Skip to content

GitLab

"src/include/gridwise_direct_convolution_3.cuh" did not exist on "a21b0d27a52794fcf23e34f496559c0f1adc1a0d"
Commit 4553de75 authored by SparkSnail's avatar SparkSnail Committed by fishyds
Browse files

Fix FrameworkController broken change (#628) 

* add serviceAccountName

* add serviceAccountName for frameworkcontroller
parent df39b5ea
Show whitespace changes
Inline Side-by-side
Showing with 144 additions and 54 deletions
src/nni_manager/rest_server/restValidationSchemas.ts
View file @ 4553de75
......@@ -108,6 +108,7 @@ export namespace ValidationSchemas {
}),
frameworkcontroller_config: joi.object({
storage: joi.string().min(1),
serviceAccountName: joi.string().min(1),
nfs: joi.object({
server: joi.string().min(1).required(),
path: joi.string().min(1).required()
......
src/nni_manager/training_service/kubernetes/frameworkcontroller/frameworkcontrollerConfig.ts
View file @ 4553de75
......@@ -18,8 +18,11 @@
*/
'use strict';
import * as assert from 'assert';
import { KubernetesTrialConfig, KubernetesTrialConfigTemplate } from '../kubernetesConfig'
import { KubernetesTrialConfig, KubernetesTrialConfigTemplate, KubernetesClusterConfigAzure,
KubernetesClusterConfigNFS, NFSConfig, KubernetesStorageKind, keyVaultConfig, AzureStorage, KubernetesClusterConfig,
StorageConfig } from '../kubernetesConfig'
export class FrameworkAttemptCompletionPolicy {
public readonly minFailedTaskCount: number;
......@@ -57,6 +60,80 @@ export class FrameworkControllerTrialConfig extends KubernetesTrialConfig{
}
}
export class FrameworkControllerClusterConfig extends KubernetesClusterConfig {
public readonly serviceAccountName: string;
constructor(apiVersion: string, serviceAccountName: string) {
super(apiVersion);
this.serviceAccountName = serviceAccountName;
}
}
export class FrameworkControllerClusterConfigNFS extends KubernetesClusterConfigNFS {
public readonly serviceAccountName: string;
constructor(
serviceAccountName: string,
apiVersion: string,
nfs: NFSConfig,
storage?: KubernetesStorageKind
) {
super(apiVersion, nfs, storage);
this.serviceAccountName = serviceAccountName;
}
public static getInstance(jsonObject: object): FrameworkControllerClusterConfigNFS {
let kubeflowClusterConfigObjectNFS = <FrameworkControllerClusterConfigNFS>jsonObject;
assert (kubeflowClusterConfigObjectNFS !== undefined)
return new FrameworkControllerClusterConfigNFS(
kubeflowClusterConfigObjectNFS.serviceAccountName,
kubeflowClusterConfigObjectNFS.apiVersion,
kubeflowClusterConfigObjectNFS.nfs,
kubeflowClusterConfigObjectNFS.storage
);
}
}
export class FrameworkControllerClusterConfigAzure extends KubernetesClusterConfigAzure {
public readonly serviceAccountName: string;
constructor(
serviceAccountName: string,
apiVersion: string,
keyVault: keyVaultConfig,
azureStorage: AzureStorage,
storage?: KubernetesStorageKind
) {
super(apiVersion, keyVault, azureStorage,storage);
this.serviceAccountName = serviceAccountName;
}
public static getInstance(jsonObject: object): FrameworkControllerClusterConfigAzure {
let kubeflowClusterConfigObjectAzure = <FrameworkControllerClusterConfigAzure>jsonObject;
return new FrameworkControllerClusterConfigAzure(
kubeflowClusterConfigObjectAzure.serviceAccountName,
kubeflowClusterConfigObjectAzure.apiVersion,
kubeflowClusterConfigObjectAzure.keyVault,
kubeflowClusterConfigObjectAzure.azureStorage,
kubeflowClusterConfigObjectAzure.storage
);
}
}
export class FrameworkControllerClusterConfigFactory {
