Add source env list in common.properties (#13317)

This commit is contained in:
Wenjun Ruan 2023-01-04 20:53:52 +08:00 committed by GitHub
parent bcf03ad4d1
commit 6634ff98af
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
5 changed files with 215 additions and 1 deletions

View File

@ -124,4 +124,7 @@ ml.mlflow.preset_repository=https://github.com/apache/dolphinscheduler-mlflow
ml.mlflow.preset_repository_version="main"
# way to collect applicationId: log(original regex match), aop
appId.collect: log
appId.collect=log
# The default env list will be load by Shell task, e.g. /etc/profile,~/.bash_profile
shell.env_source_list=

View File

@ -18,7 +18,9 @@
package org.apache.dolphinscheduler.plugin.task.api;
import org.apache.dolphinscheduler.plugin.task.api.utils.FileUtils;
import org.apache.dolphinscheduler.plugin.task.api.utils.ShellUtils;
import org.apache.commons.collections4.CollectionUtils;
import org.apache.commons.lang3.StringUtils;
import org.apache.commons.lang3.SystemUtils;
@ -93,6 +95,11 @@ public class ShellCommandExecutor extends AbstractCommandExecutor {
if (SystemUtils.IS_OS_WINDOWS) {
sb.append("@echo off").append(System.lineSeparator());
sb.append("cd /d %~dp0").append(System.lineSeparator());
if (CollectionUtils.isNotEmpty(ShellUtils.ENV_SOURCE_LIST)) {
for (String envSourceFile : ShellUtils.ENV_SOURCE_LIST) {
sb.append("call ").append(envSourceFile).append("\n");
}
}
if (StringUtils.isNotBlank(taskRequest.getEnvironmentConfig())) {
sb.append(taskRequest.getEnvironmentConfig()).append(System.lineSeparator());
}
@ -100,6 +107,11 @@ public class ShellCommandExecutor extends AbstractCommandExecutor {
sb.append("#!/bin/bash").append(System.lineSeparator());
sb.append("BASEDIR=$(cd `dirname $0`; pwd)").append(System.lineSeparator());
sb.append("cd $BASEDIR").append(System.lineSeparator());
if (CollectionUtils.isNotEmpty(ShellUtils.ENV_SOURCE_LIST)) {
for (String envSourceFile : ShellUtils.ENV_SOURCE_LIST) {
sb.append("source ").append(envSourceFile).append("\n");
}
}
if (StringUtils.isNotBlank(taskRequest.getEnvironmentConfig())) {
sb.append(taskRequest.getEnvironmentConfig()).append(System.lineSeparator());
}

View File

@ -0,0 +1,37 @@
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.dolphinscheduler.plugin.task.api.utils;
import org.apache.dolphinscheduler.common.utils.PropertyUtils;
import java.util.Arrays;
import java.util.List;
import java.util.Optional;
import java.util.stream.Collectors;
import lombok.experimental.UtilityClass;
@UtilityClass
public class ShellUtils {
public List<String> ENV_SOURCE_LIST = Arrays.stream(
Optional.ofNullable(PropertyUtils.getString("shell.env_source_list"))
.map(s -> s.split(",")).orElse(new String[0]))
.map(String::trim)
.collect(Collectors.toList());
}

View File

@ -0,0 +1,32 @@
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.dolphinscheduler.plugin.task.api.utils;
import java.util.ArrayList;
import org.junit.jupiter.api.Assertions;
import org.junit.jupiter.api.Test;
public class ShellUtilsTest {
@Test
public void testGetEnvSourceList() {
Assertions.assertEquals(new ArrayList<>(), ShellUtils.ENV_SOURCE_LIST);
}
}

