModel
 from model import result_status
 from model import triage_status
 from model.base_analysis import BaseAnalysis
 from model.base_build_model import BaseBuildModel
 from model.base_triaged_model import TriagedModel
+from model.flake.flake_culprit import FlakeCulprit
 from model.flake.flake_swarming_task import FlakeSwarmingTaskData
 
 
 class DataPoint(ndb.Model):
   build_number = ndb.IntegerProperty(indexed=False)
   pass_rate = ndb.FloatProperty(indexed=False)
   task_id = ndb.StringProperty(indexed=False)
   commit_position = ndb.IntegerProperty(indexed=False)
   git_hash = ndb.StringProperty(indexed=False)
   previous_build_commit_position = ndb.IntegerProperty(indexed=False)
@@ skipping 63 matching lines @@
   def UpdateTriageResult(self, triage_result, suspect_info, user_name,
                          version_number=None):
     super(MasterFlakeAnalysis, self).UpdateTriageResult(
         triage_result, suspect_info, user_name, version_number=version_number)
 
     if triage_result == triage_status.TRIAGED_CORRECT:
       self.result_status = result_status.FOUND_CORRECT
     else:
       self.result_status = result_status.FOUND_INCORRECT
 
+  def GetSuspectedFlakeDataPoint(self):

[chanli, 2017/01/07 02:56:28]

This function needs to be updated after our discussion at Friday afternoon,
right? since we will have only one group of data_points?

[lijeffrey, 2017/01/09 20:53:31]

Yes, per discussion we will have 1 group of data points with both build_number
and commit_position available depending on what was used to derive that point.
Renaming this function to GetDataPointOfSuspectedBuild. The returned data point
from this function is used to get blame_list to run try jobs to further identify
the culprit.

For the first version, I'm thinking we keep build_number since there are 2
stages of analysis (swarming tasks then try jobs). Since both can be time
consuming we should display the suspected build as soon as it's available even
as try jobs are still running

+    """Gets the corresponding data point to the suspected flake build."""
+    if self.suspected_flake_build_number is not None:
+      for data_point in self.data_points:
+        if data_point.build_number == self.suspected_flake_build_number:
+          return data_point
+
+    return None
+
   def Reset(self):
     super(MasterFlakeAnalysis, self).Reset()
     self.original_master_name = None
     self.original_builder_name = None
     self.original_build_number = None
     self.original_step_name = None
     self.original_test_name = None
     self.bug_id = None
     self.swarming_rerun_results = []
     self.error = None
     self.correct_regression_range = None
     self.correct_culprit = None
     self.algorithm_parameters = None
     self.suspected_flake_build_number = None
+    self.culprit = None
+    self.try_job_status = None
     self.data_points = []
     self.result_status = None
 
   # The original build/step/test in which a flake actually occurred.
   # A CQ trybot step has to be mapped to a Waterfall buildbot step.
   # A gtest suite.PRE_PRE_test has to be normalized to suite.test.
   original_master_name = ndb.StringProperty(indexed=True)
   original_builder_name = ndb.StringProperty(indexed=True)
   original_build_number = ndb.IntegerProperty(indexed=True)
   original_step_name = ndb.StringProperty(indexed=True)
@@ skipping 29 matching lines @@
   #     'max_build_numbers_to_look_back': 500,
   #     'max_flake_in_a_row': 4,
   #     'max_stable_in_a_row': 4,
   #     'upper_flake_threshold': 0.98
   # }
   algorithm_parameters = ndb.JsonProperty(indexed=False)
 
   # The suspected build number to have introduced the flakiness.
   suspected_flake_build_number = ndb.IntegerProperty()
 
+  # The culprit CL associated with the try job results, if any.
+  culprit = ndb.LocalStructuredProperty(FlakeCulprit)
+
+  # The status of the try job, if any. None if no suspected flake build number

[chanli, 2017/01/07 02:56:28]

Flake revision instead of flake build number?

[lijeffrey, 2017/01/09 20:53:31]

Renamed "None if try jobs have not been triggered" to be more specific.

+  # yet.
+  try_job_status = ndb.IntegerProperty(indexed=False)
+
   # The data points used to plot the flakiness graph build over build.
   data_points = ndb.LocalStructuredProperty(
       DataPoint, repeated=True, compressed=True)
 
   # Whether the analysis was triggered by a manual request through check flake,
   # Findit's automatic analysis upon detection, or Findit API.
   triggering_source = ndb.IntegerProperty(default=None, indexed=True)
 
   # Who triggered the analysis. Used for differentiating between manual and
   # automatic runs, and determining the most active users to gather feedback.
   triggering_user_email = ndb.StringProperty(default=None, indexed=False)
 
   # Overall conclusion of analysis result for the flake. Found untriaged, Found
   # Correct, etc. used to filter what is displayed on the check flake dashboard.
   result_status = ndb.IntegerProperty(indexed=True)