android也是基于linux的系统,因此所有的进程都是从init进程开始的(直接或间接的从init进程fock出来的)。Zygote是受精卵进程,也是系统启动过程中由init进程创建的,具体的看下启动脚本/system/core/rootdir/init.zygote64.rc:
service zygote /system/bin/app_process64 -Xzygote /system/bin --zygote --start-system-server
class main
priority -20
user root
group root readproc
socket zygote stream 660 root system
onrestart write /sys/android_power/request_state wake
onrestart write /sys/power/state on
onrestart restart audioserver
onrestart restart cameraserver
onrestart restart media
onrestart restart netd
onrestart restart wificond
writepid /dev/cpuset/foreground/tasks
可以看出,要执行的进程是/system/bin/app_process64。代码在/frameworks/base/cmds/app_process/app_main.cpp。入口函数是main:
......
// 创建AppRuntime
AppRuntime runtime(argv[0], computeArgBlockSize(argc, argv));
......
while (i < argc) {
const char* arg = argv[i++];
if (strcmp(arg, "--zygote") == 0) {
// 确认是zygote进程
zygote = true;
niceName = ZYGOTE_NICE_NAME;
} else if (strcmp(arg, "--start-system-server") == 0) {
startSystemServer = true;
} else if (strcmp(arg, "--application") == 0) {
application = true;
} else if (strncmp(arg, "--nice-name=", 12) == 0) {
niceName.setTo(arg + 12);
} else if (strncmp(arg, "--", 2) != 0) {
className.setTo(arg);
break;
} else {
--i;
break;
}
}
......
if (zygote) {
// 执行zygote进程
runtime.start("com.android.internal.os.ZygoteInit", args, zygote);
} else if (className) {
runtime.start("com.android.internal.os.RuntimeInit", args, zygote);
} else {
fprintf(stderr, "Error: no class name or --zygote supplied.\n");
app_usage();
LOG_ALWAYS_FATAL("app_process: no class name or --zygote supplied.");
}
......
如果忽略掉参数这些细节,剩下的就是AppRuntime的建立和调用AppRuntime的start方法了,启动的是com.android.internal.os.ZygoteInit。
看下AppRuntime:
class AppRuntime : public AndroidRuntime
{
public:
AppRuntime(char* argBlockStart, const size_t argBlockLength)
: AndroidRuntime(argBlockStart, argBlockLength)
, mClass(NULL)
{
}
......
};
构造函数中调用了基类的构造方法,基类在/frameworks/base/core/jni/AndroidRuntime.cpp:
AndroidRuntime::AndroidRuntime(char* argBlockStart, const size_t argBlockLength) :
mExitWithoutCleanup(false),
mArgBlockStart(argBlockStart),
mArgBlockLength(argBlockLength)
{
SkGraphics::Init();
// There is also a global font cache, but its budget is specified by
// SK_DEFAULT_FONT_CACHE_COUNT_LIMIT and SK_DEFAULT_FONT_CACHE_LIMIT.
// Pre-allocate enough space to hold a fair number of options.
mOptions.setCapacity(20);
assert(gCurRuntime == NULL); // one per process
gCurRuntime = this;
}
保留了自己作为全局gCurRuntime。
直接看start方法:
void AndroidRuntime::start(const char* className, const Vector<String8>& options, bool zygote)
{
......
JniInvocation jni_invocation;
jni_invocation.Init(NULL);
JNIEnv* env;
// 启动虚拟机
if (startVm(&mJavaVM, &env, zygote) != 0) {
return;
}
// 回调虚拟机的创建
onVmCreated(env);
/*
* Register android functions.
