WatchDog 工作原理（下）

(点击 上方公众号 ，可快速关注)

来源：伯乐在线专栏作者 - gityuan

链接：http://android.jobbole.com/84881/

点击 → 了解如何加入专栏作者

接上文

//获取等待状态【见小节3.3】

final int waitState = evaluateCheckerCompletionLocked ();

if ( waitState == COMPLETED ) {

waitedHalf = false ;

continue ;

} else if ( waitState == WAITING ) {

continue ;

} else if ( waitState == WAITED_HALF ) {

if ( ! waitedHalf ) {

//第一次进入等待时间过半的状态

ArrayList pids = new ArrayList ();

pids . add ( Process . myPid ());

//则输出栈信息【见小节3.4】

ActivityManagerService . dumpStackTraces ( true , pids , null , null ,

NATIVE_STACKS_OF_INTEREST );

waitedHalf = true ;

}

continue ;

}

//获取被阻塞的checkers

blockedCheckers = getBlockedCheckersLocked ();

subject = describeCheckersLocked ( blockedCheckers );

allowRestart = mAllowRestart ;

}

EventLog . writeEvent ( EventLogTags . WATCHDOG , subject );

ArrayList pids = new ArrayList ();

pids . add ( Process . myPid ());

if ( mPhonePid > 0 ) pids . add ( mPhonePid );

//waitedHalf=true，则追加输出栈信息【见小节3.4】

final File stack = ActivityManagerService . dumpStackTraces (

! waitedHalf , pids , null , null , NATIVE_STACKS_OF_INTEREST );

//系统已被阻塞1分钟，也不在乎多等待2s来确保stack trace信息输出

SystemClock . sleep ( 2000 );

if ( RECORD_KERNEL_THREADS ) {

//输出kernel栈信息【见小节3.5】

dumpKernelStackTraces ();

}

//触发kernel来dump所有阻塞线程【见小节3.6】

doSysRq ( 'l' );

//输出dropbox信息【见小节3.7】

Thread dropboxThread = new Thread ( "watchdogWriteToDropbox" ) {

public void run () {

mActivity . addErrorToDropBox (

"watchdog" , null , "system_server" , null , null ,

subject , null , stack , null );

}

};

dropboxThread . start ();

try {

//等待dropbox线程工作2s

dropboxThread . join ( 2000 );

} catch ( InterruptedException ignored ) {}

IActivityController controller ;

synchronized ( this ) {

controller = mController ;

}

if ( controller != null ) {

//将阻塞状态报告给activity controller，

try {

Binder . setDumpDisabled ( "Service dumps disabled due to hung system process." );

//返回值为1表示继续等待，-1表示杀死系统

int res = controller . systemNotResponding ( subject );

if ( res >= 0 ) {

waitedHalf = false ; //继续等待

continue ;

}

} catch ( RemoteException e ) {

}

}

//当debugger没有attach时，才杀死进程

if ( Debug . isDebuggerConnected ()) {

debuggerWasConnected = 2 ;

}

if ( debuggerWasConnected >= 2 ) {

Slog . w ( TAG , "Debugger connected: Watchdog is *not* killing the system process" );

} else if ( debuggerWasConnected > 0 ) {

Slog . w ( TAG , "Debugger was connected: Watchdog is *not* killing the system process" );

} else if ( ! allowRestart ) {

Slog . w ( TAG , "Restart not allowed: Watchdog is *not* killing the system process" );

} else {

Slog . w ( TAG , "*** WATCHDOG KILLING SYSTEM PROCESS: " + subject );

//遍历输出阻塞线程的栈信息

for ( int i = 0 ; i blockedCheckers . size (); i ++ ) {

Slog . w ( TAG , blockedCheckers . get ( i ). getName () + " stack trace:" );

StackTraceElement [] stackTrace

= blockedCheckers . get ( i ). getThread (). getStackTrace ();

for ( StackTraceElement element : stackTrace ) {

Slog . w ( TAG , "    at " + element );

}

}

Slog . w ( TAG , "*** GOODBYE!" );

//杀死进程system_server【见小节3.8】

Process . killProcess ( Process . myPid ());

System . exit ( 10 );

}

waitedHalf = false ;

}

}

3.2 scheduleCheckLocked

public final class HandlerChecker implements Runnable {

...

public void scheduleCheckLocked () {

if ( mMonitors . size () == 0 && mHandler . getLooper (). getQueue (). isPolling ()) {

mCompleted = true ;

return ;

}

if ( ! mCompleted ) {

return ; //有一个check正在处理中，则无需重复发送

}

mCompleted = false ;

mCurrentMonitor = null ;

mStartTime = SystemClock . uptimeMillis ();

//发送消息，插入消息队列最开头【见3.2.1】

mHandler . postAtFrontOfQueue ( this );

}

}

postAtFrontOfQueue(this)，该方法输入参数为Runnable对象，根据消息机制，回调HandlerChecker中的run方法。

3.2.1 HandlerChecker.run

public final class HandlerChecker implements Runnable {

public void run () {

final int size = mMonitors . size ();

for ( int i = 0 ; i size ; i ++ ) {

synchronized ( Watchdog . this ) {

mCurrentMonitor = mMonitors . get ( i );

}

//回调具体服务的monitor方法

mCurrentMonitor . monitor ();

}

synchronized ( Watchdog . this ) {

mCompleted = true ;

mCurrentMonitor = null ;

}

}

}

回调的方法，例如BinderThreadMonitor.monitor

3.3 evaluateCheckerCompletionLocked

private int evaluateCheckerCompletionLocked () {

int state = COMPLETED ;

for ( int i = 0 ; i mHandlerCheckers . size (); i ++ ) {

HandlerChecker hc = mHandlerCheckers . get ( i );

//【见小节3.3.1】

state = Math . max ( state , hc . getCompletionStateLocked ());

}

return state ;

}

获取mHandlerCheckers列表中等待状态值最大的state.

3.3.1 getCompletionStateLocked

public int getCompletionStateLocked () {

if ( mCompleted ) {

return COMPLETED ;

} else {

long latency = SystemClock . uptimeMillis () - mStartTime ;

if ( latency mWaitMax / 2 ) {

return WAITING ;

} else if ( latency mWaitMax ) {

return WAITED_HALF ;