On 11/14/14 12:26 AM, Tom Herbert wrote:
On Wed, Nov 12, 2014 at 5:13 PM, Mach Chen <[email protected]> wrote:
I think if we were implementing delay measurement in GUE, I would
advocate add a 64 bit optional field for timestamp, probably
containing source time stamp, and echoed timestamp for a flow (usec
resolution and similar in design TCP timestamp option). This easily
gives a precise RTT, and if clocks are precisely synchronized then one
way latency could be calculated also.
Tom,
Unless you are going to have an immediate echo packet, then you need 3
timestamps in the packet:
1. timestamp when A sent packet to B
2. timestamp when B received packet from A
3. timestamp when B sent packet to A (different than #2 unless you send
a immediate response)
A will also take a timestamp when it receives the packet from B, but
that doesn't have to be included in the packet.
Erik
_______________________________________________
nvo3 mailing list
[email protected]
https://www.ietf.org/mailman/listinfo/nvo3
