稀土掘金地址：https://juejin.cn/post/7274046488752619579
matrix 对io的监控包括四个方面
- 监控在主线程执行 IO 操作的问题
- 监控缓冲区过小的问题
- 监控重复读同一文件
- 监控内存泄漏问题
IOCanaryPlugin，内部由IOCanaryCore完成真正的操作。
start方法
根据配置进行hook的安装
//io流hook
if (ioConfig.isDetectFileIOInMainThread() || ioConfig.isDetectFileIOBufferTooSmall() || ioConfig.isDetectFileIORepeatReadSameFile()) {
IOCanaryJniBridge.install(ioConfig, this);
}
//内存泄漏hook
if (ioConfig.isDetectIOClosableLeak()) {
this.mCloseGuardHooker = new CloseGuardHooker(this);
this.mCloseGuardHooker.hook();
}
stop方法
取消hook
if (this.mCloseGuardHooker != null) {
this.mCloseGuardHooker.unHook();
}
IOCanaryJniBridge.uninstall();
IOCanaryJniBridge.install()
底层hook安装包函几个步骤，加载so，设置hook内容，分别对应了下面几个方法
loadJni
System.loadLibrary("io-canary")
执行了System.loadLibrary("io-canary")，此时会进入io_canary_jni.cc中的JNI_OnLoad方法，在这个方法中有两项关键操作，1.获取到java层的一些信息，2.设置一个回调接口，用于上传监控信息.
InitJniEnv()
static bool InitJniEnv(JavaVM *vm) {
....
jclass temp_cls = env->FindClass("com/tencent/matrix/iocanary/core/IOCanaryJniBridge");
....
}
SetIssuedCallback()
iocanary::IOCanary::Get().SetIssuedCallback(OnIssuePublish)
其中OnIssuePublish是在拿到信息之后将信息组装成java层的对象IOIssue，然后放入List中，通过调用java层IOCanaryJniBridge类的onIssuePublish实现信息的抛出。
com/tencent/matrix/iocanary/core/IOIssue
com/tencent/matrix/iocanary/core/IOCanaryJniBridge
enableDetector
通过传入定义好的type类型到底层，实现此类型的io监控，代码如下
iocanary::IOCanary::Get().RegisterDetector(static_cast<DetectorType>(detector_type));
可以看到最终是往detectors_这个vector集合中存入了对应的Detector，每个Detector都FileIODetector的子类。
- FileIOMainThreadDetector
- FileIORepeatReadDetector
- FileIOSmallBufferDetector
void IOCanary::RegisterDetector(DetectorType type) {
switch (type) {
case DetectorType::kDetectorMainThreadIO:
detectors_.push_back(new FileIOMainThreadDetector());
break;
case DetectorType::kDetectorSmallBuffer:
detectors_.push_back(new FileIOSmallBufferDetector());
break;
case DetectorType::kDetectorRepeatRead:
detectors_.push_back(new FileIORepeatReadDetector());
break;
default:
break;
}
}
setConfig
给对应的io监控设置监控阈值，存入configs_数组，配置和对应的默认值如下，超过阈值则触发监控
- kMainThreadThreshold = 500 毫秒
- kSmallBufferThreshold = 4096 kb
- kRepeatReadThreshold = 20 次
iocanary::IOCanary::Get().SetConfig(static_cast<IOCanaryConfigKey>(key), val);
void IOCanaryEnv::SetConfig(IOCanaryConfigKey key, long val) {
if (key >= IOCanaryConfigKey::kConfigKeysLen) {
return;
}
configs_[key] = val;
}
dohook
dohook是核心方法，前边配置信息准备好后，这里开始进行对应方法的hook。被hook的so文件为
const static char* TARGET_MODULES[] = {
"libopenjdkjvm.so",
"libjavacore.so",
"libopenjdk.so"
};
关于GOT hook,可以查看爱奇艺的开源框架XHook，这里不再描述细节。https://github.com/iqiyi/xHook/blob/master/docs/overview/android_plt_hook_overview.zh-CN.md
被hook的方法如下
open、open64、close、android_fdsan_close_with_tag，
如果so是libjavacore.so，会尝试hook它内部的这几个方法
read、__read_chk、write、__write_chk
open
当一个文件被打开时，回调到设置好的方法ProxyOpen中，在这里会检测是否是主线程操作，如不是则不做处理，如是主线程，则执行DoProxyOpenLogic逻辑。
int ProxyOpen(const char *pathname, int flags, mode_t mode) {
if(!IsMainThread()) {
return original_open(pathname, flags, mode);
}
int ret = original_open(pathname, flags, mode);
if (ret != -1) {
DoProxyOpenLogic(pathname, flags, mode, ret);
}
return ret;
}
在DoProxyOpenLogic方法中会获取到当前堆栈信息
static void DoProxyOpenLogic(const char *pathname, int flags, mode_t mode, int ret) {
....
