FileDocCategorySizeDatePackage
Watchdog.javaAPI DocAndroid 5.1 API19395Thu Mar 12 22:22:42 GMT 2015com.android.server

Watchdog

public class Watchdog extends Thread
This class calls its monitor every minute. Killing this process if they don't return

Fields Summary
static final String
TAG
static final boolean
localLOGV
static final boolean
DB
static final boolean
RECORD_KERNEL_THREADS
static final long
DEFAULT_TIMEOUT
static final long
CHECK_INTERVAL
static final int
COMPLETED
static final int
WAITING
static final int
WAITED_HALF
static final int
OVERDUE
public static final String[]
NATIVE_STACKS_OF_INTEREST
static Watchdog
sWatchdog
final ArrayList
mHandlerCheckers
final HandlerChecker
mMonitorChecker
android.content.ContentResolver
mResolver
com.android.server.am.ActivityManagerService
mActivity
int
mPhonePid
android.app.IActivityController
mController
boolean
mAllowRestart
Constructors Summary
private Watchdog()

        super("watchdog");
        // Initialize handler checkers for each common thread we want to check.  Note
        // that we are not currently checking the background thread, since it can
        // potentially hold longer running operations with no guarantees about the timeliness
        // of operations there.

        // The shared foreground thread is the main checker.  It is where we
        // will also dispatch monitor checks and do other work.
        mMonitorChecker = new HandlerChecker(FgThread.getHandler(),
                "foreground thread", DEFAULT_TIMEOUT);
        mHandlerCheckers.add(mMonitorChecker);
        // Add checker for main thread.  We only do a quick check since there
        // can be UI running on the thread.
        mHandlerCheckers.add(new HandlerChecker(new Handler(Looper.getMainLooper()),
                "main thread", DEFAULT_TIMEOUT));
        // Add checker for shared UI thread.
        mHandlerCheckers.add(new HandlerChecker(UiThread.getHandler(),
                "ui thread", DEFAULT_TIMEOUT));
        // And also check IO thread.
        mHandlerCheckers.add(new HandlerChecker(IoThread.getHandler(),
                "i/o thread", DEFAULT_TIMEOUT));
        // And the display thread.
        mHandlerCheckers.add(new HandlerChecker(DisplayThread.getHandler(),
                "display thread", DEFAULT_TIMEOUT));
Methods Summary
public voidaddMonitor(com.android.server.Watchdog$Monitor monitor)

        synchronized (this) {
            if (isAlive()) {
                throw new RuntimeException("Monitors can't be added once the Watchdog is running");
            }
            mMonitorChecker.addMonitor(monitor);
        }
public voidaddThread(android.os.Handler thread)

        addThread(thread, DEFAULT_TIMEOUT);
public voidaddThread(android.os.Handler thread, long timeoutMillis)

        synchronized (this) {
            if (isAlive()) {
                throw new RuntimeException("Threads can't be added once the Watchdog is running");
            }
            final String name = thread.getLooper().getThread().getName();
            mHandlerCheckers.add(new HandlerChecker(thread, name, timeoutMillis));
        }
private java.lang.StringdescribeCheckersLocked(java.util.ArrayList checkers)

        StringBuilder builder = new StringBuilder(128);
        for (int i=0; i<checkers.size(); i++) {
            if (builder.length() > 0) {
                builder.append(", ");
            }
            builder.append(checkers.get(i).describeBlockedStateLocked());
        }
        return builder.toString();
private voiddoSysRq(char c)

        try {
            FileWriter sysrq_trigger = new FileWriter("/proc/sysrq-trigger");
            sysrq_trigger.write(c);
            sysrq_trigger.close();
        } catch (IOException e) {
            Slog.w(TAG, "Failed to write to /proc/sysrq-trigger", e);
        }
private java.io.FiledumpKernelStackTraces()

        String tracesPath = SystemProperties.get("dalvik.vm.stack-trace-file", null);
        if (tracesPath == null || tracesPath.length() == 0) {
            return null;
        }

        native_dumpKernelStacks(tracesPath);
        return new File(tracesPath);
private intevaluateCheckerCompletionLocked()

        int state = COMPLETED;
        for (int i=0; i<mHandlerCheckers.size(); i++) {
            HandlerChecker hc = mHandlerCheckers.get(i);
            state = Math.max(state, hc.getCompletionStateLocked());
        }
        return state;
private java.util.ArrayListgetBlockedCheckersLocked()

        ArrayList<HandlerChecker> checkers = new ArrayList<HandlerChecker>();
        for (int i=0; i<mHandlerCheckers.size(); i++) {
            HandlerChecker hc = mHandlerCheckers.get(i);
            if (hc.isOverdueLocked()) {
                checkers.add(hc);
            }
        }
        return checkers;
public static com.android.server.WatchdoggetInstance()

        if (sWatchdog == null) {
            sWatchdog = new Watchdog();
        }

        return sWatchdog;
public voidinit(android.content.Context context, com.android.server.am.ActivityManagerService activity)

        mResolver = context.getContentResolver();
        mActivity = activity;

        context.registerReceiver(new RebootRequestReceiver(),
                new IntentFilter(Intent.ACTION_REBOOT),
                android.Manifest.permission.REBOOT, null);
private native voidnative_dumpKernelStacks(java.lang.String tracesPath)

