Merge pull request #184 from biomage-ltd/cleanup-operator

added event exporter and removed cleanup operator

chart-infra/templates/cleanup-operator-roles.yaml

@@ -0,0 +1,45 @@
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: cleanup-operator
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: Role
+metadata:
+  name: cleanup-operator
+rules:
+- apiGroups: [""]
+  resources:
+  - pods
+  verbs:
+  - get
+  - list
+  - watch
+  - delete
+- apiGroups: ["batch", "extensions"]
+  resources:
+  - jobs
+  verbs:
+  - get
+  - list
+  - watch
+  - delete
+- apiGroups: ["apps"]
+  resources:
+  - deployments
+  - deployments/scale
+  verbs:
+  - get
+  - patch
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: RoleBinding
+metadata:
+  name: cleanup-operator
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: Role
+  name: cleanup-operator
+subjects:
+- kind: ServiceAccount
+  name: cleanup-operator

chart-infra/templates/kubernetes-event-exporter-config.yaml

@@ -0,0 +1,21 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: event-exporter-cfg
+  namespace: {{.Release.Namespace}}
+data:
+  config.yaml: |
+    logLevel: info
+    logFormat: json
+    route:
+      routes:
+        - match:
+          - kind: "Pod"
+            receiver: "cleanup"
+    receivers:
+      - name: "cleanup"
+        webhook:
+          endpoint: "https://api-{{ .Values.sandboxId }}.scp-staging.biomage.net/v1/kubernetesEvents"
+          headers:
+            User-Agent: kube-event-exporter 1.0
+

chart-infra/templates/kubernetes-event-exporter-deployment.yaml

@@ -0,0 +1,31 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: event-exporter
+  namespace: {{ .Release.Namespace }}
+spec:
+  replicas: 1
+  template:
+    metadata:
+      labels:
+        app: event-exporter
+        version: v1
+    spec:
+      serviceAccountName: event-exporter
+      containers:
+        - name: event-exporter
+          image: ghcr.io/opsgenie/kubernetes-event-exporter:v0.10
+          imagePullPolicy: IfNotPresent
+          args:
+            - -conf=/data/config.yaml
+          volumeMounts:
+            - mountPath: /data
+              name: cfg
+      volumes:
+        - name: cfg
+          configMap:
+            name: event-exporter-cfg
+  selector:
+    matchLabels:
+      app: event-exporter
+      version: v1

chart-infra/templates/kubernetes-event-exporter-roles.yaml

@@ -0,0 +1,18 @@
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  namespace: {{.Release.Namespace}}
+  name: event-exporter
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: event-exporter
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: view
+subjects:
+  - kind: ServiceAccount
+    namespace: {{.Release.Namespace}}
+    name: event-exporter

pipeline-runner/R/gem2s-7-upload_to_aws.R

@@ -29,6 +29,7 @@ upload_to_aws <- function(input, pipeline_config, prev_out) {
   fpath <- file.path(tempdir(), 'experiment.rds')
   saveRDS(scdata, fpath, compress = FALSE)
 
+  # can only upload up to 50Gb because part numbers can be any number from 1 to 10,000, inclusive.
   put_object_in_s3_multipart(pipeline_config,
                              bucket = pipeline_config$source_bucket,
                              object = fpath,

pipeline-runner/R/handle_data.R

@@ -37,6 +37,7 @@ send_output_to_api <- function(pipeline_config, input, plot_data_keys, output) {
 
   msg <- list(
     experimentId = input$experimentId,
+    taskName = input$taskName,
     input = input,
     output = list(
       bucket = pipeline_config$results_bucket,

pipeline-runner/init.R

@@ -346,7 +346,7 @@ init <- function() {
                     cause = error_txt
                 )
 
-                send_pipeline_fail_update(pipeline_config, input_parse$experimentId, input_parse$processName, "Error message placeholder")
+                send_pipeline_fail_update(pipeline_config, input_parse$experimentId, input_parse$processName, error_txt)
 
                 message("Sent task failure to state machine task: ", taskToken)
                 message("recovered from error:", e$message)