def getSmartdStatus(self):
## 检查smartd状态, smartd_stat, 1 正常, 0异常
smartPID = getProcessID("smartd")
smartCfgLine = 0
fObj = open(DIRs['SMART_CFG_FILE'])
fCon = fObj.readlines()
for el in fCon:
if el.split():
if not el.startswith("#"):
smartCfgLine += 1
fObj.close()
if smartPID and smartCfgLine > 0:
smartd_stat = 1
else:
smartd_stat = 0
self.data_for_post += "smartd_stat=%s&" % smartd_stat
def getAppStatus(self):
## 检查游戏程序运行状态, 0, 关闭; 1, 正常; 2, 异常
srvFlag = str(self.srvFlag)
srvStatus, srvPidStatus, mUser = {'Success': [], 'Error': []}, {}, "*****@*****.**"
## srvNeedStart = ['DbCacheApp','LogDbApp','MailApp','SnapshotApp','CopyApp','CellMgrApp','CellApp','InterApp','GateMgrApp','GateApp','LoginApp']
for srv in gameApps:
try:
srv += "_" + srvFlag # App名_区服标识
srvPid = getProcessID(srv) # 调用shell pidof 获取pid
if "GateApp" in srv:
if srvPid:
GateAppCount = len(srvPid.split()) # GateApp个数
else:
GateAppCount = 0
if srvPid:
srvStatus['Success'].append(srv)
srvPidStatus[srv] = {srv+"_status": 1, srv+"_pid": srvPid}
else:
srvStatus['Error'].append(srv)
srvPidStatus[srv] = {srv+"_status": 0, srv+"_pid": None}
except Exception, err:
saveLog.warning("getAppStatus() error occured while get proce pid, %s" % str(err))
def getNginxStatus(self):
try:
if os.path.exists("/usr/local/nginx/logs/nginx.pid"):
fObj = open("/usr/local/nginx/logs/nginx.pid")
ngxMainPid = fObj.read().strip()
fObj.close()
else:
ngxMainPid = 0
pids = getProcessID("nginx")
if ngxMainPid:
if not pids or len(pids) < 8:
wp = ""
res = os.popen("ps -C nginx -o pid,cmd").readlines()
for l in res:
wp += "\n" + l.strip()
if self.sDb.read(telIP, "ngxAlarm") == "ON": ## 状态为"NO"且开关为"ON"时,报故障
sub = "DBTX Nginx Alarm: %s" % ps1
msg = "Datetime: %s\nNginx主进程PID:%s\nWorker_processes:%s\n少于10个!!" % (getTimeNow(), ngxMainPid, wp)
saveLog.warning(msg)
sendMail(sub, msg)
self.sDb.update(telIP, "ngxAlarm", "OFF")
else:
if self.sDb.read(telIP, "ngxAlarm") == "OFF": ## 状态OK且开关为"OFF"时,报恢复
sub = "DBTX Nginx is OK: %s" % ps1
msg = "Datetime: %s\nNginx主进程恢复开启状态." % (getTimeNow())
saveLog.info(msg)
sendMail(sub, msg)
self.sDb.update(telIP, "ngxAlarm", "ON")
else:
if self.sDb.read(telIP, "ngxAlarm") == "ON": ## 状态为"NO"且开关为"ON"时,报故障
sub = "DBTX Nginx Alarm: %s" % ps1
msg = "Datetime: %s\nNginx主进程挂了!!" % (getTimeNow())
saveLog.warning(msg)
sendMail(sub, msg)
self.sDb.update(telIP, "ngxAlarm", "OFF")
except Exception,err:
saveLog.warning("getNginxStatus, %s" % str(err))
def getCrondStatus(self):
## 检查crond状态, 1 正常, 0 异常
cronPID = getProcessID("crond")
crond_status = 1 if cronPID else 0
self.data_for_post += "crond_status=%s&" % crond_status
def getNtpdStatus(self):
## 检查ntpd状态, 1 正常, 0 异常
ntpdPID = getProcessID("ntpd")
ntpd_status = 1 if ntpdPID else 0
self.data_for_post += "ntpd_status=%s&" % ntpd_status