android zygote之启动过程分析
文章出处：http://blog.csdn.net/shift_wwx
前言：之前一篇博文（Android 的init过程详解）中记录了init启动过程，后来另一篇（Android init.rc详解 ）中记录了init.rc的解析过程，android详细的启动过程，就需要将所有的init rc文件解剖之后，从action到service挨个分析。这里记录一下zygote的启动过程。
启动命令
init.rc中：
service zygote /system/bin/app_process -Xzygote /system/bin --zygote --start-system-server
class main
socket zygote stream 660 root system
onrestart write /sys/android_power/request_state wake
onrestart write /sys/power/state on
onrestart restart media
onrestart restart netd
通过app_process引导启动zygote，/system/bin/app_process 之后的都是命令参数。
接下来的socket关键字表示这个zygote进程需要一个名称为"zygote"的socket资源，这样，系统启动后，我们就可以在/dev/socket目录下看到有一个名为zygote的文件。ActivityManagerService就是通这个socket来和zygote进程通信请求fork一个应用程序进程的了。
最后的一系列onrestart关键字表示这个zygote进程重启时需要执行的命令。
详细的可以参考Android init.rc详解
下面来分析一下source code：
int main(int argc, char* const argv[])
{
#ifdef __arm__
/*
* b/7188322 - Temporarily revert to the compat memory layout
* to avoid breaking third party apps.
*
* THIS WILL GO AWAY IN A FUTURE ANDROID RELEASE.
*
* http://git.kernel.org/?p=linux/kernel/git/torvalds/linux-2.6.git;a=commitdiff;h=7dbaa466
* changes the kernel mapping from bottom up to top-down.
* This breaks some programs which improperly embed
* an out of date copy of Android's linker.
*/
char value[PROPERTY_VALUE_MAX];
property_get("ro.kernel.qemu", value, "");
bool is_qemu = (strcmp(value, "1") == 0);
if ((getenv("NO_ADDR_COMPAT_LAYOUT_FIXUP") == NULL) && !is_qemu) {
int current = personality(0xFFFFFFFF);
if ((current & ADDR_COMPAT_LAYOUT) == 0) {
personality(current | ADDR_COMPAT_LAYOUT);
setenv("NO_ADDR_COMPAT_LAYOUT_FIXUP", "1", 1);
execv("/system/bin/app_process", argv);
return -1;
}
}
unsetenv("NO_ADDR_COMPAT_LAYOUT_FIXUP");
#endif
// 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--;
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);
// 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;
while (i < argc) {
const char* arg = argv[i++];
if (!parentDir) {
parentDir = arg;
} else if (strcmp(arg, "--zygote") == 0) {
zygote = true;
niceName = "zygote";
} 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 = arg + 12;
} else {
className = arg;
break;
}
}
if (niceName && *niceName) {
setArgv0(argv0, niceName);
set_process_name(niceName);//进程名为zygote
}
runtime.mParentDir = parentDir;//没看懂是干嘛的，应该只是做个路径保存吧，/system/bin
if (zygote) {
runtime.start("com.android.internal.os.ZygoteInit",
startSystemServer ? "start-system-server" : "");//启动zygote
} else if (className) {//除了zygote，RuntimeInit也在这里启动
// 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;
}
}
刚开始的时候直接忽略了argv[0]，直接从命令的路径开始，通过while循环逐个解析命令参数，parentDir、niceName、startSystemServer、zygote等等。
if (niceName && *niceName) {
setArgv0(argv0, niceName);
set_process_name(niceName);
}niceName是”zygote“，保存到了argv0，没看懂这个函数内部变量是干什么的？
设置了进程名为zygote。
@/syste/core/libcutils/process_name.c
void set_process_name(const char* new_name) {
#ifdef HAVE_ANDROID_OS
char propBuf[PROPERTY_VALUE_MAX];
#endif
if (new_name == NULL) {
return;
}
// We never free the old name. Someone else could be using it.
