feat: cloud native observability (#15)

* fix: update Traefik to v3 to use OpenTelemetry * fix: changed apiversion for traefik * fix: added ingress for dapr dashboard and adjusted prometheus-values * fix: using new yaml for jaeger * fix: rename files * fix: removed unintended loop due to build in retry in golang * fix: added prometheus rules and error generation script * fix: removed unncessary lines of code * fix: added chaos engineering files
infralovers · Aug 8, 2024 · d730cd2 · d730cd2
1 parent d19b709
commit d730cd2
Show file tree

Hide file tree

Showing 32 changed files with 667 additions and 95 deletions.
diff --git a/dapr-distributed-calendar/chaos-engineering/burn-cpu.yaml b/dapr-distributed-calendar/chaos-engineering/burn-cpu.yaml
@@ -0,0 +1,17 @@
+apiVersion: chaos-mesh.org/v1alpha1
+kind: StressChaos
+metadata:
+  namespace: 12-factor-app
+  name: burn-cpu-100
+spec:
+  selector:
+    namespaces:
+      - 12-factor-app
+    labelSelectors:
+      app.kubernetes.io/instance: 12-factor-app
+  mode: all
+  stressors:
+    cpu:
+      workers: 1
+      load: 100
+  duration: 30s
diff --git a/dapr-distributed-calendar/chaos-engineering/chaos-on-the-rise.yaml b/dapr-distributed-calendar/chaos-engineering/chaos-on-the-rise.yaml
@@ -0,0 +1,39 @@
+apiVersion: chaos-mesh.org/v1alpha1
+kind: Workflow
+metadata:
+  name: chaos-on-the-rise
+  namespace: 12-factor-app
+spec:
+  entry: entry
+  templates:
+    - name: entry
+      templateType: Serial
+      deadline: 2m
+      children:
+        - stress-test
+        - pod-killer
+    - name: stress-test
+      templateType: StressChaos
+      deadline: 10s
+      stressChaos:
+        selector:
+          namespaces:
+            - 12-factor-app
+          labelSelectors:
+            app: controller
+        mode: all
+        stressors:
+          cpu:
+            workers: 1
+            load: 100
+    - name: pod-killer
+      templateType: PodChaos
+      deadline: 60s
+      podChaos:
+        selector:
+          namespaces:
+            - 12-factor-app
+          labelSelectors:
+            app: controller
+        mode: all
+        action: pod-kill
diff --git a/dapr-distributed-calendar/chaos-engineering/ingress.yaml b/dapr-distributed-calendar/chaos-engineering/ingress.yaml
@@ -0,0 +1,14 @@
+apiVersion: traefik.io/v1alpha1
+kind: IngressRoute
+metadata:
+  name: chaos-ingress
+  namespace: chaos-testing
+spec:
+  entryPoints:
+    - web
+  routes:
+    - match: Host(`chaos.<ENV-NAME>-<ENV-USER-ID>-01.<ENV-ANIMAL>.<ENV-DOMAIN>`) && PathPrefix(`/`)
+      kind: Rule
+      services:
+        - name: chaos-dashboard
+          port: 2333
diff --git a/dapr-distributed-calendar/chaos-engineering/network-bandwith.yaml b/dapr-distributed-calendar/chaos-engineering/network-bandwith.yaml
@@ -0,0 +1,20 @@
+apiVersion: chaos-mesh.org/v1alpha1
+kind: NetworkChaos
+metadata:
+  name: network-bandwidth-100kbps
+  namespace: 12-factor-app
+spec:
+  action: bandwidth
+  mode: all
+  selector:
+    namespaces:
+      - 12-factor-app
+    labelSelectors:
+      app.kubernetes.io/instance: 12-factor-app
+  bandwidth:
+    rate: 100kbps
+    limit: 100
