在多线程环境中使用 pysnmp 的 SNMP 代理超时

Question

我正在尝试编写一个SNMP代理，可以用来监视我的python进程。为此，我编写了一个使用 pysnmp 实现 SNMP 代理的类。

这个代理的核心部分工作（即我可以使用 snmpwalk 来询问代理并且返回的数据是正确的）。为了允许我更新代理 MIB 值，我在它自己的线程中运行了调度程序（）。我的问题是，在使用 snmpwalk 与代理交谈时，我会出现超时（snmpwalk 正确遍历 MIB，但随后超时）。

有没有人知道我做错了什么？

代理代码如下：

import logging
from pysnmp import debug
from pysnmp.carrier.asyncore.dgram import udp
from pysnmp.entity import engine, config
from pysnmp.entity.rfc3413 import cmdrsp, context
from pysnmp.smi import exval
import threading
formatting = '[%(asctime)s-%(levelname)s]-(%(module)s) %(message)s'
logging.basicConfig(level=logging.DEBUG, format=formatting, )
class SNMPAgent(object):
    def _main(self):
        logging.debug("Creating SNMP Agent....")
        self._snmpEngine = engine.SnmpEngine()
        config.addTransport(
            self._snmpEngine,
            udp.domainName,
            udp.UdpTransport().openServerMode((self._agentHost, self._agentPort))
        )
        config.addV1System(self._snmpEngine, 'my-area', self._communityName)
        config.addVacmUser(self._snmpEngine,
                           2,
                           'my-area',
                           'noAuthNoPriv',
                           (1, 3, 6),
                           (1, 3, 6))
        snmpContext = context.SnmpContext(self._snmpEngine)
        mibBuilder = snmpContext.getMibInstrum().getMibBuilder()
        mibBuilder.loadModules('HOST-RESOURCES-MIB')
        self._mibInstrum = snmpContext.getMibInstrum()
        self._hostRunTable, = mibBuilder.importSymbols('HOST-RESOURCES-MIB', 'hrSWRunEntry')
        self._instanceId = self._hostRunTable.getInstIdFromIndices(1)

        # The following shows the OID name mapping
        #
        # hrSWRunTable          1.3.6.1.2.1.25.4.2          <TABLE>
        # hrSWRunEntry          1.3.6.1.2.1.25.4.2.1        <SEQUENCE>
        # hrSWRunIndex          1.3.6.1.2.1.25.4.2.1.1      <Integer32>
        # hrSWRunName           1.3.6.1.2.1.25.4.2.1.2      <InternationalDisplayString> 64 Char
        # hrSWRunID             1.3.6.1.2.1.25.4.2.1.3      <ProductID>
        # hrSWRunPath           1.3.6.1.2.1.25.4.2.1.4      <InternationalDisplayString> 128 octets
        # hrSWRunParameters     1.3.6.1.2.1.25.4.2.1.5      <InternationalDisplayString> 128 octets
        # hrSWRunType           1.3.6.1.2.1.25.4.2.1.6      <INTEGER>
        # hrSWRunStatus         1.3.6.1.2.1.25.4.2.1.7      <INTEGER>  <<===== This is the key variable used by Opennms
        self._setVars()
        cmdrsp.GetCommandResponder(self._snmpEngine, snmpContext)
        cmdrsp.SetCommandResponder(self._snmpEngine, snmpContext)
        cmdrsp.NextCommandResponder(self._snmpEngine, snmpContext)
        cmdrsp.BulkCommandResponder(self._snmpEngine, snmpContext)
    def runAgent(self):
        '''
        Run the Agent 
        '''
        t = threading.Thread(target=self._runAgentFunc, args = ())
        t.daemon = True
        t.start()

