add dockerfile and makefile

Signed-off-by: KunWuLuan <[email protected]>

Author: KunWuLuan

go.work

@@ -0,0 +1,3 @@
+go 1.25.1
+
+use ./historyserver

go.work.sum

@@ -0,0 +1,34 @@
+github.com/armon/go-socks5 v0.0.0-20160902184237-e75332964ef5/go.mod h1:wHh0iHkYZB8zMSxRWpUBQtwG5a7fFgvEO+odwuTv2gs=
+github.com/fxamacker/cbor/v2 v2.9.0/go.mod h1:vM4b+DJCtHn+zz7h3FFp/hDAI9WNWCsZj23V5ytsSxQ=
+github.com/go-logr/logr v1.4.2/go.mod h1:9T104GzyrTigFIr8wt5mBrctHMim0Nb2HLGrmQ40KvY=
+github.com/go-openapi/jsonpointer v0.21.0/go.mod h1:IUyH9l/+uyhIYQ/PXVA41Rexl+kOkAPDdXEYns6fzUY=
+github.com/go-openapi/jsonreference v0.20.2/go.mod h1:Bl1zwGIM8/wsvqjsOQLJ/SH+En5Ap4rVB5KVcIDZG2k=
+github.com/go-openapi/swag v0.23.0/go.mod h1:esZ8ITTYEsH1V2trKHjAN8Ai7xHb8RV+YSZ577vPjgQ=
+github.com/gogo/protobuf v1.3.2/go.mod h1:P1XiOD3dCwIKUDQYPy72D8LYyHL2YPYrpS2s69NZV8Q=
+github.com/google/gnostic-models v0.7.0/go.mod h1:whL5G0m6dmc5cPxKc5bdKdEN3UjI7OUGxBlw57miDrQ=
+github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU=
+github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
+github.com/josharian/intern v1.0.0/go.mod h1:5DoeVV0s6jJacbCEi61lwdGj/aVlrQvzHFFd8Hwg//Y=
+github.com/mailru/easyjson v0.7.7/go.mod h1:xzfreul335JAWq5oZzymOObrkdz5UnU4kGfJJLY9Nlc=
+github.com/moby/spdystream v0.5.0/go.mod h1:xBAYlnt/ay+11ShkdFKNAG7LsyK/tmNBVvVOwrfMgdI=
+github.com/mxk/go-flowrate v0.0.0-20140419014527-cca7078d478f/go.mod h1:ZdcZmHo+o7JKHSa8/e818NopupXU1YMK5fe1lsApnBw=
+github.com/onsi/ginkgo/v2 v2.21.0/go.mod h1:7Du3c42kxCUegi0IImZ1wUQzMBVecgIHjR1C+NkhLQo=
+github.com/onsi/gomega v1.35.1/go.mod h1:PvZbdDc8J6XJEpDK4HCuRBm8a6Fzp9/DmhC9C7yFlog=
+github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
+github.com/rogpeppe/go-internal v1.13.1/go.mod h1:uMEvuHeurkdAXX61udpOXGD/AzZDWNMNyH2VO9fmH0o=
+github.com/spf13/pflag v1.0.6/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=
+github.com/x448/float16 v0.8.4/go.mod h1:14CWIYCyZA/cWjXOioeEpHeN/83MdbZDRQHoFcYsOfg=
+go.yaml.in/yaml/v2 v2.4.2/go.mod h1:081UH+NErpNdqlCXm3TtEran0rJZGxAYx9hb/ELlsPU=
+go.yaml.in/yaml/v3 v3.0.4/go.mod h1:DhzuOOF2ATzADvBadXxruRBLzYTpT36CKvDb3+aBEFg=
+golang.org/x/crypto v0.36.0/go.mod h1:Y4J0ReaxCR1IMaabaSMugxJES1EpwhBHhv2bDHklZvc=
+golang.org/x/term v0.30.0/go.mod h1:NYYFdzHoI5wRh/h5tDMdMqCqPJZEuNqVR5xJLd/n67g=
+golang.org/x/text v0.23.0/go.mod h1:/BLNzu4aZCJ1+kcD0DNRotWKage4q2rGVAg4o22unh4=
+google.golang.org/protobuf v1.36.5/go.mod h1:9fA7Ob0pmnwhb644+1+CVWFRbNajQ6iRojtC/QF5bRE=
+gopkg.in/evanphx/json-patch.v4 v4.12.0/go.mod h1:p8EYWUEYMpynmqDbY58zCKCFZw8pRWMG4EsWvDvM72M=
+gopkg.in/inf.v0 v0.9.1/go.mod h1:cWUDdTG/fYaXco+Dcufb5Vnc6Gp2YChqWtbxRZE0mXw=
+k8s.io/klog/v2 v2.130.1/go.mod h1:3Jpz1GvMt720eyJH1ckRHK1EDfpxISzJ7I9OYgaDtPE=
+k8s.io/kube-openapi v0.0.0-20250710124328-f3f2b991d03b/go.mod h1:UZ2yyWbFTpuhSbFhv24aGNOdoRdJZgsIObGBUaYVsts=
+sigs.k8s.io/json v0.0.0-20241014173422-cfa47c3a1cc8/go.mod h1:mdzfpAEoE6DHQEN0uh9ZbOCuHbLK5wOm7dK4ctXE9Tg=
+sigs.k8s.io/randfill v1.0.0/go.mod h1:XeLlZ/jmk4i1HRopwe7/aU3H5n1zNUcX6TM94b3QxOY=
+sigs.k8s.io/structured-merge-diff/v6 v6.3.0/go.mod h1:M3W8sfWvn2HhQDIbGWj3S099YozAsymCo/wrT5ohRUE=
+sigs.k8s.io/yaml v1.6.0/go.mod h1:796bPqUfzR/0jLAl6XjHl3Ck7MiyVv8dbTdyT3/pMf4=

