blockCanary原理
blockCanary
对于android里面的性能优化，最主要的问题就是UI线程的阻塞导致的，对于如何准确的计算UI的绘制所耗费的时间，是非常有必要的，blockCanary是基于这个需求出现的，同样的，也是基于LeakCanary，和LeakCanary有着显示页面和堆栈信息。
使用
首先在gradle引入
implementation 'com.github.markzhai:blockcanary-android:1.5.0'
然后Application里面进行初始化和start
BlockCanary.install(this, new BlockCanaryContext()).start();
原理：
其中BlockCanaryContext表示的就是我们监测的某些参数,包括卡顿的阈值、输出文件的路径等等
//默认卡顿阈值为1000ms
public int provideBlockThreshold() {
return 1000;
}
//输出的log
public String providePath() {
return "/blockcanary/";
}
//支持文件上传
public void upload(File zippedFile) {
throw new UnsupportedOperationException();
}
//可以在卡顿提供自定义操作
@Override
public void onBlock(Context context, BlockInfo blockInfo) {
}
其中，init只是创建出BlockCanary实例。主要是start方法的操作。
/**
* Start monitoring.
*/
public void start() {
if (!mMonitorStarted) {
mMonitorStarted = true;
Looper.getMainLooper().setMessageLogging(mBlockCanaryCore.monitor);
}
}
其实就是给主线程的Looper设置一个monitor。
我们可以先看看主线程的looper实现。
public static void loop() {
...
for (;;) {
...
// This must be in a local variable, in case a UI event sets the logger
Printer logging = me.mLogging;
if (logging != null) {
logging.println(">>>>> Dispatching to " + msg.target + " " +
msg.callback + ": " + msg.what);
}
msg.target.dispatchMessage(msg);
if (logging != null) {
logging.println("<<<<< Finished to " + msg.target + " " + msg.callback);
}
...
}
}
在上面的loop循环的代码中，msg.target.dispatchMessage就是我们UI线程收到每一个消息需要执行的操作，都在其内部执行。
系统也在其执行的前后都会执行logging类的print的方法，这个方法是我们可以自定义的。所以只要我们在运行的前后都添加一个时间戳，用运行后的时间减去运行前的时间，一旦这个时间超过了我们设定的阈值，那么就可以说这个操作卡顿，阻塞了UI线程，最后通过dump出此时的各种信息，来分析各种性能瓶颈。
那么接下来可以看看这个monitor的println方法。
@Override
public void println(String x) {
//如果当前是在调试中，那么直接返回，不做处理
if (mStopWhenDebugging && Debug.isDebuggerConnected()) {
return;
}
if (!mPrintingStarted) {
//执行操作前
mStartTimestamp = System.currentTimeMillis();
mStartThreadTimestamp = SystemClock.currentThreadTimeMillis();
mPrintingStarted = true;
startDump();
} else {
//执行操作后
final long endTime = System.currentTimeMillis();
mPrintingStarted = false;
//是否卡顿
if (isBlock(endTime)) {
notifyBlockEvent(endTime);
}
stopDump();
}
}
在ui操作执行前，将会记录当前的时间戳，同时会startDump。
在ui操作执行后，将会计算当前是否卡顿了，如果卡顿了，将会回调到onBlock的onBlock方法。同时将会停止dump。
为什么操作之前就开启了startDump，而操作执行之后就stopDump呢?
private void startDump() {
if (null != BlockCanaryInternals.getInstance().stackSampler) {
BlockCanaryInternals.getInstance().stackSampler.start();
}
if (null != BlockCanaryInternals.getInstance().cpuSampler) {
BlockCanaryInternals.getInstance().cpuSampler.start();
}
}
public void start() {
if (mShouldSample.get()) {
return;
}
mShouldSample.set(true);
HandlerThreadFactory.getTimerThreadHandler().removeCallbacks(mRunnable);
HandlerThreadFactory.getTimerThreadHandler().postDelayed(mRunnable,
BlockCanaryInternals.getInstance().getSampleDelay());
}
其实startDump的时候并没有马上start，而是会postDelay一个runnable，这个runnable就是执行dump的真正的操作，delay的时间就是我们设置的阈值的0.8
也就是，一旦我们的stop在设置的延迟时间之前执行，就不会真正的执行dump操作。
public void stop() {
if (!mShouldSample.get()) {
return;
}
mShouldSample.set(false);
HandlerThreadFactory.getTimerThreadHandler().removeCallbacks(mRunnable);
}
只有当stop操作在设置的延迟时间之后执行，才会执行dump操作。
private Runnable mRunnable = new Runnable() {
@Override
public void run() {
doSample();
if (mShouldSample.get()) {
HandlerThreadFactory.getTimerThreadHandler()
.postDelayed(mRunnable, mSampleInterval);
}
}
};
这个doSameple分别会dump出stack信息和cpu信息。
cpu:
try {
cpuReader = new BufferedReader(new InputStreamReader(
new FileInputStream("/proc/stat")), BUFFER_SIZE);
String cpuRate = cpuReader.readLine();
if (cpuRate == null) {
cpuRate = "";
}
if (mPid == 0) {
mPid = android.os.Process.myPid();
}
pidReader = new BufferedReader(new InputStreamReader(
new FileInputStream("/proc/" + mPid + "/stat")), BUFFER_SIZE);
String pidCpuRate = pidReader.readLine();
if (pidCpuRate == null) {
pidCpuRate = "";
}
parse(cpuRate, pidCpuRate);
}
stack:
protected void doSample() {
StringBuilder stringBuilder = new StringBuilder();
for (StackTraceElement stackTraceElement : mCurrentThread.getStackTrace()) {
stringBuilder
.append(stackTraceElement.toString())
.append(BlockInfo.SEPARATOR);
}
synchronized (sStackMap) {
if (sStackMap.size() == mMaxEntryCount && mMaxEntryCount > 0) {
sStackMap.remove(sStackMap.keySet().iterator().next());
}
sStackMap.put(System.currentTimeMillis(), stringBuilder.toString());
}
}
这样，整个blockCanary的执行过程就完毕了。
ANR
当卡顿时间大于一定值之后，将会造成ANR，那么Android系统的ANR是如何检测出来的呢？其实就是通过Watchdog来实现的，这个Watchdog是一个线程。
public class Watchdog extends Thread {
}
我们主要看一下其中的run方法的实现。
@Override
public void run() {
boolean waitedHalf = false;
while (true) {
final ArrayList 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 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);
}
在这个run方法中，会开启一个死循环,主要用于持续检测ANR
while (true) {
}
通过wait，设置每一次休眠时间，
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);
}
当timeout计算完毕之后，会尝试获取当前各个的线程的状态
final int waitState = evaluateCheckerCompletionLocked();
private int evaluateCheckerCompletionLocked() {
int state = COMPLETED;
for (int i=0; ipublic 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;
}
}
return OVERDUE;
}
一旦有线程等待时间超过了最大等待时间，则表示当前已经有ANR。需要dump此时的堆栈信息。
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 pids = new ArrayList();
pids.add(Process.myPid());
ActivityManagerService.dumpStackTraces(true, pids, null, null,
getInterestingNativePids());
waitedHalf = true;
}
continue;
}
此外，还有一个第三方库，ANRWatchDog，也是用来检测Anr的，其实原理更加简单，
public void run() {
setName("|ANR-WatchDog|");
int lastTick;
int lastIgnored = -1;
while (!isInterrupted()) {
lastTick = _tick;
_uiHandler.post(_ticker);
try {
Thread.sleep(_timeoutInterval);
}
catch (InterruptedException e) {
_interruptionListener.onInterrupted(e);
return ;
}
// If the main thread has not handled _ticker, it is blocked. ANR.
if (_tick == lastTick) {
if (!_ignoreDebugger && Debug.isDebuggerConnected()) {
if (_tick != lastIgnored)
Log.w("ANRWatchdog", "An ANR was detected but ignored because the debugger is connected (you can prevent this with setIgnoreDebugger(true))");
lastIgnored = _tick;
continue ;
}
ANRError error;
if (_namePrefix != null)
error = ANRError.New(_namePrefix, _logThreadsWithoutStackTrace);
else
error = ANRError.NewMainOnly();
_anrListener.onAppNotResponding(error);
return;
}
}
}
它会在线程中，利用uiHanlder抛出一个计数器，然后wait指定时间，一旦等待时间到达，那么它会检查计数的值是否发生改变，如果没有发生改变，表示uiHandler的计算方法并没有执行到。也就是出现了Anr，此时需要dump堆栈信息。