int len = strlen(new_name);
char* copy = (char*) malloc(len + 1);
strcpy(copy, new_name);
process_name = (const char*) copy;
#if defined(HAVE_PRCTL)
if (len < 16) {
prctl(PR_SET_NAME, (unsigned long) new_name, 0, 0, 0);
} else {
prctl(PR_SET_NAME, (unsigned long) new_name + len - 15, 0, 0, 0);
}
#endif
#ifdef HAVE_ANDROID_OS
// If we know we are not running in the emulator, then return.
if (running_in_emulator == 0) {
return;
}
// If the "running_in_emulator" variable has not been initialized,
// then do it now.
if (running_in_emulator == -1) {
property_get("ro.kernel.qemu", propBuf, "");
if (propBuf[0] == '1') {
running_in_emulator = 1;
} else {
running_in_emulator = 0;
return;
}
}
// If the emulator was started with the "-trace file" command line option
// then we want to record the process name in the trace even if we are
// not currently tracing instructions (so that we will know the process
// name when we do start tracing instructions). We do not need to execute
// this code if we are just running in the emulator without the "-trace"
// command line option, but we don't know that here and this function
// isn't called frequently enough to bother optimizing that case.
int fd = open(PROCESS_NAME_DEVICE, O_RDWR);
if (fd < 0)
return;
write(fd, process_name, strlen(process_name) + 1);
close(fd);
#endif
}后来通过
runtime.start("com.android.internal.os.ZygoteInit",
startSystemServer ? "start-system-server" : "");来启动zygote，具体start做了什么可以参考
Dalvik虚拟机的启动过程
public static void main(String argv[]) {
try {
// Start profiling the zygote initialization.
SamplingProfilerIntegration.start();
registerZygoteSocket();
EventLog.writeEvent(LOG_BOOT_PROGRESS_PRELOAD_START,
SystemClock.uptimeMillis());
if(!SystemProperties.getBoolean("config.enable_quickboot", false)) {
preload();
}
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();
// Disable tracing so that forked processes do not inherit stale tracing tags from
// Zygote.
Trace.setTracingEnabled(false);
// 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();
} else if (!argv[1].equals("")) {
throw new RuntimeException(argv[0] + USAGE_STRING);
}
Log.i(TAG, "Accepting command socket connections");
runSelectLoop();
closeServerSocket();
} catch (MethodAndArgsCaller caller) {
caller.run();
} catch (RuntimeException ex) {
Log.e(TAG, "Zygote died with exception", ex);
closeServerSocket();
throw ex;
}
}
最主要的就是做了三件事情：
1）创建zygote socket，用来和ActivityManagerService通讯
2）startSystemServer启动system_server
3）调用runSelectLoopMode函数进入一个无限循环在前面创建的socket接口上等待ActivityManagerService请求创建新的应用程序进程。
接下来对main函数做简单的分析：
1、数据统计
// Start profiling the zygote initialization. SamplingProfilerIntegration.start(); ...... // Finish profiling the zygote initialization. SamplingProfilerIntegration.writeZygoteSnapshot();
2、registerZygoteSocket
private static void registerZygoteSocket() {
if (sServerSocket == null) {
int fileDesc;
try {
String env = System.getenv(ANDROID_SOCKET_ENV);
fileDesc = Integer.parseInt(env);
} catch (RuntimeException ex) {
throw new RuntimeException(
ANDROID_SOCKET_ENV + " unset or invalid", ex);
}
try {
sServerSocket = new LocalServerSocket(
createFileDescriptor(fileDesc));
} catch (IOException ex) {
throw new RuntimeException(
"Error binding to local socket '" + fileDesc + "'", ex);
}
}
}
这个socket接口是通过文件描述符来创建的，这个文件描符代表的就是我们前面说的/dev/socket/zygote文件了。这个文件描述符是通过环境变量ANDROID_SOCKET_ENV得到的，它定义为：
private static final String ANDROID_SOCKET_ENV = "ANDROID_SOCKET_zygote";那么，这个环境变量的值又是由谁来设置的呢？我们知道，系统启动脚本文件system/core/rootdir/init.rc是由init进程来解释执行的，而init进程的源代码位于system/core/init目录中，在init.c文件中，是由service_start函数来解释init.rc文件中的service命令的：
void service_start(struct service *svc, const char *dynamic_args)
{
......