historyserver/Dockerfile

@@ -0,0 +1,32 @@
+ARG TARGETOS
+ARG TARGETARCH
+
+FROM --platform=$BUILDPLATFORM golang:1.25.1 as builder
+ENV GOPROXY=https://goproxy.cn,direct
+ARG BUILD_RAYSERVER_DASHBOARD 
+
+RUN if [ "$BUILD_RAYSERVER_DASHBOARD" = "yes" ] ; then \
+ curl -o install.sh https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh && chmod +x install.sh && ./install.sh && /bin/bash -c "source $HOME/.nvm/nvm.sh && nvm install 14 && nvm use 14" ;\
+else \
+ echo "$BUILD_RAYSERVER_DASHBOARD not yes, no need install nvm"; \
+fi
+
+WORKDIR /historyserver
+COPY . .
+
+RUN if [ "$BUILD_RAYSERVER_DASHBOARD" = "yes" ] ; then \
+ /bin/bash -c "source $HOME/.nvm/nvm.sh && cd dashboard/ray/client && npm ci && npm run build" ;\
+else \
+ mkdir -p dashboard/ray/client/build ;\
+ echo "do not npm run build"; \
+fi
+
+RUN make build GOOS=${TARGETOS} GOARCH=${TARGETARCH}
+
+FROM ubuntu:22.04
+
+RUN apt-get update && apt-get upgrade -y && rm -rf /var/cache/apt/ && apt-get install -y ca-certificates
+
+COPY --from=builder /historyserver/output/bin/historyserver /usr/local/bin/historyserver
+COPY --from=builder /historyserver/output/bin/collector /usr/local/bin/collector
+COPY --from=builder /historyserver/dashboard/ray/client/build /dashboard/ray/build

