一、JDK线程池监控参数
线程池提供了以下几个方法可以监控线程池的使用情况:
方法 | 含义 |
getActiveCount() | 线程池中正在执行任务的线程数量 |
getCompletedTaskCount() | 线程池已完成的任务数量,该值小于等于taskCount |
getCorePoolSize() | 线程池的核心线程数量 |
getLargestPoolSize() | 线程池曾经创建过的最大线程数量。通过这个数据可以知道线程池是否满过,也就是达到了maximumPoolSize |
getMaximumPoolSize() | 线程池的最大线程数量 |
getPoolSize() | 线程池当前的线程数量 |
getTaskCount() | 线程池已经执行的和未执行的任务总数 |
通过这些方法,可以对线程池进行监控,在 ThreadPoolExecutor 类中提供了几个空方法,如 beforeExecute 方法, afterExecute 方法和 terminated 方法,可以扩展这些方法在执行前或执行后增加一些新的操作,例如统计线程池的执行任务的时间等,可以继承自 ThreadPoolExecutor 来进行扩展。
package com.dxz.threadpool; import org.slf4j.Logger; import org.slf4j.LoggerFactory; import java.util.Date; import java.util.List; import java.util.Objects; import java.util.concurrent.*; import java.util.concurrent.atomic.AtomicInteger; /** * 继承ThreadPoolExecutor类,覆盖了shutdown(), shutdownNow(), beforeExecute() 和 afterExecute() * 方法来统计线程池的执行情况 * <p> * Created by on 2019/4/19. */ public class JDKThreadPoolMonitor extends ThreadPoolExecutor { private static final Logger LOGGER = LoggerFactory.getLogger(ThreadPoolMonitor.class); /** * 保存任务开始执行的时间,当任务结束时,用任务结束时间减去开始时间计算任务执行时间 */ private ConcurrentHashMap<String, Date> startTimes; /** * 线程池名称,一般以业务名称命名,方便区分 */ private String poolName; /** * 调用父类的构造方法,并初始化HashMap和线程池名称 * * @param corePoolSize 线程池核心线程数 * @param maximumPoolSize 线程池最大线程数 * @param keepAliveTime 线程的最大空闲时间 * @param unit 空闲时间的单位 * @param workQueue 保存被提交任务的队列 * @param poolName 线程池名称 */ public ThreadPoolMonitor(int corePoolSize, int maximumPoolSize, long keepAliveTime, TimeUnit unit, BlockingQueue<Runnable> workQueue, String poolName) { this(corePoolSize, maximumPoolSize, keepAliveTime, unit, workQueue, Executors.defaultThreadFactory(), poolName); } /** * 调用父类的构造方法,并初始化HashMap和线程池名称 * * @param corePoolSize 线程池核心线程数 * @param maximumPoolSize 线程池最大线程数 * @param keepAliveTime 线程的最大空闲时间 * @param unit 空闲时间的单位 * @param workQueue 保存被提交任务的队列 * @param threadFactory 线程工厂 * @param poolName 线程池名称 */ public ThreadPoolMonitor(int corePoolSize, int maximumPoolSize, long keepAliveTime, TimeUnit unit, BlockingQueue<Runnable> workQueue, ThreadFactory threadFactory, String poolName) { super(corePoolSize, maximumPoolSize, keepAliveTime, unit, workQueue, threadFactory); this.startTimes = new ConcurrentHashMap<>(); this.poolName = poolName; } /** * 线程池延迟关闭时(等待线程池里的任务都执行完毕),统计线程池情况 */ @Override public void shutdown() { // 统计已执行任务、正在执行任务、未执行任务数量 LOGGER.info("{} Going to shutdown. Executed tasks: {}, Running tasks: {}, Pending tasks: {}", this.poolName, this.getCompletedTaskCount(), this.getActiveCount(), this.getQueue().size()); super.shutdown(); } /** * 线程池立即关闭时,统计线程池情况 */ @Override public List<Runnable> shutdownNow() { // 统计已执行任务、正在执行任务、未执行任务数量 LOGGER.info("{} Going to immediately shutdown. Executed tasks: {}, Running tasks: {}, Pending tasks: {}", this.poolName, this.getCompletedTaskCount(), this.getActiveCount(), this.getQueue().size()); return super.shutdownNow(); } /** * 任务执行之前,记录任务开始时间 */ @Override protected