Feature #313
Bug #312: QoS/AQM holy grail much closer to achieved
Per-packet RED in linux would be useful
| Status: | New | Start date: | 11/29/2011 | |
|---|---|---|---|---|
| Priority: | Normal | Due date: | ||
| Assignee: |  Dave Täht |
% Done: | 0% |
|
| Category: | Networking | Spent time: | - | |
| Target version: | Cerowrt-Someday |
Description
Many simulations that I've read tend to use a per packet, rather than per byte, form of RED.
This makes enormous sense in that a version of RED that does it only on bytes barely budges when faced with pure ack packets rather than mixed workloads. And certainly doesn't account very well for asymmetric
bandwidths.
regrettably, RED in linux is bytes, with an average packet size parameter. Twiddle that number as I may and I don't get particularly good results. So writing/finding a version of red that comes closer to the ns2 model may help.