533
社区成员
Audio是多媒体子系统中的一个重要模块,其涉及的内容比较多,有音频的渲染、音频的采集、音频的策略管理等。本文主要针对音频渲染功能进行详细地分析,并通过源码中提供的例子,对音频渲染进行流程的梳理。
foundation/multimedia/audio_framework
audio_framework
├── frameworks
│ ├── js #js 接口
│ │ └── napi
│ │ └── audio_renderer #audio_renderer NAPI接口
│ │ ├── include
│ │ │ ├── audio_renderer_callback_napi.h
│ │ │ ├── renderer_data_request_callback_napi.h
│ │ │ ├── renderer_period_position_callback_napi.h
│ │ │ └── renderer_position_callback_napi.h
│ │ └── src
│ │ ├── audio_renderer_callback_napi.cpp
│ │ ├── audio_renderer_napi.cpp
│ │ ├── renderer_data_request_callback_napi.cpp
│ │ ├── renderer_period_position_callback_napi.cpp
│ │ └── renderer_position_callback_napi.cpp
│ └── native #native 接口
│ └── audiorenderer
│ ├── BUILD.gn
│ ├── include
│ │ ├── audio_renderer_private.h
│ │ └── audio_renderer_proxy_obj.h
│ ├── src
│ │ ├── audio_renderer.cpp
│ │ └── audio_renderer_proxy_obj.cpp
│ └── test
│ └── example
│ └── audio_renderer_test.cpp
├── interfaces
│ ├── inner_api #native实现的接口
│ │ └── native
│ │ └── audiorenderer #audio渲染本地实现的接口定义
│ │ └── include
│ │ └── audio_renderer.h
│ └── kits #js调用的接口
│ └── js
│ └── audio_renderer #audio渲染NAPI接口的定义
│ └── include
│ └── audio_renderer_napi.h
└── services #服务端
└── audio_service
├── BUILD.gn
├── client #IPC调用中的proxy端
│ ├── include
│ │ ├── audio_manager_proxy.h
│ │ ├── audio_service_client.h
│ └── src
│ ├── audio_manager_proxy.cpp
│ ├── audio_service_client.cpp
└── server #IPC调用中的server端
├── include
│ └── audio_server.h
└── src
├── audio_manager_stub.cpp
└── audio_server.cpp
在OpenAtom OpenHarmony(以下简称“OpenHarmony”)系统中,音频模块提供了功能测试代码,本文选取了其中的音频渲染例子作为切入点来进行介绍,例子采用的是对wav格式的音频文件进行渲染。wav格式的音频文件是wav头文件和音频的原始数据,不需要进行数据解码,所以音频渲染直接对原始数据进行操作,文件路径为:
foundation/multimedia/audio_framework/frameworks/native/audiorenderer/test/example/audio_renderer_test.cpp
bool TestPlayback(int argc, char *argv[]) const
{
FILE* wavFile = fopen(path, "rb");
//读取wav文件头信息
size_t bytesRead = fread(&wavHeader, 1, headerSize, wavFile);
//设置AudioRenderer参数
AudioRendererOptions rendererOptions = {};
rendererOptions.streamInfo.encoding = AudioEncodingType::ENCODING_PCM;
rendererOptions.streamInfo.samplingRate = static_cast<AudioSamplingRate>(wavHeader.SamplesPerSec);
rendererOptions.streamInfo.format = GetSampleFormat(wavHeader.bitsPerSample);
rendererOptions.streamInfo.channels = static_cast<AudioChannel>(wavHeader.NumOfChan);
rendererOptions.rendererInfo.contentType = contentType;
rendererOptions.rendererInfo.streamUsage = streamUsage;
rendererOptions.rendererInfo.rendererFlags = 0;
//创建AudioRender实例
unique_ptr<AudioRenderer> audioRenderer = AudioRenderer::Create(rendererOptions);
shared_ptr<AudioRendererCallback> cb1 = make_shared<AudioRendererCallbackTestImpl>();
//设置音频渲染回调
ret = audioRenderer->SetRendererCallback(cb1);
//InitRender方法主要调用了audioRenderer实例的Start方法,启动音频渲染
if (!InitRender(audioRenderer)) {
