本帖最后由 xioaxu790 于 2014-8-17 16:05 编辑 问题导读 1、assignTasks方法最后返回分配任务列表的是什么？ 2、为什么调度器只分配MapTask和ReduceTask？ 3、JobQueueTaskScheduler的任务调度实现原则是什么？ JobTracker启动流程源码级分析 ，TaskTracker启动过程源码级分析 )，taskTracker会通过心跳与JobTracker通信，并获取分配它的任务。用户将作业提交到JobTracker之后，放入相应的数据结构中，静等被分配。mapreduce job提交流程源码级分析（三） 这篇文章已经分析了用户提交作业的最后步骤，主要是构造作业对应的JobInProgress并加入jobs，告知所有的JobInProgressListener。 /**
* The periodic heartbeat mechanism between the {@link TaskTracker} and
* the {@link JobTracker}.
*
* The {@link JobTracker} processes the status information sent by the
* {@link TaskTracker} and responds with instructions to start/stop
* tasks or jobs, and also 'reset' instructions during contingencies.
*/
public synchronized HeartbeatResponse heartbeat(TaskTrackerStatus status,
boolean restarted,
boolean initialContact,
boolean acceptNewTasks,
short responseId)
throws IOException {
if (LOG.isDebugEnabled()) {
LOG.debug("Got heartbeat from: " + status.getTrackerName() +
" (restarted: " + restarted +
" initialContact: " + initialContact +
" acceptNewTasks: " + acceptNewTasks + ")" +
" with responseId: " + responseId);
}
// Make sure heartbeat is from a tasktracker allowed by the jobtracker.
if (!acceptTaskTracker(status)) {
throw new DisallowedTaskTrackerException(status);
}
// First check if the last heartbeat response got through
String trackerName = status.getTrackerName();
long now = clock.getTime();
if (restarted) {
faultyTrackers.markTrackerHealthy(status.getHost());
} else {
faultyTrackers.checkTrackerFaultTimeout(status.getHost(), now);
}
HeartbeatResponse prevHeartbeatResponse =
trackerToHeartbeatResponseMap.get(trackerName);
boolean addRestartInfo = false;
if (initialContact != true) {
// If this isn't the 'initial contact' from the tasktracker,
// there is something seriously wrong if the JobTracker has
// no record of the 'previous heartbeat'; if so, ask the
// tasktracker to re-initialize itself.
if (prevHeartbeatResponse == null) {
// This is the first heartbeat from the old tracker to the newly
// started JobTracker
if (hasRestarted()) {
addRestartInfo = true;
// inform the recovery manager about this tracker joining back
recoveryManager.unMarkTracker(trackerName);
} else {
// Jobtracker might have restarted but no recovery is needed
// otherwise this code should not be reached
LOG.warn("Serious problem, cannot find record of 'previous' " +
"heartbeat for '" + trackerName +
"'; reinitializing the tasktracker");
return new HeartbeatResponse(responseId,
new TaskTrackerAction[] {new ReinitTrackerAction()});
}
} else {
// It is completely safe to not process a 'duplicate' heartbeat from a
// {@link TaskTracker} since it resends the heartbeat when rpcs are
// lost see {@link TaskTracker.transmitHeartbeat()};
// acknowledge it by re-sending the previous response to let the
// {@link TaskTracker} go forward.
