全部產品
Search
文件中心

Elastic Compute Service:通過SDK執行命令

更新時間:Feb 26, 2025

雲助手命令可以在多台ECS執行個體中批量執行Shell、Bat或者PowerShell指令碼。本文介紹如何通過ECS SDK運行雲助手命令和查詢雲助手命令執行結果。

前提條件

  • ECS執行個體狀態必須為運行中Running)且已安裝雲助手Agent。如未安裝,請參見安裝雲助手Agent

  • 請確保代碼運行環境設定了環境變數ALIBABA_CLOUD_ACCESS_KEY_IDALIBABA_CLOUD_ACCESS_KEY_SECRET。具體配置方法,請參見在Linux、macOS和Windows系統配置環境變數

    說明

    為防止主帳號泄露AccessKey所帶來的安全風險,建議您建立RAM使用者,並為其授予Elastic Compute Service相關的存取權限。然後您可以使用該RAM使用者的AccessKey來調用SDK。具體操作,請參見RAM使用者

  • 為RAM使用者授予雲助手相關許可權,具體資訊,請參見授權RAM使用者使用雲助手

  • 準備好將要通過雲助手執行的命令(Shell、Bat 或 PowerShell 命令)。

  • 在專案中引入ECS SDK依賴。具體資訊,請參見ECS_SDK

情境樣本

在現代雲端運算環境中,營運管理系統是保障業務穩定啟動並執行重要工具。為確保ECS執行個體的效能與穩定性,定期檢查資源使用方式(如CPU、記憶體、磁碟等)至關重要。假設您正在開發一套自動化營運管理系統,該系統雲端式助手的免登入功能,能夠遠程在ECS執行個體中執行使用者指定的命令,從而靈活滿足多樣化的營運需求。通過傳入不同的命令內容,該系統能夠實現資源監控、日誌採集、故障排查等多項功能,顯著提升營運效率,並為業務的高效運行提供可靠支援。

import com.aliyun.ecs20140526.Client;
import com.aliyun.ecs20140526.models.*;
import com.aliyun.teaopenapi.models.Config;
import com.google.gson.Gson;

import java.util.Arrays;
import java.util.List;
import java.util.concurrent.Executors;
import java.util.concurrent.ScheduledExecutorService;
import java.util.concurrent.ScheduledFuture;
import java.util.concurrent.TimeUnit;


public class CloudAssistantService {

    /**
     * 從環境變數中擷取AccessKeyId、AccessKeySecret
     */
    private static final String ACCESS_KEY_ID = System.getenv("ALIBABA_CLOUD_ACCESS_KEY_ID");
    private static final String ACCESS_KEY_SECRET = System.getenv("ALIBABA_CLOUD_ACCESS_KEY_SECRET");
    private static final ScheduledExecutorService SCHEDULER = Executors.newScheduledThreadPool(1);
    private static volatile Client ecsClient;

    private CloudAssistantService() {
    }

    /**
     * 初始化ECS用戶端
     *
     * @param regionId 地區ID,用於指定ECS用戶端所在的地區
     * @return 返回初始化好的ECS用戶端執行個體
     * <p>
     * 該方法使用雙重檢查鎖定模式來確保安全執行緒地建立單例ECS用戶端。
     * 它首先檢查用戶端是否已經存在,如果不存在,則在同步塊中再次檢查並建立新的用戶端執行個體。
     */
    public static Client getEcsClient(String regionId) throws Exception {
        if (ecsClient == null) {
            synchronized (CloudAssistantService.class) {
                if (ecsClient == null) {
                    Config config = new Config().setAccessKeyId(ACCESS_KEY_ID).setAccessKeySecret(ACCESS_KEY_SECRET).setRegionId(regionId);
                    ecsClient = new Client(config);
                }
            }
        }
        return ecsClient;
    }

    public static void main(String[] args_) {
        try {
            // 地區ID
            String regionId = "cn-chengdu";
            getEcsClient(regionId);
            // 執行命令的ECS執行個體ID
            List<String> instanceIds = Arrays.asList("i-2vcXXXXXXXXXXXXXXXb8", "i-2vcXXXXXXXXXXXXXXXot");
            // 命令內容
            String commandContent = "#!/bin/bash\n cat /proc/meminfo";
            // 命令執行逾時時間
            long commandTimeOut = 60;