+    buffer: 10000
+    peakrate: 1000000
+    minburst: 1000000
+  duration: "10s"
diff --git a/dapr-distributed-calendar/chaos-engineering/network-corrupt.yaml b/dapr-distributed-calendar/chaos-engineering/network-corrupt.yaml
@@ -0,0 +1,17 @@
+apiVersion: chaos-mesh.org/v1alpha1
+kind: NetworkChaos
+metadata:
+  name: network-corrupt-example
+  namespace: 12-factor-app
+spec:
+  action: corrupt
+  mode: all
+  selector:
+    namespaces:
+      - 12-factor-app
+    labelSelectors:
+      app.kubernetes.io/instance: 12-factor-app
+  corrupt:
+    corrupt: "40"
+    correlation: "25"
+  duration: "10s"
diff --git a/dapr-distributed-calendar/chaos-engineering/pod-failure.yaml b/dapr-distributed-calendar/chaos-engineering/pod-failure.yaml
@@ -0,0 +1,14 @@
+apiVersion: chaos-mesh.org/v1alpha1
+kind: PodChaos
+metadata:
+  namespace: 12-factor-app
+  name: pod-failure-example
+spec:
+  selector:
+    namespaces:
+      - 12-factor-app # the namespace of the system under test (SUT) you've deployed
+    labelSelectors:
+      app.kubernetes.io/instance: 12-factor-app # the label of the pod for chaos injection
+  mode: all # the mode to run chaos action; supported modes are one/all/fixed/fixed-percent/random-max-percent
+  action: pod-failure # the specific chaos action to inject; supported actions: pod-kill/pod-failure/container-kill
+  duration: 60s # duration for the injected chaos experiment
diff --git a/dapr-distributed-calendar/chaos-engineering/schedule-chaos.yaml b/dapr-distributed-calendar/chaos-engineering/schedule-chaos.yaml
@@ -0,0 +1,21 @@
+apiVersion: chaos-mesh.org/v1alpha1
+kind: Schedule
+metadata:
+  namespace: 12-factor-app
+  name: scheduled-pod-failure
+spec:
+  schedule: 5 * * * *
+  startingDeadlineSeconds: null
+  concurrencyPolicy: Forbid
+  historyLimit: 2
+  type: PodChaos
+  podChaos:
+    selector:
+      namespaces:
+        - 12-factor-app
+      labelSelectors:
+        app: controller
+    mode: one
+    action: pod-failure
+    duration: 1m
+    gracePeriod: 0
diff --git a/dapr-distributed-calendar/error.sh b/dapr-distributed-calendar/error.sh
@@ -0,0 +1,147 @@
+#!/bin/bash
+
+ENDPOINT="${ENDPOINT:-localhost}"
+PORT="${PORT:-3000}"
+
+echo Endpoint: $ENDPOINT
+echo Port: $PORT
+
+# Update event 1
+echo 'Update event 1'
+curl --location --request PUT 'http://'$ENDPOINT':'$PORT'/updateevent/1' \
+--header 'Content-Type: application/json' \
+--data '{
+    "data": {
+        "name": "Updated Event",
+        "date": "TBD"
+    }
+}' | jq
+
+# Update event 1
+echo 'Update event 1'
+curl --location --request PUT 'http://'$ENDPOINT':'$PORT'/updateevent/1' \
+--header 'Content-Type: application/json' \
+--data '{
+    "data": {
+        "name": "Updated Event",
+        "date": "TBD"
+    }
+}' | jq
+
+# Update event 1
+echo 'Update event 1'
+curl --location --request PUT 'http://'$ENDPOINT':'$PORT'/updateevent/1' \
+--header 'Content-Type: application/json' \
+--data '{
+    "data": {
+        "name": "Updated Event",
+        "date": "TBD"
+    }
+}' | jq
+
+# Update event 1
+echo 'Update event 1'
+curl --location --request PUT 'http://'$ENDPOINT':'$PORT'/updateevent/1' \
