feat: Reference AnalysisTemplates inside an AnalysisTemplate (#3353)

Signed-off-by: Guillaume Doussin <[email protected]>
argoproj · Mar 29, 2024 · f5793e4 · f5793e4
1 parent ea398fc
commit f5793e4
Show file tree

Hide file tree

Showing 28 changed files with 2,324 additions and 1,021 deletions.
diff --git a/docs/features/analysis.md b/docs/features/analysis.md
@@ -358,6 +358,184 @@ templates together. The controller combines the `metrics` and `args` fields of a
     * Multiple metrics in the templates have the same name
     * Two arguments with the same name have different default values no matter the argument value in Rollout
 
+## Analysis Template referencing other Analysis Templates
+
+AnalysisTemplates and ClusterAnalysisTemplates may reference other templates.
+
+They can be combined with other metrics:
+
+=== "AnalysisTemplate"
+
+    ```yaml
+    apiVersion: argoproj.io/v1alpha1
+    kind: AnalysisTemplate
+    metadata:
+      name: error-rate
+    spec:
+      args:
+      - name: service-name
+      metrics:
+      - name: error-rate
+        interval: 5m
+        successCondition: result[0] <= 0.95
+        failureLimit: 3
+        provider:
+          prometheus:
+            address: http://prometheus.example.com:9090
+            query: |
+              sum(irate(
+                istio_requests_total{reporter="source",destination_service=~"{{args.service-name}}",response_code=~"5.*"}[5m]
+              )) /
+              sum(irate(
+                istio_requests_total{reporter="source",destination_service=~"{{args.service-name}}"}[5m]
+              ))
+    ---
+    apiVersion: argoproj.io/v1alpha1
+    kind: AnalysisTemplate
+    metadata:
+      name: rates
+    spec:
+      args:
+      - name: service-name
+      metrics:
+      - name: success-rate
+        interval: 5m
+        successCondition: result[0] >= 0.95
+        failureLimit: 3
+        provider:
+          prometheus:
+            address: http://prometheus.example.com:9090
+            query: |
+              sum(irate(
+                istio_requests_total{reporter="source",destination_service=~"{{args.service-name}}",response_code!~"5.*"}[5m]
+              )) /
+              sum(irate(
+                istio_requests_total{reporter="source",destination_service=~"{{args.service-name}}"}[5m]
+              ))
+      templates:
+      - templateName: error-rate
+        clusterScope: false
+    ```
+
+Or without additional metrics:
+
+=== "AnalysisTemplate"
+
+    ```yaml
+    apiVersion: argoproj.io/v1alpha1
+    kind: AnalysisTemplate
+    metadata:
+      name: success-rate
+    spec:
+      args:
+      - name: service-name
+      metrics:
+      - name: success-rate
+        interval: 5m
+        successCondition: result[0] >= 0.95
+        failureLimit: 3
+        provider:
+          prometheus:
+            address: http://prometheus.example.com:9090
+            query: |
+              sum(irate(
+                istio_requests_total{reporter="source",destination_service=~"{{args.service-name}}",response_code!~"5.*"}[5m]
+              )) /
+              sum(irate(
+                istio_requests_total{reporter="source",destination_service=~"{{args.service-name}}"}[5m]
+              ))
+    ---
+    apiVersion: argoproj.io/v1alpha1
+    kind: AnalysisTemplate
+    metadata:
+      name: error-rate
+    spec:
+      args:
+      - name: service-name
+      metrics:
+      - name: error-rate
+        interval: 5m
+        successCondition: result[0] <= 0.95
+        failureLimit: 3
+        provider:
+          prometheus:
+            address: http://prometheus.example.com:9090
+            query: |
+              sum(irate(
+                istio_requests_total{reporter="source",destination_service=~"{{args.service-name}}",response_code=~"5.*"}[5m]
+              )) /
+              sum(irate(
+                istio_requests_total{reporter="source",destination_service=~"{{args.service-name}}"}[5m]
+              ))
+    ---
+    apiVersion: argoproj.io/v1alpha1
+    kind: AnalysisTemplate
+    metadata:
+      name: rates
+    spec:
+      args:
+      - name: service-name
+      templates:
+      - templateName: success-rate
+        clusterScope: false
+      - templateName: error-rate
+        clusterScope: false
+    ```
+
+  The result in the AnalysisRun will have the aggregation of metrics of each template:
+
+  === "AnalysisRun"
+
+    ```yaml
+    # NOTE: Generated AnalysisRun from a single template referencing several templates
+    apiVersion: argoproj.io/v1alpha1
+    kind: AnalysisRun
+    metadata:
+      name: guestbook-CurrentPodHash-templates-in-template
+    spec:
+      args:
+      - name: service-name
+        value: guestbook-svc.default.svc.cluster.local
+      metrics:
+      - name: success-rate
+        interval: 5m
+        successCondition: result[0] >= 0.95
+        failureLimit: 3
+        provider:
+          prometheus:
+            address: http://prometheus.example.com:9090
+            query: |
+              sum(irate(
+                istio_requests_total{reporter="source",destination_service=~"{{args.service-name}}",response_code!~"5.*"}[5m]
+              )) /
+              sum(irate(
+                istio_requests_total{reporter="source",destination_service=~"{{args.service-name}}"}[5m]
+              ))
+      - name: error-rate
+        interval: 5m
+        successCondition: result[0] <= 0.95
+        failureLimit: 3
+        provider:
+          prometheus:
+            address: http://prometheus.example.com:9090
+            query: |
+              sum(irate(
+                istio_requests_total{reporter="source",destination_service=~"{{args.service-name}}",response_code=~"5.*"}[5m]
+              )) /
+              sum(irate(
+                istio_requests_total{reporter="source",destination_service=~"{{args.service-name}}"}[5m]
+              ))
+    ```
+
+!!! note
+    The same limitations as for the multiple templates feature apply.
+    The controller will error when merging the templates if:
+
+    * Multiple metrics in the templates have the same name
+    * Two arguments with the same name have different default values no matter the argument value in Rollout
+
+    However, if the same AnalysisTemplate is referenced several times along the chain of references, the controller will only keep it once and discard the other references.
+
 ## Analysis Template Arguments
 
