* Re: [LARTC] SFQ + RED
2001-11-27 16:53 [LARTC] SFQ + RED Michael T. Babcock
@ 2001-12-03 14:10 ` bert hubert
2001-12-03 21:05 ` Michael T. Babcock
` (8 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: bert hubert @ 2001-12-03 14:10 UTC (permalink / raw)
To: lartc
On Tue, Nov 27, 2001 at 11:53:10AM -0500, Michael T. Babcock wrote:
> I've asked this before, but does anyone feel technically inclined
> enough to try swapping in a RED queue for the per-bucket queuing done
> by SFQ? If SFQ builds a series of 'sessions' to be given fair use of
> available bandwidth, using RED to slow down those that are building up
> too fast would smooth things out.
I have no clue how you would configure that - is it even possible to
'concat' classless queues?
Regards,
bert
--
http://www.PowerDNS.com Versatile DNS Software & Services
Trilab The Technology People
Netherlabs BV / Rent-a-Nerd.nl - Nerd Available -
'SYN! .. SYN|ACK! .. ACK!' - the mating call of the internet
_______________________________________________
LARTC mailing list / LARTC@mailman.ds9a.nl
http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://ds9a.nl/2.4Routing/
^ permalink raw reply [flat|nested] 11+ messages in thread* Re: [LARTC] SFQ + RED
2001-11-27 16:53 [LARTC] SFQ + RED Michael T. Babcock
2001-12-03 14:10 ` bert hubert
@ 2001-12-03 21:05 ` Michael T. Babcock
2001-12-03 23:32 ` Don Cohen
` (7 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Michael T. Babcock @ 2001-12-03 21:05 UTC (permalink / raw)
To: lartc
> I have no clue how you would configure that - is it even possible to
> 'concat' classless queues?
Not in the present state of things, I don't believe so, no.
I'd like to be able to do that though ...
--
Michael
_______________________________________________
LARTC mailing list / LARTC@mailman.ds9a.nl
http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://ds9a.nl/2.4Routing/
^ permalink raw reply [flat|nested] 11+ messages in thread* Re: [LARTC] SFQ + RED
2001-11-27 16:53 [LARTC] SFQ + RED Michael T. Babcock
2001-12-03 14:10 ` bert hubert
2001-12-03 21:05 ` Michael T. Babcock
@ 2001-12-03 23:32 ` Don Cohen
2001-12-04 7:58 ` Martin Devera
` (6 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Don Cohen @ 2001-12-03 23:32 UTC (permalink / raw)
To: lartc
> On Tue, Nov 27, 2001 at 11:53:10AM -0500, Michael T. Babcock wrote:
> > I've asked this before, but does anyone feel technically inclined
> > enough to try swapping in a RED queue for the per-bucket queuing done
> > by SFQ? If SFQ builds a series of 'sessions' to be given fair use of
> > available bandwidth, using RED to slow down those that are building up
> > too fast would smooth things out.
I don't think this is necessary. As it is now, when you enqueue a
packet in a full SFQ queue it drops from the tail of the longest
subqueue. If you have substantial competition for the link then
your subqueue won't be allowed to grow very long to begin with.
The random variation in demand from other flows will have the effect
of jittering the maximum length of your subqueue, which is pretty
similar to what you experience with RED, isn't it?
_______________________________________________
LARTC mailing list / LARTC@mailman.ds9a.nl
http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://ds9a.nl/2.4Routing/
^ permalink raw reply [flat|nested] 11+ messages in thread* Re: [LARTC] SFQ + RED
2001-11-27 16:53 [LARTC] SFQ + RED Michael T. Babcock
` (2 preceding siblings ...)
2001-12-03 23:32 ` Don Cohen
@ 2001-12-04 7:58 ` Martin Devera
2001-12-04 18:27 ` Michael T. Babcock
` (5 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Martin Devera @ 2001-12-04 7:58 UTC (permalink / raw)
To: lartc
IMHO the RED would be useful here. SFQ limits total packet count
to 128 packets. So that one flow can simply fill whole SFQ leaving
small space for other flows.
I'm able to simulate it using one host generating huge UDP flow.