+--header 'Content-Type: application/json' \
+--data '{
+    "data": {
+        "name": "Updated Event",
+        "date": "TBD"
+    }
+}' | jq
+
+# Get event 1 (should fail)
+echo 'Get event 1 (should fail)'
+curl --location 'http://'$ENDPOINT':'$PORT'/event/1' | jq
+
+# Get event 1 (should fail)
+echo 'Get event 1 (should fail)'
+curl --location 'http://'$ENDPOINT':'$PORT'/event/1' | jq
+
+# Get event 1 (should fail)
+echo 'Get event 1 (should fail)'
+curl --location 'http://'$ENDPOINT':'$PORT'/event/1' | jq
+
+# Get event 1 (should fail)
+echo 'Get event 1 (should fail)'
+curl --location 'http://'$ENDPOINT':'$PORT'/event/1' | jq
+
+# Create event 1
+echo 'Create event 1'
+curl --location 'http://'$ENDPOINT':'$PORT'/newevent' \
+--header 'Content-Type: application/json' \
+--data '{
+    "data": {
+        "name": "Uninstall Event",
+        "date": "TBD",
+        "id": "1"
+    }
+}' |jq
+
+# Create event 1 again (should fail)
+echo 'Create event 1 again (should fail)'
+curl --location 'http://'$ENDPOINT':'$PORT'/newevent' \
+--header 'Content-Type: application/json' \
+--data '{
+    "data": {
+        "name": "Uninstall Event",
+        "date": "TBD",
+        "id": "1"
+    }
+}' | jq
+
+# Create event 1 again (should fail)
+echo 'Create event 1 again (should fail)'
+curl --location 'http://'$ENDPOINT':'$PORT'/newevent' \
+--header 'Content-Type: application/json' \
+--data '{
+    "data": {
+        "name": "Uninstall Event",
+        "date": "TBD",
+        "id": "1"
+    }
+}' | jq
+
+# Create event 1 again (should fail)
+echo 'Create event 1 again (should fail)'
+curl --location 'http://'$ENDPOINT':'$PORT'/newevent' \
+--header 'Content-Type: application/json' \
+--data '{
+    "data": {
+        "name": "Uninstall Event",
+        "date": "TBD",
+        "id": "1"
+    }
+}' | jq
+
+# Create event 1 again (should fail)
+echo 'Create event 1 again (should fail)'
+curl --location 'http://'$ENDPOINT':'$PORT'/newevent' \
+--header 'Content-Type: application/json' \
+--data '{
+    "data": {
+        "name": "Uninstall Event",
+        "date": "TBD",
+        "id": "1"
+    }
+}' | jq
+
+# Delete event 1
+echo 'Delete event 1'
+curl --location --request DELETE 'http://'$ENDPOINT':'$PORT'/event/1' | jq
+
+# Delete event 1 again (should fail)
+echo 'Delete event 1 again (should fail)'
+curl --location --request DELETE 'http://'$ENDPOINT':'$PORT'/event/1' | jq
+
+# Delete event 1 again (should fail)
+echo 'Delete event 1 again (should fail)'
+curl --location --request DELETE 'http://'$ENDPOINT':'$PORT'/event/1' | jq
+
+# Delete event 1 again (should fail)
+echo 'Delete event 1 again (should fail)'
+curl --location --request DELETE 'http://'$ENDPOINT':'$PORT'/event/1' | jq
+
+# Delete event 1 again (should fail)
+echo 'Delete event 1 again (should fail)'
+curl --location --request DELETE 'http://'$ENDPOINT':'$PORT'/event/1' | jq
diff --git a/dapr-distributed-calendar/fluent/ingress.yaml b/dapr-distributed-calendar/fluent/ingress.yaml
@@ -1,4 +1,4 @@
-apiVersion: traefik.containo.us/v1alpha1
+apiVersion: traefik.io/v1alpha1
 kind: IngressRoute
 metadata:
   name: kibana-ingress