pid_t pid;
......
pid = fork();
if (pid == 0) {
struct socketinfo *si;
......
for (si = svc->sockets; si; si = si->next) {
int socket_type = (
!strcmp(si->type, "stream") ? SOCK_STREAM :
(!strcmp(si->type, "dgram") ? SOCK_DGRAM : SOCK_SEQPACKET));
int s = create_socket(si->name, socket_type,
si->perm, si->uid, si->gid);
if (s >= 0) {
publish_socket(si->name, s);
}
}
......
}
......
}每一个service命令都会促使init进程调用fork函数来创建一个新的进程，在新的进程里面，会分析里面的socket选项，对于每一个socket选项，都会通过create_socket函数来在/dev/socket目录下创建一个文件，在这个场景中，这个文件便是zygote了，然后得到的文件描述符通过publish_socket函数写入到环境变量中去：
static void publish_socket(const char *name, int fd)
{
char key[64] = ANDROID_SOCKET_ENV_PREFIX;
char val[64];
strlcpy(key + sizeof(ANDROID_SOCKET_ENV_PREFIX) - 1,
name,
sizeof(key) - sizeof(ANDROID_SOCKET_ENV_PREFIX));
snprintf(val, sizeof(val), "%d", fd);
add_environment(key, val);
/* make sure we don't close-on-exec */
fcntl(fd, F_SETFD, 0);
}这里就将init.rc中的zygote传了进来，而ANDROID_SOCKET_ENV_PREFIX在system/core/include/cutils/sockets.h定义为：
#define ANDROID_SOCKET_ENV_PREFIX "ANDROID_SOCKET_" #define ANDROID_SOCKET_DIR "/dev/socket"因此，这里就把上面得到的文件描述符写入到以"ANDROID_SOCKET_zygote"为key值的环境变量中。又因为上面的ZygoteInit.registerZygoteSocket函数与这里创建socket文件的create_socket函数是运行在同一个进程中，因此，上面的ZygoteInit.registerZygoteSocket函数可以直接使用这个文件描述符来创建一个Java层的LocalServerSocket对象。如果其它进程也需要打开这个/dev/socket/zygote文件来和Zygote进程进行通信，那就必须要通过文件名来连接这个LocalServerSocket了。
3、preload
if(!SystemProperties.getBoolean("config.enable_quickboot", false)) {
preload();
}对于preload这里不做过多的介绍，可以参考
android 系统资源的加载和获取
4、startSystemServer
private static boolean startSystemServer()
throws MethodAndArgsCaller, RuntimeException {
long capabilities = posixCapabilitiesAsBits(
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
);
/* Hardcoded command line to start the system server */
String args[] = {
"--setuid=1000",
"--setgid=1000",
"--setgroups=1001,1002,1003,1004,1005,1006,1007,1008,1009,1010,1018,1032,3001,3002,3003,3006,3007",
"--capabilities=" + capabilities + "," + capabilities,
"--runtime-init",
"--nice-name=system_server",
"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) {
handleSystemServerProcess(parsedArgs);
}
return true;
}
对于system_server进程，可以参考
android systemserver启动详解
重要的就是pid = Zygote.forkSystemServer(),创建一个新的进程来启动SystemServer组件，返回值pid等0的地方就是新的进程要执行的路径，即新创建的进程会执行handleSystemServerProcess函数。
private static void handleSystemServerProcess(
ZygoteConnection.Arguments parsedArgs)
throws ZygoteInit.MethodAndArgsCaller {
closeServerSocket();
// set umask to 0077 so new files and directories will default to owner-only permissions.