 AnalysisTemplates may declare a set of arguments that can be passed by Rollouts. The args can then be used as in metrics configuration and are resolved at the time the AnalysisRun is created. Argument placeholders are defined as

diff --git a/docs/features/kustomize/rollout_cr_schema.json b/docs/features/kustomize/rollout_cr_schema.json
@@ -9250,11 +9250,24 @@
                             "type": "array",
                             "x-kubernetes-patch-merge-key": "name",
                             "x-kubernetes-patch-strategy": "merge"
+                        },
+                        "templates": {
+                            "items": {
+                                "properties": {
+                                    "clusterScope": {
+                                        "type": "boolean"
+                                    },
+                                    "templateName": {
+                                        "type": "string"
+                                    }
+                                },
+                                "type": "object"
+                            },
+                            "type": "array",
+                            "x-kubernetes-patch-merge-key": "templateName",
+                            "x-kubernetes-patch-strategy": "merge"
                         }
                     },
-                    "required": [
-                        "metrics"
-                    ],
                     "type": "object"
                 }
             },
@@ -13883,11 +13896,24 @@
                             "type": "array",
                             "x-kubernetes-patch-merge-key": "name",
                             "x-kubernetes-patch-strategy": "merge"
+                        },
+                        "templates": {
+                            "items": {
+                                "properties": {
+                                    "clusterScope": {
+                                        "type": "boolean"
+                                    },
+                                    "templateName": {
+                                        "type": "string"
+                                    }
+                                },
+                                "type": "object"
+                            },
+                            "type": "array",
+                            "x-kubernetes-patch-merge-key": "templateName",
+                            "x-kubernetes-patch-strategy": "merge"
                         }
                     },
-                    "required": [
-                        "metrics"
-                    ],
                     "type": "object"
                 }
             },

diff --git a/experiments/controller_test.go b/experiments/controller_test.go
@@ -303,7 +303,7 @@ func generateRSName(ex *v1alpha1.Experiment, template v1alpha1.TemplateSpec) str
 	return fmt.Sprintf("%s-%s", ex.Name, template.Name)
 }
 
-func calculatePatch(ex *v1alpha1.Experiment, patch string, templates []v1alpha1.TemplateStatus, condition *v1alpha1.ExperimentCondition) string {
+func calculatePatch(ex *v1alpha1.Experiment, patch string, templates []v1alpha1.TemplateStatus, condition *v1alpha1.ExperimentCondition, analysisRuns []*v1alpha1.ExperimentAnalysisRunStatus, message string) string {
 	patchMap := make(map[string]any)
 	err := json.Unmarshal([]byte(patch), &patchMap)
 	if err != nil {
@@ -318,6 +318,14 @@ func calculatePatch(ex *v1alpha1.Experiment, patch string, templates []v1alpha1.
 		newStatus["conditions"] = []v1alpha1.ExperimentCondition{*condition}
 		patchMap["status"] = newStatus
 	}
+	if analysisRuns != nil {
+		newStatus["analysisRuns"] = analysisRuns
+		patchMap["status"] = newStatus
+	}
+	if message != "" {
+		newStatus["message"] = message
+		patchMap["status"] = newStatus
+	}
 
 	patchBytes, err := json.Marshal(patchMap)
 	if err != nil {
@@ -806,7 +814,7 @@ func TestAddInvalidSpec(t *testing.T) {
 	expectedPatch := calculatePatch(e, `{
 		"status":{
 		}
-	}`, nil, cond)
+	}`, nil, cond, nil, "")
 	assert.JSONEq(t, expectedPatch, patch)
 }
 
@@ -853,7 +861,7 @@ func TestUpdateInvalidSpec(t *testing.T) {
 	expectedPatch := calculatePatch(e, `{
 		"status":{
 		}
-	}`, nil, cond)
+	}`, nil, cond, nil, "")
 	assert.JSONEq(t, expectedPatch, patch)
 
 }
@@ -893,7 +901,7 @@ func TestRemoveInvalidSpec(t *testing.T) {
 	expectedPatch := calculatePatch(e, `{
 		"status":{
 		}
-	}`, templateStatus, cond)
+	}`, templateStatus, cond, nil, "")
 	assert.JSONEq(t, expectedPatch, patch)
 }