Android的服务（Service）（二）Service的自动重启问题

继续上篇的分析，接下来是第二个问题”Service的自动重启问题“

（一）、Service的生命周期

（二）、Service的自动重启问题

这里要说服务的自动重启问题，这个问题其实很简单，只有两个关键的方法。代码如下：

这个方法在ActivityThread的一系列针对服务的handle方法中都有调用到ActivityManagerSerice的serviceDoneExecuting()方法，但是跟重启有关的只有handleServiceArgs()，因为只有在这里才有一个叫res的参数会起作用。

private void handleServiceArgs(ServiceArgsData data) {
Service s = mServices.get(data.token);
if (s != null) {
try {
if (data.args != null) {
data.args.setExtrasClassLoader(s.getClassLoader());
}
int res;
if (!data.taskRemoved) {
//就是回调了用户服务的onStartCommand生命周期，这个做应用的都知道了，

//这里可以通过设置其返回值来控制自己的服务是否允许被重新启动，顺理成章的这个值就是res
res = s.onStartCommand(data.args, data.flags, data.startId);
} else {
s.onTaskRemoved(data.args);
res = Service.START_TASK_REMOVED_COMPLETE;
}
...............
try {
//看看系统用这个值都干了一些什么导致有这个特性
ActivityManagerNative.getDefault().serviceDoneExecuting(
data.token, 1, data.startId, res);
} catch (RemoteException e) {
// nothing to do.
}
ensureJitEnabled();
}
..................
}
}

下面就是这个特性的关键代码，里面的注释已经写的很全了，关键其作用的就是stopIfKilled这个标志。

void serviceDoneExecutingLocked(ServiceRecord r, int type, int startId, int res) {
boolean inDestroying = mDestroyingServices.contains(r);
if (r != null) {
if (type == 1) {
// This is a call from a service start...  take care of
// book-keeping.
r.callStart = true;
switch (res) {
case Service.START_STICKY_COMPATIBILITY:
case Service.START_STICKY: {
// We are done with the associated start arguments.
r.findDeliveredStart(startId, true);
// Don't stop if killed.
r.stopIfKilled = false;
break;
}
case Service.START_NOT_STICKY: {
// We are done with the associated start arguments.
r.findDeliveredStart(startId, true);
if (r.getLastStartId() == startId) {
// There is no more work, and this service
// doesn't want to hang around if killed.
r.stopIfKilled = true;
}
break;
}
case Service.START_REDELIVER_INTENT: {
// We'll keep this item until they explicitly
// call stop for it, but keep track of the fact
// that it was delivered.
ServiceRecord.StartItem si = r.findDeliveredStart(startId, false);
if (si != null) {
si.deliveryCount = 0;
si.doneExecutingCount++;
// Don't stop if killed.
r.stopIfKilled = true;
}
break;
}
case Service.START_TASK_REMOVED_COMPLETE: {
// Special processing for onTaskRemoved().  Don't
// impact normal onStartCommand() processing.
r.findDeliveredStart(startId, true);
break;
}
default:
throw new IllegalArgumentException(
"Unknown service start result: " + res);
}
if (res == Service.START_STICKY_COMPATIBILITY) {
r.callStart = false;
}
}
final long origId = Binder.clearCallingIdentity();
serviceDoneExecutingLocked(r, inDestroying, inDestroying);
Binder.restoreCallingIdentity(origId);
} else {
Slog.w(TAG, "Done executing unknown service from pid "
+ Binder.getCallingPid());
}
}

那么这个标志位又是在哪些情况下使得服务可以重启的呢？这种场景入口很多啊，比如系统清理进程等，总之就是APP Died的情况下，入口方法不列举了，最后都会执行到这来：

final void killServicesLocked(ProcessRecord app, boolean allowRestart) {
// Report disconnected services.
if (false) {
// XXX we are letting the client link to the service for
// death notifications.
if (app.services.size() > 0) {
Iterator<ServiceRecord> it = app.services.iterator();
while (it.hasNext()) {
ServiceRecord r = it.next();
for (int conni=r.connections.size()-1; conni>=0; conni--) {
ArrayList<ConnectionRecord> cl = r.connections.valueAt(conni);
for (int i=0; i<cl.size(); i++) {
ConnectionRecord c = cl.get(i);
if (c.binding.client != app) {
try {
//c.conn.connected(r.className, null);
} catch (Exception e) {
// todo: this should be asynchronous!
Slog.w(TAG, "Exception thrown disconnected servce "
+ r.shortName
+ " from app " + app.processName, e);
}
}
}
}
}
}
}

// First clear app state from services.
for (int i=app.services.size()-1; i>=0; i--) {
ServiceRecord sr = app.services.valueAt(i);
synchronized (sr.stats.getBatteryStats()) {
sr.stats.stopLaunchedLocked();
}
if (sr.app != null) {
sr.app.services.remove(sr);
}
sr.app = null;
sr.isolatedProc = null;
sr.executeNesting = 0;
sr.forceClearTracker();
if (mDestroyingServices.remove(sr)) {
if (DEBUG_SERVICE) Slog.v(TAG, "killServices remove destroying " + sr);
}

final int numClients = sr.bindings.size();
for (int bindingi=numClients-1; bindingi>=0; bindingi--) {
IntentBindRecord b = sr.bindings.valueAt(bindingi);
if (DEBUG_SERVICE) Slog.v(TAG, "Killing binding " + b
+ ": shouldUnbind=" + b.hasBound);
b.binder = null;
b.requested = b.received = b.hasBound = false;
}
}

