context.registerReceiver(new RebootReceiver(), new IntentFilter(REBOOT_ACTION));
...
// 系统启动时间
mBootTime = System.currentTimeMillis();
}
ok,调用init函数启动完毕
2、运行中
run @ SysemServer.java
调用 Watchdog.getInstance().start(); 启动看门狗
首先看下 Watchdog 类定义: /** This class calls its monitor every minute. Killing this process if they don't return **/
public class Watchdog extends Thread {
}
long timeout = TIME_TO_WAIT;
// NOTE: We use uptimeMillis() here because we do not want to increment the time we
// wait while asleep. If the device is asleep then the thing that we are waiting
// to timeout on is asleep as well and won't have a chance to run, causing a false
// positive on when to kill things.
long start = SystemClock.uptimeMillis();
while (timeout > 0 && !mForceKillSystem) {
try {
wait(timeout); // notifyAll() is called when mForceKillSystem is set
} catch (InterruptedException e) {
Log.wtf(TAG, e);
}
timeout = TIME_TO_WAIT - (SystemClock.uptimeMillis() - start);
}
// 3、如果 mCompleted 为真表示service一切正常,后面会再讲到
if (mCompleted && !mForceKillSystem) {
// The monitors have returned.
waitedHalf = false;
continue;
}
if (!waitedHalf) {
// We've waited half the deadlock-detection interval. Pull a stack
// trace and wait another half.
ArrayList pids = new ArrayList();
pids.add(Process.myPid());
ActivityManagerService.dumpStackTraces(true, pids, null, null);
waitedHalf = true;
continue; // 不过这里会再次检测一次
} }
SystemClock.sleep(2000); // 5、打印内核栈调用关系
// Pull our own kernel thread stacks as well if we're configured for that
if (RECORD_KERNEL_THREADS) {
dumpKernelStackTraces();
}
// 6、ok,系统出问题了,检测到某个 Service 出现死锁情况,杀死SystemServer进程
// Only kill the process if the debugger is not attached.
if (!Debug.isDebuggerConnected()) {
Slog.w(TAG, "*** WATCHDOG KILLING SYSTEM PROCESS: " + name);
Process.killProcess(Process.myPid());
System.exit(10);
} else {
Slog.w(TAG, "Debugger connected: Watchdog is *not* killing the system process");
}
waitedHalf = false;
}
}
主要工作逻辑:监控线程每隔一段时间发送一条 MONITOR 线另外一个线程,另个一个线程会检查各个 Service 是否正常运行,看门狗就不停的检查并等待结果,失败则杀死SystemServer.
3、Service 检查线程
/**
* Used for scheduling monitor callbacks and checking memory usage.
*/
final class HeartbeatHandler extends Handler { @Override
public void handleMessage(Message msg) { // Looper 消息处理函数
switch (msg.what) {
case MONITOR: { // 依次检测各个服务,即调用 monitor() 函数 final int size = mMonitors.size(); for (int i = 0 ; i < size ; i++) {
mCurrentMonitor = mMonitors.get(i);
mCurrentMonitor.monitor();
}
首先加入检查队列: private ActivityManagerService() { // Add ourself to the Watchdog monitors. Watchdog.getInstance().addMonitor(this); }
然后实现 monitor() 函数: /** In this method we try to acquire our lock to make sure that we have not deadlocked */ public void monitor() { synchronized (this) { } }
明白了吧,其实就是检查这个 Service 是否发生了死锁,对于此情况就只能kill SystemServer系统了。对于死锁的产生原因非常多,但有个情况需要注意:java层死锁可能发生在调用native函数,而native函数可能与硬件交互导致时间过长而没有返回,从而导致长时间占用导致问题。
4、内存使用检测
消息发送
final class GlobalPssCollected implements Runnable {
public void run() { mHandler.sendEmptyMessage(GLOBAL_PSS); } } 检测内存处理函数: final class HeartbeatHandler extends Handler { @Override public void handleMessage(Message msg) { switch (msg.what) { case GLOBAL_PSS: { if (mHaveGlobalPss) { // During the last pass we collected pss information, so // now it is time to report it. mHaveGlobalPss = false; if (localLOGV) Slog.v(TAG, "Received global pss, logging.");