add new user info to metrics Readme (apache#30989)

* add new user info to metrics Readme

* add grant call for kubeproxyuser_ro

.test-infra/metrics/README.md

@@ -115,6 +115,13 @@ Kubernetes deployment instructions are maintained in the wiki:
 * [Community metrics](https://cwiki.apache.org/confluence/display/BEAM/Community+Metrics)
 * [Test Results Monitoring](https://cwiki.apache.org/confluence/display/BEAM/Test+Results+Monitoring)
 
+### PSQL User
+Grafana running in metrics cluster is configured to use `kubeproxyuser_ro` user which does not come with any permissions. SELECT permission was manually granted on all tables in the  `beammetrics` psql DB. Any new tables or if some table is created/recreated by automation should also add grants for the user:
+
+```
+GRANT SELECT ON table_name TO kubeproxyuser_ro;
+```
+
 
 ### Note: Basic Auth is not supported on BEAM Clusters as of March 4th 2022
 

.test-infra/metrics/sync/github/github_runs_prefetcher/code/main.py

@@ -53,7 +53,9 @@
 
 
 class Workflow:
-    def __init__(self, id, name, filename, url, category=None, threshold=0.5, is_flaky=False):
+    def __init__(
+        self, id, name, filename, url, category=None, threshold=0.5, is_flaky=False
+    ):
         self.id = id
         self.name = name
         self.filename = filename
@@ -78,7 +80,9 @@ def clone_git_beam_repo(dest_path):
     if not os.path.exists(filesystem_path):
         os.mkdir(filesystem_path)
     os.chdir(filesystem_path)
-    os.system(f"git clone --filter=blob:none --sparse https://github.com/{GIT_ORG}/beam")
+    os.system(
+        f"git clone --filter=blob:none --sparse https://github.com/{GIT_ORG}/beam"
+    )
     os.chdir("beam")
     os.system("git sparse-checkout init --cone")
     os.system(f"git sparse-checkout  set {dest_path}")
@@ -165,7 +169,9 @@ def filter_workflow_runs(run, issue):
     response = await fetch(url, semaphore, params, headers)
     if len(response):
         print(f"Found a recently closed issue for the {workflow.name} workflow")
-        workflow_runs = [run for run in workflow_runs if filter_workflow_runs(run, response[0])]
+        workflow_runs = [
+            run for run in workflow_runs if filter_workflow_runs(run, response[0])
+        ]
 
     print(f"Number of workflow runs to consider: {len(workflow_runs)}")
     if len(workflow_runs) < 3:
@@ -176,7 +182,7 @@ def filter_workflow_runs(run, issue):
     if len(workflow_runs):
         failed_runs = list(filter(lambda r: r.status == "failure", workflow_runs))
         print(f"Number of failed workflow runs: {len(failed_runs)}")
-        success_rate -= (len(failed_runs) / len(workflow_runs))
+        success_rate -= len(failed_runs) / len(workflow_runs)
 
     print(f"Success rate: {success_rate}")
     return True if success_rate < workflow.threshold else False
@@ -287,7 +293,9 @@ def append_workflow_runs(workflow, runs):
                     datetime.strptime(run["run_started_at"], "%Y-%m-%dT%H:%M:%SZ"),
                 )
                 if workflow_runs.get(workflow_run.id):
-                    print(f"Duplicate run for {workflow.id} workflow: {workflow_run.id}")
+                    print(
+                        f"Duplicate run for {workflow.id} workflow: {workflow_run.id}"
+                    )
                 workflow_runs[workflow_run.id] = workflow_run
         workflow.runs.extend(workflow_runs.values())
 
@@ -397,7 +405,9 @@ def append_workflow_runs(workflow, runs):
                             "None",
                             "None",
                             workflow.id,
-                            datetime.strptime("0001-01-01T00:00:00Z", "%Y-%m-%dT%H:%M:%SZ"),
+                            datetime.strptime(
+                                "0001-01-01T00:00:00Z", "%Y-%m-%dT%H:%M:%SZ"
+                            ),
                         )
                     )
             if len(workflow.runs) >= int(GH_NUMBER_OF_WORKFLOW_RUNS_TO_FETCH):
@@ -408,7 +418,7 @@ def append_workflow_runs(workflow, runs):
 
     for workflow in list(workflows.values()):
         runs = sorted(workflow.runs, key=lambda r: r.started_at, reverse=True)
-        workflow.runs = runs[:int(GH_NUMBER_OF_WORKFLOW_RUNS_TO_FETCH)]
+        workflow.runs = runs[: int(GH_NUMBER_OF_WORKFLOW_RUNS_TO_FETCH)]
 
     return list(workflows.values())
 
@@ -444,6 +454,12 @@ def save_workflows(workflows):
         CONSTRAINT fk_workflow FOREIGN KEY(workflow_id) REFERENCES {workflows_table_name}(workflow_id))\n"""
     cursor.execute(create_workflows_table_query)
     cursor.execute(create_workflow_runs_table_query)
+    grant_workflows_query = f"""
+    GRANT SELECT ON github_workflows TO kubeproxyuser_ro;"""
+    grant_workflow_runs_query = f"""
+    GRANT SELECT ON github_workflow_runs TO kubeproxyuser_ro;"""
+    cursor.execute(grant_workflows_query)
+    cursor.execute(grant_workflow_runs_query)
     insert_workflows_query = f"""
     INSERT INTO {workflows_table_name} (workflow_id, name, filename, url,  dashboard_category, threshold, is_flaky, retrieved_at)
     VALUES %s"""
@@ -467,7 +483,9 @@ def save_workflows(workflows):
             )
         )
         for idx, run in enumerate(workflow.runs):
-            insert_workflow_runs.append((run.id, idx+1, run.status, run.url, run.workflow_id, run.started_at))
+            insert_workflow_runs.append(
+                (run.id, idx + 1, run.status, run.url, run.workflow_id, run.started_at)
+            )
     psycopg2.extras.execute_values(cursor, insert_workflows_query, insert_workflows)
     psycopg2.extras.execute_values(
         cursor, insert_workflow_runs_query, insert_workflow_runs