问题：
多台服务集群模式执行调度周期短的任务不能均衡负载。
原因：
下面的run()方法中，不考虑halted和siglock的情况下1）只有if (triggers != null && !triggers.isEmpty())条件满足的情况下，while循环才会进入暂停状态sigLock.wait(timeUntilContinue);2）并且获取待执行trigger时最终执行的sql以及传入的条件如下,即next fire time范围为:
QuartzSchedulerThread.java
triggers = qsRsrcs.getJobStore().acquireNextTriggers(
now + idleWaitTime, Math.min(availThreadCount, qsRsrcs.getMaxBatchSize()), qsRsrcs.getBatchTimeWindow());
JobStoreSupport.java
List keys = getDelegate().selectTriggerToAcquire(conn, noLaterThan + timeWindow, getMisfireTime(), maxCount);
protected long getMisfireTime() {
long misfireTime = System.currentTimeMillis();
if (getMisfireThreshold() > 0) {
misfireTime -= getMisfireThreshold();
}
return (misfireTime > 0) ? misfireTime : 0;
}
public long getMisfireThreshold() {
return misfireThreshold;
}
String SELECT_NEXT_TRIGGER_TO_ACQUIRE = "SELECT "
+ COL_TRIGGER_NAME + ", " + COL_TRIGGER_GROUP + ", "
+ COL_NEXT_FIRE_TIME + ", " + COL_PRIORITY + " FROM "
+ TABLE_PREFIX_SUBST + TABLE_TRIGGERS + " WHERE "
+ COL_SCHEDULER_NAME + " = " + SCHED_NAME_SUBST
+ " AND " + COL_TRIGGER_STATE + " = ? AND " + COL_NEXT_FIRE_TIME + " <= ? "
+ "AND (" + COL_MISFIRE_INSTRUCTION + " = -1 OR (" +COL_MISFIRE_INSTRUCTION+ " != -1 AND "+ COL_NEXT_FIRE_TIME + " >= ?)) "
+ "ORDER BY "+ COL_NEXT_FIRE_TIME + " ASC, " + COL_PRIORITY + " DESC";
与查询条件相关的参数：
| Variable | Property Name | Default Value |
|---|---|---|
| idleWaitTime | org.quartz.scheduler.idleWaitTime | 30000L |
| maxBatchSize | org.quartz.scheduler.batchTriggerAcquisitionMaxCount | 1 |
| batchTimeWindow | org.quartz.scheduler.batchTriggerAcquisitionFireAheadTimeWindow | 0 |
| misfireThreshold | 60000L; // one minute |
所以只有run方法中的while暂停，不去获取新的trigger时其他服务才有机会拿到执行任务，以达到负载均衡。
QuartzSchedulerThread.java
public void run() {
int acquiresFailed = 0;
while (!halted.get()) {
try {
// check if we're supposed to pause...
synchronized (sigLock) {
while (paused && !halted.get()) {
try {
// wait until togglePause(false) is called...
sigLock.wait(1000L);
} catch (InterruptedException ignore) {
}
// reset failure counter when paused, so that we don't
// wait again after unpausing
acquiresFailed = 0;
}
if (halted.get()) {
break;
}
}
// wait a bit, if reading from job store is consistently
// failing (e.g. DB is down or restarting)..
if (acquiresFailed > 1) {
try {
long delay = computeDelayForRepeatedErrors(qsRsrcs.getJobStore(), acquiresFailed);
Thread.sleep(delay);
} catch (Exception ignore) {
}
}
int availThreadCount = qsRsrcs.getThreadPool().blockForAvailableThreads();
if(availThreadCount > 0) { // will always be true, due to semantics of blockForAvailableThreads...
