feat(controller): add canary steps plugin (#3521)

* making code for step plugin Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * codegen Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * unit tests Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * rpc tests Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * add rpc plugin tests Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * better message Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * add order test Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * implement terminate Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * Terminate tests Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * aborted logic + some unit test Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * unit test Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * abort test Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * load plugin Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * more tests Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * dont use newStatus Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * codegen preserve fields Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * some test before full promote problem Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * fix full promotion Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * fix plugins Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * codegen Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * add disabled rollout Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * codegen Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * fix duration cast Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * refactor to use context object Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * adding debug logs. Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * need to adjust the backoff on each reconcile Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * fix e2e Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * unit test Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * fix abort and promote logic Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * fix aborted rollout do not retry Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * add event Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * change enabled to status Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * unit tests Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * more test Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * cleanup Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * add docs Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * docs Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * makefile for e2e Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * disable e2e when not configured Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * Add some UI for the extension Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> * codegen Signed-off-by: Zach Aller <zachaller@users.noreply.github.com> --------- Signed-off-by: Alexandre Gaudreault <alexandre_gaudreault@intuit.com> Signed-off-by: Zach Aller <zachaller@users.noreply.github.com> Co-authored-by: Zach Aller <zachaller@users.noreply.github.com>
argoproj · Aug 8, 2024 · 74c1a94 · 74c1a94
1 parent 48131eb
commit 74c1a94
Show file tree

Hide file tree

Showing 61 changed files with 7,233 additions and 786 deletions.
diff --git a/Dockerfile.dev b/Dockerfile.dev
@@ -12,9 +12,12 @@ FROM gcr.io/distroless/static-debian11
 
 COPY --from=builder /etc/ssl/certs/ca-certificates.crt /etc/ssl/certs/
 COPY rollouts-controller-linux-amd64 /bin/rollouts-controller
+COPY step-plugin-e2e-linux-amd64 /bin/plugin-files/step-plugin-e2e
 
 # Use numeric user, allows kubernetes to identify this user as being
 # non-root when we use a security context with runAsNonRoot: true
 USER 999
 
+WORKDIR /home/argo-rollouts
+
 ENTRYPOINT [ "/bin/rollouts-controller" ]
diff --git a/Makefile b/Makefile
@@ -12,13 +12,17 @@ GIT_TREE_STATE=$(shell if [ -z "`git status --porcelain`" ]; then echo "clean" ;
 GIT_REMOTE_REPO=upstream
 VERSION=$(shell if [ ! -z "${GIT_TAG}" ] ; then echo "${GIT_TAG}" | sed -e "s/^v//"  ; else cat VERSION ; fi)
 
+
+TARGET_ARCH?=linux/amd64
+
 # docker image publishing options
-DOCKER_PUSH=false
-IMAGE_TAG=latest
+DOCKER_PUSH ?= false
+IMAGE_TAG ?= latest
 # build development images
 DEV_IMAGE ?= false
 
 # E2E variables
+E2E_K8S_CONTEXT ?= rancher-desktop
 E2E_INSTANCE_ID ?= argo-rollouts-e2e
 E2E_TEST_OPTIONS ?=
 E2E_PARALLEL ?= 1
@@ -149,6 +153,9 @@ gen-crd: install-go-tools-local ## generate crd manifests
 gen-mocks: install-go-tools-local ## generate mock files
 	./hack/update-mocks.sh
 
