创建集群

本文介绍如何通过EMR OpenAPI创建一个Hadoop半托管集群。

前提条件

已获取相应的SDK，Java SDK请参见SDK下载，Python SDK请参见安装SDK。

集群基本信息

需要创建的集群基本信息如下：

可用区：华东1（杭州）可用区I。
付费类型：按量付费。
集群名称：emr_openapi_demo。
开启高可用，详细实例：
- 2个Master，每个Master ecs.g5.xlarge，系统盘为1*120 GB的ESSD，数据盘为1*80 GB的高效云盘。
- 2个Core，每台Core ecs.g5.2xlarge，系统盘为1*120 GB的ESSD，数据盘为4*80 GB的高效云盘。
- 2个Task，每台Task ecs.c5.2xlarge，系统盘为1*120 GB的ESSD，数据盘为4*80 GB的高效云盘。
开启挂载公网。
设置登录密码。

自定义组件配置。


组件名	配置文件	Key	Value
Yarn	yarn-site.xml	yarn_nodemanager_heapsize	1234
Hive	hive-site.xml	hive.metastore.warehouse.dir	/user/hive/warehouse_emr

EMR OpenAPI示例

Python

#!/usr/bin/env python
#coding=utf-8

from aliyunsdkcore.client import AcsClient
from aliyunsdkcore.acs_exception.exceptions import ClientException
from aliyunsdkcore.acs_exception.exceptions import ServerException
from aliyunsdkemr.request.v20160408.CreateClusterV2Request import CreateClusterV2Request

client = AcsClient('<accessKeyId>', '<accessSecret>', 'cn-hangzhou')

request = CreateClusterV2Request()
request.set_accept_format('json')

request.set_Name("emr_openapi_demo")
request.set_ZoneId("cn-hangzhou-i")
request.set_EmrVer("EMR-3.23.0")
request.set_ClusterType("HADOOP")
request.set_HostGroups([
  {
    "HostGroupName": "master_group",
    "HostGroupType": "MASTER",
    "ChargeType": "PostPaid",
    "NodeCount": 2,
    "InstanceType": "ecs.g5.xlarge",
    "DiskType": "CLOUD_EFFICIENCY",
    "DiskCapacity": 80,
    "DiskCount": 1,
    "SysDiskType": "CLOUD_ESSD",
    "SysDiskCapacity": 120,
    "VSwitchId": "vsw-bp11t4amri1iuj*****"
  },
  {
    "HostGroupName": "core_group",
    "HostGroupType": "CORE",
    "ChargeType": "PostPaid",
    "NodeCount": 2,
    "InstanceType": "ecs.g5.2xlarge",
    "DiskType": "CLOUD_EFFICIENCY",
    "DiskCapacity": 80,
    "DiskCount": 4,
    "SysDiskType": "CLOUD_ESSD",
    "SysDiskCapacity": 120,
    "VSwitchId": "vsw-bp11t4amri1iuj*****"
  },
  {
    "HostGroupName": "task_group",
    "HostGroupType": "TASK",
    "ChargeType": "PostPaid",
    "NodeCount": 2,
    "InstanceType": "ecs.c5.xlarge",
    "DiskType": "CLOUD_EFFICIENCY",
    "DiskCapacity": 80,
    "DiskCount": 4,
    "SysDiskType": "CLOUD_ESSD",
    "SysDiskCapacity": 120,
    "VSwitchId": "vsw-bp11t4amri1iuj*****"
  }
])
request.set_SecurityGroupId("sg-bp13cqwumhn7x*****")
request.set_IsOpenPublicIp(True)
request.set_SecurityGroupName("newgroup")
request.set_ChargeType("PostPaid")
request.set_VpcId("vpc-bp1gjl3y9fezuk*****")
request.set_VSwitchId("vsw-bp11t4amri1iuj*****")
request.set_NetType("vpc")
request.set_UserDefinedEmrEcsRole("AliyunEmrEcsDefaultRole")
request.set_HighAvailabilityEnable(True)
request.set_IoOptimized(True)
request.set_SshEnable(True)
request.set_MasterPwd("EMRtest12345!")
request.set_DepositType("HALF_MANAGED")
request.set_MachineType("ECS")
request.set_Configs([
  {
    "ServiceName": "YARN",
    "FileName": "yarn-site",
    "ConfigKey": "yarn_nodemanager_heapsize",
    "ConfigValue": "1234"
  },
  {
    "ServiceName": "HIVE",
    "FileName": "hive-site",
    "ConfigKey": "hive.metastore.warehouse.dir",
    "ConfigValue": "/user/hive/warehouse_emr"
  }
])

response = client.do_action_with_exception(request)
# python2:  print(response) 
print(str(response, encoding='utf-8'))

Java

import com.aliyuncs.DefaultAcsClient;
import com.aliyuncs.IAcsClient;
import com.aliyuncs.exceptions.ClientException;
import com.aliyuncs.exceptions.ServerException;
import com.aliyuncs.profile.DefaultProfile;
import com.google.gson.Gson;
import java.util.*;
import com.aliyuncs.emr.model.v20160408.*;

public class CreateClusterV2 {

    public static void main(String[] args) {
        DefaultProfile profile = DefaultProfile.getProfile("cn-hangzhou", "<accessKeyId>", "<accessSecret>");
        IAcsClient client = new DefaultAcsClient(profile);