public voidprocessStarted(java.lang.String name, int pid)
        synchronized (this) {
            if ("com.android.phone".equals(name)) {
                mPhonePid = pid;
            }
        }
    
voidrebootSystem(java.lang.String reason)
Perform a full reboot of the system.
        Slog.i(TAG, "Rebooting system because: " + reason);
        IPowerManager pms = (IPowerManager)ServiceManager.getService(Context.POWER_SERVICE);
        try {
            pms.reboot(false, reason, false);
        } catch (RemoteException ex) {
        }
    
public voidrun()
        boolean waitedHalf = false;
        while (true) {
            final ArrayList<HandlerChecker> blockedCheckers;
            final String subject;
            final boolean allowRestart;
            int debuggerWasConnected = 0;
            synchronized (this) {
                long timeout = CHECK_INTERVAL;
                // Make sure we (re)spin the checkers that have become idle within
                // this wait-and-check interval
                for (int i=0; i<mHandlerCheckers.size(); i++) {
                    HandlerChecker hc = mHandlerCheckers.get(i);
                    hc.scheduleCheckLocked();
                }

                if (debuggerWasConnected > 0) {
                    debuggerWasConnected--;
                }

                // 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) {
                    if (Debug.isDebuggerConnected()) {
                        debuggerWasConnected = 2;
                    }
                    try {
                        wait(timeout);
                    } catch (InterruptedException e) {
                        Log.wtf(TAG, e);
                    }
                    if (Debug.isDebuggerConnected()) {
                        debuggerWasConnected = 2;
                    }
                    timeout = CHECK_INTERVAL - (SystemClock.uptimeMillis() - start);
                }

                final int waitState = evaluateCheckerCompletionLocked();
                if (waitState == COMPLETED) {
                    // The monitors have returned; reset
                    waitedHalf = false;
                    continue;
                } else if (waitState == WAITING) {
                    // still waiting but within their configured intervals; back off and recheck
                    continue;
                } else if (waitState == WAITED_HALF) {
                    if (!waitedHalf) {
                        // We've waited half the deadlock-detection interval.  Pull a stack
                        // trace and wait another half.
                        ArrayList<Integer> pids = new ArrayList<Integer>();
                        pids.add(Process.myPid());
                        ActivityManagerService.dumpStackTraces(true, pids, null, null,
                                NATIVE_STACKS_OF_INTEREST);
                        waitedHalf = true;
                    }
                    continue;
                }

                // something is overdue!
                blockedCheckers = getBlockedCheckersLocked();
                subject = describeCheckersLocked(blockedCheckers);
                allowRestart = mAllowRestart;
            }

            // If we got here, that means that the system is most likely hung.
            // First collect stack traces from all threads of the system process.
            // Then kill this process so that the system will restart.
            EventLog.writeEvent(EventLogTags.WATCHDOG, subject);

            ArrayList<Integer> pids = new ArrayList<Integer>();
            pids.add(Process.myPid());
            if (mPhonePid > 0) pids.add(mPhonePid);
            // Pass !waitedHalf so that just in case we somehow wind up here without having
            // dumped the halfway stacks, we properly re-initialize the trace file.
            final File stack = ActivityManagerService.dumpStackTraces(
                    !waitedHalf, pids, null, null, NATIVE_STACKS_OF_INTEREST);

            // Give some extra time to make sure the stack traces get written.
            // The system's been hanging for a minute, another second or two won't hurt much.
            SystemClock.sleep(2000);

            // Pull our own kernel thread stacks as well if we're configured for that
            if (RECORD_KERNEL_THREADS) {
                dumpKernelStackTraces();
            }

            // Trigger the kernel to dump all blocked threads, and backtraces on all CPUs to the kernel log
            doSysRq('w");
            doSysRq('l");

            // Try to add the error to the dropbox, but assuming that the ActivityManager
            // itself may be deadlocked.  (which has happened, causing this statement to
            // deadlock and the watchdog as a whole to be ineffective)
            Thread dropboxThread = new Thread("watchdogWriteToDropbox") {
                    public void run() {
                        mActivity.addErrorToDropBox(
                                "watchdog", null, "system_server", null, null,
                                subject, null, stack, null);
                    }
                };
            dropboxThread.start();
            try {
                dropboxThread.join(2000);  // wait up to 2 seconds for it to return.
            } catch (InterruptedException ignored) {}

            IActivityController controller;
            synchronized (this) {
                controller = mController;
            }
            if (controller != null) {
                Slog.i(TAG, "Reporting stuck state to activity controller");
                try {
                    Binder.setDumpDisabled("Service dumps disabled due to hung system process.");
                    // 1 = keep waiting, -1 = kill system
                    int res = controller.systemNotResponding(subject);
                    if (res >= 0) {
                        Slog.i(TAG, "Activity controller requested to coninue to wait");
                        waitedHalf = false;
                        continue;
                    }
                } catch (RemoteException e) {
                }
            }

            // Only kill the process if the debugger is not attached.
            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);
                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!");
                Process.killProcess(Process.myPid());
                System.exit(10);
            }

            waitedHalf = false;
        }
    
public voidsetActivityController(android.app.IActivityController controller)
        synchronized (this) {
            mController = controller;
        }
    
public voidsetAllowRestart(boolean allowRestart)
        synchronized (this) {
            mAllowRestart = allowRestart;
        }