public static generateFrameworkControllerClusterConfig(jsonObject: object): FrameworkControllerClusterConfig {
let storageConfig = <StorageConfig>jsonObject;
if(!storageConfig) {
throw new Error("Invalid json object as a StorageConfig instance");
}
if(storageConfig.storage && storageConfig.storage === 'azureStorage') {
return FrameworkControllerClusterConfigAzure.getInstance(jsonObject);
} else if (storageConfig.storage === undefined || storageConfig.storage === 'nfs') {
return FrameworkControllerClusterConfigNFS.getInstance(jsonObject);
}
throw new Error(`Invalid json object ${jsonObject}`);
}
}
export type FrameworkControllerJobStatus = 'AttemptRunning' | 'Completed' | 'AttemptCreationPending' | 'AttemptCreationRequested' | 'AttemptPreparing' | 'AttemptCompleted';
export type FrameworkControllerJobCompleteStatus = 'Succeeded' | 'Failed';
\ No newline at end of file
src/nni_manager/training_service/kubernetes/frameworkcontroller/frameworkcontrollerTrainingService.ts
View file @ 4553de75
......@@ -32,12 +32,13 @@ import {
TrialJobDetail, NNIManagerIpConfig
} from '../../../common/trainingService';
import { delay, generateParamFileName, getExperimentRootDir, uniqueString } from '../../../common/utils';
import { NFSConfig, KubernetesClusterConfigNFS, KubernetesClusterConfigAzure, KubernetesClusterConfigFactory } from '../kubernetesConfig'
import { NFSConfig } from '../kubernetesConfig'
import { KubernetesTrialJobDetail } from '../kubernetesData';
import { validateCodeDir } from '../../common/util';
import { AzureStorageClientUtility } from '../azureStorageClientUtils';
import { KubernetesTrainingService } from '../kubernetesTrainingService';
import { FrameworkControllerTrialConfig } from './frameworkcontrollerConfig';
import { FrameworkControllerTrialConfig, FrameworkControllerClusterConfig, FrameworkControllerClusterConfigAzure, FrameworkControllerClusterConfigNFS,
FrameworkControllerClusterConfigFactory} from './frameworkcontrollerConfig';
import { FrameworkControllerJobRestServer } from './frameworkcontrollerJobRestServer';
import { FrameworkControllerClient } from './frameworkcontrollerApiClient';
import { FrameworkControllerJobInfoCollector } from './frameworkcontrollerJobInfoCollector';
......@@ -50,6 +51,7 @@ class FrameworkControllerTrainingService extends KubernetesTrainingService imple
private fcTrialConfig?: FrameworkControllerTrialConfig; // frameworkcontroller trial configuration
private fcJobInfoCollector: FrameworkControllerJobInfoCollector; // frameworkcontroller job info collector
private fcContainerPortMap = new Map<string, number>(); // store frameworkcontroller container port
private fcClusterConfig?: FrameworkControllerClusterConfig;
constructor() {
super();
......@@ -73,7 +75,7 @@ class FrameworkControllerTrainingService extends KubernetesTrainingService imple
}
public async submitTrialJob(form: JobApplicationForm): Promise<TrialJobDetail> {
if(!this.kubernetesClusterConfig) {
if(!this.fcClusterConfig) {
throw new Error('frameworkcontrollerClusterConfig is not initialized');
}
if(!this.kubernetesCRDClient) {
......@@ -129,13 +131,13 @@ class FrameworkControllerTrainingService extends KubernetesTrainingService imple
* return: trialJobOutputUrl
*/
private async uploadCodeFiles(trialJobId: string, trialLocalTempFolder: string): Promise<string> {
if(!this.kubernetesClusterConfig) {
if(!this.fcClusterConfig) {
throw new Error('Kubeflow Cluster config is not initialized');
}
let trialJobOutputUrl: string = '';
