similar to: more manpages: TBF, RED, PRIO, SFQ

Dear list members, all 707 of you, We are back. It has taken *far* too long to get everything together again. At first we were delayed by incredible incompetence over at our vendor, who managed to ship a broken server twice. And then I was very busy, and did not manage to make time for reinstalling all services on the new server. The new server, http://outpost.powerdns.com, is very capable. It

I presently use TBF with this syntax: tc qdisc add dev eth0 parent 1:100 tbf buffer=15000/8 LIMIT=30000 MTU=1500 parent class is a cbq with rate=128Kbit when I want to add PEAK, I get always RTNETLINK error: Invalid argument. Maybe be I don''t understand this parameter. What I know about it, it''s that it can control short-term burst traffic, and it''s what I need to do.

New chapter by Esteve Camps <esteve@hades.udg.es> on ''DSMARK'' for Differential Services: http://ds9a.nl/2.4Routing/HOWTO//cvs/2.4routing/output/2.4routing-9.html#ss9.6 And three obscure settings /proc files that are now documented, thanks to Jorge Novo <jnovo@educanet.net>: /proc/sys/net/ipv4/icmp_ignore_bogus_error_responses,

Can I attach a SFQ qdisc after a TBF qdisc?

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 _______________________________________________

Hello mailing list, i stand bevor a mystery and cannot explain it J. I want to do shaping and prioritization and I have done these following configurations and simulations. I can´t explain, that the combination of PRIO and TBF is much better than the HTB (with the prio parameter) alone or in combination with the SFQ. Here are my example configurations: 2 Traffic Classes http (80 = 0x50) and

Hello, while investigating a report from Jan-Piet Mens (resulting in http://wiki.powerdns.com/trac/changeset/3109), we discovered that NSD (both 3.2.15 and 4.0.0b4) compresses labels in RP content. As far as I can see, this is not allowed by RFC3597 section 4 paragraph 1/2. PowerDNS Recursor, like Unbound and BIND, now deals with this as 3597 section 4 paragraph 4 says we SHOULD. Nevertheless,

Dear friends, thanks for the last advices about TBF. After reading the tbf.pdf document I got a better insight of the problems I had trying to limit the bandwith on my testbed with a high resolution. The question I have now is: Would I get an immediatly better resolution result if I change the #define HZ to 1000 for my Linux box? I have a Pentium Celeron 700 MHz, and I would like to see the tbf

The manual says (about prio): > Because it doesn''t actually shape, the same warning as for SFQ holds: > either use it only if your physical link is really full or wrap it > inside a classful qdisc that does shape. The latter holds for almost all > cable modems and DSL devices. I want to wrap prio inside of tbf. Here''s why: I have a server on a DSL line, which has

I thought I had this all worked out, but it seems not. The following tc configuration: tc qdisc del dev ppp0 root 2> /dev/null > /dev/null tc qdisc add dev ppp0 root handle 1: tbf rate 120kbit burst 1200 limit 1 tc qdisc add dev ppp0 parent 1:1 handle 2: prio bands 3 tc qdisc add dev ppp0 parent 2:1 handle 10: sfq perturb 20 tc qdisc add dev ppp0 parent 2:2 handle 20: sfq perturb 20 tc

Hi all, Does anybody know a package to control the bandwidth using "TCP Congestion Control" method? Best Regards Hoomaan Naimi Afranet Network Administrator

Second test after big upgrade.. -- http://www.PowerDNS.com Open source, database driven DNS Software http://netherlabs.nl Open and Closed source services

Hi! Bored by previous lhype success, I tried to boot a debootstrapped debian over nfsroot, and lo, this almost works! Commandline: # drivers/lhype/lhype_add 256m 0 ./vmlinux --tunnet=192.168.1.20 root=/dev/root nfsroot=/home/ahu/lhype-root ip=192.168.1.21:192.168.1.20:192.168.1.20 This with lhype.patch current as of this message and 2.9.20-rc4. The boot process stops after: Starting periodic

Hi! Bored by previous lhype success, I tried to boot a debootstrapped debian over nfsroot, and lo, this almost works! Commandline: # drivers/lhype/lhype_add 256m 0 ./vmlinux --tunnet=192.168.1.20 root=/dev/root nfsroot=/home/ahu/lhype-root ip=192.168.1.21:192.168.1.20:192.168.1.20 This with lhype.patch current as of this message and 2.9.20-rc4. The boot process stops after: Starting periodic

I''m trying to fill a token bucket with enough tokens to burst several gigs of data. However, it doesn''t seem to get any higher than ~3.9GB: >tc qdisc add dev eth0 root tbf rate 1440kbit latency 50ms \ burst 16000000000 >tc qdisc show dev eth0 qdisc tbf 800b: rate 1440Kbit burst 3908420240b lat 2197.8s A smaller attempt of ~1.6 gigs works just fine: >tc qdisc

Hi i have found a problem related with tbf and the latency that the tbf calculates.. I have used the following parameters for burst and limit burst 100Kbit limit 500Kbit lat81.8ms burst 6Kbit limit 6Kbit lat 0us burst 200Kbit limit 100Kbit lat 4294.9s As u can see in the 3rd column the latency for 100Kbit burst and 500Kbit limit is 81.8ms but for 200Kbit and limit 100Kbit is 4294.9s!!! How

Hi Everyone, This is a simple question but I don''t understand why the below tbf is not working as expected by throttling traffic to 5kbps If I throttle a PC''s traffic using the below when traffic exceeds 5kbps packets start getting dropped (as they should) but all traffic gets dropped. not just the bit over 5kbps. TC="tc add dev ppp0" $TC parent 8001:2 handle 2:

I am using tbf to do rate limitation. i set the rate, burst and latency parameters for tbf. but when i start passing data i notice that there is an initial burst and then the rate goes down to the configured level. is this because tbf starts with a full bucket? thanks. __________________________________________________ Do You Yahoo!? Tired of spam? Yahoo! Mail has the best spam protection

Hi all! I just started to experiment with bandwidth management using tbf. I have the folowing problems with token understanding: 1) What unit is token? Is "1 token = 1 byte" ? If this is so, then with rate=0.5mbit and HZ=100 the bucket gets filled with 0,64kb (655 tokens) every 10ms? 2) How much tokens are used for one packet (1500)? 3) And token unrelated question. Does

Hi All, I read the advanced networking howto and find a useful way to shape my adsl link. is says: "tc qdisc add dev ppp0 root tbf rate 220kbit latency 50ms burst 1500 [...] Change 220kbit to your uplinks *actual* speed, minus a few percent. If you have a really fast modem, raise ''burst'' a bit. " My adsl''s upload brandwidth is about 120 kbits/sec,