微信Android客户端的ANR监控方案

void appNotResponding(String activityShortComponentName, ApplicationInfo aInfo,    String parentShortComponentName, WindowProcessController parentProcess,    boolean aboveSystem, String annotation, boolean onlyDumpSelf) {        //......
    final boolean isSilentAnr;    synchronized (mService) {    // PowerManager.reboot() can block for a long time, so ignore ANRs while shutting down.    if (mService.mAtmInternal.isShuttingDown()) {        Slog.i(TAG, "During shutdown skipping ANR: " + this + " " + annotation);        return;    } else if (isNotResponding()) {        Slog.i(TAG, "Skipping duplicate ANR: " + this + " " + annotation);        return;    } else if (isCrashing()) {        Slog.i(TAG, "Crashing app skipping ANR: " + this + " " + annotation);        return;    } else if (killedByAm) {        Slog.i(TAG, "App already killed by AM skipping ANR: " + this + " " + annotation);        return;    } else if (killed) {        Slog.i(TAG, "Skipping died app ANR: " + this + " " + annotation);        return;    }
    // In case we come through here for the same app before completing    // this one, mark as anring now so we will bail out.    setNotResponding(true);
    // Log the ANR to the event log.    EventLog.writeEvent(EventLogTags.AM_ANR, userId, pid, processName, info.flags,            annotation);
    // Dump thread traces as quickly as we can, starting with "interesting" processes.    firstPids.add(pid);
    // Don't dump other PIDs if it's a background ANR or is requested to only dump self.    isSilentAnr = isSilentAnr();
    //......}

复制

if (!isSilentAnr && !onlyDumpSelf) {    int parentPid = pid;    if (parentProcess != null && parentProcess.getPid() > 0) {        parentPid = parentProcess.getPid();    }    if (parentPid != pid) firstPids.add(parentPid);
    if (MY_PID != pid && MY_PID != parentPid) firstPids.add(MY_PID);
    for (int i = getLruProcessList().size() - 1; i >= 0; i--) {        ProcessRecord r = getLruProcessList().get(i);        if (r != null && r.thread != null) {            int myPid = r.pid;            if (myPid > 0 && myPid != pid && myPid != parentPid && myPid != MY_PID) {                if (r.isPersistent()) {                    firstPids.add(myPid);                    if (DEBUG_ANR) Slog.i(TAG, "Adding persistent proc: " + r);                } else if (r.treatLikeActivity) {                    firstPids.add(myPid);                    if (DEBUG_ANR) Slog.i(TAG, "Adding likely IME: " + r);                } else {                    lastPids.put(myPid, Boolean.TRUE);                    if (DEBUG_ANR) Slog.i(TAG, "Adding ANR proc: " + r);                }            }        }    }}
//......
// don't dump native PIDs for background ANRs unless it is the process of interestString[] nativeProcs = null;if (isSilentAnr || onlyDumpSelf) {    for (int i = 0; i < NATIVE_STACKS_OF_INTEREST.length; i++) {        if (NATIVE_STACKS_OF_INTEREST[i].equals(processName)) {            nativeProcs = new String[] { processName };            break;        }    }} else {    nativeProcs = NATIVE_STACKS_OF_INTEREST;}
int[] pids = nativeProcs == null ? null : Process.getPidsForCommands(nativeProcs);ArrayList nativePids = null;
if (pids != null) {    nativePids = new ArrayList<>(pids.length);    for (int i : pids) {        nativePids.add(i);    }}

复制

File tracesFile = ActivityManagerService.dumpStackTraces(firstPids,        isSilentAnr ? null : processCpuTracker, isSilentAnr ? null : lastPids,        nativePids, tracesFileException, offsets);