AUDIO_ERR_LOG("AudioRendererTest: Init render failed");
fclose(wavFile);
return false;
}
//StartRender方法主要是读取wavFile文件的数据,然后通过调用audioRenderer实例的Write方法进行播放
if (!StartRender(audioRenderer, wavFile)) {
AUDIO_ERR_LOG("AudioRendererTest: Start render failed");
fclose(wavFile);
return false;
}
//停止渲染
if (!audioRenderer->Stop()) {
AUDIO_ERR_LOG("AudioRendererTest: Stop failed");
}
//释放渲染
if (!audioRenderer->Release()) {
AUDIO_ERR_LOG("AudioRendererTest: Release failed");
}
//关闭wavFile
fclose(wavFile);
return true;
}
首先读取wav文件,通过读取到wav文件的头信息对AudioRendererOptions相关的参数进行设置,包括编码格式、采样率、采样格式、通道数等。根据AudioRendererOptions设置的参数来创建AudioRenderer实例(实际上是AudioRendererPrivate),后续的音频渲染主要是通过AudioRenderer实例进行。创建完成后,调用AudioRenderer的Start方法,启动音频渲染。启动后,通过AudioRenderer实例的Write方法,将数据写入,音频数据会被播放。
1. 创建AudioRenderer
std::unique_ptr<AudioRenderer> AudioRenderer::Create(const std::string cachePath,
const AudioRendererOptions &rendererOptions, const AppInfo &appInfo)
{
ContentType contentType = rendererOptions.rendererInfo.contentType;
StreamUsage streamUsage = rendererOptions.rendererInfo.streamUsage;
AudioStreamType audioStreamType = AudioStream::GetStreamType(contentType, streamUsage);
auto audioRenderer = std::make_unique<AudioRendererPrivate>(audioStreamType, appInfo);
if (!cachePath.empty()) {
AUDIO_DEBUG_LOG("Set application cache path");
audioRenderer->SetApplicationCachePath(cachePath);
}
audioRenderer->rendererInfo_.contentType = contentType;
audioRenderer->rendererInfo_.streamUsage = streamUsage;
audioRenderer->rendererInfo_.rendererFlags = rendererOptions.rendererInfo.rendererFlags;
AudioRendererParams params;
params.sampleFormat = rendererOptions.streamInfo.format;
params.sampleRate = rendererOptions.streamInfo.samplingRate;
params.channelCount = rendererOptions.streamInfo.channels;
params.encodingType = rendererOptions.streamInfo.encoding;
if (audioRenderer->SetParams(params) != SUCCESS) {
AUDIO_ERR_LOG("SetParams failed in renderer");
audioRenderer = nullptr;
return nullptr;
}
return audioRenderer;
}
首先通过AudioStream的GetStreamType方法获取音频流的类型,根据音频流类型创建AudioRendererPrivate对象,AudioRendererPrivate是AudioRenderer的子类。紧接着对audioRenderer进行参数设置,其中包括采样格式、采样率、通道数、编码格式。设置完成后返回创建的AudioRendererPrivate实例。
2. 设置回调
int32_t AudioRendererPrivate::SetRendererCallback(const std::shared_ptr<AudioRendererCallback> &callback)
{
RendererState state = GetStatus();
if (state == RENDERER_NEW || state == RENDERER_RELEASED) {
return ERR_ILLEGAL_STATE;
}
if (callback == nullptr) {
return ERR_INVALID_PARAM;
}
// Save reference for interrupt callback
if (audioInterruptCallback_ == nullptr) {
return ERROR;
}
std::shared_ptr<AudioInterruptCallbackImpl> cbInterrupt =
std::static_pointer_cast<AudioInterruptCallbackImpl>(audioInterruptCallback_);
cbInterrupt->SaveCallback(callback);
// Save and Set reference for stream callback. Order is important here.
