[Winpcap-users] Îòâåò: WinPCAP packets capture delay..
gianluca.varenni at cacetech.com
Wed Sep 22 12:17:27 PDT 2010
From: ""Fish" (David B. Trout)" <fish at infidels.org>
Sent: Wednesday, September 22, 2010 12:06 PM
To: <winpcap-users at winpcap.org>
Subject: Re: [Winpcap-users]Îòâåò: WinPCAP packets capture delay..
> Gianluca Varenni wrote:
>> As I wrote in the other mail, I don't have an explanation. That's
>> why I would test the issue with different NIC boards and I would
>> make sure that the transmitter is actually generating packets at
>> a fixed rate (i.e. the transmitter is not introducing the delay).
> I believe he has already proven that. His oscilloscope verifies the
> ARE coming in at a steady rate. YET, despite that fact, the timestamps
> seem to indicate that they are not. THAT is the problem!
> The two measurements (oscilloscope vs. WinPCap timestamp) conflict with
> And I don't know about you, but as for me I would place my money on the
> oscilloscope being right. :)
Definitely true. The weird thing for me is using an oscilloscope to measure
packet delays. I've never seen anyone using an oscilloscope for such
measurement. I don't doubt the precision of the oscilloscope... Usually when
people make this kind of measurement the use high end network analyzers and
custom packet capture boards that timestamp packets in hardware...
> Hence the question: WHY are WinPCap's timestamps apparently wrong? What
> would be causing it?
Or even better: why are packets delivered to WinPcap with such delay from
the lower layers?
Have a nice day
> As for me, I don't know why! I can only offer conjecture/speculation (i.e.
> guesses/ideas/possibilities/hypotheses) and let you and/or others falsify
> I'm out of ideas!
> "Fish" (David B. Trout)
> fish at softdevlabs.com
> Winpcap-users mailing list
> Winpcap-users at winpcap.org
More information about the Winpcap-users