RFC 8239, "Data Center Benchmarking Methodology", August 2017

Errata ID: 6768
Status: Rejected
Type: Technical
Publication Format(s) : TEXT
Reported By: Leonard Yu
Date Reported: 2021-12-01
Rejected by: Mohamed Boucadair
Date Rejected: 2025-03-28

Section 3.2 says:

3) Measure maximum port pair buffer sizes.

      o  First iteration: Ingress port 1 sending line rate to egress
         port 2, ingress port 3 sending line rate to egress port 4, etc.
         Ingress port N-1 and port N will oversubscribe, at 1% of line
         rate, egress port 2 and port 3, respectively.  Measure the
         buffer size value by multiplying the number of extra frames
         sent by the frame size for each egress port.

      o  Second iteration: Ingress port 1 sending line rate to egress
         port 2, ingress port 3 sending line rate to egress port 4, etc.
         Ingress port N-1 and port N will oversubscribe, at 1% of line
         rate, egress port 4 and port 5, respectively.  Measure the
         buffer size value by multiplying the number of extra frames
         sent by the frame size for each egress port.

      o  Last iteration: Ingress port 1 sending line rate to egress
         port 2, ingress port 3 sending line rate to egress port 4, etc.
         Ingress port N-1 and port N will oversubscribe, at 1% of line
         rate, egress port N-3 and port N-2, respectively.  Measure the
         buffer size value by multiplying the number of extra frames
         sent by the frame size for each egress port.

It should say:

3) Measure maximum port pair buffer sizes.

      o  First iteration: Ingress port 1 sending line rate to egress
         port 2, ingress port 3 sending line rate to egress port 4, etc.
         Ingress port N-1 and port N will oversubscribe, at 1% of line
         rate, egress port 1 and port 2, respectively.  Measure the
         buffer size value by multiplying the number of extra frames
         sent by the frame size for each egress port.

      o  Second iteration: Ingress port 1 sending line rate to egress
         port 2, ingress port 3 sending line rate to egress port 4, etc.
         Ingress port N-1 and port N will oversubscribe, at 1% of line
         rate, egress port 3 and port 4, respectively.  Measure the
         buffer size value by multiplying the number of extra frames
         sent by the frame size for each egress port.

      o  Last iteration: Ingress port 1 sending line rate to egress
         port 2, ingress port 3 sending line rate to egress port 4, etc.
         Ingress port N-1 and port N will oversubscribe, at 1% of line
         rate, egress port N-3 and port N-2, respectively.  Measure the
         buffer size value by multiplying the number of extra frames
         sent by the frame size for each egress port.

Notes:

The oversubscribed ports are a pair of ingress and egress ports. The oversubscribed ports in the texts describing the first are port 2 & 3, which are incorrect, should be port 1 & 2. The oversubscribed ports in the texts describing the second are port 4 & 5, which are incorrect, should be port 3 & 4.
--VERIFIER NOTES--
See https://mailarchive.ietf.org/arch/msg/bmwg/LrV7P2Oc7ElYpOCxUtLQu3hxRLU/

Report New Errata