复制

public static Pair dumpStackTraces(String tracesFile, ArrayList firstPids,        ArrayList nativePids, ArrayList extraPids) {
    long remainingTime = 20 * 1000;        //......
    if (firstPids != null) {        int num = firstPids.size();        for (int i = 0; i < num; i++) {            //......            final long timeTaken = dumpJavaTracesTombstoned(pid, tracesFile,                                                            remainingTime);
            remainingTime -= timeTaken;            if (remainingTime <= 0) {                Slog.e(TAG, "Aborting stack trace dump (current firstPid=" + pid                        + "); deadline exceeded.");                return firstPidStart >= 0 ? new Pair<>(firstPidStart, firstPidEnd) : null;            }            //......        }    }
    //......}

复制

private static long dumpJavaTracesTombstoned(int pid, String fileName, long timeoutMs) {    final long timeStart = SystemClock.elapsedRealtime();    boolean javaSuccess = Debug.dumpJavaBacktraceToFileTimeout(pid, fileName,            (int) (timeoutMs / 1000));    //......    return SystemClock.elapsedRealtime() - timeStart;}

复制

bool debuggerd_trigger_dump(pid_t tid, DebuggerdDumpType dump_type, unsigned int timeout_ms, unique_fd output_fd) {    pid_t pid = tid;    //......
    // Send the signal.    const int signal = (dump_type == kDebuggerdJavaBacktrace) ? SIGQUIT : BIONIC_SIGNAL_DEBUGGER;    sigval val = {.sival_int = (dump_type == kDebuggerdNativeBacktrace) ? 1 : 0};    if (sigqueue(pid, signal, val) != 0) {      log_error(output_fd, errno, "failed to send signal to pid %d", pid);      return false;    }    //......    LOG(INFO) << TAG "done dumping process " << pid;    return true;}

复制

void* SignalCatcher::Run(void* arg) {    //......    // Set up mask with signals we want to handle.    SignalSet signals;    signals.Add(SIGQUIT);    signals.Add(SIGUSR1);    while (true) {        int signal_number = signal_catcher->WaitForSignal(self, signals);        if (signal_catcher->ShouldHalt()) {            runtime->DetachCurrentThread();            return nullptr;        }        switch (signal_number) {            case SIGQUIT:                  signal_catcher->HandleSigQuit();                  break;            case SIGUSR1:                  signal_catcher->HandleSigUsr1();                  break;            default:                  LOG(ERROR) << "Unexpected signal %d" << signal_number;                  break;        }    }}

复制

static void *mySigQuitCatcher(void* args) {    while (true) {        int sig;        sigset_t sigSet;        sigemptyset(&sigSet);        sigaddset(&sigSet, SIGQUIT);        sigwait(&sigSet, &sig);        if (sig == SIGQUIT) {            //Got SIGQUIT        }    }}pthread_t pid;pthread_create(&pid, nullptr, mySigQuitCatcher, nullptr);pthread_detach(pid);

复制

void signalHandler(int sig, siginfo_t* info, void* uc) {    if (sig == SIGQUIT) {        //Got An ANR    }}
struct sigaction sa;sa.sa_sigaction = signalHandler;sa.sa_flags = SA_ONSTACK | SA_SIGINFO | SA_RESTART;sigaction(SIGQUIT, &sa, nullptr);

复制

sigset_t sigSet;sigemptyset(&sigSet);sigaddset(&sigSet, SIGQUIT);pthread_sigmask(SIG_UNBLOCK, &sigSet, nullptr);

复制

int tid = getSignalCatcherThreadId(); //遍历/proc/[pid]目录，找到SignalCatcher线程的tidtgkill(getpid(), tid, SIGQUIT);

