Merge pull request #1 from BaguaSys/preonline

feat: bagua operator

.dockerignore

@@ -0,0 +1,5 @@
+# More info: https://docs.docker.com/engine/reference/builder/#dockerignore-file
+# Ignore all files which are not go type
+!**/*.go
+!**/*.mod
+!**/*.sum

.gitignore

@@ -13,3 +13,6 @@
 
 # Dependency directories (remove the comment below to include it)
 # vendor/
+.DS_Store
+.idea/
+bin/manager

Dockerfile

@@ -0,0 +1,25 @@
+# Build the manager binary
+FROM golang:1.15 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 the go source
+COPY ./ ./
+
+# Build
+RUN CGO_ENABLED=0 GOOS=linux GOARCH=amd64 GO111MODULE=on go build -a -o manager main.go
+
+# Use distroless as minimal base image to package the manager binary
+# Refer to https://github.com/GoogleContainerTools/distroless for more details
+FROM gcr.io/distroless/static:nonroot
+ARG HOME=/home/work
+WORKDIR ${HOME}
+COPY --from=builder /workspace/manager ${HOME}
+
+CMD [".manager"]

Makefile

@@ -0,0 +1,194 @@
+# VERSION defines the project version for the bundle.
+# Update this value when you upgrade the version of your project.
+# To re-generate a bundle for another specific version without changing the standard setup, you can:
+# - use the VERSION as arg of the bundle target (e.g make bundle VERSION=0.0.2)
+# - use environment variables to overwrite this value (e.g export VERSION=0.0.2)
+VERSION ?= 0.0.1
+
+# CHANNELS define the bundle channels used in the bundle.
+# Add a new line here if you would like to change its default config. (E.g CHANNELS = "preview,fast,stable")
+# To re-generate a bundle for other specific channels without changing the standard setup, you can:
+# - use the CHANNELS as arg of the bundle target (e.g make bundle CHANNELS=preview,fast,stable)
+# - use environment variables to overwrite this value (e.g export CHANNELS="preview,fast,stable")
+ifneq ($(origin CHANNELS), undefined)
+BUNDLE_CHANNELS := --channels=$(CHANNELS)
+endif
+
+# DEFAULT_CHANNEL defines the default channel used in the bundle.
+# Add a new line here if you would like to change its default config. (E.g DEFAULT_CHANNEL = "stable")
+# To re-generate a bundle for any other default channel without changing the default setup, you can:
+# - use the DEFAULT_CHANNEL as arg of the bundle target (e.g make bundle DEFAULT_CHANNEL=stable)
+# - use environment variables to overwrite this value (e.g export DEFAULT_CHANNEL="stable")
+ifneq ($(origin DEFAULT_CHANNEL), undefined)
+BUNDLE_DEFAULT_CHANNEL := --default-channel=$(DEFAULT_CHANNEL)
+endif
+BUNDLE_METADATA_OPTS ?= $(BUNDLE_CHANNELS) $(BUNDLE_DEFAULT_CHANNEL)
+
+# IMAGE_TAG_BASE defines the docker.io namespace and part of the image name for remote images.
+# This variable is used to construct full image tags for bundle and catalog images.
+#
+# For example, running 'make bundle-build bundle-push catalog-build catalog-push' will build and push both
+# kuaishou.com/operator-bundle:$VERSION and kuaishou.com/operator-catalog:$VERSION.
+IMAGE_TAG_BASE ?= kuaishou.com/operator
+
+# BUNDLE_IMG defines the image:tag used for the bundle.
+# You can use it as an arg. (E.g make bundle-build BUNDLE_IMG=<some-registry>/<project-name-bundle>:<tag>)
+BUNDLE_IMG ?= $(IMAGE_TAG_BASE)-bundle:v$(VERSION)
+
+# Image URL to use all building/pushing image targets
+IMG ?= baguasys/operator:latest
+# Produce CRDs that work back to Kubernetes 1.11 (no version conversion)
+CRD_OPTIONS ?= "crd:trivialVersions=true,crdVersions=v1beta1,preserveUnknownFields=true"
+
+# Get the currently used golang install path (in GOPATH/bin, unless GOBIN is set)
+ifeq (,$(shell go env GOBIN))
+GOBIN=$(shell go env GOPATH)/bin
+else
+GOBIN=$(shell go env GOBIN)
+endif
+
+all: build
+
+##@ General
+
+# The help target prints out all targets with their descriptions organized
+# beneath their categories. The categories are represented by '##@' and the
+# target descriptions by '##'. The awk commands is responsible for reading the
+# entire set of makefiles included in this invocation, looking for lines of the
+# file as xyz: ## something, and then pretty-format the target and help. Then,
+# if there's a line with ##@ something, that gets pretty-printed as a category.
+# More info on the usage of ANSI control characters for terminal formatting:
+# https://en.wikipedia.org/wiki/ANSI_escape_code#SGR_parameters
+# More info on the awk command:
+# http://linuxcommand.org/lc3_adv_awk.php
+
+help: ## Display this help.
+	@awk 'BEGIN {FS = ":.*##"; printf "\nUsage:\n  make \033[36m<target>\033[0m\n"} /^[a-zA-Z_0-9-]+:.*?##/ { printf "  \033[36m%-15s\033[0m %s\n", $$1, $$2 } /^##@/ { printf "\n\033[1m%s\033[0m\n", substr($$0, 5) } ' $(MAKEFILE_LIST)
+
+##@ Development
+
+manifests: controller-gen ## Generate WebhookConfiguration, ClusterRole and CustomResourceDefinition objects.
+	$(CONTROLLER_GEN) $(CRD_OPTIONS) rbac:roleName=manager-role webhook paths="./..." output:crd:artifacts:config=config/crd/bases
+
+generate: controller-gen ## Generate code containing DeepCopy, DeepCopyInto, and DeepCopyObject method implementations.
+	$(CONTROLLER_GEN) object:headerFile="hack/boilerplate.go.txt" paths="./..."
+
+fmt: ## Run go fmt against code.
+	go fmt ./...
+
+vet: ## Run go vet against code.
+	go vet ./...
+
+ENVTEST_ASSETS_DIR=$(shell pwd)/testbin
+test: manifests generate fmt vet ## Run tests.
+	mkdir -p ${ENVTEST_ASSETS_DIR}
+	test -f ${ENVTEST_ASSETS_DIR}/setup-envtest.sh || curl -sSLo ${ENVTEST_ASSETS_DIR}/setup-envtest.sh https://raw.githubusercontent.com/kubernetes-sigs/controller-runtime/v0.7.2/hack/setup-envtest.sh
+	source ${ENVTEST_ASSETS_DIR}/setup-envtest.sh; fetch_envtest_tools $(ENVTEST_ASSETS_DIR); setup_envtest_env $(ENVTEST_ASSETS_DIR); go test ./... -coverprofile cover.out
+
+##@ Build
+
+build: generate fmt vet ## Build manager binary.
+	go build -o bin/manager main.go
+
+run: manifests generate fmt vet ## Run a controller from your host.
+	go run ./main.go
+
+docker-build: test ## Build docker image with the manager.
+	docker build -t ${IMG} .
+
+docker-push: ## Push docker image with the manager.
+	docker push ${IMG}
+
+##@ Deployment
+
+install: manifests kustomize ## Install CRDs into the K8s cluster specified in ~/.kube/config.
+	$(KUSTOMIZE) build config/crd | kubectl apply -f -
+
+uninstall: manifests kustomize ## Uninstall CRDs from the K8s cluster specified in ~/.kube/config.
+	$(KUSTOMIZE) build config/crd | kubectl delete -f -
+
+deploy: manifests kustomize ## Deploy controller to the K8s cluster specified in ~/.kube/config.
+	cd config/manager && $(KUSTOMIZE) edit set image controller=${IMG}
+	$(KUSTOMIZE) build config/default | kubectl apply -f -
+
+undeploy: ## Undeploy controller from the K8s cluster specified in ~/.kube/config.
+	$(KUSTOMIZE) build config/default | kubectl delete -f -
+
+
+CONTROLLER_GEN = $(shell pwd)/bin/controller-gen
+controller-gen: ## Download controller-gen locally if necessary.
+	$(call go-get-tool,$(CONTROLLER_GEN),sigs.k8s.io/controller-tools/cmd/controller-gen@v0.4.1)
+
+KUSTOMIZE = $(shell pwd)/bin/kustomize
+kustomize: ## Download kustomize locally if necessary.
+	$(call go-get-tool,$(KUSTOMIZE),sigs.k8s.io/kustomize/kustomize/v3@v3.8.7)
+
+# go-get-tool will 'go get' any package $2 and install it to $1.
+PROJECT_DIR := $(shell dirname $(abspath $(lastword $(MAKEFILE_LIST))))
+define go-get-tool
+@[ -f $(1) ] || { \
+set -e ;\
+TMP_DIR=$$(mktemp -d) ;\
+cd $$TMP_DIR ;\
+go mod init tmp ;\
+echo "Downloading $(2)" ;\
+GOBIN=$(PROJECT_DIR)/bin go get $(2) ;\
+rm -rf $$TMP_DIR ;\
+}
+endef
+
+.PHONY: bundle
+bundle: manifests kustomize ## Generate bundle manifests and metadata, then validate generated files.
+	operator-sdk generate kustomize manifests -q
+	cd config/manager && $(KUSTOMIZE) edit set image controller=$(IMG)
+	$(KUSTOMIZE) build config/manifests | operator-sdk generate bundle -q --overwrite --version $(VERSION) $(BUNDLE_METADATA_OPTS)
+	operator-sdk bundle validate ./bundle
+
+.PHONY: bundle-build
+bundle-build: ## Build the bundle image.
+	docker build -f bundle.Dockerfile -t $(BUNDLE_IMG) .
+
+.PHONY: bundle-push
+bundle-push: ## Push the bundle image.
+	$(MAKE) docker-push IMG=$(BUNDLE_IMG)
+
+.PHONY: opm
+OPM = ./bin/opm
+opm: ## Download opm locally if necessary.
+ifeq (,$(wildcard $(OPM)))
+ifeq (,$(shell which opm 2>/dev/null))
+	@{ \
+	set -e ;\
+	mkdir -p $(dir $(OPM)) ;\
+	OS=$(shell go env GOOS) && ARCH=$(shell go env GOARCH) && \
+	curl -sSLo $(OPM) https://github.com/operator-framework/operator-registry/releases/download/v1.15.1/$${OS}-$${ARCH}-opm ;\
+	chmod +x $(OPM) ;\
+	}
+else
+OPM = $(shell which opm)
+endif
+endif
+
+# A comma-separated list of bundle images (e.g. make catalog-build BUNDLE_IMGS=example.com/operator-bundle:v0.1.0,example.com/operator-bundle:v0.2.0).
+# These images MUST exist in a registry and be pull-able.
+BUNDLE_IMGS ?= $(BUNDLE_IMG)
+
+# The image tag given to the resulting catalog image (e.g. make catalog-build CATALOG_IMG=example.com/operator-catalog:v0.2.0).
+CATALOG_IMG ?= $(IMAGE_TAG_BASE)-catalog:v$(VERSION)
+
+# Set CATALOG_BASE_IMG to an existing catalog image tag to add $BUNDLE_IMGS to that image.
+ifneq ($(origin CATALOG_BASE_IMG), undefined)
+FROM_INDEX_OPT := --from-index $(CATALOG_BASE_IMG)
+endif
+
+# Build a catalog image by adding bundle images to an empty catalog using the operator package manager tool, 'opm'.
+# This recipe invokes 'opm' in 'semver' bundle add mode. For more information on add modes, see:
+# https://github.com/operator-framework/community-operators/blob/7f1438c/docs/packaging-operator.md#updating-your-existing-operator
+.PHONY: catalog-build
+catalog-build: opm ## Build a catalog image.
+	$(OPM) index add --container-tool docker --mode semver --tag $(CATALOG_IMG) --bundles $(BUNDLE_IMGS) $(FROM_INDEX_OPT)
+
+# Push the catalog image.
+.PHONY: catalog-push
+catalog-push: ## Push a catalog image.
+	$(MAKE) docker-push IMG=$(CATALOG_IMG)

