RE: Action Points: errors..
Another option would be to pass along the error through TBD (header?) information and let the upper-level layers decide how they want to handle this. Some errors (such as PHY over-temp) may require some higher-level activity (flow throttling, fan speed increase) or the issuance of a maintenance ticket, but may not necessarily impact data reliability. Similarly, an encoding error for dummy data may not impact critical data. At this layer, we simply don't know and don't need to know.
These errors should be infrequent and may or may not impact critical data. I suggest that we indicate the errors within the protocol and leave it for the upper-level errors to figure out what to do with the packet that has this error.
--kb
-----Original Message-----
From: stds-1904-3-tf@xxxxxxxx [mailto:stds-1904-3-tf@xxxxxxxx] On Behalf Of Jouni Korhonen
Sent: Thursday, June 25, 2015 4:03 PM
To: STDS-1904-3-TF@xxxxxxxxxxxxxxxxx
Subject: Action Points: errors..
Folks,
Another AP I got relates to kicking off the discussion on errors originating from PHY/SFP.
We should have an agreement how to deal with those. My take is that we do nothing specific except discard the packet _if_ we manage to detect the error. I don't really see how we could do otherwise. We don't have enough information to do more clever recovery/heuristics.
- Jouni
--
Jouni Korhonen, CTO Office, Networking, Broadcom Corporation
O: +1-408-922-8135, M: +1-408-391-7160