基于JSCH的简易服务监控服务-WatchDog

2022-11-22 20:19:14 浏览数 (2)

需求: 程序出bug在所难免,为减少出问题时导致用户无法正常使用的时长过长,人工处理跟进以外,还需要24小时的监控服务,最好能够直接完成应急处理。

主要功能为项目失效后自动重启,重启失败或者指定多少秒以后依旧未恢复正常的话就发送短信给指定维护人员。

核心实习为spring定时任务Schduled,指定固定时长去请求需要监控的服务心跳接口,如果累计多少秒后依旧未正常响应,基本排除网络卡顿原因,此时首先重启服务,指定时间后再次检测,如果未成功恢复响应,说明重启失败或者是服务器问题,需要后端维护人员去处理,就发送短信进行通知。

要实现从服务中控制重启其他服务,这里就需要引入Jsch(Java Secure Channel),功能简而言之就是以java的方式通过jsch连接,来对服务器进行操作,发送短信就是阿里云sms服务,引入调用即可。

引入项目中使用的依赖

代码语言:javascript复制
 <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-web</artifactId>
        </dependency>
        <dependency>
            <groupId>com.alibaba.cloud</groupId>
            <artifactId>spring-cloud-starter-alibaba-nacos-discovery</artifactId>
        </dependency>
        <dependency>
            <groupId>com.alibaba.cloud</groupId>
            <artifactId>spring-cloud-starter-alibaba-nacos-config</artifactId>
        </dependency>
        <dependency>
            <groupId>org.springframework.cloud</groupId>
            <artifactId>spring-cloud-starter-openfeign</artifactId>
        </dependency>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-data-redis</artifactId>
        </dependency>
        <dependency>
            <groupId>com.aliyun</groupId>
            <artifactId>aliyun-java-sdk-core</artifactId>
        </dependency>
        <dependency>
            <groupId>org.apache.commons</groupId>
            <artifactId>commons-pool2</artifactId>
        </dependency>
        <dependency>
            <groupId>com.aliyun.oss</groupId>
            <artifactId>aliyun-sdk-oss</artifactId>
        </dependency>
        <dependency>
            <groupId>com.jcraft</groupId>
            <artifactId>jsch</artifactId>
            <version>0.1.51</version>
        </dependency>

远程连接所需数据封装成一个实体类POJO

代码语言:javascript复制
public class SshContextConf {

    private String      remoteHost;  //远程连接服务器地址
    private int         remotePort = 22; //远程连接服务器端口
    private String      userName ; // 远程连接的用户名
    private String      password; //远程连接用户的密码
    private String identity = "~/.ssh/id_rsa";
    private String passphrase = "";

    public SshContextConf(String userName, String remoteHost, String password) {
        this.userName = userName;
        this.remoteHost = remoteHost;
        this.password = password;
    }
}

JSCH调用工具类

代码语言:javascript复制
public class SshCmdClient {

    private JSch jsch;

    private Session session;

    private SshContextConf conf;

    public SshCmdClient() {
        SshContextConf conf = new SshContextConf("登录用户","登陆地址","登陆密码");
        this.conf=conf;
        jsch = new JSch();
        connect();
    }


    /**
     * 关闭ssh连接
     */
    public void close() {
        session.disconnect();
    }

    /**
     * 本地端口转发
     *
     * @param localPort      被转发的本地端口
     * @param remoteHost     转发后的服务器
     * @param remoteHostPost 转发后的服务器的端口
     */
    public void forwardingL(int localPort, String remoteHost, int remoteHostPost) {
        if (session == null) {
            throw new RuntimeException("please establish ssh connection before forwardingL");
        }
        try {
            int assinged_port = session.setPortForwardingL(localPort, remoteHost, remoteHostPost);
            System.out.println("本地端口转发成功  from localhost:"   assinged_port   " to "   remoteHost   ":"   remoteHostPost);
        } catch (JSchException e) {
            e.printStackTrace();
        }
    }

