Linux监控重要进程的实现方法linux
无论后台服务程序写的多么健壮,仍是可能会出现core dump等程序异常退出的状况,可是通常状况下须要在无shell
人为干预状况下,可以自动从新启动,保证服务进程可以服务用户。这时就须要一个监控程序来实现可以让服务进程自动从新启动。查阅相关资料及尝试一些方法以后,总结linux系统监控重要进程的实现方法:脚本检测和子进程替换。apache
一、脚本检测 (1) 基本思路: 经过shell命令(ps -e | grep "$1" | grep -v "grep" | wc -l) 获取 $1 ($1 表明进程的名字)的进程数,脚本根据进程数来决定下一步的操做。经过一个死循环,每隔几秒检查一次系统中的指定程序的进程数,这里也可以使用crontab来实现。 (2) 具体实现过程的代码以下: [ supervisor.sh ]函数
#! /bin/sh
# supervisor process
LOG_FILE=/var/log/supervisor_sh.log
# log function
function log() {
local t=$(date +"%F %X")
echo "[ $t ] $0 : $1 " >> ${LOG_FILE}
}
# check process number
# $1 : process name
function check_process() {
if [ -z $1 ]; then
log "Input parameter is empty."
return 0
fi
p_num=$(ps -e | grep "$1" | grep -v "grep" | wc -l)
log "p_num = $p_num"
echo $p_num
}
# supervisor process
while [ 1 ]
do
declare -i ch_num
p_name="apache2"
ch_num=$(check_process $p_name)
if [ $ch_num -eq 0 ]; then
killall $p_name
service $p_name start
fi
sleep 3
done
#! /bin/sh
# supervisor process
LOG_FILE=/var/log/supervisor_sh.log
# log function
function log() {
local t=$(date +"%F %X")
echo "[ $t ] $0 : $1 " >> ${LOG_FILE}
}
# check process number
# $1 : process name
function check_process() {
if [ -z $1 ]; then
log "Input parameter is empty."
return 0
fi
p_num=$(ps -e | grep "$1" | grep -v "grep" | wc -l)
log "p_num = $p_num"
echo $p_num
}
# supervisor process
while [ 1 ]
do
declare -i ch_num
p_name="apache2"
ch_num=$(check_process $p_name)
if [ $ch_num -eq 0 ]; then
killall $p_name
service $p_name start
fi
sleep 3
done
二、子进程替换 (1) 基本思路: a. 使用fork函数建立一个新的进程,在进程表中建立一个新的表项,而建立者(即父进程)按原来的流程继续执行,子进程执行本身的控制流程 b. 运用execv函数把当前进程替换为一个新的进程,新进程由path或file参数指定,可使用execv函数将程序的执行从一个程序切换到另外一个程序 c. 当fork启动一个子进程时,子进程就有了它本身的生命周期并将独立运行,此时能够在父进程中调用wait函数让父进程等待子进程的结束 (2) 基本的实现步骤: a. 首先使用fork系统调用,建立子进程 b. 在子进程中使用execv函数,执行须要自动重启的程序 c. 在父进程中执行wait函数等待子进程的结束,而后从新建立一个新的子进程 (3) 具体实现的代码以下: supervisor.c测试
/**
*
* supervisor
*
* date: 2016-08-10
*
*/
#include
#include
#include
#include
#include
#include
#include
#include
#define LOG_FILE "/var/log/supervisor.log"
void s_log(char *text) {
time_t t;
struct tm *tm;
char *log_file;
FILE *fp_log;
char date[128];
log_file = LOG_FILE;
fp_log = fopen(log_file, "a+");
if (NULL == fp_log) {
fprintf(stderr, "Could not open logfile '%s' for writing\n", log_file);
}
time(&t);
tm = localtime(&t);
strftime(date, 127, "%Y-%m-%d %H:%M:%S", tm);
/* write the message to stdout and/or logfile */
fprintf(fp_log, "[%s] %s\n", date, text);
fflush(fp_log);
fclose(fp_log);
}
int main(int argc, char **argv) {
int ret, i, status;
char *child_argv[100] = {0};
pid_t pid;
if (argc
fprintf(stderr, "Usage:%s ", argv[0]);
return -1;
}
for (i = 1; i
child_argv[i-1] = (char *)malloc(strlen(argv[i])+1);
strncpy(child_argv[i-1], argv[i], strlen(argv[i]));
//child_argv[i-1][strlen(argv[i])] = '0';
}
while(1) {
pid = fork();
if (pid == -1) {
fprintf(stderr, "fork() error.errno:%d error:%s", errno, strerror(errno));
break;
}
if (pid == 0) {
s_log(child_argv[0]);
ret = execv(child_argv[0], (char **)child_argv);
s_log("execv return");
if (ret
fprintf(stderr, "execv ret:%d errno:%d error:%s", ret, errno, strerror(errno));
continue;
}
s_log("exit child process");
exit(0);
}
if (pid > 0) {
pid = wait(&status);
fprintf(stdout, "Child process id: %d\n", pid);
//fprintf(stdout, "wait return");