View File

@ -0,0 +1,130 @@
#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
# user data local directory path, please make sure the directory exists and have read write permissions
data.basedir.path=/tmp/dolphinscheduler
# resource view suffixs
#resource.view.suffixs=txt,log,sh,bat,conf,cfg,py,java,sql,xml,hql,properties,json,yml,yaml,ini,js
# resource storage type: HDFS, S3, OSS, NONE
resource.storage.type=NONE
# resource store on HDFS/S3 path, resource file will store to this base path, self configuration, please make sure the directory exists on hdfs and have read write permissions. "/dolphinscheduler" is recommended
resource.storage.upload.base.path=/dolphinscheduler
# The AWS access key. if resource.storage.type=S3 or use EMR-Task, This configuration is required
resource.aws.access.key.id=minioadmin
# The AWS secret access key. if resource.storage.type=S3 or use EMR-Task, This configuration is required
resource.aws.secret.access.key=minioadmin
# The AWS Region to use. if resource.storage.type=S3 or use EMR-Task, This configuration is required
resource.aws.region=cn-north-1
# The name of the bucket. You need to create them by yourself. Otherwise, the system cannot start. All buckets in Amazon S3 share a single namespace; ensure the bucket is given a unique name.
resource.aws.s3.bucket.name=dolphinscheduler
# You need to set this parameter when private cloud s3. If S3 uses public cloud, you only need to set resource.aws.region or set to the endpoint of a public cloud such as S3.cn-north-1.amazonaws.com.cn
resource.aws.s3.endpoint=http://localhost:9000
# alibaba cloud access key id, required if you set resource.storage.type=OSS
resource.alibaba.cloud.access.key.id=<your-access-key-id>
# alibaba cloud access key secret, required if you set resource.storage.type=OSS
resource.alibaba.cloud.access.key.secret=<your-access-key-secret>
# alibaba cloud region, required if you set resource.storage.type=OSS
resource.alibaba.cloud.region=cn-hangzhou
# oss bucket name, required if you set resource.storage.type=OSS
resource.alibaba.cloud.oss.bucket.name=dolphinscheduler
# oss bucket endpoint, required if you set resource.storage.type=OSS
resource.alibaba.cloud.oss.endpoint=https://oss-cn-hangzhou.aliyuncs.com
# if resource.storage.type=HDFS, the user must have the permission to create directories under the HDFS root path
resource.hdfs.root.user=hdfs
# if resource.storage.type=S3, the value like: s3a://dolphinscheduler; if resource.storage.type=HDFS and namenode HA is enabled, you need to copy core-site.xml and hdfs-site.xml to conf dir
resource.hdfs.fs.defaultFS=hdfs://mycluster:8020
# whether to startup kerberos
hadoop.security.authentication.startup.state=false
# java.security.krb5.conf path
java.security.krb5.conf.path=/opt/krb5.conf
# login user from keytab username
login.user.keytab.username=hdfs-mycluster@ESZ.COM
# login user from keytab path
login.user.keytab.path=/opt/hdfs.headless.keytab
# kerberos expire time, the unit is hour
kerberos.expire.time=2
# resourcemanager port, the default value is 8088 if not specified
resource.manager.httpaddress.port=8088
# if resourcemanager HA is enabled, please set the HA IPs; if resourcemanager is single, keep this value empty
yarn.resourcemanager.ha.rm.ids=192.168.xx.xx,192.168.xx.xx
# if resourcemanager HA is enabled or not use resourcemanager, please keep the default value; If resourcemanager is single, you only need to replace ds1 to actual resourcemanager hostname
yarn.application.status.address=http://ds1:%s/ws/v1/cluster/apps/%s
# job history status url when application number threshold is reached(default 10000, maybe it was set to 1000)
yarn.job.history.status.address=http://ds1:19888/ws/v1/history/mapreduce/jobs/%s
# datasource encryption enable
datasource.encryption.enable=false
# datasource encryption salt
datasource.encryption.salt=!@#$%^&*
# data quality option
data-quality.jar.name=dolphinscheduler-data-quality-dev-SNAPSHOT.jar
#data-quality.error.output.path=/tmp/data-quality-error-data
# Network IP gets priority, default inner outer
# Whether hive SQL is executed in the same session
support.hive.oneSession=false
# use sudo or not, if set true, executing user is tenant user and deploy user needs sudo permissions; if set false, executing user is the deploy user and doesn't need sudo permissions
sudo.enable=true
# network interface preferred like eth0, default: empty
#dolphin.scheduler.network.interface.preferred=
# network IP gets priority, default: inner outer
#dolphin.scheduler.network.priority.strategy=default
# system env path
#dolphinscheduler.env.path=dolphinscheduler_env.sh
# development state
development.state=false
# rpc port
alert.rpc.port=50052
# set path of conda.sh
conda.path=/opt/anaconda3/etc/profile.d/conda.sh
# Task resource limit state
task.resource.limit.state=false
# mlflow task plugin preset repository
ml.mlflow.preset_repository=https://github.com/apache/dolphinscheduler-mlflow
# mlflow task plugin preset repository version
ml.mlflow.preset_repository_version="main"
# way to collect applicationId: log(original regex match), aop
appId.collect=log
# The default env list will be load by Shell task, e.g. /etc/profile,~/.bash_profile
# shell.env_source_list=/etc/profile,~/.bash_profile