historyserver/Makefile

@@ -0,0 +1,140 @@
+# Image URL to use all building/pushing image targets
+GOLANGCILINT_VERSION ?= v1.59.0
+GOBIN := $(shell go env GOPATH)/bin
+GOBIN_GOLANGCILINT := $(GOBIN)/golangci-lint
+
+DOCKERBUILDER_INSTANCE=historyserver
+OUT_DIR=output
+BIN_DIR=$(OUT_DIR)/bin
+BINARY_NAME=historyserver
+BINARY_NAME_COLLECTOR=collector
+
+# Setting SHELL to bash allows bash commands to be executed by recipes.
+# Options are set to exit when a recipe line exits non-zero or a piped command fails.
+SHELL = /usr/bin/env bash -o pipefail
+BUILD_TIMESTAMP = $(shell date -u +"%Y-%m-%dT%H:%M:%SZ")
+COMMIT_SHORT ?= $(shell git rev-parse --short HEAD)
+BRANCH ?= $(shell git branch --show-current)
+VERSION ?= $(shell git describe --tags --long|awk -F '-' '{print $$1"."$$2"-"$$3""}')
+
+PACKAGE = gitlab.alibaba-inc.com/eml/historyserver
+
+GO_LDFLAGS := -extldflags "-static"
+# GO_LDFLAGS += -w -s # Drop debugging symbols.
+GO_LDFLAGS += -X $(PACKAGE)/pkg.Version=$(VERSION) \
+	-X $(PACKAGE)/pkg.CommitID=$(COMMIT_SHORT) \
+	-X $(PACKAGE)/pkg.BuildDate=$(BUILD_TIMESTAMP) \
+	-X $(PACKAGE)/pkg.Branch=$(BRANCH)
+GO_BUILD_FLAGS := -ldflags '$(GO_LDFLAGS)'
+
+GOOS ?= darwin
+GOARCH ?= amd64
+
+.PHONY: all
+
+all: build
+
+.PHONY: clean
+clean:
+	rm -rf $(OUT_DIR)
+
+.PHONY: build
+build: buildcollector buildhistoryserver
+
+.PHONY: buildcollector
+#build: mod alllint test
+buildcollector: mod
+	@echo ""
+	@echo "go build ..."
+	CGO_ENABLED=0 GOOS=$(GOOS) GOARCH=$(GOARCH) go build -v $(GO_BUILD_FLAGS) -o $(BIN_DIR)/$(BINARY_NAME_COLLECTOR) ./cmd/collector/main.go
+
+.PHONY: buildhistoryserver
+#build: mod alllint test
+buildhistoryserver: mod
+	@echo ""
+	@echo "go build ..."
+	CGO_ENABLED=0 GOOS=$(GOOS) GOARCH=$(GOARCH) go build -v $(GO_BUILD_FLAGS) -o $(BIN_DIR)/$(BINARY_NAME) ./cmd/historyserver/main.go
+
+.PHONY: simplebuild
+simplebuild:
+	@echo ""
+	@echo "go build ..."
+	CGO_ENABLED=0 GOOS=$(GOOS) GOARCH=$(GOARCH) go build -v $(GO_BUILD_FLAGS)  -o $(BIN_DIR)/$(BINARY_NAME)
+
+.PHONY: mod
+mod:
+	go mod tidy
+
+.PHONY: localimage
+localimage: dockerbuilder_instance
+	docker buildx build -t historyserver:laster --platform linux/amd64 . --load
+
+.PHONY: dockerbuilder_instance
+dockerbuilder_instance:
+	@docker buildx use $(DOCKERBUILDER_INSTANCE) || docker buildx create --name $(DOCKERBUILDER_INSTANCE)
+	docker buildx use $(DOCKERBUILDER_INSTANCE)
+
+# Run tests
+.PHONY: test
+test:
+	go test -v ./pkg/... ./cmd/...
+
+.PHONY: alllint
+alllint: todolist issuelint ## Run go lint against code.
+
+.PHONY: issuelint
+issuelint: install-golint
+	@echo ""
+	@echo "-------------------- show issues info, if has issuse, return error --------------------"
+	$(GOBIN_GOLANGCILINT) run -v --print-resources-usage -c .golangci.yaml
+
+.PHONY: todolist
+todolist: install-golint ## Run go lint against code.
+	@echo ""
+	@echo "-------------------- only show TODO list info --------------------"
+	$(GOBIN_GOLANGCILINT) run  --print-resources-usage -c .golangci.info.yaml --enable-only godox
+	@echo ""
+
+install-golint: ## check golint if not exist install golint tools
+ifneq ("$(wildcard $(GOBIN_GOLANGCILINT))","")
+ifeq ($(shell $(GOBIN_GOLANGCILINT) version --format short), $(GOLANGCILINT_VERSION))
+	@echo "golangci-lint version match"
+else
+	@echo "golangci-lint version do not match"
+	@{ \
+	set -e ;\
+	echo 'installing golangci-lint-$(GOLANGCILINT_VERSION)' ;\
+	go install github.com/golangci/golangci-lint/cmd/golangci-lint@$(GOLANGCILINT_VERSION) ;\
+	echo 'Successfully installed' ;\
+	}
+endif
+else
+	@echo "golangci-lint not exist"
+	@{ \
+	set -e ;\
+	echo 'installing golangci-lint-$(GOLANGCILINT_VERSION)' ;\
+	go install github.com/golangci/golangci-lint/cmd/golangci-lint@$(GOLANGCILINT_VERSION) ;\
+	echo 'Successfully installed' ;\
+	}
+endif
+
+
+
+# Generate manifests e.g. CRD, RBAC etc.
+#manifests: controller-gen
+#	$(CONTROLLER_GEN) $(CRD_OPTIONS) rbac:roleName=manager-role webhook paths="./..." output:crd:artifacts:config=config/crd/bases
+
+# Generate code
+#generate: controller-gen
+#	$(CONTROLLER_GEN) object:headerFile=./hack/boilerplate.go.txt paths=./api/...
+
+
+# find or download controller-gen
+# download controller-gen if necessary
+#controller-gen:
+#ifeq (, $(shell which controller-gen))
+#	go get sigs.k8s.io/controller-tools/cmd/[email protected]
+#CONTROLLER_GEN=$(shell go env GOPATH)/bin/controller-gen
+#else
+#CONTROLLER_GEN=$(shell which controller-gen)
+#endif

