similar to: CBQ throughput and efficiency question

Hi all I am conducting the experiments comparing IP router forwarding delay and MPLS LSR forwarding delay, it is obvious in theory MPLS in Core should be faster than IP, but for small netork (only have several core routers), result show it is not, this is why I want emulate a large IP routing table in one core router. can I do it and how ? right now I use static routing table (by using command :

I need to shape traffic from some IP on one LAN, but I''m in trouble. There is a linux 2.4.26 connected to the Internet (eth0) / LAN(eth1) doing NAT. I''m using VLANs in the LAN Interface, that is connected to a 3Com SuperStack II in a 802.1Q tagged port. I want to create a class that will limit the traffic at 384Kbit/s. I want to create two leaf classes that limit the traffic at

Hi. I want to shape traffic from some IPs in my lan, but I''m w/ trouble. I have a linux box connected to the Internet. In the other side of this box is my LAN. I want to create the following scenario: My root qdisc is attached to a 100Mbit/s NIC I want to create a class attached to this qdisc that will limit the traffic at 384Kbit/s. I want to create two leaf classes that limits

Hi i have configured my server with cbq and gred. The problem is that the cbq doesnt drop packets. The cbq is configured at a rate of 500Kbit "qdisc cbq 4: rate 500000bit (bounded,isolated) prio no-transmit Sent 100103048 bytes 73933 pkts (dropped 0, overlimits 0) borrowed 0 overactions 0 avgidle 24000 undertime 0 " The traffic that being generated is more than 5Mbit with the

Hey there everyone, I appreciated everyone''s help so much in the last few posts I decided to post some more! :) We implemented our bandwidth management machine on the network last week and everything looked great. After looking at it today, anything past the machine is losing major packets and the latency is high. I''m using RedHat 9.0 on a Pentium 4 2.8ghz with 512mb of ram.

If I create a cbq qdisc as a leaf of a cbq class, the bandwith rate is the same of the root cbq qdisc or the rate of the cbq class? Does exist the parameter rate on the "tc qdisc add" for cbq command? tc qdisc add dev eth0 root handle 1:0 cbq bandwidth 10mbit avpkt 1000 cell 8 tc class add dev eth0 parent 1:0 classid 1:3 cbq bandwidth 10mbit rate 50kbit allot 1514 cell 8

When a Snom 200 (v2.1l) calls a C7960 (v4.4), both using g711u as default, the conversation is extremely noisy from the Snom to the Cisco, but clear in the reverse direction. Using a sniffer, I see packets from the Snom to the Cisco of 87 bytes and Cisco to Snom of 214 bytes. Asterisk is CVS from Saturday. The communications between the two was working fine on Saturday, however something has

Hello all, this is my first post here. Sorry for my english. Gentoo LAN router, 2.4.26-hardened-r2 There are 2 WAN links, one LAN link. I am doing some iptables/routing/tc magic in my scripts. What''s interesting is marking packets traveling from all IP''s in LAN. Interesting commands are: ------------- for ip in `seq 50`; do $IPTABLES -t mangle -A FORWARD -o eth2 -d

Hello everyone, I''m a newbie experimenting with CBQ shaping and am facing a few problems. Can any of you please help? TEST SETUP: +---------------+ +----------------+ | 10.0.0.103 |----------->| 10.0.0.102 | +---------------+ +----------------+ 10.0.0.103: Linux, 100Mbit/s NIC 10.0.0.102: Windows, 100Mbit/s NIC, iperf tcp server (ports 2000 and 2001) WHAT I

While I''m thinking about that review of howto changes, here are a few other responses about things I don''t believe. I''ll be interested in more info if anyone has any. ==== [from new doc] Besides being classful, CBQ is also a shaper and it is in that aspect that it really doesn''t work very well. It should work like this. I''ve not noticed that it

Hi Stef and Alexey I have read some documents about CBQ algorithm from http://www.icir.org/floyd/cbq.html but still have some question about CBQ in Linux . 1. First estimator can estimate how much bandwidth already USED per class. one estimating algorithm is EWMA (exponential weighted moving average), how about Linux implemenatation about estimator? also do you have link for this algorithm? I

hey guys i am regulating the traffic to & fro by my network through a linux gateway , its behaving strange. i regulated Downlink to 2Mbps & UPlLINK to 500Kbps. both perform well when those are done independent i.e. one at a time but when i do both from a client system ..the downlink however continues at 2mbps but the uplink falls down to 100kbps? is something wrong with my script or

Hi All , My first message and I have a little problem with my FC6 box trying to block emule traffic using layer7 . Here my network : Internet --------- ADSL Router ------------------- FC6 Box -------------------- Emule Box external ADSL : Dynamic Internal ADSL : 192.168.254.1 external FC6 : 192.168.254.3 internal FC6 : 192.168.253.1 Emule Box : 192.168.253.3 I guess that everything

Hi,All I am using iproute2 to manage bandwith for ADSL router.High,medium,low priority are needed for different protocol port on the ADSL's upstream side,as following: LAN --- |ADSL Router|------WAN When there aren't traffic on the specific priority, its bandwidth should be borrowed by other priorities.But it doesn't work.Here is my script: /usr/sbin/tc qdisc del dev nas0 root

hi all At last i got sucess !.. but am confused y it didnt work earlier..the difference today was that i reinstalled RH7.2 & complied kernel 2.4.16(not 17).. rest was same..... & the bandwidth too is under control!.. is it normal for to get more than said bandwidth--i mean i restricted a network with 8Kbit(with same script as below) but still was able to get a download(ftp) of

Hello all, I''ve got a couple redundant (Spanning Tree Protocol) boxes running FC1 minimal install + bridge-utils and they are working great for QoS + ntop monitoring. I''m wondering if I should handle the VoIP traffic a little differently. I don''t mind letting VoIP and Video lend out traffic when it isn''t being used, so that''s why I gave them such

Hello! I have a problem here. I set up a Linux 2.4 machine to do bandwidth limiting for some of our customers. Current setup is something like this: |--------| backbone |-------| |---------| |Internet|225.1-----------225.10|limiter|228.1----228.10|cust. gw2| |--------| | eth0 |-------| eth1 |---------| | 225.20

I forward this to the list also, I attached SFQ leaf to parent class, and add QUANTUM value and PERTURB value. It worked! i tried 20hosts borrowing from the same parent, no problem. Each host get its own allocated bandwidth. Btw about last email sent to this list asking about QoS, i ve read LARTC document but i cant find the solution matches my case. Need help.. I have 100Kbit allocated to

OK, finally I have made cbq run ! now I would like to know if it is posible to limit a range of IP to a speed. something like this : from 192.168.1.1 to 192.168.1.21 limit to 128K I don''t whant to limit each IP to 128K, what I would like to do is limit all 20 IP to have a max of 128K. Is it posible?

all: I"m just trying to create a simple rsvp session to familiarize myself with the protocol. I don''t ever get a rsvp RESV message only PATH AND PATH TEAR messages. There is a timeout but i''m not sure whats causing it exactly. Can anyone shed some light on why? All the configs and output are below. Please let me know if you need more information. Thanks. Jon Test