Merge pull request #1516 from adleong/alex/linkerd

stefanprodan · web-flow · commit a5173095579a · 2023-09-19T12:19:01.000+03:00
Update Linkerd tutorial to use Kubernetes Gateway API
diff --git a/docs/diagrams/flagger-linkerd-traffic-split.png b/docs/diagrams/flagger-linkerd-traffic-split.png
diff --git a/docs/gitbook/tutorials/linkerd-progressive-delivery.md b/docs/gitbook/tutorials/linkerd-progressive-delivery.md
@@ -2,16 +2,14 @@
 
 This guide shows you how to use Linkerd and Flagger to automate canary deployments.
 
-![Flagger Linkerd Traffic Split](https://raw.githubusercontent.com/fluxcd/flagger/main/docs/diagrams/flagger-linkerd-traffic-split.png)
-
 ## Prerequisites
 
-Flagger requires a Kubernetes cluster **v1.16** or newer and Linkerd **2.10** or newer.
+Flagger requires a Kubernetes cluster **v1.21** or newer and Linkerd **2.14** or newer.
 
 Install Linkerd and Prometheus (part of Linkerd Viz):
 
 ```bash
-# For linkerd versions 2.12 and later, the CRDs need to be installed beforehand
+# The CRDs need to be installed beforehand
 linkerd install --crds | kubectl apply -f -
 
 linkerd install | kubectl apply -f -
@@ -45,14 +43,9 @@ helm install linkerd-control-plane linkerd/linkerd-control-plane \
 
 helm install linkerd-viz linkerd/linkerd-viz -n linkerd-viz --create-namespace
 
-helm repo add l5d-smi https://linkerd.github.io/linkerd-smi
-helm install linkerd-smi l5d-smi/linkerd-smi -n linkerd-smi --create-namespace
-
-# Note that linkerdAuthPolicy.create=true is only required for Linkerd 2.12 and
-# later
 helm install flagger flagger/flagger \
   --n flagger-system \
-  --set meshProvider=linkerd \
+  --set meshProvider=gatewayapi:v1beta1 \
   --set metricsServer=http://prometheus.linkerd-viz:9090 \
   --set linkerdAuthPolicy.create=true
 ```
@@ -82,9 +75,65 @@ Create a deployment and a horizontal pod autoscaler:
 kubectl apply -k https://github.com/fluxcd/flagger//kustomize/podinfo?ref=main
 ```
 
-Create a canary custom resource for the podinfo deployment:
+Create a metrics template and canary custom resources for the podinfo deployment:
 
 ```yaml
+---
+apiVersion: flagger.app/v1beta1
+kind: MetricTemplate
+metadata:
+  name: success-rate
+  namespace: test
+spec:
+  provider:
+    type: prometheus
+    address: http://prometheus.linkerd-viz:9090
+  query: |
+    sum(
+      rate(
+        response_total{
+          namespace="{{ namespace }}",
+          deployment=~"{{ target }}",
+          classification!="failure",
+          direction="{{ variables.direction }}"
+        }[{{ interval }}]
+      )
+    ) 
+    / 
+    sum(
+      rate(
+        response_total{
+          namespace="{{ namespace }}",
+          deployment=~"{{ target }}",
+          direction="{{ variables.direction }}"
+        }[{{ interval }}]
+      )
+    ) 
+    * 100
+---
+apiVersion: flagger.app/v1beta1
+kind: MetricTemplate
+metadata:
+  name: latency
+  namespace: test
+spec:
+  provider:
+    type: prometheus
+    address: http://prometheus.linkerd-viz:9090
+  query: |
+    histogram_quantile(
+        0.99,
+        sum(
+            rate(
+                response_latency_ms_bucket{
+                    namespace="{{ namespace }}",
+                    deployment=~"{{ target }}",
+                    direction="{{ variables.direction }}"
+                    }[{{ interval }}]
+                )
+            ) by (le)
+        )
+---
 apiVersion: flagger.app/v1beta1
 kind: Canary
 metadata:
@@ -109,6 +158,13 @@ spec:
     port: 9898
     # container port number or name (optional)
     targetPort: 9898
+    # Reference to the Service that the generated HTTPRoute would attach to.
+    gatewayRefs:
+      - name: podinfo
+        namespace: test
+        group: core
+        kind: Service
+        port: 9898
   analysis:
     # schedule interval (default 60s)
     interval: 30s
@@ -122,18 +178,28 @@ spec:
     stepWeight: 5
     # Linkerd Prometheus checks
     metrics:
-    - name: request-success-rate
+    - name: success-rate
+      templateRef:
+        name: success-rate
+        namespace: test
       # minimum req success rate (non 5xx responses)
       # percentage (0-100)
       thresholdRange:
         min: 99
       interval: 1m
-    - name: request-duration
+      templateVariables:
+        direction: inbound
+    - name: latency
+      templateRef:
+        name: latency
+        namespace: test
       # maximum req duration P99
       # milliseconds
       thresholdRange:
         max: 500
       interval: 30s
+      templateVariables:
+        direction: inbound
     # testing (optional)
     webhooks:
       - name: acceptance-test
diff --git a/kustomize/linkerd/patch.yaml b/kustomize/linkerd/patch.yaml
@@ -10,7 +10,7 @@ spec:
           args:
             - -log-level=info
             - -include-label-prefix=app.kubernetes.io
-            - -mesh-provider=linkerd
+            - -mesh-provider=gatewayapi:v1beta1
             - -metrics-server=http://prometheus.linkerd-viz:9090
 ---
 apiVersion: rbac.authorization.k8s.io/v1
diff --git a/test/linkerd/install.sh b/test/linkerd/install.sh
@@ -2,8 +2,7 @@
 