//kJavaBridgeClass = com/tencent/matrix/iocanary/core/IOCanaryJniBridge
//kMethodIDGetJavaContext = getJavaContext() 得到的是一个JavaContext，
//是一个内部类，这个类上有一个变量stack，在java Context 创建的时候，
//就会获取到堆栈信息，保存在stack变量上
jobject java_context_obj = env->CallStaticObjectMethod(kJavaBridgeClass, kMethodIDGetJavaContext);
if (NULL == java_context_obj) {
return;
}
//堆栈信息
jstring j_stack = (jstring) env->GetObjectField(java_context_obj, kFieldIDStack);
jstring j_thread_name = (jstring) env->GetObjectField(java_context_obj, kFieldIDThreadName);
//当前线程名
char* thread_name = jstringToChars(env, j_thread_name);
char* stack = jstringToChars(env, j_stack);
JavaContext java_context(GetCurrentThreadId(), thread_name == NULL ? "" : thread_name, stack == NULL ? "" : stack);
....
//pathname是被打开的文件名，java_context中包含了堆栈和线程名
//flags和mode都是系统open方法调用传过来的值，ret是open执行的结果
//这里进入了IOCanary OnOpen方法
iocanary::IOCanary::Get().OnOpen(pathname, flags, mode, ret, java_context);
....
}
open64
同open()
close
检测是主线程，进入IOCanary OnClose方法
int ProxyClose(int fd) {
if(!IsMainThread()) {
return original_close(fd);
}
int ret = original_close(fd);
iocanary::IOCanary::Get().OnClose(fd, ret);
return ret;
}
android_fdsan_close_with_tag
同close()
read
主要是获取到read消耗的时长，然后携带信息进入IOCanary OnRead
ssize_t ProxyRead(int fd, void *buf, size_t size) {
if(!IsMainThread()) {
return original_read(fd, buf, size);
}
//获取到当前时间
int64_t start = GetTickCountMicros();
//执行原read方法
size_t ret = original_read(fd, buf, size);
//记录read时间间隔
long read_cost_us = GetTickCountMicros() - start;
//将信息传入IOCanary OnRead
iocanary::IOCanary::Get().OnRead(fd, buf, size, ret, read_cost_us);
return ret;
}
__read_chk
同read
write
ssize_t ProxyWrite(int fd, const void *buf, size_t size) {
if(!IsMainThread()) {
return original_write(fd, buf, size);
}
//获取到当前时间
int64_t start = GetTickCountMicros();
//执行write
size_t ret = original_write(fd, buf, size);
//记录时间间隔
long write_cost_us = GetTickCountMicros() - start;
//将信息传入IOCanary OnRead
iocanary::IOCanary::Get().OnWrite(fd, buf, size, ret, write_cost_us);
return ret;
}
__write_chk
同write
IOCanary
从上边open close read write方法的流向可知，最终都还是汇集到了IOCanary这个C++类中，进入对应的方法可知，IOCanary内部又调用了IOInfoCollector这个类。
。
OnOpen
void IOCanary::OnOpen(const char *pathname, int flags, mode_t mode,
int open_ret, const JavaContext& java_context) {
collector_.OnOpen(pathname, flags, mode, open_ret, java_context);
}
方法内部逻辑也很清晰，直接将文件名和相关信息组装成info,然后以文件描述符为key,info为value存入了c++的info_map_(一个std::unordered_map)中，信息存起来肯定是要用的，我们后边会看到。文件打开之后，下一步就是或读或写，继续去看read方法。
void IOInfoCollector::OnOpen(const char *pathname, int flags, mode_t mode
, int open_ret, const JavaContext& java_context) {
if (open_ret == -1) {
return;
}
//open_ret参数指的是open方法调用后的结果，也就是当前被打开的文件的文件描述符，
//如果已存在，则返回
if (info_map_.find(open_ret) != info_map_.end()) {