+gen-mocks-fast:
+	./hack/update-mocks.sh
+
 # generates openapi_generated.go
 .PHONY: gen-openapi
 gen-openapi: $(DIST_DIR)/openapi-gen ## generate openapi files
@@ -200,10 +207,11 @@ builder-image: ## build builder image
 .PHONY: image
 image:
 ifeq ($(DEV_IMAGE), true)
+	CGO_ENABLED=0 GOOS=linux GOARCH=amd64 go build -v -ldflags '${LDFLAGS}' -o ${DIST_DIR}/step-plugin-e2e-linux-amd64 ./test/cmd/step-plugin-e2e
 	CGO_ENABLED=0 GOOS=linux GOARCH=amd64 go build -v -ldflags '${LDFLAGS}' -o ${DIST_DIR}/rollouts-controller-linux-amd64 ./cmd/rollouts-controller
-	DOCKER_BUILDKIT=1 docker build -t $(IMAGE_PREFIX)argo-rollouts:$(IMAGE_TAG) -f Dockerfile.dev ${DIST_DIR}
+	DOCKER_BUILDKIT=1 docker build --platform=$(TARGET_ARCH) -t $(IMAGE_PREFIX)argo-rollouts:$(IMAGE_TAG) -f Dockerfile.dev ${DIST_DIR}
 else
-	DOCKER_BUILDKIT=1 docker build -t $(IMAGE_PREFIX)argo-rollouts:$(IMAGE_TAG)  .
+	DOCKER_BUILDKIT=1 docker build --platform=$(TARGET_ARCH) -t $(IMAGE_PREFIX)argo-rollouts:$(IMAGE_TAG)  .
 endif
 	@if [ "$(DOCKER_PUSH)" = "true" ] ; then docker push $(IMAGE_PREFIX)argo-rollouts:$(IMAGE_TAG) ; fi
 
@@ -212,15 +220,19 @@ endif
 # https://www.jetbrains.com/help/go/attach-to-running-go-processes-with-debugger.html
 .PHONY: build-sample-metric-plugin-debug
 build-sample-metric-plugin-debug: ## build sample metric plugin with debug info
-	go build -gcflags="all=-N -l" -o metric-plugin test/cmd/metrics-plugin-sample/main.go
+	go build -gcflags="all=-N -l" -o plugin-bin/metric-plugin test/cmd/metrics-plugin-sample/main.go
 
 .PHONY: build-sample-traffic-plugin-debug
 build-sample-traffic-plugin-debug: ## build sample traffic plugin with debug info
-	go build -gcflags="all=-N -l" -o traffic-plugin test/cmd/trafficrouter-plugin-sample/main.go
+	go build -gcflags="all=-N -l" -o plugin-bin/traffic-plugin test/cmd/trafficrouter-plugin-sample/main.go
+
+.PHONY: build-sample-step-plugin-debug
+build-sample-step-plugin-debug: ## build sample traffic plugin with debug info
+	go build -gcflags="all=-N -l" -o plugin-bin/step-plugin test/cmd/step-plugin-sample/main.go
 
 .PHONY: plugin-image
 plugin-image: ## build plugin image
-	DOCKER_BUILDKIT=1 docker build --target kubectl-argo-rollouts -t $(IMAGE_PREFIX)kubectl-argo-rollouts:$(IMAGE_TAG) .
+	DOCKER_BUILDKIT=1 docker build --platform=$(TARGET_ARCH) --target kubectl-argo-rollouts -t $(IMAGE_PREFIX)kubectl-argo-rollouts:$(IMAGE_TAG) .
 	if [ "$(DOCKER_PUSH)" = "true" ] ; then docker push $(IMAGE_PREFIX)kubectl-argo-rollouts:$(IMAGE_TAG) ; fi
 
 ##@ Test
@@ -233,6 +245,12 @@ test: test-kustomize ## run all tests
 test-kustomize: ## run kustomize tests
 	./test/kustomize/test.sh
 
+setup-e2e:
+	@kubectl apply --context='${E2E_K8S_CONTEXT}' -f manifests/crds/rollout-crd.yaml
+	@kubectl apply --context='${E2E_K8S_CONTEXT}' -n argo-rollouts -f test/e2e/step-plugin/argo-rollouts-config.yaml
+	@rm -rf plugin-bin
+	@go build -gcflags="all=-N -l" -o plugin-bin/e2e-step-plugin test/cmd/step-plugin-e2e/main.go
+
 .PHONY: start-e2e
 start-e2e: ## start e2e test environment
 	mkdir -p coverage-output-e2e

diff --git a/docs/CONTRIBUTING.md b/docs/CONTRIBUTING.md
@@ -1,24 +1,27 @@
 # Contributing
+
 ## Before You Start
+
 Argo Rollouts is written in Golang. If you do not have a good grounding in Go, try out [the tutorial](https://tour.golang.org/).
 
