寫一個python的服務監控程式

寫一個python的服務監控程式

前言:

Redhat下安裝Python2.7

rhel6.4內建的是2.6， 發現有的機器是python2.4。 到python網站下載原始碼，解壓到Redhat上，然後運行下面的命令：

# ./configure --prefix=/usr/local/python27

# make

# make install

這樣安裝之後預設不會啟用Python2.7，需要使用/usr/local/python27/bin/python2.7調用新版本的python。

而下面的安裝方式會直接接管現有的python

# ./configure

# make

# make install

開始：
服務子進程被監控主進程建立並監控，當子進程異常關閉，主進程可以再次啟動之。使用了python的subprocess模組。就這個簡單的代碼，居然互連網上沒有現成可用的例子。沒辦法，我寫好了貢獻出來吧。

首先是主進程代碼：service_mgr.py

#!/usr/bin/python#-*- coding: UTF-8 -*-# cheungmine# stdin、stdout和stderr分別表示子程式的標準輸入、標準輸出和標準錯誤。# # 可選的值有:#   subprocess.PIPE - 表示需要建立一個新的管道.#   一個有效檔案描述符（其實是個正整數）#   一個檔案對象#   None - 不會做任何重新導向工作，子進程的檔案描述符會繼承父進程的.# # stderr的值還可以是STDOUT, 表示子進程的標準錯誤也輸出到標準輸出.# # subprocess.PIPE# 一個可以被用於Popen的stdin、stdout和stderr 3個參數的特輸值，表示需要建立一個新的管道.# # subprocess.STDOUT# 一個可以被用於Popen的stderr參數的特輸值，表示子程式的標準錯誤匯合到標準輸出.################################################################################import osimport sysimport getoptimport timeimport datetimeimport codecsimport optparseimport ConfigParserimport signalimport subprocessimport select# logging# require python2.6.6 and laterimport logging  from logging.handlers import RotatingFileHandler## log settings: SHOULD BE CONFIGURED BY configLOG_PATH_FILE = "./my_service_mgr.log"LOG_MODE = 'a'LOG_MAX_SIZE = 4*1024*1024 # 4M per fileLOG_MAX_FILES = 4          # 4 Files: my_service_mgr.log.1, printmy_service_mgrlog.2, ...  LOG_LEVEL = logging.DEBUG  LOG_FORMAT = "%(asctime)s %(levelname)-10s[%(filename)s:%(lineno)d(%(funcName)s)] %(message)s"  handler = RotatingFileHandler(LOG_PATH_FILE, LOG_MODE, LOG_MAX_SIZE, LOG_MAX_FILES)formatter = logging.Formatter(LOG_FORMAT)handler.setFormatter(formatter)Logger = logging.getLogger()Logger.setLevel(LOG_LEVEL)Logger.addHandler(handler) # color output#pid = os.getpid() def print_error(s):    print '\033[31m[%d: ERROR] %s\033[31;m' % (pid, s)def print_info(s):    print '\033[32m[%d: INFO] %s\033[32;m' % (pid, s)def print_warning(s):    print '\033[33m[%d: WARNING] %s\033[33;m' % (pid, s)def start_child_proc(command, merged):    try:        if command is None:            raise OSError, "Invalid command"        child = None        if merged is True:            # merge stdout and stderr            child = subprocess.Popen(command,                stderr=subprocess.STDOUT, # 表示子進程的標準錯誤也輸出到標準輸出                stdout=subprocess.PIPE    # 表示需要建立一個新的管道            )        else:            # DO NOT merge stdout and stderr            child = subprocess.Popen(command,                stderr=subprocess.PIPE,                stdout=subprocess.PIPE)        return child    except subprocess.CalledProcessError:        pass # handle errors in the called executable    except OSError:        pass # executable not found    raise OSError, "Failed to run command!"def run_forever(command):    print_info("start child process with command: " + ' '.join(command))    Logger.info("start child process with command: " + ' '.join(command))    merged = False    child = start_child_proc(command, merged)    line = ''    errln = ''    failover = 0    while True:        while child.poll() != None:            failover = failover + 1            print_warning("child process shutdown with return code: " + str(child.returncode))                       Logger.critical("child process shutdown with return code: " + str(child.returncode))            print_warning("restart child process again, times=%d" % failover)            Logger.info("restart child process again, times=%d" % failover)            child = start_child_proc(command, merged)        # read child process stdout and log it        ch = child.stdout.read(1)        if ch != '' and ch != '\n':            line += ch        if ch == '\n':            print_info(line)            line = ''        if merged is not True:            # read child process stderr and log it            ch = child.stderr.read(1)            if ch != '' and ch != '\n':                errln += ch            if ch == '\n':                Logger.info(errln)                print_error(errln)                errln = ''    Logger.exception("!!!should never run to this!!!")  if __name__ == "__main__":    run_forever(["python", "./testpipe.py"])

然後是子進程代碼：testpipe.py

#!/usr/bin/python#-*- coding: UTF-8 -*-# cheungmine# 類比一個woker進程,10秒掛掉import osimport sysimport timeimport randomcnt = 10while cnt >= 0:    time.sleep(0.5)    sys.stdout.write("OUT: %s\n" % str(random.randint(1, 100000)))    sys.stdout.flush()    time.sleep(0.5)    sys.stderr.write("ERR: %s\n" % str(random.randint(1, 100000)))    sys.stderr.flush()    #print str(cnt)    #sys.stdout.flush()    cnt = cnt - 1sys.exit(-1)

$ python service_mgr.py