PROJECT

@@ -0,0 +1,19 @@
+domain: kuaishou.com
+layout:
+- go.kubebuilder.io/v3
+plugins:
+  manifests.sdk.operatorframework.io/v2: {}
+  scorecard.sdk.operatorframework.io/v2: {}
+projectName: operator
+repo: github.com/BaguaSys/operator
+resources:
+- api:
+    crdVersion: v1
+    namespaced: true
+  controller: true
+  domain: kuaishou.com
+  group: bagua
+  kind: Bagua
+  path: github.com/BaguaSys/operator/api/v1alpha1
+  version: v1alpha1
+version: "3"

README.md

@@ -1,2 +1,63 @@
-# operator
-Kubernetes operator for Bagua distributed training job.
+# Kubernetes operator for Bagua jobs
+
+This repository implements a kubernetes operator for Bagua distributed training job which supports static and elastic workloads. See [CRD definition](https://github.com/BaguaSys/operator/blob/preonline/config/crd/bases/bagua.kuaishou.com_baguas.yaml).
+
+### Prerequisites
+- Kubernetes
+- kubectl
+
+
+### Installation
+#### Run the operator locally
+```shell
+
+git clone https://github.com/BaguaSys/operator.git
+cd operator
+
+# install crd
+kubectl apply -f config/crd/bases/bagua.kuaishou.com_baguas.yaml
+
+go run ./main.go
+```
+#### Deploy the operator
+Install Bagua on an existing Kubernetes cluster.
+```shell
+kubectl apply -f https://raw.githubusercontent.com/BaguaSys/operator/master/deploy/deployment.yaml
+```
+Enjoy! Bagua will create resources in namespace `bagua`.
+
+
+### Examples
+You can get demos in `config/samples`, and run as follows,
+- static mode
+```shell
+
+kubectl apply -f config/samples/bagua_v1alpha1_bagua_static.yaml
+```
+Verify pods are running
+```yaml
+
+kubectl get pods
+
+NAME                           READY   STATUS    RESTARTS   AGE
+bagua-sample-static-master-0   1/1     Running   0          45s
+bagua-sample-static-worker-0   1/1     Running   0          45s
+bagua-sample-static-worker-1   1/1     Running   0          45s
+```
+
+- elastic mode
+```shell
+
+kubectl apply -f config/samples/bagua_v1alpha1_bagua_elastic.yaml
+```
+Verify pods are running
+```yaml
+
+kubectl get pods
+
+NAME                            READY   STATUS    RESTARTS   AGE
+bagua-sample-elastic-etcd-0     1/1     Running   0          63s
+bagua-sample-elastic-worker-0   1/1     Running   0          63s
+bagua-sample-elastic-worker-1   1/1     Running   0          63s
+bagua-sample-elastic-worker-2   1/1     Running   0          63s
+```