// Clean up any connections this application has to other services.
for (int i=app.connections.size()-1; i>=0; i--) {
ConnectionRecord r = app.connections.valueAt(i);
removeConnectionLocked(r, app, null);
}
app.connections.clear();

ServiceMap smap = getServiceMap(app.userId);

// Now do remaining service cleanup.
for (int i=app.services.size()-1; i>=0; i--) {
ServiceRecord sr = app.services.valueAt(i);
// Sanity check: if the service listed for the app is not one
// we actually are maintaining, drop it.
if (smap.mServicesByName.get(sr.name) != sr) {
ServiceRecord cur = smap.mServicesByName.get(sr.name);
Slog.wtf(TAG, "Service " + sr + " in process " + app
+ " not same as in map: " + cur);
app.services.removeAt(i);
continue;
}

// Any services running in the application may need to be placed
// back in the pending list.
// 这里还是分很多种情况的
// 允许重启时，如果当前服务所在进程crash超过两次，并且不是persistent的进程就结束不会重启了
if (allowRestart && sr.crashCount >= 2 && (sr.serviceInfo.applicationInfo.flags
&ApplicationInfo.FLAG_PERSISTENT) == 0) {
Slog.w(TAG, "Service crashed " + sr.crashCount
+ " times, stopping: " + sr);
EventLog.writeEvent(EventLogTags.AM_SERVICE_CRASHED_TOO_MUCH,
sr.userId, sr.crashCount, sr.shortName, app.pid);
bringDownServiceLocked(sr);
} else if (!allowRestart) {
// 不允许重启直接挂掉
bringDownServiceLocked(sr);
} else {
//
boolean canceled = scheduleServiceRestartLocked(sr, true);

// Should the service remain running?  Note that in the
// extreme case of so many attempts to deliver a command
// that it failed we also will stop it here.
if (sr.startRequested && (sr.stopIfKilled || canceled)) {
if (sr.pendingStarts.size() == 0) {
sr.startRequested = false;
if (sr.tracker != null) {
sr.tracker.setStarted(false, mAm.mProcessStats.getMemFactorLocked(),
SystemClock.uptimeMillis());
}
if (!sr.hasAutoCreateConnections()) {
// Whoops, no reason to restart!
bringDownServiceLocked(sr);
}
}
}
}
}

if (!allowRestart) {
app.services.clear();

// Make sure there are no more restarting services for this process.
for (int i=mRestartingServices.size()-1; i>=0; i--) {
ServiceRecord r = mRestartingServices.get(i);
if (r.processName.equals(app.processName) &&
r.serviceInfo.applicationInfo.uid == app.info.uid) {
mRestartingServices.remove(i);
clearRestartingIfNeededLocked(r);
}
}
for (int i=mPendingServices.size()-1; i>=0; i--) {
ServiceRecord r = mPendingServices.get(i);
if (r.processName.equals(app.processName) &&
r.serviceInfo.applicationInfo.uid == app.info.uid) {
mPendingServices.remove(i);
}
}
}

// Make sure we have no more records on the stopping list.
int i = mDestroyingServices.size();
while (i > 0) {
i--;
ServiceRecord sr = mDestroyingServices.get(i);
if (sr.app == app) {
sr.forceClearTracker();
mDestroyingServices.remove(i);
if (DEBUG_SERVICE) Slog.v(TAG, "killServices remove destroying " + sr);
}
}

app.executingServices.clear();
}  

private final boolean scheduleServiceRestartLocked(ServiceRecord r,
boolean allowCancel) {
boolean canceled = false;

ServiceMap smap = getServiceMap(r.userId);
if (smap.mServicesByName.get(r.name) != r) {
ServiceRecord cur = smap.mServicesByName.get(r.name);
Slog.wtf(TAG, "Attempting to schedule restart of " + r
+ " when found in map: " + cur);
return false;
}

final long now = SystemClock.uptimeMillis();

if ((r.serviceInfo.applicationInfo.flags
&ApplicationInfo.FLAG_PERSISTENT) == 0) {
long minDuration = SERVICE_RESTART_DURATION;
long resetTime = SERVICE_RESET_RUN_DURATION;

