lkml.org 
[lkml]   [1999]   [Dec]   [8]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
SubjectRe: Again: EQL - someone's use this thing yet?
Date
Hello!

> Excellent. So we can shoot eql.c for 2.4 ? (please...)

eql has real applications not covered by teql: f.e. balancing between tunnels.
teql requires flow controlled interfaces and balances real link
capacities, rather than simply sends with apriory rates.

With all the drawbacks of apriory eql scheme for physical interfaces,
it is still useful for software interfaces and interfaces with
huge internal queues. Well, and eql is not very trivial,
it would be sad to lose this code.

John Carol Langford <jcl@gs176.sp.cs.cmu.edu> did new eql,
based on teql skeleton with different hard_start_xmit() more than year ago,
but unfortunately, he disappeared from horizont. Seems, the last version
was pretty clean, I could try to search him to query status.


> and get rid of all the crufty master/slave stuff it has

Well, it was hidden completely inside eql.c. I deleted
some strange fields from struct net_device ("pkt_queue" and "slave")
in softnet patch, but it is because current kernel does not reference
them really.

Alexey

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2005-03-22 13:55    [W:0.105 / U:1.220 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site