Merge pull request #1570 from cliveseldon/1560_surface_errors

Add Events and fix State for SeldonDeployments
SeldonIO · Mar 22, 2020 · 20ef400 · 20ef400
2 parents 367d234 + 2288189
commit 20ef400
Show file tree

Hide file tree

Showing 12 changed files with 672 additions and 181 deletions.
diff --git a/doc/source/workflow/troubleshooting.md b/doc/source/workflow/troubleshooting.md
@@ -54,6 +54,15 @@ For a model with invalid json/yaml an example is shown below:
 }
 ```
 
+## Check all events on the SeldonDeployment
+
+```bash
+kubectl describe sdep mysdep
+```
+
+This will show each event from the operator including create, update, delete and error events.
+
+
 ## My Seldon Deployment remains in "creating" state
 
 Check if the pods are running successfully.

diff --git a/helm-charts/seldon-core-operator/templates/clusterrole_seldon-manager-role.yaml b/helm-charts/seldon-core-operator/templates/clusterrole_seldon-manager-role.yaml
@@ -11,6 +11,13 @@ metadata:
     app.kubernetes.io/version: '{{ .Chart.Version }}'
   name: seldon-manager-role-{{ .Release.Namespace }}
 rules:
+- apiGroups:
+  - ''
+  resources:
+  - events
+  verbs:
+  - create
+  - patch
 - apiGroups:
   - ''
   resources:

diff --git a/operator/apis/machinelearning/v1/seldondeployment_types.go b/operator/apis/machinelearning/v1/seldondeployment_types.go
@@ -349,9 +349,18 @@ type ServiceStatus struct {
 	ExplainerFor string `json:"explainerFor,omitempty" protobuf:"string,4,opt,name=explainerFor"`
 }
 
+type StatusState string
+
+// CRD Status values
+const (
+	StatusStateAvailable StatusState = "Available"
+	StatusStateCreating  StatusState = "Creating"
+	StatusStateFailed    StatusState = "Failed"
+)
+
 // SeldonDeploymentStatus defines the observed state of SeldonDeployment
 type SeldonDeploymentStatus struct {
-	State            string                      `json:"state,omitempty" protobuf:"string,1,opt,name=state"`
+	State            StatusState                 `json:"state,omitempty" protobuf:"string,1,opt,name=state"`
 	Description      string                      `json:"description,omitempty" protobuf:"string,2,opt,name=description"`
 	DeploymentStatus map[string]DeploymentStatus `json:"deploymentStatus,omitempty" protobuf:"bytes,3,opt,name=deploymentStatus"`
 	ServiceStatus    map[string]ServiceStatus    `json:"serviceStatus,omitempty" protobuf:"bytes,4,opt,name=serviceStatus"`

diff --git a/operator/config/rbac/role.yaml b/operator/config/rbac/role.yaml
@@ -6,6 +6,13 @@ metadata:
   creationTimestamp: null
   name: manager-role
 rules:
+- apiGroups:
+  - ""
+  resources:
+  - events
+  verbs:
+  - create
+  - patch
 - apiGroups:
   - ""
   resources:

diff --git a/operator/constants/constants.go b/operator/constants/constants.go
@@ -17,3 +17,26 @@ const (
 
 	FirstPortNumber = 9000
 )
+
+const (
+	ControllerName = "seldon-controller-manager"
+)
+
+// Event messages
+const (
+	EventsCreateVirtualService  = "CreateVirtualService"
+	EventsUpdateVirtualService  = "UpdateVirtualService"
+	EventsCreateDestinationRule = "CreateDestinationRule"
+	EventsUpdateDestinationRule = "UpdateDestinationRule"
+	EventsCreateService         = "CreateService"
+	EventsUpdateService         = "UpdateService"
+	EventsCreateHPA             = "CreateHPA"
+	EventsUpdateHPA             = "UpdateHPA"
+	EventsDeleteHPA             = "DeleteHPA"
+	EventsCreateDeployment      = "CreateDeployment"
+	EventsUpdateDeployment      = "UpdateDeployment"
+	EventsDeleteDeployment      = "DeleteDeployment"
+	EventsInternalError         = "InternalError"
+	EventsUpdated               = "Updated"
+	EventsUpdateFailed          = "UpdateFailed"
+)