 ## Pre-requisites
+
 Install:
 
-* [docker](https://docs.docker.com/install/#supported-platforms)
-* [golang](https://golang.org/)
-* [kubectl](https://kubernetes.io/docs/tasks/tools/#kubectl)
-* [kustomize](https://github.com/kubernetes-sigs/kustomize/releases) >= 4.5.5
-* [k3d](https://k3d.io/) recommended
+- [docker](https://docs.docker.com/install/#supported-platforms)
+- [golang](https://golang.org/)
+- [kubectl](https://kubernetes.io/docs/tasks/tools/#kubectl)
+- [kustomize](https://github.com/kubernetes-sigs/kustomize/releases) >= 4.5.5
+- [k3d](https://k3d.io/) recommended
 
 Kustomize is required for unit tests (`make test` is using it), so you [must install it](https://kubectl.docs.kubernetes.io/installation/kustomize/)
 locally if you wish to make code contributions to Argo Rollouts.
 
 Argo Rollout additionally uses the following tools
 
-* `golangci-lint` to lint the project.
-* `protoc` and `swagger-codegen` to generate proto related files
-* `yarn` to build the UI
+- `golangci-lint` to lint the project.
+- `protoc` and `swagger-codegen` to generate proto related files
+- `yarn` to build the UI
 
 Run the following commands to install them:
 
@@ -56,10 +59,9 @@ cd ~/go/src/github.com/argoproj/argo-rollouts
 
 The `make controller` command will build the controller.
 
-* `make install-tools-local` - Runs scripts to install codegen utility CLIs necessary for codegen.
-
-* `make codegen` - Runs the code generator that creates the informers, client, lister, and deepcopies from the types.go and modifies the open-api spec.
+- `make install-tools-local` - Runs scripts to install codegen utility CLIs necessary for codegen.
 
+- `make codegen` - Runs the code generator that creates the informers, client, lister, and deepcopies from the types.go and modifies the open-api spec.
 
 ## Running Controller Locally
 
@@ -83,11 +85,7 @@ make test
 ## Running E2E tests
 
 The end-to-end tests need to run against a kubernetes cluster with the Argo Rollouts controller
-running. The rollout controller can be started with the command:
-
-```
-make start-e2e
-```
+running.
 
 Start and prepare your cluster for e2e tests:
 
@@ -98,6 +96,12 @@ kubectl apply -k manifests/crds
 kubectl apply -f test/e2e/crds
 ```
 
+The rollout controller can be started with the command:
+
+```
+make start-e2e
+```
+
 Then run the e2e tests:
 
 ```
@@ -112,9 +116,10 @@ E2E_TEST_OPTIONS="-run 'TestCanarySuite' -testify.m 'TestCanaryScaleDownOnAbortN
 
 ## Running the UI
 
-If you'd like to run the UI locally, you first need a running Rollouts controller. This can be a locally running controller with a k3d cluster, as described above, or a controller running in a remote Kubernetes cluster. 
+If you'd like to run the UI locally, you first need a running Rollouts controller. This can be a locally running controller with a k3d cluster, as described above, or a controller running in a remote Kubernetes cluster.
 
 In order for the local React app to communicate with the controller and Kubernetes API, run the following to open a port forward to the dashboard:
+
 ```bash
 kubectl argo rollouts dashboard
 ```
@@ -127,6 +132,7 @@ make plugin
 ```
 
 In another terminal, run the following to start the UI:
+
 ```bash
 cd ui
 yarn install
@@ -142,11 +148,11 @@ that handle a specific aspect of Progressive Delivery.
 