复制

void appNotResponding(String activityShortComponentName, ApplicationInfo aInfo,        String parentShortComponentName, WindowProcessController parentProcess,        boolean aboveSystem, String annotation, boolean onlyDumpSelf) {    //......    synchronized (mService) {        if (isSilentAnr() && !isDebugging()) {            kill("bg anr", ApplicationExitInfo.REASON_ANR, true);            return;        }
        // Set the app's notResponding state, and look up the errorReportReceiver        makeAppNotRespondingLocked(activityShortComponentName,                annotation != null ? "ANR " + annotation : "ANR", info.toString());
        // show ANR dialog ......    }}
private void makeAppNotRespondingLocked(String activity, String shortMsg, String longMsg) {    setNotResponding(true);    // mAppErrors can be null if the AMS is constructed with injector only. This will only    // happen in tests.    if (mService.mAppErrors != null) {        notRespondingReport = mService.mAppErrors.generateProcessError(this,                ActivityManager.ProcessErrorStateInfo.NOT_RESPONDING,                activity, shortMsg, longMsg, null);    }    startAppProblemLocked();    getWindowProcessController().stopFreezingActivities();}

复制

private static boolean checkErrorState() {    try {        Application application = sApplication == null ? Matrix.with().getApplication() : sApplication;        ActivityManager am = (ActivityManager) application.getSystemService(Context.ACTIVITY_SERVICE);        List procs = am.getProcessesInErrorState();        if (procs == null) return false;        for (ActivityManager.ProcessErrorStateInfo proc : procs) {            if (proc.pid != android.os.Process.myPid()) continue;            if (proc.condition != ActivityManager.ProcessErrorStateInfo.NOT_RESPONDING) continue;            return true;        }        return false;    } catch (Throwable t){        MatrixLog.e(TAG,"[checkErrorState] error : %s", t.getMessage());    }    return false;}

复制

private static boolean isMainThreadStuck(){    try {        MessageQueue mainQueue = Looper.getMainLooper().getQueue();        Field field = mainQueue.getClass().getDeclaredField("mMessages");        field.setAccessible(true);        final Message mMessage = (Message) field.get(mainQueue);        if (mMessage != null) {            long when = mMessage.getWhen();            if(when == 0) {                return false;            }            long time = when - SystemClock.uptimeMillis();            long timeThreshold = BACKGROUND_MSG_THRESHOLD;            if (foreground) {                timeThreshold = FOREGROUND_MSG_THRESHOLD;            }            return time < timeThreshold;        }    } catch (Exception e){        return false;    }    return false;}

复制

int (*original_connect)(int __fd, const struct sockaddr* __addr, socklen_t __addr_length);int my_connect(int __fd, const struct sockaddr* __addr, socklen_t __addr_length) {    if (strcmp(__addr->sa_data, "/dev/socket/tombstoned_java_trace") == 0) {        isTraceWrite = true;        signalCatcherTid = gettid();    }    return original_connect(__fd, __addr, __addr_length);}
int (*original_open)(const char *pathname, int flags, mode_t mode);int my_open(const char *pathname, int flags, mode_t mode) {    if (strcmp(pathname, "/data/anr/traces.txt") == 0) {        isTraceWrite = true;        signalCatcherTid = gettid();    }    return original_open(pathname, flags, mode);}
ssize_t (*original_write)(int fd, const void* const __pass_object_size0 buf, size_t count);ssize_t my_write(int fd, const void* const buf, size_t count) {    if(isTraceWrite && signalCatcherTid == gettid()) {        isTraceWrite = false;        signalCatcherTid = 0;        char *content = (char *) buf;        printAnrTrace(content);    }    return original_write(fd, buf, count);}
void hookAnrTraceWrite() {    int apiLevel = getApiLevel();    if (apiLevel < 19) {        return;    }    if (apiLevel >= 27) {        plt_hook("libcutils.so", "connect", (void *) my_connect, (void **) (&original_connect));    } else {        plt_hook("libart.so", "open", (void *) my_open, (void **) (&original_open));    }
    if (apiLevel >= 30 || apiLevel == 25 || apiLevel ==24) {        plt_hook("libc.so", "write", (void *) my_write, (void **) (&original_write));    } else if (apiLevel == 29) {        plt_hook("libbase.so", "write", (void *) my_write, (void **) (&original_write));    } else {        plt_hook("libart.so", "write", (void *) my_write, (void **) (&original_write));    }}

复制