return;
}
std::shared_ptr<IOInfo> info = std::make_shared<IOInfo>(pathname, java_context);
info_map_.insert(std::make_pair(open_ret, info));
}
OnRead
void IOCanary::OnRead(int fd, const void *buf, size_t size,
ssize_t read_ret, long read_cost) {
collector_.OnRead(fd, buf, size, read_ret, read_cost);
}
看起来关键内容在CountRWInfo中，从方法名上可以看出，读和写都与此方法有关，所以我们先不看CountRWInfo方法内容，看完write后再去深入CountRWInfo方法。
void IOInfoCollector::OnRead(int fd, const void *buf, size_t size,
ssize_t read_ret, long read_cost) {
if (read_ret == -1 || read_cost < 0) {
return;
}
if (info_map_.find(fd) == info_map_.end()) {
return;
}
CountRWInfo(fd, FileOpType::kRead, size, read_cost);
}
OnWrite
void IOCanary::OnWrite(int fd, const void *buf, size_t size,
ssize_t write_ret, long write_cost) {
collector_.OnWrite(fd, buf, size, write_ret, write_cost);
}
和read一样，进入了CountRWInfo方法
void IOInfoCollector::OnWrite(int fd, const void *buf, size_t size,
ssize_t write_ret, long write_cost) {
if (write_ret == -1 || write_cost < 0) {
return;
}
if (info_map_.find(fd) == info_map_.end()) {
return;
}
CountRWInfo(fd, FileOpType::kWrite, size, write_cost);
}
CountRWInfo
CountRWInfo将每个文件对应的信息封装到IOInfo这个类中，封装的信息包函：
- 读(写)次数
- 文件大小
- 读(写)消耗的时长
- 单次读(写)最大时长
- 读(写)间隔小于8000微妙的总时长
- 缓存区大小
- 读写类型，读还是写
在一个文件被读写过程中，这个方法会不断的被调用，并更新对应的信息，读写完成之后，得到最终的信息，执行close方法。
void IOInfoCollector::CountRWInfo(int fd, const FileOpType &fileOpType, long op_size, long rw_cost) {
if (info_map_.find(fd) == info_map_.end()) {
return;
}
const int64_t now = GetSysTimeMicros();
//读写次数
info_map_[fd]->op_cnt_ ++;
//文件大小
info_map_[fd]->op_size_ += op_size;
//读写消耗的时长
info_map_[fd]->rw_cost_us_ += rw_cost;
//单次读写最大时长
if (rw_cost > info_map_[fd]->max_once_rw_cost_time_μs_) {
info_map_[fd]->max_once_rw_cost_time_μs_ = rw_cost;
}
//读写间隔小于8000微妙的总时长
if (info_map_[fd]->last_rw_time_μs_ > 0 && (now - info_map_[fd]->last_rw_time_μs_) < kContinualThreshold) {
info_map_[fd]->current_continual_rw_time_μs_ += rw_cost;
} else {
info_map_[fd]->current_continual_rw_time_μs_ = rw_cost;
}
if (info_map_[fd]->current_continual_rw_time_μs_ > info_map_[fd]->max_continual_rw_cost_time_μs_) {
info_map_[fd]->max_continual_rw_cost_time_μs_ = info_map_[fd]->current_continual_rw_time_μs_;
}
info_map_[fd]->last_rw_time_μs_ = now;
//缓存区大小
if (info_map_[fd]->buffer_size_ < op_size) {
info_map_[fd]->buffer_size_ = op_size;
}
//读写类型，读还是写
if (info_map_[fd]->op_type_ == FileOpType::kInit) {
info_map_[fd]->op_type_ = fileOpType;
}
}
OnClose
void IOCanary::OnClose(int fd, int close_ret) {
std::shared_ptr<IOInfo> info = collector_.OnClose(fd, close_ret);
if (info == nullptr) {
return;
}
OfferFileIOInfo(info);
}
close时记录总时长，文件大小，然后返回，返回后进入OfferFileIOInfo方法
std::shared_ptr<IOInfo> IOInfoCollector::OnClose(int fd, int close_ret) {
