python 開發練習之監控

時間 2019-11-11

標籤 python 開發練習監控欄目 Python 简体版

原文原文鏈接

本節內容ios

爲何要作監控？ redis

經常使用監控系統設計討論sql

監控系統架構設計express

監控表結構設計django

爲何要作監控？

–熟悉IT監控系統的設計原理

–開發一個簡版的類Zabbix監控系統

–掌握自動化開發項目的程序設計思路及架構解藕原則

經常使用監控系統設計討論

Zabbix

Nagios

監控系統需求討論

1.可監控經常使用系統服務、應用、網絡設備等

2.一臺主機上可監控多個不一樣服務、不一樣服務的監控間隔可不一樣

3.同一個服務在不一樣主機上的監控間隔、報警閾值可不一樣

4.能夠批量的給一批主機添加、刪除、修改要監控的服務

5.告警級別：

不一樣的服務由於業務重要程度不一樣，若是出了問題能夠設置不一樣的報警級別
能夠指定特定的服務或告警級別的事件通知給特定的用戶
告警的升級設定

6.歷史數據的存儲和優化

實現用最少的空間佔用量存儲最多的有效數據
如何作到1s中以內取出一臺主機上全部服務的5年的監控數據？

7. 數據可視化，如何作出簡潔美觀的用戶界面？安全

8.如何實現單機支持5000+機器監控需求？

9.採起何種通訊方式？主動、被動？

10.如何實現監控服務器的水平擴展？

採用什麼架構？

•Mysql

•主動通訊？ Snmp,wget…

•被動通訊？Agent ---how to communicate with the monitor server

•Socket server –> Sockect client

•可否用現成的c/s架構？ Rabbit mq, redis 訂閱發佈， http ?

採用HTTP好處

1.接口設計簡單服務器

2.容易水平擴展作分佈式網絡

3.Socket穩定成熟，省去較多的通訊維護精力架構

Http特性：分佈式

1.短鏈接

2.無狀態

3.安全認證

4.被動通訊

#!_*_coding:utf8_*_
from django.db import models

# Create your models here.




class Host(models.Model):
    name =  models.CharField(max_length=64,unique=True)
    ip_addr =  models.GenericIPAddressField(unique=True)
    host_groups = models.ManyToManyField('HostGroup',blank=True) # A B C
    templates = models.ManyToManyField("Template",blank=True) # A D E
    monitored_by_choices = (
        ('agent','Agent'),
        ('snmp','SNMP'),
        ('wget','WGET'),
    )
    monitored_by = models.CharField(u'監控方式',max_length=64,choices=monitored_by_choices)
    status_choices= (
        (1,'Online'),
        (2,'Down'),
        (3,'Unreachable'),
        (4,'Offline'),
    )
    status = models.IntegerField(u'狀態',choices=status_choices,default=1)
    memo = models.TextField(u"備註",blank=True,null=True)

    def __unicode__(self):
        return self.name

class HostGroup(models.Model):
    name =  models.CharField(max_length=64,unique=True)
    templates = models.ManyToManyField("Template",blank=True)
    memo = models.TextField(u"備註",blank=True,null=True)
    def __unicode__(self):
        return self.name

class ServiceIndex(models.Model):
    name = models.CharField(max_length=64)
    key =models.CharField(max_length=64)
    data_type_choices = (
        ('int',"int"),
        ('float',"float"),
        ('str',"string")
    )
    data_type = models.CharField(u'指標數據類型',max_length=32,choices=data_type_choices,default='int')
    memo = models.CharField(u"備註",max_length=128,blank=True,null=True)
    def __unicode__(self):
        return "%s.%s" %(self.name,self.key)

class Service(models.Model):
    name = models.CharField(u'服務名稱',max_length=64,unique=True)
    interval = models.IntegerField(u'監控間隔',default=60)
    plugin_name = models.CharField(u'插件名',max_length=64,default='n/a')
    items = models.ManyToManyField('ServiceIndex',verbose_name=u"指標列表",blank=True)
    memo = models.CharField(u"備註",max_length=128,blank=True,null=True)

    def __unicode__(self):
        return self.name
    #def get_service_items(obj):
    #    return ",".join([i.name for i in obj.items.all()])

class Template(models.Model):
    name = models.CharField(u'模版名稱',max_length=64,unique=True)
    services = models.ManyToManyField('Service',verbose_name=u"服務列表")
    triggers = models.ManyToManyField('Trigger',verbose_name=u"觸發器列表",blank=True)
    def __unicode__(self):
        return self.name
'''
class TriggerExpression(models.Model):
    name = models.CharField(u"觸發器表達式名稱",max_length=64,blank=True,null=True)
    service = models.ForeignKey(Service,verbose_name=u"關聯服務")
    service_index = models.ForeignKey(ServiceIndex,verbose_name=u"關聯服務指標")
    logic_type_choices = (('or','OR'),('and','AND'))
    logic_type = models.CharField(u"邏輯關係",choices=logic_type_choices,max_length=32,blank=True,null=True)
    left_sibling = models.ForeignKey('self',verbose_name=u"左邊條件",blank=True,null=True,related_name='left_sibling_condition' )
    operator_type_choices = (('eq','='),('lt','<'),('gt','>'))
    operator_type = models.CharField(u"運算符",choices=operator_type_choices,max_length=32)
    data_calc_type_choices = (
        ('avg','Average'),
        ('max','Max'),
        ('hit','Hit'),
        ('last','Last'),
    )
    data_calc_func= models.CharField(u"數據處理方式",choices=data_calc_type_choices,max_length=64)
    data_calc_args = models.CharField(u"函數傳入參數",help_text=u"如果多個參數,則用,號分開,第一個值是時間",max_length=64)
    threshold = models.IntegerField(u"閾值")

