similar to: HTB/SFQ dequeueing in pairs

I posted earlier when I noticed that htb was releasing packets in pairs, even though my burst/quantums were 1 pkt. To fix I set HTB_HYSTERESIS 0 in net/sched/sch_htb.c . This gives a noticable gain in upstream worst case latency, for me with 256kbit/s up I used to see +90 sometimes, now it''s +45. For the many who have 128 up it should limit them to +90 rather than +180. Andy.

hi all! i have a dsl connection with 1280 kbps for downstream and 256 kbps for upstream, and i want to manage the bandwidth to give high priority to voip traffic and low priority to p2p traffic. i found the script jdg-qos. i readed on this forum (i have a dsl-g604t router with MCMCC firmware) http://www.dslreports.com/forum/remark,16250220 that the two parameters of the jdg-qos script (DWIFLIMIT

> > SFQ is very useful as a leaf qdisc. But by default, its internal queue > > length is 128 which is too much for small classes or even for > > not-so-fast links. Changing SFQ_DEPTH in net/sched/ sch_sfq.c to about > > 10-20 results in flows responding much faster to bandwidth changes. I''m not sure I understand what problem is being described, but I suspect

I read the sched/qdiscs code from kernel source ... and I have some questions : When the .enqueue, .dequeue, .drop, .requeue functions are called ? What is the event that triggers them and how often this event apears ( per second ? ) ? When a qdisc is dequeued ( when it''s limit is reached ) ? Thanks _______________________________________________ LARTC mailing list /

Hi there! Some questions I couldn''t find an answer for: IPtables: - Is it possible to filter those ACK-packets (to eleminate problems with ADSL-connections) with IPtables? It wasn''t possible with IPchains, so u32 had to be used. Now there is this nice little --tcp-flags option. But I just don''t know if this is all I need. The u32 was checking for packetsize too. So if

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

Anyone notices that using sfq qdisc adds latency compared to pfifo? With "sfq perturb 10" ping latency is around 100-120ms, while with "pfifo limit 3" drops to ~10-30ms (qdiscs belong to htb class). I''m missing something or is this expected? { $TC_CLASS parent 1:1 classid 1:20 htb prio 0 rate 900kbit ceil 1000kbit burst 7k $TC_QDISC parent 1:20 handle 200: {pfifo

Hello, I have one Q. What is better when using as leaf in one leaf with several hosts (like subnet) to splice traffic equaly to user number? Like 2 users = 256/2, 3 = 256/3 and so on. WRR was pretty good for this job, but it''s only for 2.4.21 kernels and mine''s 2.4.22. So what is better: SFQ or TBF? -- Artūras Šlajus _______________________________________________

Can I use the same SFQ queue dicipline for all the classe in a CBQ or HBT system?

Hello, Why linux users use SFQ as leaf queueing discipline instead of RED and other? -- Best Regards, S.Mehdi Sheikhalishahi, Bye.

> From: Martin Devera <devik@cdi.cz> > Subject: [LARTC] (E)SFQ suggestion > Hi, > just simple note. Maybe it is already in progress :) > > There are attempts to replace hashing routine in SFQ to > consider IPs or ports. > What about to use HRR - roundrobin around bunch of IP > adresses and then smaller WRR for ports per IP ? > It would solve both

Can I attach a SFQ qdisc after a TBF qdisc?

Hello all, I have a few question regarding PRIO and what it is. Is it used to prioritize what classes get what? I read the how to but it isn''t exactly clear. Also about SFQ. Does this disciplines keep traffic within a queue fair? for example if I classify all http connections to 1:10 and I have packets in the queue and another person is also sending packets to the queue.

Please see below Jon Flechsenhaar Boeing WNW Team Network Services (714)-762-1231 202-E7 -----Original Message----- From: Flechsenhaar, Jon J Sent: Wednesday, September 27, 2006 9:35 AM To: lartc@mailman.ds9a.nl Subject: [LARTC] 2.6.14 - HTB/SFQ QoS broken? Jody: I don''t know if you answer basic HTB questions but I''l try anyway. I''m implementing AF and EF with a

http://ds9a.nl/lartc/manpages I finished some more manpages, and improved others. New are tc-tbf.8, tc-sfq.8, tc-prio.8 and tc-red.8. Please check & use them. http://ds9a.nl/lartc/manpages -- http://www.PowerDNS.com Versatile DNS Software & Services Trilab The Technology People Netherlabs BV / Rent-a-Nerd.nl -

<P>&nbsp;</P> <P>Hi All,</P> <P>Is there a way in linux to monitor the performance of an SFQ in terms of the WFI (worst case fair index), Max Min etc?</P> <P>Any help, or guidance appreciated,</P> <P>Barry.</P> _______________________________________________ LARTC mailing list / LARTC@mailman.ds9a.nl

Hi, I have a 3Mbit (up,down) connection going through a Linux box (Debian 600mhz, 500mb ram) using NAT to approx 125 users. Presently I am shaping by marking packets by their port numbers. I''m prioritizing 22, 23, 25, 80, 81, 110, 443, 500, 3389, 1214, 6881:6889, etc, into their appropriate classes depending on weather there getting more or less bandwidth. This has worked pretty

Dear all, I''m reading codes in sch_sqf.c in kernel 2.4 of Linux. I find I messed up with the concept of slot, bucket and hash tables. Could anyone explain the data stucture of the hash tables a little to me. Thanks very much. Best, Franklin BTW: I can not understand why the number of entries of dep[SFQ_DEPTH*] should be twice:( _______________________________________________ LARTC

The limit parameter for SFQ qdiscs isn''t listed in the howto. Based on a mail from this list from 4 may 2002 ("SFQ queue lengths - generalization"), I''d guess it limits the number of packets/bytes in in the queue, but wether it does so by number of bytes, packets, or time spent in the queue I don''t know. Perhaps someone in the know could add a line to the