    /**
     * 远程端口转发
     *
     * @param remotePort 被转发的远程端口
     * @param localHost  转发后的服务器地址
     * @param localPort  转发后的服务器的端口
     */
    public void forwardingR(int remotePort, String localHost, int localPort) {
        if (session == null) {
            throw new RuntimeException("please establish ssh connection before forwardingR");
        }
        try {
            session.setPortForwardingR(remotePort, localHost, localPort);
            System.out.println("远程端口转发成功  from "   conf.getRemoteHost()   ":"   remotePort   " to "   localHost   ":"   localPort);
        } catch (JSchException e) {
            e.printStackTrace();
        }
    }


    /**
     * 取消已分配的本地端口转发
     *
     * @param localPort 被转发的本地端口
     */
    public void delForwardingL(int localPort) {
        try {
            session.delPortForwardingL(localPort);
        } catch (JSchException e) {
            e.printStackTrace();
        }
    }

    /**
     * 取消已分配的远程端口转发
     *
     * @param remotePort 被转发的远程端口
     */
    public void delForwardingR(int remotePort) {
        try {
            session.delPortForwardingR(remotePort);
        } catch (JSchException e) {
            e.printStackTrace();
        }
    }

    /**
     * 执行指令没有返回结果
     */
    public void executeExecN(String command) {
        executeExec(command, false);
    }

    /**
     * 执行指令有返回结果
     */
    public List<String> executeExec(String command) {
        return executeExec(command, true);
    }


    /**
     * 执行指令
     *
     * @param command    指令
     * @param needResult 是否需要返回急指令执行结果
     * @return 指令执行结果
     */
    public List<String> executeExec(String command, boolean needResult) {
        isDisconnect();
        List<String> resultLines = null;
        ChannelExec execChannel = null;
        try {
            execChannel = (ChannelExec) session.openChannel("exec");
            execChannel.setCommand(command);
            execChannel.setErrStream(System.err);
            execChannel.connect(10000);
            if (needResult) {
                resultLines = collectResult(execChannel.getInputStream());
            }
        } catch (IOException | JSchException e) {
            e.printStackTrace();
        } finally {
            if (execChannel != null) {
                try {
                    execChannel.disconnect();
                } catch (Exception e) {
                    System.out.println("JSch channel disconnect error:"   e);
                }
            }
        }
        return resultLines;
    }


    /**
     * 收集脚本执行的结果
     *
     * @param input ssh连接通道输入流
     * @return 脚本执行的结果
     */
    private List<String> collectResult(InputStream input) {
        List<String> resultLines = new ArrayList<>();
        try {
            BufferedReader inputReader = new BufferedReader(new InputStreamReader(input));
            String inputLine = null;
            while ((inputLine = inputReader.readLine()) != null) {
                resultLines.add(inputLine);
            }
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            if (input != null) {
                try {
                    input.close();
                } catch (Exception e) {
                    System.err.println("JSch inputStream close error:"   e);
                }
            }
        }
        return resultLines;
    }

    /**
     * 上传文件
     *
     * @param lfile 被上传的本地文件
     * @param rfile 上传后的服务器保存的位置
     */
    public void upload(String lfile, String rfile) {
        FileInputStream fis = null;
        try {
            boolean ptimestamp = false;
            // exec 'scp -t rfile' remotely
            rfile = rfile.replace("'", "'\''");
            rfile = "'"   rfile   "'";
            String command = "scp "   (ptimestamp ? "-p" : "")   " -t "   rfile;
            Channel channel = session.openChannel("exec");
            ((ChannelExec) channel).setCommand(command);

            // get I/O streams for remote scp
            OutputStream out = channel.getOutputStream();
            InputStream in = channel.getInputStream();

            channel.connect();

            if (checkAck(in) != 0) {
                return;
            }

            File _lfile = new File(lfile);

            if (ptimestamp) {
                command = "T "   (_lfile.lastModified() / 1000)   " 0";
                // The access time should be sent here,
                // but it is not accessible with JavaAPI ;-<
                command  = (" "   (_lfile.lastModified() / 1000)   " 0n");
                out.write(command.getBytes());
                out.flush();
                if (checkAck(in) != 0) {
                    System.exit(0);
                }
            }