if (prevHeartbeatResponse.getResponseId() != responseId) {
LOG.info("Ignoring 'duplicate' heartbeat from '" +
trackerName + "'; resending the previous 'lost' response");
return prevHeartbeatResponse;
}
}
}
// Process this heartbeat
short newResponseId = (short)(responseId + 1); //响应编号+1
status.setLastSeen(now);
if (!processHeartbeat(status, initialContact, now)) {
if (prevHeartbeatResponse != null) {
trackerToHeartbeatResponseMap.remove(trackerName);
}
return new HeartbeatResponse(newResponseId,
new TaskTrackerAction[] {new ReinitTrackerAction()});
}
// Initialize the response to be sent for the heartbeat
if (recoveryManager.shouldSchedule() && acceptNewTasks && !isBlacklisted) {
TaskTrackerStatus taskTrackerStatus = getTaskTrackerStatus(trackerName);
if (taskTrackerStatus == null) {
LOG.warn("Unknown task tracker polling; ignoring: " + trackerName);
} else {
//setup和cleanup的task优先级最高
List<Task> tasks = getSetupAndCleanupTasks(taskTrackerStatus);
if (tasks == null ) {
//任务调度器分配任务
tasks = taskScheduler.assignTasks(taskTrackers.get(trackerName)); //分配任务Map OR Reduce Task
}
if (tasks != null) {
for (Task task : tasks) {
//将任务放入actions列表，返回给TaskTracker
expireLaunchingTasks.addNewTask(task.getTaskID());
if(LOG.isDebugEnabled()) {
LOG.debug(trackerName + " -> LaunchTask: " + task.getTaskID());
}
actions.add(new LaunchTaskAction(task));
}
}
}
}
// Check for tasks to be killed
List<TaskTrackerAction> killTasksList = getTasksToKill(trackerName);
if (killTasksList != null) {
actions.addAll(killTasksList);
}
// Check for jobs to be killed/cleanedup
List<TaskTrackerAction> killJobsList = getJobsForCleanup(trackerName);
if (killJobsList != null) {
actions.addAll(killJobsList);
}
// Check for tasks whose outputs can be saved
List<TaskTrackerAction> commitTasksList = getTasksToSave(status);
if (commitTasksList != null) {
actions.addAll(commitTasksList);
}
// calculate next heartbeat interval and put in heartbeat response
int nextInterval = getNextHeartbeatInterval();
response.setHeartbeatInterval(nextInterval);
response.setActions(
actions.toArray(new TaskTrackerAction[actions.size()]));
// check if the restart info is req
if (addRestartInfo) {
response.setRecoveredJobs(recoveryManager.getJobsToRecover());
}
// Update the trackerToHeartbeatResponseMap
trackerToHeartbeatResponseMap.put(trackerName, response);
// Done processing the hearbeat, now remove 'marked' tasks
removeMarkedTasks(trackerName);
return response;
} 复制代码 //JobQueueTaskScheduler最重要的方法是assignTasks，他实现了工作调度。
@Override
public synchronized List<Task> assignTasks(TaskTracker taskTracker)
throws IOException {
TaskTrackerStatus taskTrackerStatus = taskTracker.getStatus();
ClusterStatus clusterStatus = taskTrackerManager.getClusterStatus();
final int numTaskTrackers = clusterStatus.getTaskTrackers();
final int clusterMapCapacity = clusterStatus.getMaxMapTasks();
final int clusterReduceCapacity = clusterStatus.getMaxReduceTasks();
Collection<JobInProgress> jobQueue =
jobQueueJobInProgressListener.getJobQueue();
//首先它会检查 TaskTracker 端还可以做多少个 map 和 reduce 任务，将要派发的任务数是否超出这个数，
//是否超出集群的任务平均剩余可负载数。如果都没超出，则为此TaskTracker 分配一个 MapTask 或 ReduceTask 。
//
// Get map + reduce counts for the current tracker.
//
final int trackerMapCapacity = taskTrackerStatus.getMaxMapSlots();
final int trackerReduceCapacity = taskTrackerStatus.getMaxReduceSlots();
final int trackerRunningMaps = taskTrackerStatus.countMapTasks();
final int trackerRunningReduces = taskTrackerStatus.countReduceTasks();
// Assigned tasks
List<Task> assignedTasks = new ArrayList<Task>();
//
// Compute (running + pending) map and reduce task numbers across pool
//
//计算剩余的map和reduce的工作量：remaining
int remainingReduceLoad = 0;
int remainingMapLoad = 0;
synchronized (jobQueue) {
for (JobInProgress job : jobQueue) {
if (job.getStatus().getRunState() == JobStatus.RUNNING) {
remainingMapLoad += (job.desiredMaps() - job.finishedMaps());
if (job.scheduleReduces()) {
remainingReduceLoad +=
}
}
}
}
// Compute the 'load factor' for maps and reduces
double mapLoadFactor = 0.0;
if (clusterMapCapacity > 0) {
mapLoadFactor = (double)remainingMapLoad / clusterMapCapacity;
}
double reduceLoadFactor = 0.0;
if (clusterReduceCapacity > 0) {
reduceLoadFactor = (double)remainingReduceLoad / clusterReduceCapacity;
}
//
// In the below steps, we allocate first map tasks (if appropriate),
// and then reduce tasks if appropriate. We go through all jobs
// in order of job arrival; jobs only get serviced if their
// predecessors are serviced, too.
//
//
// We assign tasks to the current taskTracker if the given machine
// has a workload that's less than the maximum load of that kind of
// task.