        CreateClusterV2Request request = new CreateClusterV2Request();
        request.setRegionId("cn-hangzhou");
        request.setName("emr_openapi_demo");
        request.setZoneId("cn-hangzhou-i");
        request.setEmrVer("EMR-3.23.0");
        request.setClusterType("HADOOP");

        List<CreateClusterV2Request.HostGroup> hostGroupList = new ArrayList<CreateClusterV2Request.HostGroup>();

        CreateClusterV2Request.HostGroup hostGroup1 = new CreateClusterV2Request.HostGroup();
        hostGroup1.setHostGroupName("master_group");
        hostGroup1.setHostGroupType("MASTER");
        hostGroup1.setChargeType("PostPaid");
        hostGroup1.setNodeCount(2);
        hostGroup1.setInstanceType("ecs.g5.xlarge");
        hostGroup1.setDiskType("CLOUD_EFFICIENCY");
        hostGroup1.setDiskCapacity(80);
        hostGroup1.setDiskCount(1);
        hostGroup1.setSysDiskType("CLOUD_ESSD");
        hostGroup1.setSysDiskCapacity(120);
        hostGroup1.setVSwitchId("vsw-bp11t4amri1iuj*****");
        hostGroupList.add(hostGroup1);

        CreateClusterV2Request.HostGroup hostGroup2 = new CreateClusterV2Request.HostGroup();
        hostGroup2.setHostGroupName("core_group");
        hostGroup2.setHostGroupType("CORE");
        hostGroup2.setChargeType("PostPaid");
        hostGroup2.setNodeCount(2);
        hostGroup2.setInstanceType("ecs.g5.2xlarge");
        hostGroup2.setDiskType("CLOUD_EFFICIENCY");
        hostGroup2.setDiskCapacity(80);
        hostGroup2.setDiskCount(4);
        hostGroup2.setSysDiskType("CLOUD_ESSD");
        hostGroup2.setSysDiskCapacity(120);
        hostGroup2.setVSwitchId("vsw-bp11t4amri1iuj*****");
        hostGroupList.add(hostGroup2);

        CreateClusterV2Request.HostGroup hostGroup3 = new CreateClusterV2Request.HostGroup();
        hostGroup3.setHostGroupName("task_group");
        hostGroup3.setHostGroupType("TASK");
        hostGroup3.setChargeType("PostPaid");
        hostGroup3.setNodeCount(2);
        hostGroup3.setInstanceType("ecs.c5.xlarge");
        hostGroup3.setDiskType("CLOUD_EFFICIENCY");
        hostGroup3.setDiskCapacity(80);
        hostGroup3.setDiskCount(4);
        hostGroup3.setSysDiskType("CLOUD_ESSD");
        hostGroup3.setSysDiskCapacity(120);
        hostGroup3.setVSwitchId("vsw-bp11t4amri1iuj*****");
        hostGroupList.add(hostGroup3);
        request.setHostGroups(hostGroupList);
        request.setSecurityGroupId("sg-bp13cqwumhn7x*****");
        request.setIsOpenPublicIp(true);
        request.setSecurityGroupName("newgroup");
        request.setChargeType("PostPaid");
        request.setVpcId("vpc-bp1gjl3y9fezukq*****");
        request.setVSwitchId("vsw-bp11t4amri1iuj*****");
        request.setNetType("vpc");
        request.setUserDefinedEmrEcsRole("AliyunEmrEcsDefaultRole");
        request.setHighAvailabilityEnable(true);
        request.setIoOptimized(true);
        request.setSshEnable(true);
        request.setMasterPwd("EMRtest12345!");
        request.setDepositType("HALF_MANAGED");
        request.setMachineType("ECS");

        List<CreateClusterV2Request.Config> configList = new ArrayList<CreateClusterV2Request.Config>();

        CreateClusterV2Request.Config config1 = new CreateClusterV2Request.Config();
        config1.setServiceName("YARN");
        config1.setFileName("yarn-site");
        config1.setConfigKey("yarn_nodemanager_heapsize");
        config1.setConfigValue("1234");
        configList.add(config1);

        CreateClusterV2Request.Config config2 = new CreateClusterV2Request.Config();
        config2.setServiceName("HIVE");
        config2.setFileName("hive-site");
        config2.setConfigKey("hive.metastore.warehouse.dir");
        config2.setConfigValue("/user/hive/warehouse_emr");
        configList.add(config2);
        request.setConfigs(configList);

        try {
            CreateClusterV2Response response = client.getAcsResponse(request);
            System.out.println(new Gson().toJson(response));
        } catch (ServerException e) {
            e.printStackTrace();
        } catch (ClientException e) {
            System.out.println("ErrCode:" + e.getErrCode());
            System.out.println("ErrMsg:" + e.getErrMsg());
            System.out.println("RequestId:" + e.getRequestId());
        }

    }
}

参数	描述
ChargeType	付费类型，PrePaid为包年包月。
Period	包年包月时间（包月数有：1、2、3、4、5、6、7、8、9、12、24、36）。当ChargeType为PrePaid时，必填。
HostGroup.N.ChargeType	机器组机器付费类型。
HostGroup.N.Period	包年包月时间（包月数有1、2、3、4、5、6、7、8、9、12、24、36）。当HostGroup.n.ChargeType为PrePaid时，必填。

参数	描述
ClusterType	当创建Gateway集群时，取值为GATEWAY。
HostGroup.N.HostGroupType	Gateway实例，取值为GATEWAY。
RelatedClusterId	当前是Gateway集群时，其关联的主集群ID。

前提条件

集群基本信息

EMR OpenAPI示例

更多配置