void beforeExecute(Thread t, Runnable r) { startTimes.put(String.valueOf(r.hashCode()), new Date()); } /** * 任务执行之后,计算任务结束时间 */ @Override protected void afterExecute(Runnable r, Throwable t) { Date startDate = startTimes.remove(String.valueOf(r.hashCode())); Date finishDate = new Date(); long diff = finishDate.getTime() - startDate.getTime(); // 统计任务耗时、初始线程数、核心线程数、正在执行的任务数量、 // 已完成任务数量、任务总数、队列里缓存的任务数量、池中存在的最大线程数、 // 最大允许的线程数、线程空闲时间、线程池是否关闭、线程池是否终止 LOGGER.info("{}-pool-monitor: " + "Duration: {} ms, PoolSize: {}, CorePoolSize: {}, Active: {}, " + "Completed: {}, Task: {}, Queue: {}, LargestPoolSize: {}, " + "MaximumPoolSize: {}, KeepAliveTime: {}, isShutdown: {}, isTerminated: {}", this.poolName, diff, this.getPoolSize(), this.getCorePoolSize(), this.getActiveCount(), this.getCompletedTaskCount(), this.getTaskCount(), this.getQueue().size(), this.getLargestPoolSize(), this.getMaximumPoolSize(), this.getKeepAliveTime(TimeUnit.MILLISECONDS), this.isShutdown(), this.isTerminated()); } /** * 创建固定线程池,代码源于Executors.newFixedThreadPool方法,这里增加了poolName * * @param nThreads 线程数量 * @param poolName 线程池名称 * @return ExecutorService对象 */ public static ExecutorService newFixedThreadPool(int nThreads, String poolName) { return new ThreadPoolMonitor(nThreads, nThreads, 0L, TimeUnit.MILLISECONDS, new LinkedBlockingQueue<>(), poolName); } /** * 创建缓存型线程池,代码源于Executors.newCachedThreadPool方法,这里增加了poolName * * @param poolName 线程池名称 * @return ExecutorService对象 */ public static ExecutorService newCachedThreadPool(String poolName) { return new ThreadPoolMonitor(0, Integer.MAX_VALUE, 60L, TimeUnit.SECONDS, new SynchronousQueue<>(), poolName); } /** * 生成线程池所用的线程,只是改写了线程池默认的线程工厂,传入线程池名称,便于问题追踪 */ static class EventThreadFactory implements ThreadFactory { private static final AtomicInteger poolNumber = new AtomicInteger(1); private final ThreadGroup group; private final AtomicInteger threadNumber = new AtomicInteger(1); private final String namePrefix; /** * 初始化线程工厂 * * @param poolName 线程池名称 */ EventThreadFactory(String poolName) { SecurityManager s = System.getSecurityManager(); group = Objects.nonNull(s) ? s.getThreadGroup() : Thread.currentThread().getThreadGroup(); namePrefix = poolName + "-pool-" + poolNumber.getAndIncrement() + "-thread-"; } @Override public Thread newThread(Runnable r) { Thread t = new Thread(group, r, namePrefix + threadNumber.getAndIncrement(), 0); if (t.isDaemon()) t.setDaemon(false); if (t.getPriority() != Thread.NORM_PRIORITY) t.setPriority(Thread.NORM_PRIORITY); return t; } } }
ThreadPoolMonitor 类继承了 ThreadPoolExecutor 类,重写了shutdown() 、shutdownNow() 、beforeExecute() 和 afterExecute()方法来统计线程池的执行情况,这四个方法是 ThreadPoolExecutor 类预留给开发者进行扩展的方法,具体如下:
方法 | 含义 |
shutdown() | 线程池延迟关闭时(等待线程池里的任务都执行完毕),统计已执行任务、正在执行任务、未执行任务数量 |
shutdownNow() | 线程池立即关闭时,统计已执行任务、正在执行任务、未执行任务数量 |
beforeExecute(Thread t, Runnable r) | 任务执行之前,记录任务开始时间,startTimes这个HashMap以任务的hashCode为key,开始时间为值 |