historyserver/backend/collector/runtime/logcollector/collector.go

@@ -14,6 +14,7 @@ import (
 	"github.com/fsnotify/fsnotify"
 	"github.com/hpcloud/tail"
 	"github.com/ray-project/kuberay/historyserver/backend/collector/storage"
+	"github.com/ray-project/kuberay/historyserver/utils"
 	"github.com/sirupsen/logrus"
 )
 
@@ -29,6 +30,7 @@ type RayLogHandler struct {
 
 	RayClusterName string
 	RayClusterID   string
+	RayNodeName    string
 
 	LogBatching  int
 	PushInterval time.Duration
@@ -80,16 +82,16 @@ func (r *RayLogHandler) PushLog(absoluteLogPathName string) error {
 	// subdir events/aa/
 	// filename a.txt
 	subdir, filename := filepath.Split(relativePath)
-
+	logDir := utils.GetLogDir(r.RootDir, r.RayClusterName, r.RayClusterID, r.RayNodeName)
 	if len(subdir) != 0 {
-		dirName := path.Join(r.RootDir, subdir)
+		dirName := path.Join(logDir, subdir)
 		if err := r.Writter.CreateDirectory(dirName); err != nil {
 			logrus.Errorf("Failed to create directory '%s': %v", dirName, err)
 			return err
 		}
 	}
 
-	objectName := path.Join(r.RootDir, subdir, filename)
+	objectName := path.Join(logDir, subdir, filename)
 	logrus.Infof("Begin to create and append oss object %s by absoluteLogPathName %s, oss subdir [%s] filename [%s] relativePath[%s]",
 		objectName, absoluteLogPathName, subdir, filename, relativePath)
 

historyserver/backend/collector/runtime/logcollector/meta.go

@@ -41,7 +41,7 @@ func (r *RayLogHandler) PersistMetaLoop(stop chan struct{}) {
 		logrus.Errorf("Build cluster meta information error %v", err)
 		return
 	}
-	fileName := path.Clean(clistDir + "/" + r.RayClusterName + "_" + r.RayClusterID + "_" + path.Base(r.SessionDir) + "_" + fmt.Sprintf("%v", timestamp))
+	fileName := path.Clean(clistDir + "/" + r.RayClusterName + "#" + r.RayClusterID + "#" + path.Base(r.SessionDir) + "#" + fmt.Sprintf("%v", timestamp))
 	if err := r.Writter.WriteFile(fileName, bytes.NewReader(data)); err != nil {
 		logrus.Errorf("CreateObjectIfNotExist %s error %v", fileName, err)
 		return