if(this.kubernetesClusterConfig.storageType === 'azureStorage') {
if(this.fcClusterConfig.storageType === 'azureStorage') {
try{
//upload local files to azure storage
await AzureStorageClientUtility.uploadDirectory(this.azureStorageClient,
......@@ -146,8 +148,8 @@ class FrameworkControllerTrainingService extends KubernetesTrainingService imple
this.log.error(error);
return Promise.reject(error);
}
} else if(this.kubernetesClusterConfig.storageType === 'nfs') {
let nfsFrameworkControllerClusterConfig: KubernetesClusterConfigNFS = <KubernetesClusterConfigNFS>this.kubernetesClusterConfig;
} else if(this.fcClusterConfig.storageType === 'nfs') {
let nfsFrameworkControllerClusterConfig: FrameworkControllerClusterConfigNFS = <FrameworkControllerClusterConfigNFS>this.fcClusterConfig;
// Creat work dir for current trial in NFS directory
await cpp.exec(`mkdir -p ${this.trialLocalNFSTempFolder}/nni/${getExperimentId()}/${trialJobId}`);
// Copy code files from local dir to NFS mounted dir
......@@ -170,7 +172,7 @@ class FrameworkControllerTrainingService extends KubernetesTrainingService imple
throw new Error('frameworkcontroller trial config is not initialized');
}
for(let taskRole of this.fcTrialConfig.taskRoles) {
portScript += `${taskRole.name}_port=${this.fcContainerPortMap.get(taskRole.name)} `;
portScript += `FB_${taskRole.name.toUpperCase()}_PORT=${this.fcContainerPortMap.get(taskRole.name)} `;
}
return `${portScript} . /mnt/frameworkbarrier/injector.sh && ${command}`;
}
......@@ -229,9 +231,9 @@ class FrameworkControllerTrainingService extends KubernetesTrainingService imple
case TrialConfigMetadataKey.FRAMEWORKCONTROLLER_CLUSTER_CONFIG:
let frameworkcontrollerClusterJsonObject = JSON.parse(value);
this.kubernetesClusterConfig = KubernetesClusterConfigFactory.generateKubernetesClusterConfig(frameworkcontrollerClusterJsonObject);
if(this.kubernetesClusterConfig.storageType === 'azureStorage') {
let azureFrameworkControllerClusterConfig = <KubernetesClusterConfigAzure>this.kubernetesClusterConfig;
this.fcClusterConfig = FrameworkControllerClusterConfigFactory.generateFrameworkControllerClusterConfig(frameworkcontrollerClusterJsonObject);
if(this.fcClusterConfig.storageType === 'azureStorage') {
let azureFrameworkControllerClusterConfig = <FrameworkControllerClusterConfigAzure>this.fcClusterConfig;
this.azureStorageAccountName = azureFrameworkControllerClusterConfig.azureStorage.accountName;
this.azureStorageShare = azureFrameworkControllerClusterConfig.azureStorage.azureShare;
await this.createAzureStorage(
......@@ -240,8 +242,8 @@ class FrameworkControllerTrainingService extends KubernetesTrainingService imple
azureFrameworkControllerClusterConfig.azureStorage.accountName,
azureFrameworkControllerClusterConfig.azureStorage.azureShare
);
} else if(this.kubernetesClusterConfig.storageType === 'nfs') {
let nfsFrameworkControllerClusterConfig = <KubernetesClusterConfigNFS>this.kubernetesClusterConfig;
} else if(this.fcClusterConfig.storageType === 'nfs') {
let nfsFrameworkControllerClusterConfig = <FrameworkControllerClusterConfigNFS>this.fcClusterConfig;
await this.createNFSStorage(
nfsFrameworkControllerClusterConfig.nfs.server,
nfsFrameworkControllerClusterConfig.nfs.path
......@@ -292,7 +294,7 @@ class FrameworkControllerTrainingService extends KubernetesTrainingService imple
* @param podResources pod template
*/
private generateFrameworkControllerJobConfig(trialJobId: string, trialWorkingFolder: string, frameworkcontrollerJobName : string, podResources : any) : any {