afterExecute(Runnable r, Throwable t) | 任务执行之后,计算任务结束时间。统计任务耗时、初始线程数、核心线程数、正在执行的任务数量、已完成任务数量、任务总数、队列里缓存的任务数量、池中存在的最大线程数、最大允许的线程数、线程空闲时间、线程池是否关闭、线程池是否终止信息 |
监控日志:
22:50:25.376 [cellphone-pool-1-thread-3] INFO org.cellphone.common.pool.ThreadPoolMonitor - cellphone-pool-monitor: Duration: 1009 ms, PoolSize: 3, CorePoolSize: 3, Active: 1, Completed: 17, Task: 18, Queue: 0, LargestPoolSize: 3, MaximumPoolSize: 3, KeepAliveTime: 0, isShutdown: false, isTerminated: false
一般我们会依赖 beforeExecute 和 afterExecute 这两个方法统计的信息,具体原因请参考需要注意部分的最后一项。有了这些信息之后,我们可以根据业务情况和统计的线程池信息合理调整线程池大小,根据任务耗时长短对自身服务和依赖的其他服务进行调优,提高服务的可用性。
注意事项
1. 在 afterExecute 方法中需要注意,需要调用 ConcurrentHashMap 的 remove 方法移除并返回任务的开始时间信息,而不是调用 get 方法,因为在高并发情况下,线程池里要执行的任务很多,如果只获取值不移除的话,会使 ConcurrentHashMap 越来越大,引发内存泄漏或溢出问题。该行代码如下:
Date startDate = startTimes.remove(String.valueOf(r.hashCode()));
2. 有了ThreadPoolMonitor类之后,我们可以通过 newFixedThreadPool(int nThreads, String poolName) 和 newCachedThreadPool(String poolName) 方法创建两个日常我们使用最多的线程池,跟默认的 Executors 里的方法不同的是,这里需要传入 poolName 参数,该参数主要是用来给线程池定义一个与业务相关并有具体意义的线程池名字,方便我们排查线上问题。
3. 在生产环境中,谨慎调用 shutdown() 和 shutdownNow() 方法,因为调用这两个方法之后,线程池会被关闭,不再接收新的任务,如果有新任务提交到一个被关闭的线程池,会抛出 java.util.concurrent.RejectedExecutionException 异常。其实在使用Spring等框架来管理类的生命周期的条件下,也没有必要调用这两个方法来关闭线程池,线程池的生命周期完全由该线程池所属的Spring管理的类决定。
二、spring中实时打印线程池关键信息
package com.dxz.threadpool; /** * @author duanxz * 2021年4月6日 下午5:31:46 */ public class ThreadpoolInfo { private String label; private int activeCount; private int corePoolSize; private int maxPoolSize; private int poolSize; private String threadGroupName; private int queueRemainingCapacity; private int queueSize; private String hostAddress; public String getLabel() { return label; } public void setLabel(String label) { this.label = label; } public int getActiveCount() { return activeCount; } public void setActiveCount(int activeCount) { this.activeCount = activeCount; } public int getCorePoolSize() { return corePoolSize; } public void setCorePoolSize(int corePoolSize) { this.corePoolSize = corePoolSize; } public int getMaxPoolSize() { return maxPoolSize; } public void setMaxPoolSize(int maxPoolSize) { this.maxPoolSize = maxPoolSize; } public int getPoolSize() { return poolSize; } public void setPoolSize(int poolSize) { this.poolSize = poolSize; } public String getThreadGroupName() { return threadGroupName; } public void setThreadGroupName(String threadGroupName) { this.threadGroupName = threadGroupName; } public int getQueueRemainingCapacity() { return queueRemainingCapacity; } public void setQueueRemainingCapacity(int queueRemainingCapacity) { this.queueRemainingCapacity = queueRemainingCapacity; } public int getQueueSize() { return queueSize; } public void setQueueSize(int queueSize) { this.queueSize = queueSize; } public String getHostAddress() { return hostAddress; } public void setHostAddress(String hostAddress) { this.hostAddress = hostAddress; } @Override public String toString() { return "ThreadpoolInfo [label=" + label + ", 正在执行任务的线程数量=" + activeCount + ", corePoolSize=" + corePoolSize + ", maxPoolSize=" + maxPoolSize + ", 线程池当前的线程数量=" + poolSize + ", threadGroupName=" + threadGroupName + ", 队列剩余数量=" + queueRemainingCapacity + ", 队列使用数量=" + queueSize + ", hostAddress=" + hostAddress + "]"; } }