    def __unicode__(self):
        return "%s %s(%s(%s))" %(self.service_index,self.operator_type,self.data_calc_func,self.data_calc_args)
'''


class TriggerExpression(models.Model):
    #name = models.CharField(u"觸發器表達式名稱",max_length=64,blank=True,null=True)
    trigger = models.ForeignKey('Trigger',verbose_name=u"所屬觸發器")
    service = models.ForeignKey(Service,verbose_name=u"關聯服務")
    service_index = models.ForeignKey(ServiceIndex,verbose_name=u"關聯服務指標")
    specified_index_key = models.CharField(verbose_name=u"只監控專門指定的指標key",max_length=64,blank=True,null=True)
    operator_type_choices = (('eq','='),('lt','<'),('gt','>'))
    operator_type = models.CharField(u"運算符",choices=operator_type_choices,max_length=32)
    data_calc_type_choices = (
        ('avg','Average'),
        ('max','Max'),
        ('hit','Hit'),
        ('last','Last'),
    )
    data_calc_func= models.CharField(u"數據處理方式",choices=data_calc_type_choices,max_length=64)
    data_calc_args = models.CharField(u"函數傳入參數",help_text=u"如果多個參數,則用,號分開,第一個值是時間",max_length=64)
    threshold = models.IntegerField(u"閾值")


    logic_type_choices = (('or','OR'),('and','AND'))
    logic_type = models.CharField(u"與一個條件的邏輯關係",choices=logic_type_choices,max_length=32,blank=True,null=True)
    #next_condition = models.ForeignKey('self',verbose_name=u"右邊條件",blank=True,null=True,related_name='right_sibling_condition' )
    def __unicode__(self):
        return "%s %s(%s(%s))" %(self.service_index,self.operator_type,self.data_calc_func,self.data_calc_args)
    class Meta:
        pass #unique_together = ('trigger_id','service')

class Trigger(models.Model):
    name = models.CharField(u'觸發器名稱',max_length=64)
    #expressions= models.TextField(u"表達式")
    severity_choices = (
        (1,'Information'),
        (2,'Warning'),
        (3,'Average'),
        (4,'High'),
        (5,'Diaster'),
    )
    #expressions = models.ManyToManyField(TriggerExpression,verbose_name=u"條件表達式")
    severity = models.IntegerField(u'告警級別',choices=severity_choices)
    enabled = models.BooleanField(default=True)
    memo = models.TextField(u"備註",blank=True,null=True)

    def __unicode__(self):
        return "<serice:%s, severity:%s>" %(self.name,self.get_severity_display())



class Action(models.Model):
    name =  models.CharField(max_length=64,unique=True)
    host_groups = models.ManyToManyField('HostGroup',blank=True)
    hosts = models.ManyToManyField('Host',blank=True)

    conditions = models.TextField(u'告警條件')
    interval = models.IntegerField(u'告警間隔(s)',default=300)
    operations = models.ManyToManyField('ActionOperation')

    recover_notice = models.BooleanField(u'故障恢復後發送通知消息',default=True)
    recover_subject = models.CharField(max_length=128,blank=True,null=True)
    recover_message = models.TextField(blank=True,null=True)

    enabled = models.BooleanField(default=True)

    def __unicode__(self):
        return self.name

class ActionOperation(models.Model):
    name =  models.CharField(max_length=64)
    step = models.SmallIntegerField(u"第n次告警",default=1)
    action_type_choices = (
        ('email','Email'),
        ('sms','SMS'),
        ('script','RunScript'),
    )
    action_type = models.CharField(u"動做類型",choices=action_type_choices,default='email',max_length=64)
    #notifiers= models.ManyToManyField(host_models.UserProfile,verbose_name=u"通知對象",blank=True)
    def __unicode__(self):
        return self.name


class Maintenance(models.Model):
    name =  models.CharField(max_length=64,unique=True)
    hosts = models.ManyToManyField('Host',blank=True)
    host_groups = models.ManyToManyField('HostGroup',blank=True)
    content = models.TextField(u"維護內容")
    start_time = models.DateTimeField()
    end_time = models.DateTimeField()

    def __unicode__(self):
        return self.name

''''
CPU
    idle 80
    usage  90
    system  30
    user
    iowait  50

memory :
    usage
    free
    swap
    cache
    buffer

load:
    load1
    load 5
    load 15
'''