| To: | Ronghua Zhang <rz5b@xxxxxxxxxxxxxxx> |
|---|---|
| Subject: | Re: [PATCH] proportional share accept() |
| From: | "David S. Miller" <davem@xxxxxxxxxx> |
| Date: | Sun, 29 Feb 2004 22:05:13 -0800 |
| Cc: | kashyapv@xxxxxxxxxx, shemminger@xxxxxxxx, netdev@xxxxxxxxxxx |
| In-reply-to: | <Pine.GSO.4.51.0402261659350.24561@xxxxxxxxxxxxxxxxxxxxx> |
| References: | <Pine.LNX.4.44.0402251119060.3691-100000@xxxxxxxxxxxxxxxxxxxxxxxxxxx> <Pine.GSO.4.51.0402261659350.24561@xxxxxxxxxxxxxxxxxxxxx> |
| Sender: | netdev-bounce@xxxxxxxxxxx |
On Thu, 26 Feb 2004 17:08:23 -0500 (EST) Ronghua Zhang <rz5b@xxxxxxxxxxxxxxx> wrote: > www.cs.virginia.edu/~rz5b/research/kernel-qos.htm I looked at this, it's basically netfilter TCP port rewriting which knows about per-socket quotas and limits. You could write this as a 10 line netfilter module, with zero modifications to any of the core net/ipv4 TCP code at all. And that's how I'd like to see something like this done. Otherwise it looks like a nice way of doing this. |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: [PATCH] 2.6.3 fix vlan-encapsulated fragmented IP traffic, David S. Miller |
|---|---|
| Next by Date: | Re: Submission #3 for S2io 10GbE driver, Jeff Garzik |
| Previous by Thread: | Re: [PATCH] proportional share accept(), David S. Miller |
| Next by Thread: | Re: [PATCH] proportional share accept(), Stephen Hemminger |
| Indexes: | [Date] [Thread] [Top] [All Lists] |