historyserver/backend/collector/runtime/logcollector/util.go

@@ -33,11 +33,6 @@ type JobUrlInfo struct {
 }
 
 var metaCommonUrlInfo = []*UrlInfo{
-	&UrlInfo{
-		Key:  utils.OssMetaFile_ClusterSessionName,
-		Path: "/tmp/ray/session_[1-9].*",
-		Type: MetaTypeFileNames,
-	},
 	&UrlInfo{
 		Key:  utils.OssMetaFile_ClusterStatus,
 		Url:  "http://localhost:8265/api/cluster_status?format=1",

historyserver/backend/collector/runtime/runtime.go

@@ -4,22 +4,26 @@ import (
 	"fmt"
 	"net/http"
 	"path"
+	"strings"
 	"time"
 
 	"github.com/ray-project/kuberay/historyserver/backend/collector/runtime/logcollector"
 	"github.com/ray-project/kuberay/historyserver/backend/collector/storage"
 	"github.com/ray-project/kuberay/historyserver/backend/types"
+	"github.com/ray-project/kuberay/historyserver/utils"
 )
 
 func NewCollector(config *types.RayCollectorConfig, writter storage.StorageWritter) RayLogCollector {
 	handler := logcollector.RayLogHandler{
-		LogFiles: make(chan string),
+		EnableMeta: config.Role == "Head",
+		LogFiles:   make(chan string),
 
 		RootDir:    config.RootDir,
 		SessionDir: config.SessionDir,
 
-		RayClusterName: config.RayNodeName,
+		RayClusterName: config.RayClusterName,
 		RayClusterID:   config.RayClusterID,
+		RayNodeName:    config.RayNodeName,
 
 		LogBatching:  config.LogBatching,
 		PushInterval: config.PushInterval,
@@ -33,7 +37,9 @@ func NewCollector(config *types.RayCollectorConfig, writter storage.StorageWritt
 		},
 		Writter: writter,
 	}
-	rootMetaDir := fmt.Sprintf("%s/", path.Clean(path.Join(handler.RootDir, handler.RayClusterName+"_"+handler.RayClusterID, "_meta")))
+	logDir := strings.TrimSpace(path.Join(config.SessionDir, utils.RAY_SESSIONDIR_LOGDIR_NAME))
+	handler.LogDir = logDir
+	rootMetaDir := fmt.Sprintf("%s/", path.Clean(path.Join(handler.RootDir, handler.RayClusterName+"_"+handler.RayClusterID, "meta")))
 	handler.MetaDir = rootMetaDir
 
 	return &handler

historyserver/backend/collector/storage/aliyunoss/README.md

@@ -0,0 +1,11 @@
+This module is the collector for aliyunoss.
+
+Oss endpoint and oss bucket are read from /var/collector-config/data.
+
+Content in /var/collector-config/data should be in json format, like 
+`{"ossBucket": "", "ossEndpoint": ""}`
+
+Set `--runtime-class-name=aliyunoss` to enable this module.
+
+Currently this module can only be used in ack environment. Oidc must be 
+enabled for the cluster, and permission for write the oss must be granted.

historyserver/backend/collector/storage/aliyunoss/ray/config.go

@@ -12,5 +12,13 @@ type config struct {
 func (c *config) complete(rcc *types.RayCollectorConfig, jd map[string]interface{}) {
 	c.RayCollectorConfig = *rcc
 	c.OSSBucket = jd["ossBucket"].(string)
-	c.OSSBucket = jd["ossEndpoint"].(string)
+	c.OSSEndpoint = jd["ossEndpoint"].(string)
+}
+
+func (c *config) completeHSConfig(rcc *types.RayHistoryServerConfig, jd map[string]interface{}) {
+	c.RayCollectorConfig = types.RayCollectorConfig{
+		RootDir: rcc.RootDir,
+	}
+	c.OSSBucket = jd["ossBucket"].(string)
+	c.OSSEndpoint = jd["ossEndpoint"].(string)
 }