Update

Signed-off-by: Yi Chen <[email protected]>

.dockerignore

@@ -1,21 +1,31 @@
+.github/
 .idea/
 .vscode/
 bin/
 charts/
 docs/
+config/
 examples/
+hack/
 manifest/
-sparkctl/sparkctl
-sparkctl/sparkctl-linux-amd64
-sparkctl/sparkctl-darwin-amd64
+spark-docker/
+sparkctl/
 test/
 vendor/
+.dockerignore
 .DS_Store
 .gitignore
 .gitlab-ci.yaml
+.golangci.yaml
 .pre-commit-config.yaml
+ADOPTERS.md
+CODE_OF_CONDUCT.md
+codecov.ymal
 CONTRIBUTING.md
+cover.out
+Dockerfile
+LICENSE
 OWNERS
+PROJECT
 README.md
-spark-operator
 test.sh

.golangci.yaml

@@ -24,14 +24,14 @@ linters-settings:
       - default
       - prefix(github.com/kubeflow/spark-operator)
   depguard:
-    main:
+    Main:
       files:
         - $all
         - "!$test"
       listMode: Lax
       deny:
         reflect: Please don't use reflect package
-    test:
+    Test:
       files:
         - $test
       listMode: Lax

Dockerfile

@@ -16,35 +16,26 @@
 
 ARG SPARK_IMAGE=spark:3.5.0
 
-FROM golang:1.22-alpine as builder
+FROM golang:1.22.0 as builder
 
 WORKDIR /workspace
 
-# Copy the Go Modules manifests
-COPY go.mod go.mod
-COPY go.sum go.sum
-# Cache deps before building and copying source so that we don't need to re-download as much
-# and so that source changes don't invalidate our downloaded layer
-RUN go mod download
+COPY . .
 
-# Copy the go source code
-COPY api/ api/
-COPY cmd/ cmd/
-COPY internal/ internal/
-COPY pkg/ pkg/
-
-# Build
 ARG TARGETARCH
-RUN CGO_ENABLED=0 GOOS=linux GOARCH=${TARGETARCH} GO111MODULE=on go build -a -o /usr/bin/spark-operator cmd/main.go
+
+RUN CGO_ENABLED=0 GOOS=linux GOARCH=${TARGETARCH} GO111MODULE=on make build-operator
 
 FROM ${SPARK_IMAGE}
+
 USER root
-COPY --from=builder /usr/bin/spark-operator /usr/bin/
-RUN apt-get update --allow-releaseinfo-change \
-    && apt-get update \
+
+RUN apt-get update \
     && apt-get install -y tini \
     && rm -rf /var/lib/apt/lists/*
 
+COPY --from=builder /workspace/bin/spark-operator /usr/bin/spark-operator
+
 COPY entrypoint.sh /usr/bin/
 
 ENTRYPOINT ["/usr/bin/entrypoint.sh"]

Makefile

@@ -12,20 +12,30 @@ endif
 SHELL = /usr/bin/env bash -o pipefail
 .SHELLFLAGS = -ec
 
+# Version information.
+# OPERATOR_VERSION ?= $$(grep appVersion $(SPARK_OPERATOR_CHART_PATH)/Chart.yaml | awk '{print $$2}')
+VERSION=v2.0.0
+BUILD_DATE = $(shell date -u +"%Y-%m-%dT%H:%M:%S%:z")
+GIT_COMMIT = $(shell git rev-parse HEAD)
+GIT_TAG = $(shell if [ -z "`git status --porcelain`" ]; then git describe --exact-match --tags HEAD 2>/dev/null; fi)
+GIT_TREE_STATE = $(shell if [ -z "`git status --porcelain`" ]; then echo "clean" ; else echo "dirty"; fi)
+GIT_SHA = $(shell git rev-parse --short HEAD || echo "HEAD")
+GIT_VERSION = ${VERSION}-${GIT_SHA}
+
+REPO=github.com/kubeflow/spark-operator
 SPARK_OPERATOR_GOPATH=/go/src/github.com/kubeflow/spark-operator
+SPARK_OPERATOR_CHART_PATH=charts/spark-operator-chart
+OPERATOR_VERSION ?= $$(grep appVersion $(SPARK_OPERATOR_CHART_PATH)/Chart.yaml | awk '{print $$2}')
 DEP_VERSION:=`grep DEP_VERSION= Dockerfile | awk -F\" '{print $$2}'`
 BUILDER=`grep "FROM golang:" Dockerfile | awk '{print $$2}'`
 UNAME:=`uname | tr '[:upper:]' '[:lower:]'`
-REPO=github.com/kubeflow/spark-operator
-SPARK_OPERATOR_CHART_PATH=charts/spark-operator-chart
 
 # CONTAINER_TOOL defines the container tool to be used for building images.
 # Be aware that the target commands are only tested with Docker which is
 # scaffolded by default. However, you might want to replace it to use other
 # tools. (i.e. podman)
 CONTAINER_TOOL ?= docker
 
-OPERATOR_VERSION ?= $$(grep appVersion $(SPARK_OPERATOR_CHART_PATH)/Chart.yaml | awk '{print $$2}')
 # Image URL to use all building/pushing image targets
 IMAGE_REPOSITORY ?= docker.io/kubeflow/spark-operator
 IMAGE_TAG ?= $(OPERATOR_VERSION)
@@ -93,13 +103,14 @@ go-vet: ## Run go vet against code.
 
 .PHONY: lint
 lint: golangci-lint ## Run golangci-lint linter
+	@echo "Running golangci-lint run..."
 	$(GOLANGCI_LINT) run
 
 .PHONY: lint-fix
 lint-fix: golangci-lint ## Run golangci-lint linter and perform fixes
+	@echo "Running golangci-lint run --fix..."
 	$(GOLANGCI_LINT) run --fix
 
-
 .PHONY: unit-test
 unit-test: envtest ## Run unit tests.
 	@echo "Running unit tests..."
@@ -114,9 +125,16 @@ e2e-test: envtest kind-create-cluster ## Run the e2e tests against a Kind k8s in
 
 ##@ Build
 
+override LDFLAGS += \
+  -X ${REPO}.version=${VERSION} \
+  -X ${REPO}.buildDate=${BUILD_DATE} \
+  -X ${REPO}.gitCommit=${GIT_COMMIT} \
+  -X ${REPO}.gitTreeState=${GIT_TREE_STATE} \
+  -extldflags "-static"
+
 .PHONY: build-operator
 build-operator: ## Build Spark operator
-	go build -o bin/spark-operator cmd/main.go
+	go build -o bin/spark-operator -ldflags '${LDFLAGS}' cmd/main.go
 
 .PHONY: build-sparkctl
 build-sparkctl: ## Build sparkctl binary
@@ -171,16 +189,13 @@ docker-push: ## Push docker image with the operator.
 # - have enabled BuildKit. More info: https://docs.docker.com/develop/develop-images/build_enhancements/
 # - be able to push the image to your registry (i.e. if you do not set a valid value via IMG=<myregistry/image:<tag>> then the export will fail)
 # To adequately provide solutions that are compatible with multiple platforms, you should consider using this option.
-PLATFORMS ?= linux/arm64,linux/amd64
+PLATFORMS ?= linux/amd64,linux/arm64
 .PHONY: docker-buildx
 docker-buildx: ## Build and push docker image for the operator for cross-platform support
-	# copy existing Dockerfile and insert --platform=${BUILDPLATFORM} into Dockerfile.cross, and preserve the original Dockerfile
-	sed -e '1 s/\(^FROM\)/FROM --platform=\$$\{BUILDPLATFORM\}/; t' -e ' 1,// s//FROM --platform=\$$\{BUILDPLATFORM\}/' Dockerfile > Dockerfile.cross
 	- $(CONTAINER_TOOL) buildx create --name spark-operator-builder
 	$(CONTAINER_TOOL) buildx use spark-operator-builder
-	- $(CONTAINER_TOOL) buildx build --push --platform=$(PLATFORMS) --tag ${IMAGE_REPOSITORY}:${IMAGE_TAG} -f Dockerfile.cross .
+	- $(CONTAINER_TOOL) buildx build --push --platform=$(PLATFORMS) --tag ${IMAGE_REPOSITORY}:${IMAGE_TAG} -f Dockerfile .
 	- $(CONTAINER_TOOL) buildx rm spark-operator-builder
-	rm Dockerfile.cross
 
 ##@ Helm
 
@@ -222,11 +237,11 @@ kind-delete-custer: kind ## Delete the created kind cluster.
 	rm -f $(KIND_KUBE_CONFIG)
 
 .PHONY: install
-install: manifests kustomize ## Install CRDs into the K8s cluster specified in ~/.kube/config.
+install-crd: manifests kustomize ## Install CRDs into the K8s cluster specified in ~/.kube/config.
 	$(KUSTOMIZE) build config/crd | $(KUBECTL) apply -f -
 
 .PHONY: uninstall
-uninstall: manifests kustomize ## Uninstall CRDs from the K8s cluster specified in ~/.kube/config. Call with ignore-not-found=true to ignore resource not found errors during deletion.
+uninstall-crd: manifests kustomize ## Uninstall CRDs from the K8s cluster specified in ~/.kube/config. Call with ignore-not-found=true to ignore resource not found errors during deletion.
 	$(KUSTOMIZE) build config/crd | $(KUBECTL) delete --ignore-not-found=$(ignore-not-found) -f -
 
 .PHONY: deploy

charts/spark-operator-chart/README.md

@@ -83,7 +83,7 @@ See [helm uninstall](https://helm.sh/docs/helm/helm_uninstall) for command docum
 | batchScheduler.enable | bool | `false` | Enable batch scheduler for spark jobs scheduling. If enabled, users can specify batch scheduler name in spark application |
 | commonLabels | object | `{}` | Common labels to add to the resources |
 | controller.ingressUrlFormat | string | `""` | Ingress URL format. Requires the UI service to be enabled by setting `controller.uiService.enable` to true. |
-| controller.logLevel | int | `1` | Set higher levels for more verbose logging |
+| controller.logLevel | string | `"info"` | Configure the verbosity of logging, can be one of `debug`, `info`, `error` |
 | controller.rbac.annotations | object | `{}` | Optional annotations for the controller RBAC resources |
 | controller.rbac.create | bool | `true` | Specifies whether to create RBAC resources for the controller |
 | controller.replicaCount | int | `1` | Number of replicas of controller, leader election will be enabled if this is greater than 1 |
@@ -111,9 +111,9 @@ See [helm uninstall](https://helm.sh/docs/helm/helm_uninstall) for command docum
 | priorityClassName | string | `""` | A priority class to be used for running spark-operator pod. |
 | prometheus.metrics.enable | bool | `true` | Specifies whether to enable prometheus metrics scraping |
 | prometheus.metrics.endpoint | string | `"/metrics"` | Metrics serving endpoint |
-| prometheus.metrics.port | int | `10254` | Metrics port |
+| prometheus.metrics.port | int | `8080` | Metrics port |
 | prometheus.metrics.portName | string | `"metrics"` | Metrics port name |
-| prometheus.metrics.prefix | string | `""` | Metric prefix, will be added to all exported metrics |
+| prometheus.metrics.prefix | string | `""` | Metrics prefix, will be added to all exported metrics |
 | prometheus.podMonitor.create | bool | `false` | Specifies whether to create pod monitor. Note that prometheus metrics should be enabled as well. |
 | prometheus.podMonitor.jobLabel | string | `"spark-operator-podmonitor"` | The label to use to retrieve the job name from |
 | prometheus.podMonitor.labels | object | `{}` | Pod monitor labels |
@@ -133,7 +133,7 @@ See [helm uninstall](https://helm.sh/docs/helm/helm_uninstall) for command docum
 | volumes | list | `[]` |  |
 | webhook.enable | bool | `true` | Specifies whether to enable webhook server |
 | webhook.failurePolicy | string | `"Fail"` | Specifies how unrecognized errors are handled, allowed values are `Ignore` or `Fail`. |
-| webhook.logLevel | int | `1` | Set higher levels for more verbose logging |
+| webhook.logLevel | string | `"info"` | Configure the verbosity of logging, can be one of `debug`, `info`, `error` |
 | webhook.port | int | `9443` | Specifies webhook port |
 | webhook.portName | string | `"webhook"` | Specifies webhook service port name |
 | webhook.rbac.annotations | object | `{}` | Optional annotations for the webhook RBAC resources |