// However, if the cluster is close to getting loaded i.e. we don't
// have enough _padding_ for speculative executions etc., we only
// schedule the "highest priority" task i.e. the task from the job
// with the highest priority.
//
final int trackerCurrentMapCapacity =
Math.min((int)Math.ceil(mapLoadFactor * trackerMapCapacity),
trackerMapCapacity);
int availableMapSlots = trackerCurrentMapCapacity - trackerRunningMaps;
boolean exceededMapPadding = false;
if (availableMapSlots > 0) {
exceededMapPadding =
exceededPadding(true, clusterStatus, trackerMapCapacity);
}
int numLocalMaps = 0;
int numNonLocalMaps = 0;
scheduleMaps:
for (int i=0; i < availableMapSlots; ++i) {
synchronized (jobQueue) {
for (JobInProgress job : jobQueue) {
if (job.getStatus().getRunState() != JobStatus.RUNNING) {
continue;
}
Task t = null;
// Try to schedule a node-local or rack-local Map task
t =
job.obtainNewNodeOrRackLocalMapTask(taskTrackerStatus,
numTaskTrackers, taskTrackerManager.getNumberOfUniqueHosts());
if (t != null) {
++numLocalMaps;
// Don't assign map tasks to the hilt!
// Leave some free slots in the cluster for future task-failures,
// speculative tasks etc. beyond the highest priority job
if (exceededMapPadding) {
break scheduleMaps;
}
// Try all jobs again for the next Map task
break;
}
// Try to schedule a node-local or rack-local Map task
//产生 Map 任务使用 JobInProgress 的obtainNewMapTask() 方法，
//实质上最后调用了 JobInProgress 的 findNewMapTask() 访问nonRunningMapCache 。
t =
job.obtainNewNonLocalMapTask(taskTrackerStatus, numTaskTrackers,
taskTrackerManager.getNumberOfUniqueHosts());
if (t != null) {
++numNonLocalMaps;
// We assign at most 1 off-switch or speculative task
// This is to prevent TaskTrackers from stealing local-tasks
// from other TaskTrackers.
break scheduleMaps;
}
}
}
}
int assignedMaps = assignedTasks.size();
//
// Same thing, but for reduce tasks
// However we _never_ assign more than 1 reduce task per heartbeat
final int trackerCurrentReduceCapacity =
Math.min((int)Math.ceil(reduceLoadFactor * trackerReduceCapacity),
trackerReduceCapacity);
final int availableReduceSlots =
Math.min((trackerCurrentReduceCapacity - trackerRunningReduces), 1);
boolean exceededReducePadding = false;
if (availableReduceSlots > 0) {
exceededReducePadding = exceededPadding(false, clusterStatus,
trackerReduceCapacity);
synchronized (jobQueue) {
for (JobInProgress job : jobQueue) {
if (job.getStatus().getRunState() != JobStatus.RUNNING ||
job.numReduceTasks == 0) {
continue;
}
//使用JobInProgress.obtainNewReduceTask() 方法，
//实质上最后调用了JobInProgress的 findNewReduceTask() 访问 nonRuningReduceCache
Task t =
job.obtainNewReduceTask(taskTrackerStatus, numTaskTrackers,
taskTrackerManager.getNumberOfUniqueHosts()
);
if (t != null) {
assignedTasks.add(t);
break;
}
// Don't assign reduce tasks to the hilt!
// Leave some free slots in the cluster for future task-failures,
// speculative tasks etc. beyond the highest priority job
if (exceededReducePadding) {
break;
}
}
}
}
if (LOG.isDebugEnabled()) {
LOG.debug("Task assignments for " + taskTrackerStatus.getTrackerName() + " --> " +
"[" + mapLoadFactor + ", " + trackerMapCapacity + ", " +
trackerCurrentMapCapacity + ", " + trackerRunningMaps + "] -> [" +
(trackerCurrentMapCapacity - trackerRunningMaps) + ", " +
assignedMaps + " (" + numLocalMaps + ", " + numNonLocalMaps +
trackerCurrentReduceCapacity + "," + trackerRunningReduces +
"] -> [" + (trackerCurrentReduceCapacity - trackerRunningReduces) +
", " + (assignedTasks.size()-assignedMaps) + "]");
}
return assignedTasks;
} 复制代码 http://www.cnblogs.com/lxf20061900/p/3775963.html 
/2 
京ICP备2020039040号
简书网举报电话：021-34700000
提升卡
置顶卡
沉默卡
喧嚣卡
变色卡
千斤顶
显身卡