s_log("Wait child process return");
}
}
return 0;
}
/**
*
* supervisor
*
* date: 2016-08-10
*
*/
#include
#include
#include
#include
#include
#include
#include
#include
#define LOG_FILE "/var/log/supervisor.log"
void s_log(char *text) {
time_t t;
struct tm *tm;
char *log_file;
FILE *fp_log;
char date[128];
log_file = LOG_FILE;
fp_log = fopen(log_file, "a+");
if (NULL == fp_log) {
fprintf(stderr, "Could not open logfile '%s' for writing\n", log_file);
}
time(&t);
tm = localtime(&t);
strftime(date, 127, "%Y-%m-%d %H:%M:%S", tm);
/* write the message to stdout and/or logfile */
fprintf(fp_log, "[%s] %s\n", date, text);
fflush(fp_log);
fclose(fp_log);
}
int main(int argc, char **argv) {
int ret, i, status;
char *child_argv[100] = {0};
pid_t pid;
if (argc < 2) {
fprintf(stderr, "Usage:%s ", argv[0]);
return -1;
}
for (i = 1; i < argc; ++i) {
child_argv[i-1] = (char *)malloc(strlen(argv[i])+1);
strncpy(child_argv[i-1], argv[i], strlen(argv[i]));
//child_argv[i-1][strlen(argv[i])] = '0';
}
while(1) {
pid = fork();
if (pid == -1) {
fprintf(stderr, "fork() error.errno:%d error:%s", errno, strerror(errno));
break;
}
if (pid == 0) {
s_log(child_argv[0]);
ret = execv(child_argv[0], (char **)child_argv);
s_log("execv return");
if (ret < 0) {
fprintf(stderr, "execv ret:%d errno:%d error:%s", ret, errno, strerror(errno));
continue;
}
s_log("exit child process");
exit(0);
}
if (pid > 0) {
pid = wait(&status);
fprintf(stdout, "Child process id: %d\n", pid);
//fprintf(stdout, "wait return");
s_log("Wait child process return");
}
}
return 0;
}
(4) 测试验证 a. 假设须要自动重启的程序为demo.c,其代码实现以下所示:spa
/*
*
* demo
*
*/
#include
#include
#include
#include
#include
#include
#include
#include
#define LOG_FILE "/var/log/demo.log"
void demo_log(int num) {
time_t t;
struct tm *tm;
char *log_file;
FILE *fp_log;
char date[128];
log_file = LOG_FILE;
fp_log = fopen(log_file, "a+");
if (NULL == fp_log) {
fprintf(stderr, "Could not open logfile '%s' for writing\n", log_file);
}
time(&t);
tm = localtime(&t);
strftime(date,127,"%Y-%m-%d %H:%M:%S",tm);
/* write the message to stdout and/or logfile */
fprintf(fp_log, "[%s] num = %d\n", date, num);
fflush(fp_log);
fclose(fp_log);
}
int main(int argc, char **argv[]) {
int num = 0;
while(1) {
sleep(10);
num++;
demo_log(num);
}
}
/*
*
* demo
*
*/
#include
#include
#include
#include
#include
#include
#include
#include
#define LOG_FILE "/var/log/demo.log"
void demo_log(int num) {
time_t t;
struct tm *tm;
char *log_file;
FILE *fp_log;
char date[128];
log_file = LOG_FILE;
fp_log = fopen(log_file, "a+");
if (NULL == fp_log) {
fprintf(stderr, "Could not open logfile '%s' for writing\n", log_file);
}
time(&t);
tm = localtime(&t);
strftime(date,127,"%Y-%m-%d %H:%M:%S",tm);
/* write the message to stdout and/or logfile */
fprintf(fp_log, "[%s] num = %d\n", date, num);
fflush(fp_log);
fclose(fp_log);
}
int main(int argc, char **argv[]) {
int num = 0;
while(1) {
sleep(10);
num++;
demo_log(num);
}
}
b. 测试准备和说明:.net
b1. 以上相关服务程序编译后的二进制文件为: supervisor 和 democode
b2. 执行以下测试命令 ./supervisor ./demoblog
c. 测试的结果:生命周期
c1. execv(progname, arg) 执行成功后,其后的代码不会执行;只有当执行错误时,才会返回 -1。原来调用execv进程的代码段会被progname应用程序的代码段替换。
c2. 当kill掉子进程时,父进程wait函数会接收到子进程退出的信号,进而循环再启动子进程,此过程实时性很是高。
c3. 当kill掉父进程时,子进程会被init进程接管,若是此时再kill掉子进程,则子进程会退出。
c4. 当同时kill掉父子进程,则父子进程都会退出。