 set -o errexit
 
-LINKERD_VER="stable-2.13.2"
-LINKERD_SMI_VER="0.2.0"
+LINKERD_VER="stable-2.14.0"
 REPO_ROOT=$(git rev-parse --show-toplevel)
 
 mkdir -p ${REPO_ROOT}/bin
@@ -18,10 +17,6 @@ ${REPO_ROOT}/bin/linkerd install --crds | kubectl apply -f -
 ${REPO_ROOT}/bin/linkerd install | kubectl apply -f -
 ${REPO_ROOT}/bin/linkerd check
 
-echo ">>> Installing Linkerd SMI"
-${REPO_ROOT}/bin/linkerd-smi install | kubectl apply -f -
-${REPO_ROOT}/bin/linkerd-smi check
-
 echo ">>> Installing Linkerd Viz"
 ${REPO_ROOT}/bin/linkerd viz install | kubectl apply -f -
 kubectl -n linkerd-viz rollout status deploy/prometheus
diff --git a/test/linkerd/test-canary.sh b/test/linkerd/test-canary.sh
@@ -6,6 +6,40 @@ set -o errexit
 
 REPO_ROOT=$(git rev-parse --show-toplevel)
 
+cat <<EOF | kubectl apply -f -
+apiVersion: flagger.app/v1beta1
+kind: MetricTemplate
+metadata:
+  name: success-rate
+  namespace: linkerd
+spec:
+  provider:
+    type: prometheus
+    address: http://prometheus.linkerd-viz:9090
+  query: |
+    sum(
+      rate(
+        response_total{
+          namespace="{{ namespace }}",
+          deployment=~"{{ target }}",
+          classification!="failure",
+          direction="{{ variables.direction }}"
+        }[{{ interval }}]
+      )
+    ) 
+    / 
+    sum(
+      rate(
+        response_total{
+          namespace="{{ namespace }}",
+          deployment=~"{{ target }}",
+          direction="{{ variables.direction }}"
+        }[{{ interval }}]
+      )
+    ) 
+    * 100
+EOF
+
 cat <<EOF | kubectl apply -f -
 apiVersion: flagger.app/v1beta1
 kind: MetricTemplate
@@ -47,18 +81,27 @@ spec:
     port: 80
     targetPort: http
     portDiscovery: true
+    gatewayRefs:
+      - name: podinfo
+        namespace: test
+        group: core
+        kind: Service
+        port: 80
   analysis:
     interval: 15s
     threshold: 15
     maxWeight: 50
     stepWeight: 10
     metrics:
-    - name: request-success-rate
-      threshold: 99
+    - name: success-rate
+      templateRef:
+        name: success-rate
+        namespace: linkerd
+      thresholdRange:
+        min: 99
       interval: 1m
-    - name: request-duration
-      threshold: 500
-      interval: 30s
+      templateVariables:
+        direction: inbound
     - name: latency
       templateRef:
         name: latency
@@ -106,6 +149,12 @@ spec:
   service:
     port: 9898
     portDiscovery: true
+    gatewayRefs:
+      - name: podinfo
+        namespace: test
+        group: core
+        kind: Service
+        port: 9898
   analysis:
     interval: 15s
     threshold: 15
@@ -194,18 +243,35 @@ spec:
   service:
     port: 80
     targetPort: 9898
+    gatewayRefs:
+      - name: podinfo
+        namespace: test
+        group: core
+        kind: Service
+        port: 80
   analysis:
     interval: 15s
     threshold: 3
     maxWeight: 50
     stepWeight: 10
     metrics:
-    - name: request-success-rate
-      threshold: 99
+    - name: success-rate
+      templateRef:
+        name: success-rate
+        namespace: linkerd
+      thresholdRange:
+        min: 99
       interval: 1m
-    - name: request-duration
+      templateVariables:
+        direction: inbound
+    - name: latency
+      templateRef:
+        name: latency
+        namespace: linkerd
       threshold: 500
       interval: 30s
+      templateVariables:
+        direction: inbound
     webhooks:
       - name: http-acceptance-test
         type: pre-rollout
diff --git a/test/linkerd/test-steps.sh b/test/linkerd/test-steps.sh