            // 執行命令
            String invokeId = runCommand(commandContent, regionId, instanceIds, commandTimeOut);
            // 查詢命令執行結果
            DescribeInvocationsResponse invocationResult = describeInvocations(regionId, invokeId, commandTimeOut);
            System.out.println("The command execution result:" + new Gson().toJson(invocationResult));
            // 省略記錄記錄檔操作

        } catch (Exception e) {
            throw new RuntimeException(e);
        } finally {
            SCHEDULER.shutdown();
        }
    }

    /**
     * 在指定執行個體上執行命令
     *
     * @param commandContent 要執行的命令內容
     * @param regionId       執行個體所在的地區ID
     * @param instanceIds    要執行命令的ECS執行個體ID集合
     * @param commandTimeOut 命令執行的逾時時間
     * @return 返回命令執行的調用ID
     */
    public static String runCommand(String commandContent, String regionId, List<String> instanceIds, long commandTimeOut) {
        try {
            System.out.println("runCommand start...");
            RunCommandRequest request = new RunCommandRequest();
            request.setRegionId(regionId);
            request.setType(Constants.COMMAND_TYPE.RUN_SHELL_SCRIPT);
            request.setCommandContent(commandContent);
            request.setInstanceId(instanceIds);
            request.setTimeout(commandTimeOut);
            RunCommandResponse runCommandResponse = ecsClient.runCommand(request);
            return runCommandResponse.body.invokeId;
        } catch (Exception e) {
            throw new RuntimeException("runCommand failed", e);
        }
    }

    /**
     * 查詢雲助手命令執行結果
     *
     * @param regionId       地區ID,用於指定調用結果所屬的地區
     * @param invokeId       調用ID,用於唯一標識一次調用
     * @param commandTimeOut 命令執行的逾時時間
     */
    public static DescribeInvocationsResponse describeInvocations(String regionId, String invokeId, long commandTimeOut) {
        DescribeInvocationsRequest describeInvocationsRequest = new DescribeInvocationsRequest()
                .setRegionId(regionId)
                .setInvokeId(invokeId);

        long delay = 2;
        // 設定最大重試次數
        int maxRetries = (int) (commandTimeOut / delay); 
        int retryCount = 0;

        try {
            while (retryCount < maxRetries) {
                ScheduledFuture<DescribeInvocationsResponse> future = SCHEDULER.schedule(() ->
                        ecsClient.describeInvocations(describeInvocationsRequest), delay, TimeUnit.SECONDS);
                DescribeInvocationsResponse results = future.get();
                List<DescribeInvocationsResponseBody.DescribeInvocationsResponseBodyInvocationsInvocation> invocationList = results.body.invocations.invocation;
                if (invocationList.isEmpty()) {
                    throw new RuntimeException("The command execution result was not found.");
                }
                DescribeInvocationsResponseBody.DescribeInvocationsResponseBodyInvocationsInvocation invocationResult = results.body.invocations.invocation.get(0);
                String invocationStatus = invocationResult.invocationStatus;
                switch (invocationStatus) {
                    case Constants.INVOCATION_STATUS.PENDING:
                    case Constants.INVOCATION_STATUS.RUNNING:
                    case Constants.INVOCATION_STATUS.STOPPING:
                        retryCount++;
                        continue;
                    default:
                        return results;
                }
            }
            throw new RuntimeException("Max retries exceeded for command execution result.");
        } catch (Exception e) {
            throw new RuntimeException("describeInvocationResults failed", e);
        }
    }


    public static class Constants {
        // 命令類型
        public static final class COMMAND_TYPE {
            // 適用於Linux執行個體的Shell命令。
            public static final String RUN_SHELL_SCRIPT = "RunShellScript";
            // 適用於Windows執行個體的Bat命令。
            public static final String RUN_BAT_SCRIPT = "RunBatScript";
            // 適用於Windows執行個體的PowerShell命令。
            public static final String RUN_POWERSHELL_SCRIPT = "RunPowerShellScript";
        }