    def _runAgentFunc(self):
        try:
            self._snmpEngine.transportDispatcher.jobStarted(1)
            self._snmpEngine.transportDispatcher.runDispatcher()
        except:
            self._snmpEngine.transportDispatcher.closeDispatcher()
            raise
    def updateAgentStatus(self, runStatus, text1, text2):
        self._mibDict = {"hrSWRunIndex" : 1, 
                         "hrSWRunName" : self._name,
                         "hrSWRunID" : self._enterpriseMIB,   
                         "hrSWRunPath" : text1[:128] if text1 is not None else '',     
                         "hrSWRunParameters" : text2[:128] if text1 is not None else '',
                         "hrSWRunType" : 4,
                         "hrSWRunStatus" : 1
                         }
        self._setVars()
    def _setVars(self):
        varBinds = self._mibInstrum.writeVars((
            (self._hostRunTable.name + (1,) + self._instanceId, self._mibDict["hrSWRunIndex"]),
            (self._hostRunTable.name + (2,) + self._instanceId, self._mibDict["hrSWRunName"]), # <=== Must match OpenNMS service-name variable
            (self._hostRunTable.name + (3,) + self._instanceId, self._mibDict["hrSWRunID" ]),  #  
            (self._hostRunTable.name + (4,) + self._instanceId, self._mibDict["hrSWRunPath"]),
            (self._hostRunTable.name + (5,) + self._instanceId, self._mibDict["hrSWRunParameters"]),
            (self._hostRunTable.name + (6,) + self._instanceId, self._mibDict["hrSWRunType"]), # Values are ==> unknown(1), operatingSystem(2), deviceDriver(3), application(4)     
            (self._hostRunTable.name + (7,) + self._instanceId, self._mibDict["hrSWRunStatus"])  #<<=== This is the status number OpenNMS looks at Values are ==> running(1), runnable(2), notRunnable(3), invalid(4)
            ))
    def __init__(self, name, host, port, community, text1='Service up', text2=''):
        '''
        #=======================================================================
        # Constructor
        # name      -- the (process) name the agent should publish (must match 
        #              the openNMS name
        # host      -- the host name or ip the agent will run on
        # port      -- the port the snmp agent will listen on
        # community -- the community name the agent will use (usually 'public')
        # text1     -- the first status text string published (128 char max)
        # text2     -- the second status text string published (128 char max) 
        #=======================================================================
        '''
        self._name = name
        self._agentHost = host
        self._agentPort = port
        self._communityName = community
        self._enterpriseMIB = (1, 3, 6, 1, 4, 1, 50000, 0) # Made up for now
        self._mibInstrum = None
        self._snmpEngine = None
        self._dataChanged = False
        self._mibDict = {"hrSWRunIndex" : 1, 
                         "hrSWRunName" : self._name,
                         "hrSWRunID" : self._enterpriseMIB,   
                         "hrSWRunPath" : text1[:128] if text1 is not None else '',     
                         "hrSWRunParameters" : text2[:128] if text1 is not None else '',
                         "hrSWRunType" : 4,
                         "hrSWRunStatus" : 1
                         }
        self._main()

我按如下方式调用此代码（这只是测试我可以更改状态）：

from SNMPAgent import SNMPAgent
from time import sleep
agent = SNMPAgent("test", "127.0.0.1", 12345, "public", "This is my test message 1", "This is my test message 2")
    agent.runAgent()
    sleep(10) # Wait for it to start
    while True:
        agent.updateAgentStatus(3, "Oh no", "Something is wrong!")
        sleep(30)
        agent.updateAgentStatus(2, "Whew", "Everything is fixed")
        sleep(30)

要遍历代理 MIB，我使用：

snmpwalk -v 2c -c public -n my-context 127.0.0.1:12345 1.3.6.1.2.1.25.4.2

这显示了数据更新，但在遍历 MIB 结束时，代理超时：

HOST-RESOURCES-MIB::hrSWRunIndex.1 = INTEGER: 1
HOST-RESOURCES-MIB::hrSWRunName.1 = STRING: "test"
HOST-RESOURCES-MIB::hrSWRunID.1 = OID: SNMPv2-SMI::enterprises.50000.0
HOST-RESOURCES-MIB::hrSWRunPath.1 = STRING: "Whew"
HOST-RESOURCES-MIB::hrSWRunParameters.1 = STRING: "Everything is fixed"
HOST-RESOURCES-MIB::hrSWRunType.1 = INTEGER: application(4)
HOST-RESOURCES-MIB::hrSWRunStatus.1 = INTEGER: running(1)
Timeout: No Response from 127.0.0.1:12345

Answer 1

启用 pysnmp 调试会显示由特定 OID 的未设置整数值导致的序列化错误：

[2017-01-13 02:05:18,387-DEBUG]-(debug) generateResponseMsg: Message:
 version='version-2c'
 community=public
 data=PDUs:
  response=ResponsePDU:
   request-id=1950819527
   error-status='noError'
   error-index=0
   variable-bindings=VarBindList:
    VarBind:
     name=1.3.6.1.2.1.25.5.1.1.1.1
     =_BindValue:
      value=ObjectSyntax:
       simple=SimpleSyntax:
        integer-value=<no value>
2017-01-13 02:05:18,387 pysnmp: generateResponseMsg: serialization failure: Uninitialized ASN.1 value ("__eq__" attribute looked up)
[2017-01-13 02:05:18,387-DEBUG]-(debug) generateResponseMsg: serialization failure: Uninitialized ASN.1 value ("__eq__" attribute looked up)
2017-01-13 02:05:18,388 pysnmp: StatusInformation: {'errorIndication': <pysnmp.proto.errind.SerializationError object at 0x10162f828>}
[2017-01-13 02:05:18,388-DEBUG]-(debug) StatusInformation: {'errorIndication': <pysnmp.proto.errind.SerializationError object at 0x10162f828>}

您可能应该确保为所有非默认的 SNMP 表列设置值。

作为旁注，您似乎在没有显式同步的情况下从主线程和 SNMP 代理线程管理 MIB。这可能会导致竞争条件...