*/
// 注册函数
if (startReg(env) < 0) {
ALOGE("Unable to register all android natives\n");
return;
}
......
jclass stringClass;
jobjectArray strArray;
jstring classNameStr;
// 获得一个string的对象的引用
stringClass = env->FindClass("java/lang/String");
assert(stringClass != NULL);
// 创建一个String数组对象
strArray = env->NewObjectArray(options.size() + 1, stringClass, NULL);
assert(strArray != NULL);
classNameStr = env->NewStringUTF(className);
assert(classNameStr != NULL);
// 设置第一个string数组的第一个元素是classNameStr,在这里就是ZygoteInit的全名
env->SetObjectArrayElement(strArray, 0, classNameStr);
// 设置其他参数
for (size_t i = 0; i < options.size(); ++i) {
jstring optionsStr = env->NewStringUTF(options.itemAt(i).string());
assert(optionsStr != NULL);
env->SetObjectArrayElement(strArray, i + 1, optionsStr);
}
/*
* Start VM. This thread becomes the main thread of the VM, and will
* not return until the VM exits.
*/
// 转换类中间的.为/,这里是转换格式
char* slashClassName = toSlashClassName(className);
// 从jni环境中找到这个类
jclass startClass = env->FindClass(slashClassName);
if (startClass == NULL) {
ALOGE("JavaVM unable to locate class '%s'\n", slashClassName);
/* keep going */
} else {
// 调用找到的类的main方法,这里就是调用ZygoteInit的main方法
jmethodID startMeth = env->GetStaticMethodID(startClass, "main",
"([Ljava/lang/String;)V");
if (startMeth == NULL) {
ALOGE("JavaVM unable to find main() in '%s'\n", className);
/* keep going */
} else {
env->CallStaticVoidMethod(startClass, startMeth, strArray);
#if 0
if (env->ExceptionCheck())
threadExitUncaughtException(env);
#endif
}
}
free(slashClassName);
......
}
关键部分已经给出了注释。总结一下:
1.启动虚拟机startVM;
2.通过startReg注册jni方法;
3.调用ZygoteInit类的main方法;
startVm基本上就是为这个进程建立一个Dalvik虚拟机环境,为当前线程初始化一个jni环境。startReg基本上是注册一大堆的jni方法,以供后面调用。不是本文重点,因此这里不再累述。
下面我们要关注的是ZygoteInit类的main方法了。
/frameworks/base/core/java/com/android/internal/os/ZygoteInit.java:
public static void main(String argv[]) {
ZygoteServer zygoteServer = new ZygoteServer();
......
zygoteServer.registerServerSocket(socketName);
......
preload();
......
if (startSystemServer) {
startSystemServer(abiList, socketName, zygoteServer);
}
......
zygoteServer.runSelectLoop(abiList);
......
}
1.创建ZygoteServer(可以看出是个cs架构的东西);
2.注册socket(使用socket进行通讯方式);
3.预加载;
4.启动SystemServer;
5.运行select循环体;
里面涉及到ZygoteHooks的运转,为了不影响整体,暂时做个标记,后面再阅读。
这里可以看到Zygote基本上是个cs架构的情况,并且通过socket进行这种架构的通讯。先来看看预加载过程:
static void preload() {
Log.d(TAG, "begin preload");
Trace.traceBegin(Trace.TRACE_TAG_DALVIK, "BeginIcuCachePinning");
beginIcuCachePinning();
Trace.traceEnd(Trace.TRACE_TAG_DALVIK);
Trace.traceBegin(Trace.TRACE_TAG_DALVIK, "PreloadClasses");
//预加载位于framework/base/preload-classes文件中的类
preloadClasses();
Trace.traceEnd(Trace.TRACE_TAG_DALVIK);
Trace.traceBegin(Trace.TRACE_TAG_DALVIK, "PreloadResources");
// 预加载资源
preloadResources();
Trace.traceEnd(Trace.TRACE_TAG_DALVIK);
Trace.traceBegin(Trace.TRACE_TAG_DALVIK, "PreloadOpenGL");
// 预加载资源
preloadOpenGL();
Trace.traceEnd(Trace.TRACE_TAG_DALVIK);
//通过System.loadLibrary()方法,预加载"android","compiler_rt","jnigraphics"这3个共享库
preloadSharedLibraries();
//预加载文本连接符资源
preloadTextResources();
// webview的初始化
// Ask the WebViewFactory to do any initialization that must run in the zygote process,
// for memory sharing purposes.
WebViewFactory.prepareWebViewInZygote();
endIcuCachePinning();
warmUpJcaProviders();
Log.d(TAG, "end preload");
}
看到了吧,都是android本身的一些资源的初始化过程,就是在这里完成的。
下面再看下startSystemServer:
private static boolean startSystemServer(String abiList, String socketName, ZygoteServer zygoteServer)
throws Zygote.MethodAndArgsCaller, RuntimeException {
long capabilities = posixCapabilitiesAsBits(
OsConstants.CAP_IPC_LOCK,
OsConstants.CAP_KILL,
OsConstants.CAP_NET_ADMIN,
OsConstants.CAP_NET_BIND_SERVICE,
OsConstants.CAP_NET_BROADCAST,
OsConstants.CAP_NET_RAW,
OsConstants.CAP_SYS_MODULE,
OsConstants.CAP_SYS_NICE,
OsConstants.CAP_SYS_RESOURCE,
OsConstants.CAP_SYS_TIME,
OsConstants.CAP_SYS_TTY_CONFIG,
OsConstants.CAP_WAKE_ALARM
);
/* Containers run without this capability, so avoid setting it in that case */
if (!SystemProperties.getBoolean(PROPERTY_RUNNING_IN_CONTAINER, false)) {
capabilities |= posixCapabilitiesAsBits(OsConstants.CAP_BLOCK_SUSPEND);
}
/* Hardcoded command line to start the system server */
String args[] = {
"--setuid=1000",
"--setgid=1000",
"--setgroups=1001,1002,1003,1004,1005,1006,1007,1008,1009,1010,1018,1021,1032,3001,3002,3003,3006,3007,3009,3010",
"--capabilities=" + capabilities + "," + capabilities,
"--nice-name=system_server",
"--runtime-args",
"com.android.server.SystemServer",
};
ZygoteConnection.Arguments parsedArgs = null;
int pid;
try {
parsedArgs = new ZygoteConnection.Arguments(args);
ZygoteConnection.applyDebuggerSystemProperty(parsedArgs);
ZygoteConnection.applyInvokeWithSystemProperty(parsedArgs);
/* Request to fork the system server process */
pid = Zygote.forkSystemServer(
parsedArgs.uid, parsedArgs.gid,
parsedArgs.gids,
parsedArgs.debugFlags,
null,
parsedArgs.permittedCapabilities,
parsedArgs.effectiveCapabilities);
} catch (IllegalArgumentException ex) {
throw new RuntimeException(ex);
}
/* For child process */
if (pid == 0) {
if (hasSecondZygote(abiList)) {
waitForSecondaryZygote(socketName);
}
zygoteServer.closeServerSocket();
handleSystemServerProcess(parsedArgs);
}
return true;
}
其实主要的就是Zygote.forkSystemServer这句话,前面的都是参数的配置。再向下看一层/frameworks/base/core/java/com/android/internal/os/Zygote.java:
public static int forkSystemServer(int uid, int gid, int[] gids, int debugFlags,
int[][] rlimits, long permittedCapabilities, long effectiveCapabilities) {
VM_HOOKS.preFork();
int pid = nativeForkSystemServer(
uid, gid, gids, debugFlags, rlimits, permittedCapabilities, effectiveCapabilities);
// Enable tracing as soon as we enter the system_server.
