Merge pull request #80 from jtaleric/add-ack

Adding method to ack

README.md

@@ -163,6 +163,21 @@ You can open the match requirement by using the ```--node-count``` option to fin
 
 **_NOTE:_**  The ```cmr```, ```--hunter-analyze``` and ```--anomaly-detection``` flags are mutually exclusive. They cannot be used together because they represent different algorithms designed for distinct use cases.
 
+#### Ack known bugs
+To ack known regressions, you must provide a yaml file with the uuid and metric which the regression was identified at. Example below
+
+```
+---
+ack :
+  - uuid: "af24e294-93da-4729-a9cc-14acf38454e1",
+    metric: "etcdCPU_avg"
+    reason: "started thread with etcd team"
+```
+
+ack'ing regressions will ensure Orion doesn't continue to notify users of the same issues.
+
+Engineers should add a `reason` that could link to a JIRA or Slack thread. Or the `reason` could be the changepoint % diff is too low to alert component teams. 
+
 ### Daemon mode
 The core purpose of Daemon mode is to operate Orion as a self-contained server, dedicated to handling incoming requests. By sending a POST request accompanied by a test name of predefined tests, users can trigger change point detection on the provided metadata and metrics. Following the processing, the response is formatted in JSON, providing a structured output for seamless integration and analysis. To trigger daemon mode just use the following commands
 

ack/example_ack.yaml

@@ -0,0 +1,14 @@
+---
+ack :
+  - uuid: "7f7337aa-cee3-4a36-b154-a7c48ed1fb75"
+    metric: "etcdCPU_avg"
+    reason: "Under our 10% target"
+  - uuid: "22e90f4e-1c79-4d9d-b2f6-b95a7072738c"
+    metric: "kubelet_avg"
+    reason: "Opened Dialog with node team"
+  - uuid: "22e90f4e-1c79-4d9d-b2f6-b95a7072738c"
+    metric: "ovnCPU_avg"
+    reason: "OCPBUGS111111"
+  - uuid: "93201652-b496-4594-b1ac-7eb9a32cd609"
+    metric: "apiserverCPU_avg"
+    reason: "opened discussion with api team"

orion.py

@@ -11,7 +11,7 @@
 import uvicorn
 from fmatch.logrus import SingletonLogger
 from pkg.runTest import run
-from pkg.config import load_config
+from pkg.config import load_config, load_ack
 import pkg.constants as cnsts
 
 warnings.filterwarnings("ignore", message="Unverified HTTPS request.*")
@@ -78,6 +78,7 @@ def cli(max_content_width=120):  # pylint: disable=unused-argument
 )
 @click.option("--filter", is_flag=True, help="Generate percent difference in comparison")
 @click.option("--config", default="config.yaml", help="Path to the configuration file")
+@click.option("--ack", default="", help="Optional ack YAML to ack known regressions")
 @click.option(
     "--save-data-path", default="data.csv", help="Path to save the output file"
 )
@@ -122,6 +123,8 @@ def cmd_analysis(**kwargs):
     level = logging.DEBUG if kwargs["debug"] else logging.INFO
     logger_instance = SingletonLogger(debug=level, name="Orion")
     logger_instance.info("🏹 Starting Orion in command-line mode")
+    if len(kwargs["ack"]) > 1 :
+       kwargs["ackMap"] = load_ack(kwargs["ack"])
     kwargs["configMap"] = load_config(kwargs["config"])
     output, regression_flag = run(**kwargs)
     if output is None:

pkg/algorithms/edivisive/edivisive.py

@@ -16,15 +16,23 @@ class EDivisive(Algorithm):
     def _analyze(self):
         self.dataframe["timestamp"] = pd.to_datetime(self.dataframe["timestamp"])
         self.dataframe["timestamp"] = self.dataframe["timestamp"].astype(int) // 10**9
-        series= self.setup_series()
+        series = self.setup_series()
         change_points_by_metric = series.analyze().change_points
 
-        # filter by direction
+
+        # Process if we have ack'ed regression
+        ackSet = set()
+        if len(self.options["ack"]) > 1 :
+            for ack in self.options["ackMap"]["ack"]:
+                pos = series.find_by_attribute("uuid",ack["uuid"])
+                ackSet.add(str(pos[0]) + "_" + ack["metric"])
+
+        # filter by direction and ack'ed issues
         for metric, changepoint_list in change_points_by_metric.items():
             for i in range(len(changepoint_list)-1, -1, -1):
-                if ((self.metrics_config[metric]["direction"] == 1 and changepoint_list[i].stats.mean_1 > changepoint_list[i].stats.mean_2) or
-                    (self.metrics_config[metric]["direction"] == -1 and changepoint_list[i].stats.mean_1 < changepoint_list[i].stats.mean_2) ):
+                if ((self.metrics_config[metric]["direction"] == 1 and changepoint_list[i].stats.mean_1 > changepoint_list[i].stats.mean_2) or (self.metrics_config[metric]["direction"] == -1 and changepoint_list[i].stats.mean_1 < changepoint_list[i].stats.mean_2) or (str(changepoint_list[i].index) + "_" + changepoint_list[i].metric in ackSet)):
                     del changepoint_list[i]
+
         if [val for li in change_points_by_metric.values() for val in li]:
             self.regression_flag=True
         return series, change_points_by_metric

pkg/config.py

@@ -54,6 +54,23 @@ def load_config(config: str, parameters: Dict= None) -> Dict[str, Any]:
     rendered_config = yaml.safe_load(rendered_config_yaml)
     return rendered_config
 
+def load_ack(ack: str) -> Dict[str,Any]:
+    logger_instance = SingletonLogger.getLogger("Orion")
+    try:
+        with open(ack, "r", encoding="utf-8") as template_file:
+            template_content = template_file.read()
+            logger_instance.debug("The %s file has successfully loaded", ack)
+    except FileNotFoundError as e:
+        logger_instance.error("Config file not found: %s", e)
+        sys.exit(1)
+    except Exception as e:  # pylint: disable=broad-exception-caught
+        logger_instance.error("An error occurred: %s", e)
+        sys.exit(1)
+
+    required_parameters = get_template_variables(template_content)
+
+    rendered_config = yaml.safe_load(template_content)
+    return rendered_config
 
 def get_template_variables(template_content: str) -> Set[str]:
     """Extracts all variables from the Jinja2 template content."""