        // 雲助手命令執行結果
        public static final class INVOCATION_STATUS {
            // 系統正在校正或發送命令。
            public static final String PENDING = "Pending";
            // 命令正在執行個體上執行。
            public static final String RUNNING = "Running";
            // 正在停止執行的命令。
            public static final String STOPPING = "Stopping";
        }
    }
}
import os
import time
import logging
from alibabacloud_ecs20140526 import models as ecs_20140526_models
from alibabacloud_ecs20140526.client import Client as Ecs20140526Client
from alibabacloud_tea_openapi import models as open_api_models

# 配置日誌
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')

ACCESS_KEY_ID = os.getenv("ALIBABA_CLOUD_ACCESS_KEY_ID")
ACCESS_KEY_SECRET = os.getenv("ALIBABA_CLOUD_ACCESS_KEY_SECRET")

if not ACCESS_KEY_ID or not ACCESS_KEY_SECRET:
    raise EnvironmentError(
        "Missing required environment variables: ALIBABA_CLOUD_ACCESS_KEY_ID and ALIBABA_CLOUD_ACCESS_KEY_SECRET")


def get_ecs_client(region_id):
    config = open_api_models.Config(
        access_key_id=ACCESS_KEY_ID,
        access_key_secret=ACCESS_KEY_SECRET,
        region_id=region_id
    )
    return Ecs20140526Client(config)


def execute_command(client, command_content, region_id, instance_ids, command_timeout, command_type):
    if not instance_ids:
        raise ValueError("Instance IDs list cannot be empty.")

    valid_command_types = ["RunShellScript", "RunBatScript", "RunPowerShellScript"]
    if command_type not in valid_command_types:
        raise ValueError(f"Invalid command type: {command_type}. Valid types are {valid_command_types}.")

    request = ecs_20140526_models.RunCommandRequest()
    request.region_id = region_id
    request.type = command_type
    request.command_content = command_content
    request.instance_ids = instance_ids
    request.timeout = command_timeout

    try:
        run_command_response = client.run_command(request)
        return run_command_response.to_map()['body']['InvokeId']
    except Exception as e:
        logging.error(f"Failed to execute command: {e}")
        raise


def query_invocations(client, region_id, invoke_id):
    request = ecs_20140526_models.DescribeInvocationsRequest()
    request.region_id = region_id
    request.invoke_ids = [invoke_id]

    try:
        describe_invocations_response = client.describe_invocations(request)
        return describe_invocations_response.to_map()['body']
    except Exception as e:
        logging.error(f"Failed to query invocations: {e}")
        raise


def wait_for_command_completion(client, region_id, invoke_id, max_retries, backoff_factor=2):
    retry_count = 0
    while retry_count < max_retries:
        time.sleep(backoff_factor ** retry_count)
        results = query_invocations(client, region_id, invoke_id)
        invocation_list = results.get('Invocations', {}).get('Invocation', [])
        if not invocation_list:
            raise RuntimeError("The command execution result was not found.")

        invocation_result = invocation_list[0]
        invocation_status = invocation_result.get('InvocationStatus')
        logging.info(f"Current invocation status: {invocation_status}")

        if invocation_status == "Finished":
            print("query_invocations result:", results)
            break
        elif invocation_status in ["Failed", "Stopped"]:
            raise RuntimeError(f"Command execution failed with status: {invocation_status}")
        else:
            retry_count += 1
    else:
        raise TimeoutError("Command execution timed out.")


def main():
    # 地區ID
    region_id = "cn-chengdu"
    # 執行命令的ECS執行個體ID
    instance_ids = ["i-2vcXXXXXXXXXXXXXXXb8", "i-2vcXXXXXXXXXXXXXXXot"]
    # 命令內容
    command_content = "#!/bin/bash\n cat /proc/meminfo"
    # 逾時時間
    command_timeout = 60
    # 命令類型,支援RunShellScript、RunBatScript、RunPowerShellScript
    command_type = "RunShellScript"

    client = get_ecs_client(region_id)
    invoke_id = execute_command(client, command_content, region_id, instance_ids, command_timeout, command_type)

    max_retries = max(int(command_timeout // 2), 1)
    wait_for_command_completion(client, region_id, invoke_id, max_retries)


if __name__ == "__main__":
    main()