if (pid == 0) {
Trace.setTracingEnabled(true);
}
VM_HOOKS.postForkCommon();
return pid;
}
根据传递进来的uid,gid等调用函数nativeForkSystemServer,最终会在/frameworks/base/core/jni/com_android_internal_os_Zygote.cpp下的ForkAndSpecializeCommon中调用fork函数,那么实际上就可以知道,就是在c层fork分裂出一个进程来作为SystemServer。
现在我们回来看java层的ZygoteInit.java,继续看看与socket相关的部分,首先是registerServerSocket:
void registerServerSocket(String socketName) {
if (mServerSocket == null) {
int fileDesc;
final String fullSocketName = ANDROID_SOCKET_PREFIX + socketName;
try {
String env = System.getenv(fullSocketName);
fileDesc = Integer.parseInt(env);
} catch (RuntimeException ex) {
throw new RuntimeException(fullSocketName + " unset or invalid", ex);
}
try {
FileDescriptor fd = new FileDescriptor();
fd.setInt$(fileDesc);
mServerSocket = new LocalServerSocket(fd);
} catch (IOException ex) {
throw new RuntimeException(
"Error binding to local socket '" + fileDesc + "'", ex);
}
}
}
这里设置了文件描述符,然后创建了LocalServerSocket赋值给了mServerSocket。/frameworks/base/core/java/android/net/LocalServerSocket.java:
public LocalServerSocket(FileDescriptor fd) throws IOException
{
impl = new LocalSocketImpl(fd);
impl.listen(LISTEN_BACKLOG);
localAddress = impl.getSockAddress();
}
new出LocalSocketImpl后,直接就开始listen了。下面暂时不用特别看了吧,就是一个走的正常的网络socket了。这里应该就可以证明是以socket的方法进行的通讯。然后再来看看runSelectLoop:
void runSelectLoop(String abiList) throws Zygote.MethodAndArgsCaller {
ArrayList<FileDescriptor> fds = new ArrayList<FileDescriptor>();
ArrayList<ZygoteConnection> peers = new ArrayList<ZygoteConnection>();
fds.add(mServerSocket.getFileDescriptor());
peers.add(null);
while (true) {
StructPollfd[] pollFds = new StructPollfd[fds.size()];
for (int i = 0; i < pollFds.length; ++i) {
pollFds[i] = new StructPollfd();
pollFds[i].fd = fds.get(i);
pollFds[i].events = (short) POLLIN;
}
try {
Os.poll(pollFds, -1);
} catch (ErrnoException ex) {
throw new RuntimeException("poll failed", ex);
}
for (int i = pollFds.length - 1; i >= 0; --i) {
if ((pollFds[i].revents & POLLIN) == 0) {
continue;
}
if (i == 0) {
ZygoteConnection newPeer = acceptCommandPeer(abiList);
peers.add(newPeer);
fds.add(newPeer.getFileDesciptor());
} else {
boolean done = peers.get(i).runOnce(this);
if (done) {
peers.remove(i);
fds.remove(i);
}
}
}
}
}
进入一个死循环,每次都将所有要观察的fd建立成数组,然后调用Os.poll(pollFds, -1)阻塞等待fd的变化。后面一个for循环是当fd有变化(即有客户端连接,也就是说有其他进程想要与ZygoteServer通讯),此时调用ZygoteConnection的runOnce方法。这个方法如果简单看下的话,最终是要调用Zygote.forkAndSpecialize分裂出进程来的,也就是说这个方法是一旦有连接建立后就表示有app启动了,此时就要fork分裂出新的进程来,代码暂时就不贴了。
至此为止,Zygote的过程基本分析完毕。总结一下:
1.系统启动,通过init进程会启动Zygote进程。确切的将是通过runtime调用了ZygoteInit,这个初始化过程;
2.Zygote是cs架构的,基于socket通讯机制的,在ZygoteInit过程中会启动ZygoteServer,为了等待接收socket的通讯来进行启动app进程的处理;
3.分裂出SystemServer进程,负责启动系统的一些关键服务。包括3类(广播类、核心类、其他类);
最后附图一张便于理解: