使用ACE监控启动进程，进程崩溃后自动重启(windows/linux通用)

//使用ACE监控启动进程，进程崩溃后自动重启(windows/linux通用)

原理：

监护程序使用子进程的方式启动各个进程，

子进程退出时，监护程序能够得到相应的退出信号，

从而在子进程退出后，在重新启动相应的子进程。

//----------------------------------------------------------

//配置文件ProcessManager.conf格式

//./PROCESS_MANAGER 1

//./PROCESS_MANAGER 2

//----------------------------------------------------------

// main.cpp

// main.cpp
#include "CProcessManager.h"
int main(int argc, char *argv[])
{
// Running as a child for test.
if (argc > 1)
{
ACE_OS::sleep(10);
return 0;
}
// set output log file
ACE_OS::setprogname("ProcessManager");
ACE_Date_Time tvTime(ACE_OS::gettimeofday());
char szLogFileName[256];
memset(szLogFileName, 0, sizeof(szLogFileName));
snprintf(szLogFileName, sizeof(szLogFileName), "log/%s_%04d%02d%02d_%02d%02d%02d.log",
ACE_OS::getprogname(),
(int)tvTime.year(), (int)tvTime.month(),  (int)tvTime.day(),
(int)tvTime.hour(), (int)tvTime.minute(), (int)tvTime.second());

ACE_OSTREAM_TYPE *pLogOutput = new ofstream(szLogFileName);
ACE_LOG_MSG->msg_ostream(pLogOutput, true);
ACE_LOG_MSG->set_flags(ACE_Log_Msg::OSTREAM);
// Prepends timestamp and message priority to each message
ACE_LOG_MSG->set_flags(ACE_Log_Msg::VERBOSE_LITE);
//ACE_LOG_MSG->clr_flags(ACE_Log_Msg::STDERR);

ACE_DEBUG((LM_INFO, ACE_TEXT("[%N:%l]: ---ProcessManager START---.\n")));
int nRet = 0;
CProcessManager *pProcMng = new CProcessManager();
// 启动进程监控
nRet = pProcMng->ProcessMonitor();
if(nRet != 0)
{
ACE_DEBUG((LM_ERROR, ACE_TEXT("[%N:%l]: ---ProcessMonitor Error---\n")));
}
delete pProcMng;
ACE_DEBUG((LM_INFO, ACE_TEXT("[%N:%l]: ---ProcessManager STOP---.\n")));
ACE_LOG_MSG->clr_flags(ACE_Log_Msg::OSTREAM);
delete pLogOutput;
return 0;
}

头文件CProcessManager.h

类的定义如下

//CProcessManager.h
#include <stdio.h>
#include <stdlib.h>
#include <vector>
#include <string>
#include <map>
using namespace std;

#include "ace/OS.h"
#include "ace/streams.h"
#include "ace/Log_Msg.h"
#include "ace/Date_Time.h"
#include "ace/Event_Handler.h"
#include "ace/Reactor.h"
#include "ace/Process_Manager.h"

// 进程监控，进程崩溃后，自动重新启动进程
class CProcessManager
{
public:
CProcessManager(){};
virtual ~CProcessManager(){};
// 从配置文件读取进程列表信息
virtual int ReadConfigProcessInfo(char *pFileName);
// 启动进程，并进行进程监控，进程崩溃后，自动重新启动进程
virtual int ProcessMonitor();

private:
vector<string> m_vConfigProcessInfo;       // 进程列表信息
};

// 回调事件，程序退出后，执行handle_exit函数
class CProcessExitHandler: public ACE_Event_Handler
{
public:
CProcessExitHandler(){};
virtual ~CProcessExitHandler(){};
// 程序退出后，执行该函数
virtual int handle_exit(ACE_Process* process);
};

//CProcessManager.cpp类中函数的实现

//实现自动重新启动进程

//CProcessManager.cpp
#include "CProcessManager.h"

ACE_Process_Manager *g_pPM;             // 进程管理
map<string, pid_t> g_mapProcessInfo;    // 进程ID管理列表

// 读取进程列表配置文件
int CProcessManager::ReadConfigProcessInfo(char *pFileName)
{
char *pTemp = NULL;
char szTemp[1024];
string strTemp = "";
if(NULL == pFileName)
{
ACE_DEBUG((LM_ERROR, ACE_TEXT("[%N:%l]: Parameter FileName is null.\n")));
return -1;
}
// 文件格式
//./PROCESS_MANAGER 1
//./PROCESS_MANAGER 2
// 打开进程列表配置文件
FILE *fp = fopen(pFileName, "r");
if(NULL == fp)
{
ACE_DEBUG((LM_ERROR, ACE_TEXT("[%N:%l]: file open error.[%s]\n"), pFileName));
return -2;
}
// 循环读取进程列表配置文件
while(1)
{
memset(szTemp, 0, sizeof(szTemp));
pTemp = fgets(szTemp, sizeof(szTemp), fp);
if(NULL == pTemp)
{
break;
}
// 去掉注释
if(szTemp[0] == '#')
{
continue;
}
strTemp = szTemp;
if(strTemp.length() == 0)
{
continue;
}
// 去掉回车换行
if(strTemp[strTemp.length() - 1] == '\n')
{
strTemp[strTemp.length() - 1] = 0;
}
if(strTemp.length() == 0)
{
continue;
}
if(strTemp[strTemp.length() - 1] == '\r')
{
strTemp[strTemp.length() - 1] = 0;
}
if(strTemp.length() == 0)
{
continue;
}
// 把读取的进程信息放到[进程列表信息]全局变量
m_vConfigProcessInfo.push_back(strTemp);
}
// 关闭进程列表配置文件
fclose(fp);
// [进程列表信息]不应该为0
if(m_vConfigProcessInfo.size() == 0)
{
ACE_DEBUG((LM_ERROR, ACE_TEXT("[%N:%l]: Process list is null.[%s]\n"), pFileName));
return -3;
}
return 0;
}

// 进程监控
// 根据配置文件启动进程，并注册进程退出时回调函数
int CProcessManager::ProcessMonitor()
{
int nRet = 0;
vector<string>::iterator itrConfig;
string strStartProcess;

m_vConfigProcessInfo.clear();

// 读取进程列表配置文件
nRet = ReadConfigProcessInfo("ProcessManager.conf");
if(nRet != 0)
{
ACE_DEBUG((LM_ERROR,
ACE_TEXT("[%N:%l]: ReadConfigProcessInfo[%s] error.\n"), "ProcessManager.conf"));
return -1;
}

// Instantiate a process manager with space for 100 processes.
g_pPM = new ACE_Process_Manager(ACE_Process_Manager::DEFAULT_SIZE, ACE_Reactor::instance());
CProcessExitHandler procExitHandler;
// 循环配置进程列表，启动进程
for(itrConfig = m_vConfigProcessInfo.begin(); itrConfig != m_vConfigProcessInfo.end(); ++itrConfig)
{
strStartProcess = *itrConfig;
// 启动进程
ACE_Process_Options options;
options.command_line(strStartProcess.c_str());
pid_t pid = g_pPM->spawn(options);
// 启动进程失败
if (pid == ACE_INVALID_PID)
{
ACE_DEBUG((LM_ERROR,
ACE_TEXT("[%N:%l]: start a child process success(%d)%s\n"),
pid, strStartProcess.c_str()));
return -1;
}
ACE_DEBUG((LM_INFO,
ACE_TEXT("[%N:%l]: start a child process success(%d)%s\n"),
pid, strStartProcess.c_str()));
// 注册回调(进程退出时，调用该回调)
g_pPM->register_handler(&procExitHandler, pid);
// 添加启动成功的进程到进程ID管理列表
g_mapProcessInfo[strStartProcess] = pid;
ACE_OS::sleep(1);
}

// Run the reactor event loop waiting for events to occur.
ACE_Reactor::instance()->run_reactor_event_loop();
//ACE_Reactor::instance()->end_reactor_event_loop();
return 0;
}

// 进程退出回调函数
// 程序退出后，执行该函数，重新启动进程
int CProcessExitHandler::handle_exit(ACE_Process* process)
{
map<string, pid_t>::iterator itrProcess;

ACE_DEBUG((LM_INFO,
ACE_TEXT("[%N:%l]: Process %d exited with exit code %d\n"),
process->getpid (), process->return_value()));

// 循环进程ID管理列表，根据进程ID找到退出的进程，重新启动进程
for(itrProcess = g_mapProcessInfo.begin(); itrProcess != g_mapProcessInfo.end(); ++itrProcess)
{
// 根据进程ID，查找进程名
if(itrProcess->second == process->getpid())
{
// 重新启动进程
ACE_Process_Options options;
options.command_line(itrProcess->first.c_str());
pid_t pid = g_pPM->spawn(options);
// 重新启动进程失败
if (pid == ACE_INVALID_PID)
{
ACE_DEBUG((LM_ERROR,
ACE_TEXT("[%N:%l]: restart a child process error(%d)%s\n"),
pid, itrProcess->first.c_str()));
return -1;
}
ACE_DEBUG((LM_INFO,
ACE_TEXT("[%N:%l]: restart a child process success(%d)%s\n"),
pid, itrProcess->first.c_str()));
// 注册回调(进程退出时，调用该回调)
g_pPM->register_handler(this, pid);
// 添加启动成功的进程到进程ID管理列表
itrProcess->second = pid;
break;
}
}
return 0;
}