List triggers;
long now = System.currentTimeMillis();
clearSignaledSchedulingChange();
try {
triggers = qsRsrcs.getJobStore().acquireNextTriggers(
now + idleWaitTime, Math.min(availThreadCount, qsRsrcs.getMaxBatchSize()), qsRsrcs.getBatchTimeWindow());
acquiresFailed = 0;
if (log.isDebugEnabled())
log.debug("batch acquisition of " + (triggers == null ? 0 : triggers.size()) + " triggers");
} catch (JobPersistenceException jpe) {
if (acquiresFailed == 0) {
qs.notifySchedulerListenersError(
"An error occurred while scanning for the next triggers to fire.",
jpe);
}
if (acquiresFailed < Integer.MAX_VALUE)
acquiresFailed++;
continue;
} catch (RuntimeException e) {
if (acquiresFailed == 0) {
getLog().error("quartzSchedulerThreadLoop: RuntimeException "
+e.getMessage(), e);
}
if (acquiresFailed < Integer.MAX_VALUE)
acquiresFailed++;
continue;
}
if (triggers != null && !triggers.isEmpty()) {
now = System.currentTimeMillis();
long triggerTime = triggers.get(0).getNextFireTime().getTime();
long timeUntilTrigger = triggerTime - now;
while(timeUntilTrigger > 2) {
synchronized (sigLock) {
if (halted.get()) {
break;
}
if (!isCandidateNewTimeEarlierWithinReason(triggerTime, false)) {
try {
// we could have blocked a long while
// on 'synchronize', so we must recompute
now = System.currentTimeMillis();
timeUntilTrigger = triggerTime - now;
if(timeUntilTrigger >= 1)
sigLock.wait(timeUntilTrigger);
} catch (InterruptedException ignore) {
}
}
}
if(releaseIfScheduleChangedSignificantly(triggers, triggerTime)) {
break;
}
now = System.currentTimeMillis();
timeUntilTrigger = triggerTime - now;
}
// this happens if releaseIfScheduleChangedSignificantly decided to release triggers
if(triggers.isEmpty())
continue;
// set triggers to 'executing'
List bndles = new ArrayList();
boolean goAhead = true;
synchronized(sigLock) {
goAhead = !halted.get();
}
if(goAhead) {
try {
List res = qsRsrcs.getJobStore().triggersFired(triggers);
if(res != null)
bndles = res;
} catch (SchedulerException se) {
qs.notifySchedulerListenersError(
"An error occurred while firing triggers '"
+ triggers + "'", se);
//QTZ-179 : a problem occurred interacting with the triggers from the db
//we release them and loop again
for (int i = 0; i < triggers.size(); i++) {
qsRsrcs.getJobStore().releaseAcquiredTrigger(triggers.get(i));
}
continue;
}
}
for (int i = 0; i < bndles.size(); i++) {
TriggerFiredResult result = bndles.get(i);
TriggerFiredBundle bndle = result.getTriggerFiredBundle();
Exception exception = result.getException();
if (exception instanceof RuntimeException) {
getLog().error("RuntimeException while firing trigger " + triggers.get(i), exception);
qsRsrcs.getJobStore().releaseAcquiredTrigger(triggers.get(i));
continue;
}
// it's possible to get 'null' if the triggers was paused,
// blocked, or other similar occurrences that prevent it being
// fired at this time... or if the scheduler was shutdown (halted)
if (bndle == null) {
qsRsrcs.getJobStore().releaseAcquiredTrigger(triggers.get(i));
continue;
}
JobRunShell shell = null;
try {
shell = qsRsrcs.getJobRunShellFactory().createJobRunShell(bndle);
shell.initialize(qs);
} catch (SchedulerException se) {
qsRsrcs.getJobStore().triggeredJobComplete(triggers.get(i), bndle.getJobDetail(), CompletedExecutionInstruction.SET_ALL_JOB_TRIGGERS_ERROR);
continue;
}
if (qsRsrcs.getThreadPool().runInThread(shell) == false) {
// this case should never happen, as it is indicative of the
// scheduler being shutdown or a bug in the thread pool or
// a thread pool being used concurrently - which the docs
// say not to do...
getLog().error("ThreadPool.runInThread() return false!");
qsRsrcs.getJobStore().triggeredJobComplete(triggers.get(i), bndle.getJobDetail(), CompletedExecutionInstruction.SET_ALL_JOB_TRIGGERS_ERROR);
}
}
continue; // while (!halted)
}
} else { // if(availThreadCount > 0)
// should never happen, if threadPool.blockForAvailableThreads() follows contract
continue; // while (!halted)
}
long now = System.currentTimeMillis();
long waitTime = now + getRandomizedIdleWaitTime();
long timeUntilContinue = waitTime - now;
synchronized(sigLock) {
try {
if(!halted.get()) {
// QTZ-336 A job might have been completed in the mean time and we might have
// missed the scheduled changed signal by not waiting for the notify() yet
// Check that before waiting for too long in case this very job needs to be
// scheduled very soon
if (!isScheduleChanged()) {
sigLock.wait(timeUntilContinue);
}
}
} catch (InterruptedException ignore) {
}
}
} catch(RuntimeException re) {
getLog().error("Runtime error occurred in main trigger firing loop.", re);
}
} // while (!halted)
// drop references to scheduler stuff to aid garbage collection...
qs = null;
qsRsrcs = null;
}
其他：
https://www.quartz-scheduler.org/documentation/quartz-2.3.0/tutorials/tutorial-lesson-11.html