if (audioStreamCallback_ == nullptr) {
audioStreamCallback_ = std::make_shared<AudioStreamCallbackRenderer>();
if (audioStreamCallback_ == nullptr) {
return ERROR;
}
}
std::shared_ptr<AudioStreamCallbackRenderer> cbStream =
std::static_pointer_cast<AudioStreamCallbackRenderer>(audioStreamCallback_);
cbStream->SaveCallback(callback);
(void)audioStream_->SetStreamCallback(audioStreamCallback_);
return SUCCESS;
}
参数传入的回调主要涉及到两个方面:一方面是AudioInterruptCallbackImpl中设置了我们传入的渲染回调,另一方面是AudioStreamCallbackRenderer中也设置了渲染回调。
3. 启动渲染
bool AudioRendererPrivate::Start(StateChangeCmdType cmdType) const
{
AUDIO_INFO_LOG("AudioRenderer::Start");
RendererState state = GetStatus();
AudioInterrupt audioInterrupt;
switch (mode_) {
case InterruptMode::SHARE_MODE:
audioInterrupt = sharedInterrupt_;
break;
case InterruptMode::INDEPENDENT_MODE:
audioInterrupt = audioInterrupt_;
break;
default:
break;
}
AUDIO_INFO_LOG("AudioRenderer::Start::interruptMode: %{public}d, streamType: %{public}d, sessionID: %{public}d",
mode_, audioInterrupt.streamType, audioInterrupt.sessionID);
if (audioInterrupt.streamType == STREAM_DEFAULT || audioInterrupt.sessionID == INVALID_SESSION_ID) {
return false;
}
int32_t ret = AudioPolicyManager::GetInstance().ActivateAudioInterrupt(audioInterrupt);
if (ret != 0) {
AUDIO_ERR_LOG("AudioRendererPrivate::ActivateAudioInterrupt Failed");
return false;
}
return audioStream_->StartAudioStream(cmdType);
}
AudioPolicyManager::GetInstance().ActivateAudioInterrupt这个操作主要是根据AudioInterrupt来进行音频中断的激活,这里涉及了音频策略相关的内容,后续会专门出关于音频策略的文章进行分析。这个方法的核心是通过调用AudioStream的StartAudioStream方法来启动音频流。
bool AudioStream::StartAudioStream(StateChangeCmdType cmdType)
{
int32_t ret = StartStream(cmdType);
resetTime_ = true;
int32_t retCode = clock_gettime(CLOCK_MONOTONIC, &baseTimestamp_);
if (renderMode_ == RENDER_MODE_CALLBACK) {
isReadyToWrite_ = true;
writeThread_ = std::make_unique<std::thread>(&AudioStream::WriteCbTheadLoop, this);
} else if (captureMode_ == CAPTURE_MODE_CALLBACK) {
isReadyToRead_ = true;
readThread_ = std::make_unique<std::thread>(&AudioStream::ReadCbThreadLoop, this);
}
isFirstRead_ = true;
isFirstWrite_ = true;
state_ = RUNNING;
AUDIO_INFO_LOG("StartAudioStream SUCCESS");
if (audioStreamTracker_) {
AUDIO_DEBUG_LOG("AudioStream:Calling Update tracker for Running");
audioStreamTracker_->UpdateTracker(sessionId_, state_, rendererInfo_, capturerInfo_);
}
return true;
}
AudioStream的StartAudioStream主要的工作是调用StartStream方法,StartStream方法是AudioServiceClient类中的方法。AudioServiceClient类是AudioStream的父类。接下来看一下AudioServiceClient的StartStream方法。
int32_t AudioServiceClient::StartStream(StateChangeCmdType cmdType)
{
int error;
lock_guard<mutex> lockdata(dataMutex);
pa_operation *operation = nullptr;
pa_threaded_mainloop_lock(mainLoop);
pa_stream_state_t state = pa_stream_get_state(paStream);
streamCmdStatus = 0;
stateChangeCmdType_ = cmdType;
operation = pa_stream_cork(paStream, 0, PAStreamStartSuccessCb, (void *)this);
while (pa_operation_get_state(operation) == PA_OPERATION_RUNNING) {
pa_threaded_mainloop_wait(mainLoop);
}
pa_operation_unref(operation);
pa_threaded_mainloop_unlock(mainLoop);
if (!streamCmdStatus) {
AUDIO_ERR_LOG("Stream Start Failed");
ResetPAAudioClient();
return AUDIO_CLIENT_START_STREAM_ERR;
} else {
AUDIO_INFO_LOG("Stream Started Successfully");
return AUDIO_CLIENT_SUCCESS;
}
}
StartStream方法中主要是调用了pulseaudio库的pa_stream_cork方法进行流启动,后续就调用到了pulseaudio库中了。pulseaudio库我们暂且不分析。
4. 写入数据
int32_t AudioRendererPrivate::Write(uint8_t *buffer, size_t bufferSize)
{
return audioStream_->Write(buffer, bufferSize);
}
通过调用AudioStream的Write方式实现功能,接下来看一下AudioStream的Write方法。
size_t AudioStream::Write(uint8_t *buffer, size_t buffer_size)
{
int32_t writeError;
StreamBuffer stream;
stream.buffer = buffer;
stream.bufferLen = buffer_size;
isWriteInProgress_ = true;
if (isFirstWrite_) {
if (RenderPrebuf(stream.bufferLen)) {
return ERR_WRITE_FAILED;
}
isFirstWrite_ = false;
}
size_t bytesWritten = WriteStream(stream, writeError);
isWriteInProgress_ = false;
if (writeError != 0) {
AUDIO_ERR_LOG("WriteStream fail,writeError:%{public}d", writeError);
return ERR_WRITE_FAILED;
}
return bytesWritten;
}
Write方法中分成两个阶段,首次写数据,先调用RenderPrebuf方法,将preBuf_的数据写入后再调用WriteStream进行音频数据的写入。
size_t AudioServiceClient::WriteStream(const StreamBuffer &stream, int32_t &pError)
{
size_t cachedLen = WriteToAudioCache(stream);
if (!acache.isFull) {
pError = error;
return cachedLen;
}
pa_threaded_mainloop_lock(mainLoop);
const uint8_t *buffer = acache.buffer.get();
size_t length = acache.totalCacheSize;
error = PaWriteStream(buffer, length);
acache.readIndex += acache.totalCacheSize;
acache.isFull = false;
if (!error && (length >= 0) && !acache.isFull) {
uint8_t *cacheBuffer = acache.buffer.get();
uint32_t offset = acache.readIndex;
uint32_t size = (acache.writeIndex - acache.readIndex);
if (size > 0) {
if (memcpy_s(cacheBuffer, acache.totalCacheSize, cacheBuffer + offset, size)) {
AUDIO_ERR_LOG("Update cache failed");
pa_threaded_mainloop_unlock(mainLoop);
pError = AUDIO_CLIENT_WRITE_STREAM_ERR;
return cachedLen;
}
AUDIO_INFO_LOG("rearranging the audio cache");
}
acache.readIndex = 0;
acache.writeIndex = 0;
if (cachedLen < stream.bufferLen) {
StreamBuffer str;
str.buffer = stream.buffer + cachedLen;
str.bufferLen = stream.bufferLen - cachedLen;
AUDIO_DEBUG_LOG("writing pending data to audio cache: %{public}d", str.bufferLen);
cachedLen += WriteToAudioCache(str);
}
}
pa_threaded_mainloop_unlock(mainLoop);
pError = error;
return cachedLen;
}
WriteStream方法不是直接调用pulseaudio库的写入方法,而是通过WriteToAudioCache方法将数据写入缓存中,如果缓存没有写满则直接返回,不会进入下面的流程,只有当缓存写满后,才会调用下面的PaWriteStream方法。该方法涉及对pulseaudio库写入操作的调用,所以缓存的目的是避免对pulseaudio库频繁地做IO操作,提高了效率。
本文主要对OpenHarmony 3.2 Beta多媒体子系统的音频渲染模块进行介绍,首先梳理了Audio Render的整体流程,然后对几个核心的方法进行代码的分析。整体的流程主要通过pulseaudio库启动流,然后通过pulseaudio库的pa_stream_write方法进行数据的写入,最后播放出音频数据。
音频渲染主要分为以下几个层次:
(1)AudioRenderer的创建,实际创建的是它的子类AudioRendererPrivate实例。
(2)通过AudioRendererPrivate设置渲染的回调。
(3)启动渲染,这一部分代码最终会调用到pulseaudio库中,相当于启动了pulseaudio的流。(4)通过pulseaudio库的pa_stream_write方法将数据写入设备,进行播放。
对OpenHarmony 3.2 Beta多媒体系列开发感兴趣的读者,也可以阅读我之前写过几篇文章:
《OpenHarmony 3.2 Beta多媒体系列——视频录制》
《OpenHarmony 3.2 Beta源码分析之MediaLibrary》