2、
package com.dxz.threadpool; import java.net.InetAddress; import java.util.concurrent.ThreadPoolExecutor; import org.slf4j.Logger; import org.slf4j.LoggerFactory; import org.springframework.beans.factory.annotation.Autowired; import org.springframework.boot.autoconfigure.condition.ConditionalOnProperty; import org.springframework.context.annotation.Configuration; import org.springframework.core.task.AsyncTaskExecutor; import org.springframework.scheduling.annotation.Scheduled; import org.springframework.scheduling.concurrent.ThreadPoolTaskExecutor; @Configuration @ConditionalOnProperty(name = "palmpay.sync.pool.enable", havingValue = "true") public class ThreadPoolMonitor { private static final Logger LOG = LoggerFactory.getLogger(ThreadPoolMonitor.class); @Autowired private ThreadPoolTaskExecutor syncExceutor; @Autowired private AsyncTaskExecutor asyncExecutor; @Scheduled(cron = "0/5 * * * * *") public void getThreadInfo(){ /*if(!LOG.isDebugEnabled()) { return; }*/ InetAddress inte = null; try{ inte = InetAddress.getLocalHost(); }catch(Exception e){ } Object [] threadpools = {syncExceutor, asyncExecutor}; for(Object threadpool : threadpools){ ThreadpoolInfo info = new ThreadpoolInfo(); if(threadpool instanceof ThreadPoolTaskExecutor) { info.setLabel(((ThreadPoolTaskExecutor) threadpool).getThreadNamePrefix()); //存活数量 info.setActiveCount(((ThreadPoolTaskExecutor) threadpool).getActiveCount()); //线程池基本大小 info.setCorePoolSize(((ThreadPoolTaskExecutor) threadpool).getCorePoolSize()); //最大数量 info.setMaxPoolSize(((ThreadPoolTaskExecutor) threadpool).getMaxPoolSize()); //当前线程池大小 info.setPoolSize(((ThreadPoolTaskExecutor) threadpool).getPoolSize()); //线程组名字 ThreadGroup threadGroup = ((ThreadPoolTaskExecutor) threadpool).getThreadGroup(); info.setThreadGroupName(threadGroup != null ? threadGroup.getName() : ""); ThreadPoolExecutor threadPoolExecutor = ((ThreadPoolTaskExecutor) threadpool).getThreadPoolExecutor(); //队列剩余长度 info.setQueueRemainingCapacity(threadPoolExecutor.getQueue().remainingCapacity()); //队列使用长度 info.setQueueSize(threadPoolExecutor.getQueue().size()); //服务器地址 info.setHostAddress(inte.getHostAddress()); } LOG.info(info.toString()); /*if(LOG.isDebugEnabled()) { LOG.debug(info.toString()); }*/ } } }
每5秒打印一次:
2021-04-07 19:21:05,007 [pool-3-thread-1] INFO c.t.p.c.t.ThreadPoolMonitor - ThreadpoolInfo [label=sync-, 正在执行任务的线程数量=0, corePoolSize=10, maxPoolSize=50, 线程池当前的线程数量=10, threadGroupName=, 队列剩余数量=30, 队列使用数量=0, hostAddress=10.200.110.100] 2021-04-07 19:21:05,007 [pool-3-thread-1] INFO c.t.p.c.t.ThreadPoolMonitor - ThreadpoolInfo [label=async-, 正在执行任务的线程数量=0, corePoolSize=10, maxPoolSize=50, 线程池当前的线程数量=0, threadGroupName=, 队列剩余数量=30, 队列使用数量=0, hostAddress=10.200.110.100]