 The controllers are:
 
-* [Rollout Controller](https://github.com/argoproj/argo-rollouts/blob/master/rollout/controller.go)
-* [Service Controller](https://github.com/argoproj/argo-rollouts/blob/master/service/service.go)
-* [Ingress Controller](https://github.com/argoproj/argo-rollouts/blob/master/ingress/ingress.go)
-* [Experiment Controller](https://github.com/argoproj/argo-rollouts/blob/master/experiments/controller.go)
-* [AnalysisRun Controller](https://github.com/argoproj/argo-rollouts/blob/master/analysis/controller.go)
+- [Rollout Controller](https://github.com/argoproj/argo-rollouts/blob/master/rollout/controller.go)
+- [Service Controller](https://github.com/argoproj/argo-rollouts/blob/master/service/service.go)
+- [Ingress Controller](https://github.com/argoproj/argo-rollouts/blob/master/ingress/ingress.go)
+- [Experiment Controller](https://github.com/argoproj/argo-rollouts/blob/master/experiments/controller.go)
+- [AnalysisRun Controller](https://github.com/argoproj/argo-rollouts/blob/master/analysis/controller.go)
 
 ### Tips
 
@@ -158,36 +164,35 @@ KUBECONFIG=~/.kube/minikube make test-e2e
 ```
 
 2. To run a specific e2e test, set the `E2E_TEST_OPTIONS` environment variable to specify the test
-(or test regex):
+   (or test regex):
 
 ```shell
 make test-e2e E2E_TEST_OPTIONS="-testify.m ^TestRolloutRestart$"
 ```
 
 3. The e2e tests are designed to run as quickly as possible, eliminating readiness and termination
-delays. However, it is often desired to artificially slow down the tests for debugging purposes,
-as well as to understand what the test is doing. To delay startup and termination of pods, set the
-`E2E_POD_DELAY` to an integer value in seconds. This environment variable is often coupled with
-`E2E_TEST_OPTIONS` to debug and slow down a specific test.
+   delays. However, it is often desired to artificially slow down the tests for debugging purposes,
+   as well as to understand what the test is doing. To delay startup and termination of pods, set the
+   `E2E_POD_DELAY` to an integer value in seconds. This environment variable is often coupled with
+   `E2E_TEST_OPTIONS` to debug and slow down a specific test.
 
 ```shell
 make test-e2e E2E_POD_DELAY=10
 ```
 
 4. Increasing the timeout. The E2E tests time out waiting on conditions to be met within 60 seconds.
-If debugging the rollout controller, it may be useful to increase this timeout while say sitting
-at a debugger breakpoint:
+   If debugging the rollout controller, it may be useful to increase this timeout while say sitting
+   at a debugger breakpoint:
 
 ```shell
 make test-e2e E2E_WAIT_TIMEOUT=999999
 ```
 
-
 5. The e2e tests leverage a feature of the controller allowing the controller to be sharded with
-a user-specific "instance id" label. This allows the tests to operate only on rollouts with the
-specified label, and prevents any other controllers (including the system rollout controller),
-from also operating on the same set of rollouts. This value can be changed (from the default of
-`argo-rollouts-e2e`), using the `E2E_INSTANCE_ID` environment variable:
+   a user-specific "instance id" label. This allows the tests to operate only on rollouts with the
+   specified label, and prevents any other controllers (including the system rollout controller),
+   from also operating on the same set of rollouts. This value can be changed (from the default of
+   `argo-rollouts-e2e`), using the `E2E_INSTANCE_ID` environment variable:
 
 ```shell
 make start-e2e E2E_INSTANCE_ID=foo
@@ -200,7 +205,6 @@ Alternatively, the e2e tests can be run against the system controller (i.e. with
 make start-e2e E2E_INSTANCE_ID=''
 ```
 
-
 6. Working on CRDs? While editing them directly works when you are finding the shape of things you want, the final CRDs are autogenerated. Make sure to regenerate them by running `make gen-crd` before submitting PRs. They are controlled by the relevant annotations in the types file:
 
 eg: Analysis Templates are controlled by annotations in `pkg/apis/rollouts/v1alpha1/analysis_types.go`.
@@ -242,14 +246,16 @@ kubectl -n argo-rollouts apply -f manifests/install.yaml
 ```
 
 ## Upgrading Kubernetes Libraries
+
 Argo Rollouts has a dependency on the kubernetes/kubernetes repo for some of the functionality that has not been
 pushed into the other kubernetes repositories yet. In order to import the kubernetes/kubernetes repo, all of the
 associated repos have to pinned to the correct version specified by the kubernetes/kubernetes release. The
 `./hack/update-k8s-dependencies.sh` updates all the dependencies to the those correct versions.
 