charts/spark-operator-chart/templates/controller/deployment.yaml

@@ -69,10 +69,10 @@ spec:
         - --enable-batch-scheduler={{ .Values.batchScheduler.enable }}
         {{- if .Values.prometheus.metrics.enable }}
         - --enable-metrics=true
-        - --metrics-labels=app_type
-        - --metrics-port={{ .Values.prometheus.metrics.port }}
+        - --metrics-bind-address=:{{ .Values.prometheus.metrics.port }}
         - --metrics-endpoint={{ .Values.prometheus.metrics.endpoint }}
         - --metrics-prefix={{ .Values.prometheus.metrics.prefix }}
+        - --metrics-labels=app_type
         {{- end }}
         - --leader-election=true
         - --leader-election-lock-name={{ include "spark-operator.controller.leaderElectionName" . }}

charts/spark-operator-chart/templates/controller/rbac.yaml

@@ -30,28 +30,45 @@ rules:
   - ""
   resources:
   - pods
-  - persistentvolumeclaims
   verbs:
-  - "*"
+  - get
+  - list
+  - watch
+  - create
+  - update
+  - patch
+  - delete
+  - deletecollection
 - apiGroups:
   - ""
   resources:
-  - services
   - configmaps
   verbs:
-  - create
   - get
+  - create
+  - update
+  - patch
   - delete
+- apiGroups:
+  - ""
+  resources:
+  - services
+  verbs:
+  - get
+  - list
+  - watch
+  - create
   - update
   - patch
+  - delete
 - apiGroups:
   - extensions
   - networking.k8s.io
   resources:
   - ingresses
   verbs:
-  - create
   - get
+  - create
   - delete
 - apiGroups:
   - ""
@@ -85,13 +102,31 @@ rules:
   - sparkoperator.k8s.io
   resources:
   - sparkapplications
-  - sparkapplications/status
-  - sparkapplications/finalizers
   - scheduledsparkapplications
+  verbs:
+  - get
+  - list
+  - watch
+  - create
+  - update
+  - patch
+  - delete
+- apiGroups:
+  - sparkoperator.k8s.io
+  resources:
+  - sparkapplications/status
   - scheduledsparkapplications/status
+  verbs:
+  - get
+  - update
+  - patch
+- apiGroups:
+  - sparkoperator.k8s.io
+  resources:
+  - sparkapplications/finalizers
   - scheduledsparkapplications/finalizers
   verbs:
-  - "*"
+  - update
 {{- if .Values.batchScheduler.enable }}
 {{/* required for the `volcano` batch scheduler */}}
 - apiGroups:

charts/spark-operator-chart/templates/spark/rbac.yaml

@@ -35,11 +35,18 @@ rules:
   - ""
   resources:
   - pods
-  - services
   - configmaps
   - persistentvolumeclaims
+  - services
   verbs:
-  - "*"
+  - get
+  - list
+  - watch
+  - create
+  - update
+  - patch
+  - delete
+  - deletecollection
 
 ---
 apiVersion: rbac.authorization.k8s.io/v1

charts/spark-operator-chart/templates/webhook/deployment.yaml

@@ -57,6 +57,15 @@ spec:
         - --webhook-svc-name={{ include "spark-operator.webhook.serviceName" . }}
         - --webhook-svc-namespace={{ .Release.Namespace }}
         - --webhook-port={{ .Values.webhook.port }}
+        - --mutating-webhook-name={{ include "spark-operator.webhook.name" . }}
+        - --validating-webhook-name={{ include "spark-operator.webhook.name" . }}
+        {{- if .Values.prometheus.metrics.enable }}
+        - --enable-metrics=true
+        - --metrics-bind-address=:{{ .Values.prometheus.metrics.port }}
+        - --metrics-endpoint={{ .Values.prometheus.metrics.endpoint }}
+        - --metrics-prefix={{ .Values.prometheus.metrics.prefix }}
+        - --metrics-labels=app_type
+        {{- end }}
         - --leader-election=true
         - --leader-election-lock-name={{ include "spark-operator.webhook.leaderElectionName" . }}
         - --leader-election-lock-namespace={{ .Release.Namespace }}

charts/spark-operator-chart/templates/webhook/secret.yaml

@@ -22,7 +22,7 @@ metadata:
   labels:
     {{- include "spark-operator.webhook.labels" . | nindent 4 }}
   annotations:
-    helm.sh/hook: pre-install
+    helm.sh/hook: pre-install,pre-upgrade,pre-rollback
     helm.sh/hook-delete-policy: before-hook-creation
 data:
   ca-key.pem: ""