if (info_map_.find(fd) == info_map_.end()) {
return nullptr;
}
//从打开到关闭的总时长
info_map_[fd]->total_cost_μs_ = GetSysTimeMicros() - info_map_[fd]->start_time_μs_;
//获取到文件大小
info_map_[fd]->file_size_ = GetFileSize(info_map_[fd]->path_.c_str());
std::shared_ptr<IOInfo> info = info_map_[fd];
//从map中移除
info_map_.erase(fd);
//返回信息
return info;
}
OfferFileIOInfo将info放入队列，并调用notify_one方法通知消费者消费，这里用到了生产消费模式，生产者将生产果实放在队列中，消费者从队列取出进行消费，我们找下消费者在哪。
void IOCanary::OfferFileIOInfo(std::shared_ptr<IOInfo> file_io_info) {
std::unique_lock<std::mutex> lock(queue_mutex_);
queue_.push_back(file_io_info);
queue_cv_.notify_one();
lock.unlock();
}
可以看到，IOCanary在创建的时候，启动了一个线程
IOCanary::IOCanary() {
exit_ = false;
std::thread detect_thread(&IOCanary::Detect, this);
detect_thread.detach();
}
线程中有一个无限循环，它负责不停的从队列中拿info，如果队列为空则挂起线程等待。
前边我们看到了拿到一条info之后，将info放入到队列中，然后通知消费者消费，此时消费者线程会从TakeFileIOInfo方法中被唤醒，并拿到一条info，交给各个detector去检测。
检测完成之后，满足条件的信息会被放入published_issues中，然后issued_callback_将信息回调出去。前边提到有三个detector接下来具体看下他们的内部逻辑。
void IOCanary::Detect() {
std::vector<Issue> published_issues;
std::shared_ptr<IOInfo> file_io_info;
while (true) {
published_issues.clear();
int ret = TakeFileIOInfo(file_io_info);
if (ret != 0) {
break;
}
for (auto detector : detectors_) {
detector->Detect(env_, *file_io_info, published_issues);
}
if (issued_callback_ && !published_issues.empty()) {
issued_callback_(published_issues);
}
file_io_info = nullptr;
}
}
FileIOMainThreadDetector
检测主线程io
void FileIOMainThreadDetector::Detect(const IOCanaryEnv &env, const IOInfo &file_io_info,
std::vector<Issue>& issues) {
//必须是主线程才会执行
if (GetMainThreadId() == file_io_info.java_context_.thread_id_) {
int type = 0;
//单次io时长超过13毫秒，要记录
//constexpr static const int kPossibleNegativeThreshold = 13*1000;
if (file_io_info.max_once_rw_cost_time_μs_ > IOCanaryEnv::kPossibleNegativeThreshold) {
type = 1;
}
//最大连续读写时长超过env.GetMainThreadThreshold()=500
if(file_io_info.max_continual_rw_cost_time_μs_ > env.GetMainThreadThreshold()) {
type |= 2;
}
if (type != 0) {
Issue issue(kType, file_io_info);
issue.repeat_read_cnt_ = type;
//存入
PublishIssue(issue, issues);
}
}
}
FileIORepeatReadDetector
监听重复读取同一文件
void FileIORepeatReadDetector::Detect(const IOCanaryEnv &env,
const IOInfo &file_io_info,
std::vector<Issue>& issues) {
const std::string& path = file_io_info.path_;
if (observing_map_.find(path) == observing_map_.end()) {
if (file_io_info.max_continual_rw_cost_time_μs_ < env.kPossibleNegativeThreshold) {
return;
}
observing_map_.insert(std::make_pair(path, std::vector<RepeatReadInfo>()));
}
std::vector<RepeatReadInfo>& repeat_infos = observing_map_[path];
if (file_io_info.op_type_ == FileOpType::kWrite) {
repeat_infos.clear();
return;
}
RepeatReadInfo repeat_read_info(file_io_info.path_, file_io_info.java_context_.stack_, file_io_info.java_context_.thread_id_,