if(!this.kubernetesClusterConfig) {
if(!this.fcClusterConfig) {
throw new Error('frameworkcontroller Cluster config is not initialized');
}
......@@ -346,7 +348,7 @@ class FrameworkControllerTrainingService extends KubernetesTrainingService imple
private generateTaskRoleConfig(trialWorkingFolder: string, replicaImage: string, runScriptFile: string, podResources: any, containerPort: number): any {
if(!this.kubernetesClusterConfig) {
if(!this.fcClusterConfig) {
throw new Error('frameworkcontroller Cluster config is not initialized');
}
......@@ -355,7 +357,7 @@ class FrameworkControllerTrainingService extends KubernetesTrainingService imple
}
let volumeSpecMap = new Map<string, object>();
if(this.kubernetesClusterConfig.storageType === 'azureStorage'){
if(this.fcClusterConfig.storageType === 'azureStorage'){
volumeSpecMap.set('nniVolumes', [
{
name: 'nni-vol',
......@@ -369,7 +371,7 @@ class FrameworkControllerTrainingService extends KubernetesTrainingService imple
emptyDir: {}
}])
}else {
let frameworkcontrollerClusterConfigNFS: KubernetesClusterConfigNFS = <KubernetesClusterConfigNFS> this.kubernetesClusterConfig;
let frameworkcontrollerClusterConfigNFS: FrameworkControllerClusterConfigNFS = <FrameworkControllerClusterConfigNFS> this.fcClusterConfig;
volumeSpecMap.set('nniVolumes', [
{
name: 'nni-vol',
......@@ -382,10 +384,8 @@ class FrameworkControllerTrainingService extends KubernetesTrainingService imple
emptyDir: {}
}])
}
let taskRole = {
pod: {
spec: {
containers: [
let containers = [
{
name: 'framework',
image: replicaImage,
......@@ -402,8 +402,9 @@ class FrameworkControllerTrainingService extends KubernetesTrainingService imple
ports: [{
containerPort: containerPort
}]
}],
initContainers: [
}]
let initContainers = [
{
name: 'frameworkbarrier',
image: 'frameworkcontroller/frameworkbarrier',
......@@ -412,11 +413,20 @@ class FrameworkControllerTrainingService extends KubernetesTrainingService imple
name: 'frameworkbarrier-volume',
mountPath: '/mnt/frameworkbarrier'
}]
}],
}]
let spec: any = {
containers: containers,
initContainers: initContainers,
restartPolicy: 'OnFailure',
volumes: volumeSpecMap.get('nniVolumes'),
hostNetwork: false
};
if(this.fcClusterConfig.serviceAccountName) {
spec.serviceAccountName = this.fcClusterConfig.serviceAccountName;
}
let taskRole = {
pod: {
spec: spec
}
}
return taskRole;
......
src/nni_manager/training_service/kubernetes/kubeflow/kubeflowConfig.ts
View file @ 4553de75
......@@ -32,8 +32,8 @@ export type OperatorApiVersion = 'v1alpha2' | 'v1beta1';
export class KubeflowClusterConfig extends KubernetesClusterConfig {
public readonly operator: KubeflowOperator;
constructor(codeDir: string, operator: KubeflowOperator) {
super(codeDir);
constructor(apiVersion: string, operator: KubeflowOperator) {
super(apiVersion);
this.operator = operator;
}
}
......
tools/nni_cmd/config_schema.py
View file @ 4553de75
......@@ -216,12 +216,14 @@ frameworkcontroller_trial_schema = {
frameworkcontroller_config_schema = {
'frameworkcontrollerConfig':Or({
Optional('storage'): Or('nfs', 'azureStorage'),
Optional('serviceAccountName'): str,
'nfs': {
'server': str,
'path': str
}
},{
Optional('storage'): Or('nfs', 'azureStorage'),
Optional('serviceAccountName'): str,
'keyVault': {
'vaultName': Regex('([0-9]|[a-z]|[A-Z]|-){1,127}'),
'name': Regex('([0-9]|[a-z]|[A-Z]|-){1,127}')
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment