Android Zygote进程启动过程

浏览数：23 / 时间：2015年06月11日

Zygote, 意为“受精卵”，Android系统中几乎所有的应用进程都是由Zygote进程孵化出来的，Java环境也是由Zygote创建起来的，它建立了我们app运行所需要的环境，是app的祖先，因此，分析它的启动以及内部逻辑显得非常有必要。

Android系统是基于Linux内核的，而在Linux系统中，所有的进程都是init进程的子孙进程，也就是说，所有的进程都是直接或者间接地由init进程fork出来的。Zygote进程也不例外，它是在系统启动的过程，由init进程创建的。在系统启动脚本system/core/rootdir/init.rc文件中，我们可以看到启动Zygote进程的脚本命令：
service zygote /system/bin/app_process -Xzygote /system/bin --zygote --start-system-server  
    socket zygote stream 666   # zygote需要一个套接字
    onrestart write /sys/android_power/request_state wake  # zygote重启的话，需要执行这个操作
    onrestart write /sys/power/state on  
    onrestart restart media  
    onrestart restart netd
上述脚本表示要启动一个进程，名称为zygote, 可执行文件为/system/bin/app_process， --Xzygote /system/bin --zygote --start-system-server这些是传给zygote的参数，其余部分的作用见注释。

app_process对应的源码在frameworks/base/cmds/app_process目录下，其入口函数main在文件app_main.cpp中，接下来我们就从这个main函数入手来分析zygote的内部逻辑。

注意：本文的源码分析基于Android 4.4。

/*
* 启动zygote的方式为/system/bin/app_process -Xzygote /system/bin --zygote --start-system-server
* 所以 argc == 5
*      argv里头存的就是这5个参数argv[0]=="/system/bin/app_process" ,argv[1] == "-Xzygote"....
*/
int main(int argc, char* const argv[])
{
    ......
    // These are global variables in ProcessState.cpp
    mArgC = argc;
    mArgV = argv;

    mArgLen = 0;
    for (int i=0; i<argc; i++) {
        mArgLen += strlen(argv[i]) + 1;
    }
    mArgLen--;
    // 以上代码主要是将参数相关信息保存到全局变量中

    AppRuntime runtime;
    const char* argv0 = argv[0];

    // Process command line arguments
    // ignore argv[0]
    argc--;
    argv++;

    // Everything up to ‘--‘ or first non ‘-‘ arg goes to the vm

    int i = runtime.addVmArguments(argc, argv); // 这个函数会返回1，表示只处理了-Xzytote这一个参数，所谓的处理实际上就是将这个参数添加到了runtime对象的mOptions 变量中。

    // Parse runtime arguments.  Stop at first unrecognized option.
    bool zygote = false;
    bool startSystemServer = false;
    bool application = false;
    const char* parentDir = NULL;
    const char* niceName = NULL;
    const char* className = NULL;
    // 进入循环之前 i == 1, argc == 4  argv 指向“-Xzygote” 
    while (i < argc) {
        const char* arg = argv[i++];
        if (!parentDir) {
            parentDir = arg;  // parentDir被赋值为"/system/bin"
        } else if (strcmp(arg, "--zygote") == 0) {  
            zygote = true;
            niceName = "zygote"; // 进程名
        } else if (strcmp(arg, "--start-system-server") == 0) {
            startSystemServer = true;
        } else if (strcmp(arg, "--application") == 0) { // 不走这个分支
            application = true;
        } else if (strncmp(arg, "--nice-name=", 12) == 0) {  // 不走这个分支
            niceName = arg + 12;
        } else {  // 不走这个分支
            className = arg;
            break;
        }
    }

    if (niceName && *niceName) {  // 设置进程名
        setArgv0(argv0, niceName);
        set_process_name(niceName);
    }

    runtime.mParentDir = parentDir;

    if (zygote) { // 走这个分支
        runtime.start("com.android.internal.os.ZygoteInit",
                startSystemServer ? "start-system-server" : "");
    } else if (className) {
        // Remainder of args get passed to startup class main()
        runtime.mClassName = className;
        runtime.mArgC = argc - i;
        runtime.mArgV = argv + i;
        runtime.start("com.android.internal.os.RuntimeInit",
                application ? "application" : "tool");
    } else {
        fprintf(stderr, "Error: no class name or --zygote supplied.\n");
        app_usage();
        LOG_ALWAYS_FATAL("app_process: no class name or --zygote supplied.");
        return 10;
    }
}

main函数主要就是创建了runtime实例，并且解析参数，然后调用runtime的start函数，接着我们分析AppRuntime的start函数：

/*
 * Start the Android runtime.  This involves starting the virtual machine
 * and calling the "static void main(String[] args)" method in the class
 * named by "className".
 *
 * Passes the main function two arguments, the class name and the specified
 * options string.
 */
 // 首先我们明确下传进来的参数  className == "com.android.internal.os.ZygoteInit"  options == "start-system-server"
void AndroidRuntime::start(const char* className, const char* options)
{
    ALOGD("\n>>>>>> AndroidRuntime START %s <<<<<<\n",
            className != NULL ? className : "(unknown)");