file_io_info.op_size_, file_io_info.file_size_);
if (repeat_infos.size() == 0) {
repeat_infos.push_back(repeat_read_info);
return;
}
if((GetTickCount() - repeat_infos[repeat_infos.size() - 1].op_timems) > 17) { //17ms todo astrozhou add to params
repeat_infos.clear();
}
bool found = false;
int repeatCnt;
for (auto& info : repeat_infos) {
if (info == repeat_read_info) {
found = true;
info.IncRepeatReadCount();
repeatCnt = info.GetRepeatReadCount();
break;
}
}
if (!found) {
repeat_infos.push_back(repeat_read_info);
return;
}
if (repeatCnt >= env.GetRepeatReadThreshold()) {
Issue issue(kType, file_io_info);
issue.repeat_read_cnt_ = repeatCnt;
issue.stack = repeat_read_info.GetStack();
PublishIssue(issue, issues);
}
}
FileIOSmallBufferDetector
监听缓存区过小
void FileIOSmallBufferDetector::Detect(const IOCanaryEnv &env, const IOInfo &file_io_info,
std::vector<Issue>& issues) {
if (file_io_info.op_cnt_ > env.kSmallBufferOpTimesThreshold && (file_io_info.op_size_ / file_io_info.op_cnt_) < env.GetSmallBufferThreshold()
&& file_io_info.max_continual_rw_cost_time_μs_ >= env.kPossibleNegativeThreshold) {
PublishIssue(Issue(kType, file_io_info), issues);
}
}
OnIssuePublish
所有信息都拿到之后就开始要回调了，也就回到了我们最开始开到的
iocanary::IOCanary::Get().SetIssuedCallback(OnIssuePublish)
void OnIssuePublish(const std::vector<Issue>& published_issues) {
....
//这里new了一个Java层的List
jobject j_issues = env->NewObject(kListClass, kMethodIDListConstruct);
//遍历所有的info，拿到信息，每一条信息创建一个Java层的IOIssue对象，封装到这个对象中
for (const auto& issue : published_issues) {
jint type = issue.type_;
jstring path = env->NewStringUTF(issue.file_io_info_.path_.c_str());
jlong file_size = issue.file_io_info_.file_size_;
jint op_cnt = issue.file_io_info_.op_cnt_;
jlong buffer_size = issue.file_io_info_.buffer_size_;
jlong op_cost_time = issue.file_io_info_.rw_cost_us_/1000;
jint op_type = issue.file_io_info_.op_type_;
jlong op_size = issue.file_io_info_.op_size_;
jstring thread_name = env->NewStringUTF(issue.file_io_info_.java_context_.thread_name_.c_str());
jstring stack = env->NewStringUTF(issue.stack.c_str());
jint repeat_read_cnt = issue.repeat_read_cnt_;
jobject issue_obj = env->NewObject(kIssueClass, kMethodIDIssueConstruct, type, path, file_size, op_cnt, buffer_size,
op_cost_time, op_type, op_size, thread_name, stack, repeat_read_cnt);
//讲IOIssue对象add到List中
env->CallBooleanMethod(j_issues, kMethodIDListAdd, issue_obj);
....
}
//回调到Java层的IOCanaryJniBridge类中的静态方法onIssuePublish中
env->CallStaticVoidMethod(kJavaBridgeClass, kMethodIDOnIssuePublish, j_issues);
....
}
后边在Java层onIssuePublish中就开始拼接信息转为json打印到控制台或上传服务器，流程至此就算结束了。
总结
IOCanaryPlugin通过hook底层io方法open、read、write、close来实现对io操作的拦截，于是所有的io操作都会被监控到，这样就可以在每一个io操作的过程中记录操作的信息，并分析io操作是否超过设定阈值，如满足条件则进行上报。
网友评论