Merge pull request #1 from Project-HAMi/update

Add README.md and corresponding yaml file
Project-HAMi · Sep 14, 2024 · b6df990 · b6df990
2 parents aa1f98a + ced24cb
commit b6df990
Show file tree

Hide file tree

Showing 3 changed files with 184 additions and 10 deletions.
diff --git a/README.md b/README.md
@@ -1,30 +1,30 @@
 # Ascend Device Plugin
 
-## 说明
+## Introduction
 
-基于[HAMi](https://github.com/Project-HAMi/HAMi)调度机制的ascend device plugin。
+This Ascend device plugin is implemented for [HAMi](https://github.com/Project-HAMi/HAMi) scheduling.
 
-支持基于显存调度，显存是基于昇腾的虚拟化模板来切分的，会找到满足显存需求的最小模板来作为容器的显存。
+Memory slicing is supported based on virtualization template, lease available template is automatically used. For detailed information, check [templeate](./config.yaml)
 
-启动容器依赖[ascend-docker-runtime](https://gitee.com/ascend/ascend-docker-runtime)。
+## Prequisites
 
-## 编译
+[ascend-docker-runtime](https://gitee.com/ascend/ascend-docker-runtime)。
 
-### 编译二进制文件
+## Compile
 
 ```bash
 make all
 ```
 
-### 编译镜像
+### Build
 
 ```bash
 docker buildx build -t $IMAGE_NAME .
 ```
 
-## 部署
+## Deployment
 
-由于和HAMi的一些依赖关系，部署集成在HAMi的部署中，修改HAMi chart values中的以下部分即可。
+Due to dependencies with HAMi, the deployment is integrated into the HAMi deployment, you need to set 'devices.ascend.enabled=true'. The device-plugin is automaticaly deployed. For more details ,see 'devices' section in values.yaml.
 
 ```yaml
 devices:
@@ -45,7 +45,8 @@ devices:
       - huawei.com/Ascend310P-memory
 ```
 
-## 使用
+
+## Usage
 
 ```yaml
 ...

diff --git a/README_cn.md b/README_cn.md
@@ -0,0 +1,60 @@
+# Ascend Device Plugin
+
+## 说明
+
+基于[HAMi](https://github.com/Project-HAMi/HAMi)调度机制的ascend device plugin。
+
+支持基于显存调度，显存是基于昇腾的虚拟化模板来切分的，会找到满足显存需求的最小模板来作为容器的显存。
+
+启动容器依赖[ascend-docker-runtime](https://gitee.com/ascend/ascend-docker-runtime)。
+
+## 编译
+
+### 编译二进制文件
+
+```bash
+make all
+```
+
+### 编译镜像
+
+```bash
+docker buildx build -t $IMAGE_NAME .
+```
+
+## 部署
+
+由于和HAMi的一些依赖关系，部署集成在HAMi的部署中，修改HAMi chart values中的以下部分即可。
+
+```yaml
+devices:
+  ascend:
+    enabled: true
+    image: "ascend-device-plugin:master"
+    imagePullPolicy: IfNotPresent
+    extraArgs: []
+    nodeSelector:
+      ascend: "on"
+    tolerations: []
+    resources:
+      - huawei.com/Ascend910A
+      - huawei.com/Ascend910A-memory
+      - huawei.com/Ascend910B
+      - huawei.com/Ascend910B-memory
+      - huawei.com/Ascend310P
+      - huawei.com/Ascend310P-memory
+```
+
+## 使用
+
+```yaml
+...
+    containers:
+    - name: npu_pod
+      ...
+      resources:
+        limits:
+          huawei.com/Ascend910B: "1"
+          # 不填写显存默认使用整张卡
+          huawei.com/Ascend910B-memory: "4096"
+```
diff --git a/ascend-device-plugin.yaml b/ascend-device-plugin.yaml
@@ -0,0 +1,113 @@
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: hami-ascend
+rules:
+  - apiGroups: [""]
+    resources: ["pods"]
+    verbs: ["get", "list", "update", "watch", "patch"]
+  - apiGroups: [""]
+    resources: ["nodes"]
+    verbs: ["get", "patch"]
+----
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: hami-ascend
+subjects:
+  - kind: ServiceAccount
+    name: hami-ascend
+    namespace: kube-system
+roleRef:
+  kind: ClusterRole
+  name: hami-ascend
+  apiGroup: rbac.authorization.k8s.io
+----
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: hami-ascend
+  namespace: kube-system
+  labels:
+    app.kubernetes.io/component: "hami-ascend"
+----
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  name: hami-ascend-device-plugin
+  namespace: kube-system
+  labels:
+    app.kubernetes.io/component: hami-ascend-device-plugin
+spec:
+  selector:
+    matchLabels:
+      app.kubernetes.io/component: hami-ascend-device-plugin
+      hami.io/webhook: ignore
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/component: hami-ascend-device-plugin
+        hami.io/webhook: ignore
+    spec:
+      priorityClassName: "system-node-critical"
+      serviceAccountName: hami-ascend
+      containers:
+        - image: projecthami/ascend-device-plugin:main
+          imagePullPolicy: IfNotPresent
+          name: device-plugin
+          resources:
+            requests:
+              memory: 500Mi
+              cpu: 500m
+            limits:
+              memory: 500Mi
+              cpu: 500m
+          args:
+            - --config_file
+            - /ascend-config.yaml
+          securityContext:
+            privileged: true
+            readOnlyRootFilesystem: false
+          volumeMounts:
+            - name: device-plugin
+              mountPath: /var/lib/kubelet/device-plugins
+            - name: pod-resource
+              mountPath: /var/lib/kubelet/pod-resources
+            - name: hiai-driver
+              mountPath: /usr/local/Ascend/driver
+              readOnly: true
+            - name: log-path
+              mountPath: /var/log/mindx-dl/devicePlugin
+            - name: tmp
+              mountPath: /tmp
+            - name: device-config
+              mountPath: /ascend-config.yaml
+              subPath: ascend-config.yaml
+              readOnly: true
+          env:
+            - name: NODE_NAME
+              valueFrom:
+                fieldRef:
+                  fieldPath: spec.nodeName
+      volumes:
+        - name: device-plugin
+          hostPath:
+            path: /var/lib/kubelet/device-plugins
+        - name: pod-resource
+          hostPath:
+            path: /var/lib/kubelet/pod-resources
+        - name: hiai-driver
+          hostPath:
+            path: /usr/local/Ascend/driver
+        - name: log-path
+          hostPath:
+            path: /var/log/mindx-dl/devicePlugin
+            type: Directory
+        - name: tmp
+          hostPath:
+            path: /tmp
+        - name: device-config
+          configMap:
+            name: hami-scheduler-device
+      nodeSelector:
+        ascend: "on"