    /*
     * ‘startSystemServer == true‘ means runtime is obsolete and not run from
     * init.rc anymore, so we print out the boot start event here.
     */
    if (strcmp(options, "start-system-server") == 0) {
        /* track our progress through the boot sequence */
        const int LOG_BOOT_PROGRESS_START = 3000;
        LOG_EVENT_LONG(LOG_BOOT_PROGRESS_START,
                       ns2ms(systemTime(SYSTEM_TIME_MONOTONIC)));
    }

    const char* rootDir = getenv("ANDROID_ROOT");
    if (rootDir == NULL) {
        rootDir = "/system";
        if (!hasDir("/system")) {
            LOG_FATAL("No root directory specified, and /android does not exist.");
            return;
        }
        setenv("ANDROID_ROOT", rootDir, 1);  //配置ANDROID_ROOT环境变量
    }

    //const char* kernelHack = getenv("LD_ASSUME_KERNEL");
    //ALOGD("Found LD_ASSUME_KERNEL=‘%s‘\n", kernelHack);

    /* start the virtual machine */
    JniInvocation jni_invocation;
    jni_invocation.Init(NULL);
    JNIEnv* env;
    if (startVm(&mJavaVM, &env) != 0) { // 创建虚拟机
        return;
    }
    onVmCreated(env);

    /*
     * Register android functions.
     */
    if (startReg(env) < 0) {
        ALOGE("Unable to register all android natives\n");
        return;
    }

    /*
     * We want to call main() with a String array with arguments in it.
     * At present we have two arguments, the class name and an option string.
     * Create an array to hold them.
     */
    jclass stringClass;
    jobjectArray strArray;
    jstring classNameStr;
    jstring optionsStr;

    stringClass = env->FindClass("java/lang/String");
    assert(stringClass != NULL);
    strArray = env->NewObjectArray(2, stringClass, NULL);
    assert(strArray != NULL);
    classNameStr = env->NewStringUTF(className);
    assert(classNameStr != NULL);
    env->SetObjectArrayElement(strArray, 0, classNameStr);
    optionsStr = env->NewStringUTF(options);
    env->SetObjectArrayElement(strArray, 1, optionsStr);

    /*
     * Start VM.  This thread becomes the main thread of the VM, and will
     * not return until the VM exits.
     */
    char* slashClassName = toSlashClassName(className);
    jclass startClass = env->FindClass(slashClassName);
    if (startClass == NULL) {
        ALOGE("JavaVM unable to locate class ‘%s‘\n", slashClassName);
        /* keep going */
    } else {
        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 {
            /* 调用com.android.internal.os.ZygoteInit的main函数，strArray是参数，数组里面有两个元素,
            className == "com.android.internal.os.ZygoteInit"  options == "start-system-server" */
            env->CallStaticVoidMethod(startClass, startMeth, strArray);

#if 0
            if (env->ExceptionCheck())
                threadExitUncaughtException(env);
#endif
        }
    }
    free(slashClassName);

    ALOGD("Shutting down VM\n");
    if (mJavaVM->DetachCurrentThread() != JNI_OK)
        ALOGW("Warning: unable to detach main thread\n");
    if (mJavaVM->DestroyJavaVM() != 0)
        ALOGW("Warning: VM did not shut down cleanly\n");
}

start函数主要做了以下几件事情：

调用startVm函数创建虚拟机；
调用startReg函数注册Android Natvie函数；
让虚拟机去执行com.android.internal.os.ZygoteInit的main函数。

接下来我们分析下com.android.internal.os.ZygoteInit的main函数，创建虚拟机以及注册native函数的过程后续再分析。

public static void main(String argv[]) {
        try {
            // Start profiling the zygote initialization.
            SamplingProfilerIntegration.start();

            registerZygoteSocket();  // 1、创建一个套接字，用于监听ams发过来的fork请求
            EventLog.writeEvent(LOG_BOOT_PROGRESS_PRELOAD_START,
                SystemClock.uptimeMillis());
            preload(); // 2、加载classes 和resources, 后面会详细分析
            EventLog.writeEvent(LOG_BOOT_PROGRESS_PRELOAD_END,
                SystemClock.uptimeMillis());

            // Finish profiling the zygote initialization.
            SamplingProfilerIntegration.writeZygoteSnapshot();

            // Do an initial gc to clean up after startup
            gc();

            // If requested, start system server directly from Zygote
            if (argv.length != 2) {
                throw new RuntimeException(argv[0] + USAGE_STRING);
            }

            if (argv[1].equals("start-system-server")) {
                startSystemServer(); //3、 创建system server进程，ams wms pms等常见service都在该进程里面
            } else if (!argv[1].equals("")) {
                throw new RuntimeException(argv[0] + USAGE_STRING);
            }

            Log.i(TAG, "Accepting command socket connections");

            if (ZYGOTE_FORK_MODE) {
                runForkMode();
            } else {
                runSelectLoopMode(); // 4、进入循环监听模式，监听外来请求
            }

            closeServerSocket();
        } catch (MethodAndArgsCaller caller) {
            caller.run();
        } catch (RuntimeException ex) {
            Log.e(TAG, "Zygote died with exception", ex);
            closeServerSocket();
            throw ex;
        }
    }