            // send "C0644 filesize filename", where filename should not include '/'
            long filesize = _lfile.length();
            command = "C0644 "   filesize   " ";
            if (lfile.lastIndexOf('/') > 0) {
                command  = lfile.substring(lfile.lastIndexOf('/')   1);
            } else {
                command  = lfile;
            }
            command  = "n";
            out.write(command.getBytes());
            out.flush();
            if (checkAck(in) != 0) {
                return;
            }

            // send a content of lfile
            fis = new FileInputStream(lfile);
            byte[] buf = new byte[1024];
            while (true) {
                int len = fis.read(buf, 0, buf.length);
                if (len <= 0) {
                    break;
                }
                out.write(buf, 0, len); //out.flush();
            }
            fis.close();
            fis = null;
            // send ''
            buf[0] = 0;
            out.write(buf, 0, 1);
            out.flush();
            if (checkAck(in) != 0) {
                return;
            }
            out.close();
            channel.disconnect();
        } catch (Exception e) {
            e.printStackTrace();
            try {
                if (fis != null) {
                    fis.close();
                }
            } catch (Exception e1) {
                e1.printStackTrace();
            }
        }
    }

    /**
     * 下载文件
     *
     * @param source      被下载的文件
     * @param destination 下载后本地保存的路径
     * @return
     */
    public long download(String source, String destination) {
        FileOutputStream fileOutputStream = null;
        try {
            ChannelExec channel = (ChannelExec) session.openChannel("exec");
            channel.setCommand("scp -f "   source);
            OutputStream out = channel.getOutputStream();
            InputStream in = channel.getInputStream();
            channel.connect();
            byte[] buf = new byte[1024];
            //send ''
            buf[0] = 0;
            out.write(buf, 0, 1);
            out.flush();
            while (true) {
                if (checkAck(in) != 'C') {
                    break;
                }
            }
            //read '644 '
            in.read(buf, 0, 4);
            long fileSize = 0;
            while (true) {
                if (in.read(buf, 0, 1) < 0) {
                    break;
                }
                if (buf[0] == ' ') {
                    break;
                }
                fileSize = fileSize * 10L   (long) (buf[0] - '0');
            }
            String file = null;
            for (int i = 0; ; i  ) {
                in.read(buf, i, 1);
                if (buf[i] == (byte) 0x0a) {
                    file = new String(buf, 0, i);
                    break;
                }
            }
            // send ''
            buf[0] = 0;
            out.write(buf, 0, 1);
            out.flush();
            // read a content of lfile
            if (Files.isDirectory(Paths.get(destination))) {
                fileOutputStream = new FileOutputStream(destination   File.separator   file);
            } else {
                fileOutputStream = new FileOutputStream(destination);
            }
            long sum = 0;
            while (true) {
                int len = in.read(buf, 0, buf.length);
                if (len <= 0) {
                    break;
                }
                sum  = len;
                if (len >= fileSize) {
                    fileOutputStream.write(buf, 0, (int) fileSize);
                    break;
                }
                fileOutputStream.write(buf, 0, len);
                fileSize -= len;
            }
            return sum;
        } catch (Exception e) {
            e.printStackTrace();
        } finally {
            if (fileOutputStream != null) {
                try {
                    fileOutputStream.close();
                } catch (Exception e) {
                    e.printStackTrace();
                }
            }
        }
        return -1;
    }

    private int checkAck(InputStream in) throws IOException {
        int b = in.read();
        // b may be 0 for success,
        //          1 for error,
        //          2 for fatal error,
        //          -1
        if (b == 0) {
            return b;
        }
        if (b == -1) {
            return b;
        }

        if (b == 1 || b == 2) {
            StringBuffer sb = new StringBuffer();
            int c;
            do {
                c = in.read();
                sb.append((char) c);
            }
            while (c != 'n');
            if (b == 1) { // error
                System.out.print(sb.toString());
            }
            if (b == 2) { // fatal error
                System.out.print(sb.toString());
            }
        }
        return b;
    }

    /**
     * 判断是否断开ssh连接进行重连
     */
    private void isDisconnect() {
        if (!session.isConnected()) {
            connect();
        }
    }

    /**
     * 建立ssh连接
     */
    private void connect() {
        try {
            if (Files.exists(Paths.get(conf.getIdentity()))) {
                jsch.addIdentity(conf.getIdentity(), conf.getPassphrase());
            }
            session = jsch.getSession(conf.getUserName(), conf.getRemoteHost(), conf.getRemotePort());
            session.setPassword(conf.getPassword());
            session.setConfig("StrictHostKeyChecking", "no"); // 关闭确认提示
            session.connect(30000);
        } catch (JSchException e) {
            e.printStackTrace();
        }
    }
}

监控重启逻辑实现

代码语言:javascript复制
public class ServerScheduled {
    @Autowired
    RestTemplateClient restTemplateClient;
    @Autowired
    RedisTemplate<String, String> redisTemplate;
    @Autowired
    SmsUtil smsUtil;

    private SshServiceClient sshServiceClient() {
        return new SshServiceClient();
    }
    private SshCmdClient sshCmdClient(){
        return new SshCmdClient();
    }


    @Scheduled(fixedDelay = 10000)
    public void serviceHeart() throws IOException {
        String heart = null;
        try {
            heart = restTemplateClient.serviceHeart();
        } catch (Exception e) {
            heart = "GG";
        }
        int newTime = 0;
        log.info("heart:{}", heart);
        if (!StringUtils.pathEquals("ok", heart)) {
            String time = redisTemplate.opsForValue().get("qdchess-watchdog:service-time");
            if (time == null) {
                redisTemplate.opsForValue().set("qdchess-watchdog:service-time", 1   "");
            } else {
                newTime = Integer.parseInt(time);
            }
            if (newTime < 6) {
                redisTemplate.opsForValue().set("qdchess-watchdog:service-time", (newTime   1)   "");
            } else if (newTime == 6) {
                redisTemplate.opsForValue().set("qdchess-watchdog:service-time", (newTime   1)   "");
                log.info("服务已断开:{}秒", newTime * 10);
                log.info("------------重启服务------------");
                try {
                    String cmd = "cd /home/dragon/qdchess;  "  
                            "ps -ef | grep qdchess-service-1.0.0.jar | grep -v grep | awk '{print $2}' | xargs kill -9;"  
                            " nohup java -jar qdchess-service-1.0.0.jar  > qdchess-service.out 2>&1 &";
                    List<String> result = sshServiceClient().executeExec(cmd);
                    log.info("result:{}", result);

                } catch (Exception e) {
                    e.printStackTrace();
                    log.info("----------重启报错----------");
                }finally {
                    sshServiceClient().close();
                }
            } else if (newTime == 18 || newTime == 30 || newTime == 90 || newTime == 180 || newTime == 360 || newTime == 720) {
                //3分钟||5分钟||15分钟||30分钟||60分钟||120分钟
                redisTemplate.opsForValue().set("qdchess-watchdog:service-time", (newTime   1)   "");
                log.info("服务已断开:{}秒", newTime * 10);
                log.info("------------发送短信------------");
                smsUtil.sendSms("1*********8", "qdchess-service", newTime * 10);//smsUtil为短信工具类,以前的文章中有。
              
                log.info("------------再次重启服务------------");
                try {
                    String cmd = "cd /home/dragon/qdchess;  "  
                            "ps -ef | grep qdchess-service-1.0.0.jar | grep -v grep | awk '{print $2}' | xargs kill -9;"  
                            " nohup java -jar qdchess-service-1.0.0.jar  > qdchess-service.out 2>&1 &";
                    List<String> result = sshServiceClient().executeExec(cmd);
                    log.info("result:{}", result);
                } catch (Exception e) {
                    e.printStackTrace();
                    log.info("----------重启报错----------");
                }finally {
                    sshServiceClient().close();
                }
            } else {
                redisTemplate.opsForValue().set("qdchess-watchdog:service-time", (newTime   1)   "");
                log.info("服务已断开:{}秒", newTime * 10);
            }
        } else {
            redisTemplate.delete("qdchess-watchdog:service-time");
        }
    }
}

此处需要监控的那边的服务有一个为heart的心跳接口用于检测状态,如果不方便修改也可以使用其他的接口,主要就是可以确保服务器的运行状态即可。

Post Views: 195

0 人点赞