* [LARTC] How to see the sfq hash table ?
@ 2007-08-16 13:29 David Boreham
2007-08-22 23:24 ` Andy Furniss
2007-08-23 4:15 ` Corey Hickey
0 siblings, 2 replies; 3+ messages in thread
From: David Boreham @ 2007-08-16 13:29 UTC (permalink / raw)
To: lartc
I'm grappling with a problem that looks like sfq is not working
(packets don't get fairly queued, they appear to be always
sent FIFO). My configuration appears to be correct.
The machine is running quite an old kernel and if I could
convince myself that the sfq code it has is just broken, I'd
spend the time to upgrade it. Is there any way to inspect or
dump the sfq hash table on a running machine ?
Thanks.
_______________________________________________
LARTC mailing list
LARTC@mailman.ds9a.nl
http://mailman.ds9a.nl/cgi-bin/mailman/listinfo/lartc
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [LARTC] How to see the sfq hash table ?
2007-08-16 13:29 [LARTC] How to see the sfq hash table ? David Boreham
@ 2007-08-22 23:24 ` Andy Furniss
2007-08-23 4:15 ` Corey Hickey
1 sibling, 0 replies; 3+ messages in thread
From: Andy Furniss @ 2007-08-22 23:24 UTC (permalink / raw)
To: lartc
David Boreham wrote:
> I'm grappling with a problem that looks like sfq is not working
> (packets don't get fairly queued, they appear to be always
> sent FIFO). My configuration appears to be correct.
> The machine is running quite an old kernel and if I could
> convince myself that the sfq code it has is just broken, I'd
> spend the time to upgrade it. Is there any way to inspect or
> dump the sfq hash table on a running machine ?
I don't think so - I would use tcpdump, if you use perturb don't set it
too low as it causes packet reordering.
There is currently work going on to merge sfq/esfq and the hash will be
jhash so should be better than the current one.
Andy.
_______________________________________________
LARTC mailing list
LARTC@mailman.ds9a.nl
http://mailman.ds9a.nl/cgi-bin/mailman/listinfo/lartc
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [LARTC] How to see the sfq hash table ?
2007-08-16 13:29 [LARTC] How to see the sfq hash table ? David Boreham
2007-08-22 23:24 ` Andy Furniss
@ 2007-08-23 4:15 ` Corey Hickey
1 sibling, 0 replies; 3+ messages in thread
From: Corey Hickey @ 2007-08-23 4:15 UTC (permalink / raw)
To: lartc
Andy Furniss wrote:
> David Boreham wrote:
>> I'm grappling with a problem that looks like sfq is not working
>> (packets don't get fairly queued, they appear to be always
>> sent FIFO). My configuration appears to be correct.
>> The machine is running quite an old kernel and if I could
>> convince myself that the sfq code it has is just broken, I'd
>> spend the time to upgrade it. Is there any way to inspect or
>> dump the sfq hash table on a running machine ?
>
> I don't think so
I don't know of any way either, though I will probably write one
eventually for diagnostic use.
> - I would use tcpdump, if you use perturb don't set it
> too low as it causes packet reordering.
A couple other notes:
1. SFQ won't do much unless it's attached to a rate limiting qdisc such
as HTB, with a specified rate less than that of your Internet connection.
2. SFQ doesn't currently handle more than 128 concurrent flows (TCP
connections, etc.), and I would expect the fairness to degrade sooner
than that. I have been working on patches to address this, among other
things.
> There is currently work going on to merge sfq/esfq and the hash will be
> jhash so should be better than the current one.
My own role in that is taking forever, but I am indeed still working on
it...
-Corey
_______________________________________________
LARTC mailing list
LARTC@mailman.ds9a.nl
http://mailman.ds9a.nl/cgi-bin/mailman/listinfo/lartc
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2007-08-23 4:15 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2007-08-16 13:29 [LARTC] How to see the sfq hash table ? David Boreham
2007-08-22 23:24 ` Andy Furniss
2007-08-23 4:15 ` Corey Hickey
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.