tcpdump mailing list archives
Re: Clock Accuracy (was: no subject)
From: "Steve Bonds" <pow7yec02 () sneakemail com>
Date: Tue, 29 Apr 2003 17:17:45 -0700 (PDT)
Kenny: This really isn't a tcpdump question per se, but a question about the precision of your system's local clock. You can find out more than you ever wanted to know about system time by following some links from the NTP (Network Time Protocol) website: http://www.ntp.org I also found this useful: http://www.tldp.org/HOWTO/mini/Clock.html And google is always helpful: http://www.google.com/search?hl=en&q=linux+clock+precision http://www.google.com/search?hl=en&q=linux+time+precision The answer is-- there is no one answer. It will depend on who made your motherboard, the patches applied to Linux, and possibly on what programs are running at the time. The tcpdump warning is just that-- a warning that even though your timestamps are recorded to the microsecond (millionths of a second), they may only be accurate to some level higher than that. Most modern PCs can be expected to be precise to a level of 10 milliseconds (thousandths of a second) for time measurements made in quick succession, and some do much better. -- Steve On Tue, 29 Apr 2003, qshao-at-sfu.ca |TCPdump Workers| wrote:
Hi, there: I am fresh man here. I have collected some data from a PIII machine, under Redhat 7.0 ,kernel 2.2.16-22 tcpdump version: 3.7.1. I was wondering if someone can tell me the granularity of the timestamps. I read some description about tcpdump file which said " Timestamps have millisecond precision, even though they are reported using six digits past the decimal. " Is it true? I thought it should be depend on the machine, if I am right, can anyone give me a feeling about the time granularity my data? millisecond? or serval microseconds? Many thanks! Kenny
- This is the TCPDUMP workers list. It is archived at http://www.tcpdump.org/lists/workers/index.html To unsubscribe use mailto:tcpdump-workers-request () tcpdump org?body=unsubscribe
Current thread:
- no subject qshao (Apr 29)
- Re: Clock Accuracy (was: no subject) Steve Bonds (Apr 29)
- Re: no subject Guy Harris (Apr 29)