// Any delivered but not yet finished starts should be put back
// on the pending list.
final int N = r.deliveredStarts.size();
if (N > 0) {
for (int i=N-1; i>=0; i--) {
ServiceRecord.StartItem si = r.deliveredStarts.get(i);
si.removeUriPermissionsLocked();
//注意了，这里的canceled如果为true还是需要结束服务的
//还要关注一下delivery的上限和doneExecuting的上限
if (si.intent == null) {
// We'll generate this again if needed.
} else if (!allowCancel || (si.deliveryCount < ServiceRecord.MAX_DELIVERY_COUNT
&& si.doneExecutingCount < ServiceRecord.MAX_DONE_EXECUTING_COUNT)) {
//重新在pendingStart中添加si，所以会在下次执行时重新带入intent进去
r.pendingStarts.add(0, si);
long dur = SystemClock.uptimeMillis() - si.deliveredTime;
dur *= 2;
if (minDuration < dur) minDuration = dur;
if (resetTime < dur) resetTime = dur;
} else {
Slog.w(TAG, "Canceling start item " + si.intent + " in service "
+ r.name);
canceled = true;
}
}
r.deliveredStarts.clear();
}

r.totalRestartCount++;
if (r.restartDelay == 0) {
r.restartCount++;
r.restartDelay = minDuration;
} else {
// If it has been a "reasonably long time" since the service
// was started, then reset our restart duration back to
// the beginning, so we don't infinitely increase the duration
// on a service that just occasionally gets killed (which is
// a normal case, due to process being killed to reclaim memory).
if (now > (r.restartTime+resetTime)) {
r.restartCount = 1;
r.restartDelay = minDuration;
} else {
r.restartDelay *= SERVICE_RESTART_DURATION_FACTOR;
if (r.restartDelay < minDuration) {
r.restartDelay = minDuration;
}
}
}

r.nextRestartTime = now + r.restartDelay;

// Make sure that we don't end up restarting a bunch of services
// all at the same time.
boolean repeat;
do {
repeat = false;
for (int i=mRestartingServices.size()-1; i>=0; i--) {
ServiceRecord r2 = mRestartingServices.get(i);
if (r2 != r && r.nextRestartTime
>= (r2.nextRestartTime-SERVICE_MIN_RESTART_TIME_BETWEEN)
&& r.nextRestartTime
< (r2.nextRestartTime+SERVICE_MIN_RESTART_TIME_BETWEEN)) {
r.nextRestartTime = r2.nextRestartTime + SERVICE_MIN_RESTART_TIME_BETWEEN;
r.restartDelay = r.nextRestartTime - now;
repeat = true;
break;
}
}
} while (repeat);

} else {
// Persistent processes are immediately restarted, so there is no
// reason to hold of on restarting their services.
r.totalRestartCount++;
r.restartCount = 0;
r.restartDelay = 0;
r.nextRestartTime = now;
}

if (!mRestartingServices.contains(r)) {
r.createdFromFg = false;
mRestartingServices.add(r);
r.makeRestarting(mAm.mProcessStats.getMemFactorLocked(), now);
}

r.cancelNotification();

mAm.mHandler.removeCallbacks(r.restarter);
// 最关键的操作在这里，忘ActivityManagerService的handler里面post一个重启的Runnable
// 这个东西前面启动过程创建ServiceRecord时有的，很简单就是一个ServiceRestarter，它里面保存了这个ServiceRecord本身
// 重启的时候根据这个record就可以直接启动服务了
mAm.mHandler.postAtTime(r.restarter, r.nextRestartTime);
r.nextRestartTime = SystemClock.uptimeMillis() + r.restartDelay;
Slog.w(TAG, "Scheduling restart of crashed service "
+ r.shortName + " in " + r.restartDelay + "ms");
EventLog.writeEvent(EventLogTags.AM_SCHEDULE_SERVICE_RESTART,
r.userId, r.shortName, r.restartDelay);

return canceled;
}

private class ServiceRestarter implements Runnable {
private ServiceRecord mService;

void setService(ServiceRecord service) {
mService = service;
}

public void run() {
synchronized(mAm) {
//后面的事情就顺利成章了。
performServiceRestartLocked(mService);
}
}
}

整个这个过程中，有好几个参数控制着是否需要重启，也定了很多参数的上限等等，这里单独列出来解释一下。

ServiceRecord.crashCount、ServiceRecord.StartItem.deliveryCount、ServiceRecord.StartItem.doneExecutingCount

crashCount顾名思义啊，就是crash的次数，这个在handleAppCrashLocked()中自增的，很明显每crash一次就会自增，没什么好说的

deliveryCount也很好理解，他是属于StartItem的，所以表示的是启动信息，是执行onStartCommand方法的次数，也就是外部startService的次数

doneExecutingCount跟deliveryCount还很有关联，类似的也是说的这个服务执行的次数，那么它们有什么区别呢？

还有两个标志位Service.START_FLAG_RETRY、Service.START_FLAG_REDELIVERY要一起看。这个在ActivesService.sendServiceArgsLocked()中可以看到。意思就是说这个服务是直接重启还是重新发送发送请求。

它们还是互斥的，这点在serviceDoneExecutingLocked()方法的START_REDELIVER_INTENT分支处理中可以得到结论，总的来说就是说onStartCommand返回START_STICKY是允许重启，而START_REDELIVER_INTENT会重新将上次的intent请求发送出去，服务中会重新接收到这个。

最后将在下篇论第三个问题

（三）、Service与其客户端的绑定如何实现，即跨进程调用问题。