All others flow goes away :(
devik
On Mon, 3 Dec 2001, Don Cohen wrote:
>
> > On Tue, Nov 27, 2001 at 11:53:10AM -0500, Michael T. Babcock wrote:
> > > I've asked this before, but does anyone feel technically inclined
> > > enough to try swapping in a RED queue for the per-bucket queuing done
> > > by SFQ? If SFQ builds a series of 'sessions' to be given fair use of
> > > available bandwidth, using RED to slow down those that are building up
> > > too fast would smooth things out.
>
> I don't think this is necessary. As it is now, when you enqueue a
> packet in a full SFQ queue it drops from the tail of the longest
> subqueue. If you have substantial competition for the link then
> your subqueue won't be allowed to grow very long to begin with.
> The random variation in demand from other flows will have the effect
> of jittering the maximum length of your subqueue, which is pretty
> similar to what you experience with RED, isn't it?
>
> _______________________________________________
> LARTC mailing list / LARTC@mailman.ds9a.nl
> http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://ds9a.nl/2.4Routing/
>
>
_______________________________________________
LARTC mailing list / LARTC@mailman.ds9a.nl
http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://ds9a.nl/2.4Routing/
^ permalink raw reply [flat|nested] 11+ messages in thread* Re: [LARTC] SFQ + RED
2001-11-27 16:53 [LARTC] SFQ + RED Michael T. Babcock
` (3 preceding siblings ...)
2001-12-04 7:58 ` Martin Devera
@ 2001-12-04 18:27 ` Michael T. Babcock
2001-12-06 16:23 ` bert hubert
` (4 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Michael T. Babcock @ 2001-12-04 18:27 UTC (permalink / raw)
To: lartc
> The random variation in demand from other flows will have the effect
> of jittering the maximum length of your subqueue, which is pretty
> similar to what you experience with RED, isn't it?
Not quite, no. The dropping of packets is based on actual calculations in
RED that aren't available in SFQ. SFQ drops _all_ the packets off the end
and doesn't start doing so before congestion happens -- RED is designed to
drop packets before getting overly congested so that the stream speeds stay
steady and don't try to climb above what's available.
--
Michael T. Babcock
_______________________________________________
LARTC mailing list / LARTC@mailman.ds9a.nl
http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://ds9a.nl/2.4Routing/
^ permalink raw reply [flat|nested] 11+ messages in thread* Re: [LARTC] SFQ + RED
2001-11-27 16:53 [LARTC] SFQ + RED Michael T. Babcock
` (4 preceding siblings ...)
2001-12-04 18:27 ` Michael T. Babcock
@ 2001-12-06 16:23 ` bert hubert
2001-12-06 16:37 ` Michael T. Babcock
` (3 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: bert hubert @ 2001-12-06 16:23 UTC (permalink / raw)
To: lartc
On Tue, Dec 04, 2001 at 01:27:02PM -0500, Michael T. Babcock wrote:
> > The random variation in demand from other flows will have the effect
> > of jittering the maximum length of your subqueue, which is pretty
> > similar to what you experience with RED, isn't it?
>
> Not quite, no. The dropping of packets is based on actual calculations in
> RED that aren't available in SFQ. SFQ drops _all_ the packets off the end
> and doesn't start doing so before congestion happens -- RED is designed to
> drop packets before getting overly congested so that the stream speeds stay
> steady and don't try to climb above what's available.
GRED might be what you want, if you can get anybody to explain you how it
works. I don't get it yet.
Regards,
bert
--
http://www.PowerDNS.com Versatile DNS Software & Services
Trilab The Technology People
Netherlabs BV / Rent-a-Nerd.nl - Nerd Available -
'SYN! .. SYN|ACK! .. ACK!' - the mating call of the internet
_______________________________________________
LARTC mailing list / LARTC@mailman.ds9a.nl
http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://ds9a.nl/2.4Routing/
^ permalink raw reply [flat|nested] 11+ messages in thread* Re: [LARTC] SFQ + RED
2001-11-27 16:53 [LARTC] SFQ + RED Michael T. Babcock
` (5 preceding siblings ...)
2001-12-06 16:23 ` bert hubert
@ 2001-12-06 16:37 ` Michael T. Babcock
2001-12-06 18:12 ` bert hubert
` (2 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Michael T. Babcock @ 2001-12-06 16:37 UTC (permalink / raw)
To: lartc
On Thu, Dec 06, 2001 at 05:23:50PM +0100, bert hubert wrote:
> GRED might be what you want, if you can get anybody to explain you how it
> works. I don't get it yet.