Libcore.os.umask(S_IRWXG | S_IRWXO);
if (parsedArgs.niceName != null) {
Process.setArgV0(parsedArgs.niceName);
}
if (parsedArgs.invokeWith != null) {
WrapperInit.execApplication(parsedArgs.invokeWith,
parsedArgs.niceName, parsedArgs.targetSdkVersion,
null, parsedArgs.remainingArgs);
} else {
/*
* Pass the remaining arguments to SystemServer.
*/
RuntimeInit.zygoteInit(parsedArgs.targetSdkVersion, parsedArgs.remainingArgs);
}
/* should never reach here */
}
由于由Zygote进程创建的子进程会继承Zygote进程在前面Step 2中创建的Socket文件描述符，而这里的子进程又不会用到它，因此，这里就调用closeServerSocket函数来关闭它。这个函数接着调用RuntimeInit.zygoteInit函数来进一步执行启动SystemServer组件的操作。详细的可以参考android systemserver启动详解
5、runSelectLoop
/**
* Runs the zygote process's select loop. Accepts new connections as
* they happen, and reads commands from connections one spawn-request's
* worth at a time.
*
* @throws MethodAndArgsCaller in a child process when a main() should
* be executed.
*/
private static void runSelectLoop() throws MethodAndArgsCaller {
ArrayList<FileDescriptor> fds = new ArrayList<FileDescriptor>();
ArrayList<ZygoteConnection> peers = new ArrayList<ZygoteConnection>();
FileDescriptor[] fdArray = new FileDescriptor[4];
fds.add(sServerSocket.getFileDescriptor());
peers.add(null);
int loopCount = GC_LOOP_COUNT;
while (true) {
int index;
/*
* Call gc() before we block in select().
* It's work that has to be done anyway, and it's better
* to avoid making every child do it. It will also
* madvise() any free memory as a side-effect.
*
* Don't call it every time, because walking the entire
* heap is a lot of overhead to free a few hundred bytes.
*/
if (loopCount <= 0) {//Zygote每循环GC_LOOP_COUNT（这里的值是10）次就会进行一次内存回收</span></span>
gc();
loopCount = GC_LOOP_COUNT;
} else {
loopCount--;
}
try {
fdArray = fds.toArray(fdArray);
index = selectReadable(fdArray);//内部由select()实现，在没有客户端事件时会堵塞
} catch (IOException ex) {
throw new RuntimeException("Error in select()", ex);
}
if (index < 0) {
throw new RuntimeException("Error in select()");
} else if (index == 0) {//index==0表示selcet接收到的是Zygote的socket的事件
ZygoteConnection newPeer = acceptCommandPeer();
peers.add(newPeer);
fds.add(newPeer.getFileDesciptor());
} else {//调用ZygoteConnection对象的runOnce方法，ZygoteConnection是在index == 0时被添加到peers的
boolean done;
done = peers.get(index).runOnce();
if (done) {
peers.remove(index);
fds.remove(index);
}
}
}
}
这就是在等待ActivityManagerService来连接这个Socket，然后调用ZygoteConnection.runOnce函数来创建新的应用程序
这样，Zygote进程就启动完成了，学习到这里，我们终于都对Android系统中的进程有了一个深刻的认识了，这里总结一下：
1. 系统启动时init进程会创建Zygote进程，Zygote进程负责后续Android应用程序框架层的其它进程的创建和启动工作。
2. Zygote进程会首先创建一个SystemServer进程，SystemServer进程负责启动系统的关键服务，如包管理服务PackageManagerService和应用程序组件管理服务ActivityManagerService。
3. 当我们需要启动一个Android应用程序时，ActivityManagerService会通过Socket进程间通信机制，通知Zygote进程为这个应用程序创建一个新的进程。