Merge pull request #11 from run-x/jd/updating

More updates

charts/opta/Chart.yaml

@@ -2,7 +2,7 @@ apiVersion: v2
 name: opta-agent
 description: The Opta Agent to monitor your environment via the opta ui.
 home: https://github.com/run-x/opta-agent
-version: 0.1.2
+version: 0.1.3
 appVersion: 0.1.0
 type: application
 kubeVersion: ">= 1.18.0-0"

charts/opta/README.md

@@ -1,10 +1,10 @@
 # Opta Agent
 
-[![Artifact Hub](https://img.shields.io/endpoint?url=https://artifacthub.io/badge/repository/opta-agent)](https://artifacthub.io/packages/search?repo=opta-agent) ![Version: 0.1.1](https://img.shields.io/badge/Version-0.1.1-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: 0.1.0](https://img.shields.io/badge/AppVersion-0.1.0-informational?style=flat-square)
+[![Artifact Hub](https://img.shields.io/endpoint?url=https://artifacthub.io/badge/repository/opta-agent)](https://artifacthub.io/packages/search?repo=opta-agent) ![Version: 0.1.3](https://img.shields.io/badge/Version-0.1.3-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: 0.1.0](https://img.shields.io/badge/AppVersion-0.1.0-informational?style=flat-square)
 
 ## Requirements
 
-Kubernetes: `>= 1.18.0`
+Kubernetes: `>= 1.18.0-0`
 
 ## Maintainers
 
@@ -20,6 +20,8 @@ Kubernetes: `>= 1.18.0`
 | optaAgent.containerResourceLimits.memory | string | `"256Mi"` |  |
 | optaAgent.containerResourceRequests.cpu | string | `"100m"` |  |
 | optaAgent.containerResourceRequests.memory | string | `"128Mi"` |  |
+| optaAgent.debug | bool | `false` |  |
 | optaAgent.image | string | `"runx1/opta-agent:latest"` |  |
 | optaAgent.namespace | string | `"opta-agent"` |  |
-| optaAgent.token | string | `"nil"` |  |
+| optaAgent.token | string | `"nil"` |  |
+| optaAgent.verbose | bool | `false` |  |

charts/opta/templates/cluster_role.yaml

@@ -41,4 +41,10 @@ rules:
       - list
       - get
       - watch
-      - patch
+      - patch
+  - apiGroups:
+      - ""
+    resources:
+      - events
+    verbs:
+      - create

charts/opta/templates/deployment.yaml

@@ -27,6 +27,14 @@ spec:
               protocol: TCP
               containerPort: 8080
           env:
+            {{- if .Values.optaAgent.verbose }}
+            - name: VERBOSE
+              value: "true"
+            {{- end }}
+            {{- if .Values.optaAgent.debug }}
+            - name: DEBUG
+              value: "true"
+            {{- end }}
             - name: OPTA_TOKEN
               valueFrom:
                 secretKeyRef:

charts/opta/values.yaml

@@ -1,5 +1,7 @@
 optaAgent:
   namespace: "opta-agent"
+  verbose: false
+  debug: false
   token: nil
   image: "runx1/opta-agent:latest"
   containerResourceRequests:

srv/handlers.py

@@ -37,6 +37,8 @@ async def get_service(environment_name, service_name):
             headers={"opta": jwt},
         ) as resp:
             json = await resp.json()
+            if len(json) == 0:
+                return None
             service = json[0]
             return service
 
@@ -131,10 +133,16 @@ async def update_opta_ui_pod_status(uid, status, labels, logger, **_):
     if not is_valid_opta_pod(labels):
         return
     try:
+        logger.info(f"Routine check on pod {uid}")
         environment_name = labels.get("opta.dev/environment-name")
         service_name = labels.get("opta.dev/layer-name")
 
         service = await get_service(environment_name, service_name)
+        if service is None:
+            raise Exception(
+                f"No service with name {service_name} found in this environment-- has opta apply been run on it after "
+                "adding the runx module?"
+            )
         service_id = service["id"]
         created_at = get_pod_created_time_from_status(status)
 
@@ -147,18 +155,24 @@ async def update_opta_ui_pod_status(uid, status, labels, logger, **_):
             updated_at=datetime.now().isoformat(),
         )
     except Exception:
-        logger.info(f"Failed to update pod {uid}")
+        logger.error(f"Failed to update pod {uid}:", exc_info=True)
 
 
 @kopf.on.delete("pods", retries=5)
 async def delete_opta_ui_pod(uid, logger, labels, status, **_):
     if not is_valid_opta_pod(labels):
         return
     try:
+        logger.info(f"Deletion detected on pod {uid}")
         environment_name = labels.get("opta.dev/environment-name")
         service_name = labels.get("opta.dev/layer-name")
 
         service = await get_service(environment_name, service_name)
+        if service is None:
+            raise Exception(
+                f"No service with name {service_name} found in this environment-- has opta apply been run on it after "
+                "adding the runx module?"
+            )
         service_id = service["id"]
         created_at = get_pod_created_time_from_status(status)
 
@@ -172,15 +186,21 @@ async def delete_opta_ui_pod(uid, logger, labels, status, **_):
             deleted_at=datetime.now().isoformat(),
         )
     except Exception:
-        logger.info(f"Failed to delete pod {uid}")
+        logger.error(f"Failed to delete pod {uid}:", exc_info=True)
 
 
 @kopf.on.update("deployment", field="spec.replicas")
-async def update_deployment_info(old, new, labels, logger, **_):
+async def update_deployment_info(uid, old, new, labels, logger, **_):
     try:
+        logger.info(f"Replica changed detected on deployment {uid}")
         environment_name = labels.get("opta.dev/environment-name")
         service_name = labels.get("opta.dev/layer-name")
         service = await get_service(environment_name, service_name)
+        if service is None:
+            raise Exception(
+                f"No service with name {service_name} found in this environment-- has opta apply been run on it after "
+                "adding the runx module?"
+            )
         service_id = service["id"]
 
         await post_event(
@@ -190,5 +210,5 @@ async def update_deployment_info(old, new, labels, logger, **_):
             timestamp=datetime.now().isoformat(),
             message=f"scaled from {old} pods to {new} pods",
         )
-    except Exception as e:
-        logger.error(e)
+    except Exception:
+        logger.error(f"Failed to send replica change event for deployment {uid}:", exc_info=True)

startup.sh

@@ -7,4 +7,14 @@ source $(pipenv --venv)/bin/activate
 # TODO should be separated into prestart and start scripts
 cd srv
 
-kopf run handlers.py --liveness=http://0.0.0.0:8080/healthz  --verbose
+if [[ -n ${VERBOSE} ]]; then
+	echo "Running verbose mode"
+	kopf run handlers.py --liveness=http://0.0.0.0:8080/healthz  --verbose --log-format=full --namespace=!kube-system,!linkerd
+fi
+
+if [[ -n ${DEBUG} ]]; then
+	echo "Running debug mode"
+	kopf run handlers.py --liveness=http://0.0.0.0:8080/healthz  --debug --log-format=full --namespace=!kube-system,!linkerd
+fi
+
+kopf run handlers.py --liveness=http://0.0.0.0:8080/healthz --log-format=full --namespace=!kube-system,!linkerd