I'm sure I can find documentation on how GRED is _supposed_ to work, but how
it is configured in the Linux implementation would be a different issue
entirely ;-).
--
Michael T. Babcock
CTO, FibreSpeed Ltd. (Hosting, Security, Consultation, Database, etc)
http://www.fibrespeed.net/~mbabcock/
_______________________________________________
LARTC mailing list / LARTC@mailman.ds9a.nl
http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://ds9a.nl/2.4Routing/
^ permalink raw reply [flat|nested] 11+ messages in thread* Re: [LARTC] SFQ + RED
2001-11-27 16:53 [LARTC] SFQ + RED Michael T. Babcock
` (6 preceding siblings ...)
2001-12-06 16:37 ` Michael T. Babcock
@ 2001-12-06 18:12 ` bert hubert
2002-06-06 9:21 ` Jan Coppens
2002-06-06 11:38 ` Alexey Talikov
9 siblings, 0 replies; 11+ messages in thread
From: bert hubert @ 2001-12-06 18:12 UTC (permalink / raw)
To: lartc
On Thu, Dec 06, 2001 at 11:37:37AM -0500, Michael T. Babcock wrote:
> On Thu, Dec 06, 2001 at 05:23:50PM +0100, bert hubert wrote:
> > GRED might be what you want, if you can get anybody to explain you how it
> > works. I don't get it yet.
>
> I'm sure I can find documentation on how GRED is _supposed_ to work, but how
> it is configured in the Linux implementation would be a different issue
> entirely ;-).
GRED was invented for Linux by Jamal Hadi Salim - there is only one GRED.
Regards,
bert
--
http://www.PowerDNS.com Versatile DNS Software & Services
Trilab The Technology People
Netherlabs BV / Rent-a-Nerd.nl - Nerd Available -
'SYN! .. SYN|ACK! .. ACK!' - the mating call of the internet
_______________________________________________
LARTC mailing list / LARTC@mailman.ds9a.nl
http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://ds9a.nl/2.4Routing/
^ permalink raw reply [flat|nested] 11+ messages in thread* [LARTC] SFQ + RED
2001-11-27 16:53 [LARTC] SFQ + RED Michael T. Babcock
` (7 preceding siblings ...)
2001-12-06 18:12 ` bert hubert
@ 2002-06-06 9:21 ` Jan Coppens
2002-06-06 11:38 ` Alexey Talikov
9 siblings, 0 replies; 11+ messages in thread
From: Jan Coppens @ 2002-06-06 9:21 UTC (permalink / raw)
To: lartc
Hi all,
Is there any implemented qdisc that combines the benefits of a SFQ with
those of a RED queue. Something like a FRED, CBT or DWRED?
thx,
Jan
_______________________________________________
LARTC mailing list / LARTC@mailman.ds9a.nl
http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://lartc.org/
^ permalink raw reply [flat|nested] 11+ messages in thread* Re: [LARTC] SFQ + RED
2001-11-27 16:53 [LARTC] SFQ + RED Michael T. Babcock
` (8 preceding siblings ...)
2002-06-06 9:21 ` Jan Coppens
@ 2002-06-06 11:38 ` Alexey Talikov
9 siblings, 0 replies; 11+ messages in thread
From: Alexey Talikov @ 2002-06-06 11:38 UTC (permalink / raw)
To: lartc
Add RED on IMQ see http://luxik.cdi.cz/~patrick/imq/
and SFQ on network device or vice versa
send all incoming packets to imq
modprobe imq mumdevs=1
iptables -t mangle -A PREROUTING -i $IN_DEV -j IMQ --todev 0
ip link set imq0 up
06.06.2002 14:21:55, "Jan Coppens" <Jan.Coppens@intec.rug.ac.be> wrote:
>Hi all,
>
>Is there any implemented qdisc that combines the benefits of a SFQ with
>those of a RED queue. Something like a FRED, CBT or DWRED?
>
>thx,
>Jan
>
>_______________________________________________
>LARTC mailing list / LARTC@mailman.ds9a.nl
>http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://lartc.org/
>
-----------------------------------
mailto:alexey_talikov@texlab.com.uz
BR
Alexey Talikov
FORTEK
-----------------------------------
_______________________________________________
LARTC mailing list / LARTC@mailman.ds9a.nl
http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://lartc.org/
^ permalink raw reply [flat|nested] 11+ messages in thread