 ## Upgrading Notifications Engine
-Argo Rollouts has a dependency on the [argoproj/notifications-engines](https://github.com/argoproj/notifications-engine) repo 
-for the notifications functionality and related documentation. 
+
+Argo Rollouts has a dependency on the [argoproj/notifications-engines](https://github.com/argoproj/notifications-engine) repo
+for the notifications functionality and related documentation.
 
 This is updated by upgrading the Go library in `go.mod` by running the commands:
 

diff --git a/go.mod b/go.mod
@@ -19,6 +19,7 @@ require (
 	github.com/gogo/protobuf v1.3.2
 	github.com/golang/mock v1.6.0
 	github.com/golang/protobuf v1.5.4
+	github.com/google/uuid v1.6.0
 	github.com/grpc-ecosystem/grpc-gateway v1.16.0
 	github.com/hashicorp/go-plugin v1.6.1
 	github.com/influxdata/influxdb-client-go/v2 v2.13.0
@@ -128,7 +129,6 @@ require (
 	github.com/google/gofuzz v1.2.0 // indirect
 	github.com/google/s2a-go v0.1.7 // indirect
 	github.com/google/shlex v0.0.0-20191202100458-e7afc7fbc510 // indirect
-	github.com/google/uuid v1.6.0 // indirect
 	github.com/googleapis/enterprise-certificate-proxy v0.3.2 // indirect
 	github.com/googleapis/gax-go/v2 v2.12.0 // indirect
 	github.com/gorilla/websocket v1.5.0 // indirect

diff --git a/hack/update-mocks.sh b/hack/update-mocks.sh
@@ -21,3 +21,13 @@ mockery \
     --dir "${PROJECT_ROOT}"/rollout/trafficrouting \
     --name TrafficRoutingReconciler \
     --output "${PROJECT_ROOT}"/rollout/mocks
+
+mockery \
+    --dir "${PROJECT_ROOT}"/rollout/steps/plugin \
+    --name "Resolver|StepPlugin" \
+    --output "${PROJECT_ROOT}"/rollout/steps/plugin/mocks
+
+mockery \
+    --dir "${PROJECT_ROOT}"/rollout/steps/plugin/rpc \
+    --name "StepPlugin" \
+    --output "${PROJECT_ROOT}"/rollout/steps/plugin/rpc/mocks
diff --git a/manifests/crds/rollout-crd.yaml b/manifests/crds/rollout-crd.yaml
@@ -662,6 +662,16 @@ spec:
                                   - type: string
                                   x-kubernetes-int-or-string: true
                               type: object
+                            plugin:
+                              properties:
+                                config:
+                                  type: object
+                                  x-kubernetes-preserve-unknown-fields: true
+                                name:
+                                  type: string
+                              required:
+                              - name
+                              type: object
                             setCanaryScale:
                               properties:
                                 matchTrafficWeight:
@@ -3721,6 +3731,45 @@ spec:
                     type: object
                   stablePingPong:
                     type: string
+                  stepPluginStatuses:
+                    items:
+                      properties:
+                        backoff:
+                          type: string
+                        disabled:
+                          type: boolean
+                        executions:
+                          format: int32
+                          type: integer
+                        finishedAt:
+                          format: date-time
+                          type: string
+                        index:
+                          format: int32
+                          type: integer
+                        message:
+                          type: string
+                        name:
+                          type: string
+                        operation:
+                          type: string
+                        phase:
+                          type: string
+                        startedAt:
+                          format: date-time
+                          type: string
+                        status:
+                          type: object
+                          x-kubernetes-preserve-unknown-fields: true
+                        updatedAt:
+                          format: date-time
+                          type: string
+                      required:
+                      - index
+                      - name
+                      - operation
+                      type: object
+                    type: array
                   weights:
                     properties:
                       additional: