Re: [LARTC] CBQ Rate
And different prio's in the filter statement will not change much. It only determines the order the filters are checked. But wasn't there a bug in 'tc' that would delete all your filters that had the same prio, when you only wanted to delete one of them? -- Damjan Georgievski jabberID: [EMAIL PROTECTED] ___ LARTC mailing list / [EMAIL PROTECTED] http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://lartc.org/
RE: [LARTC] CBQ Rate
It is me again. is there nos a trouble in my script : ... rate 5Mbit weight 0.3 ... -- is it compatible ?? Thanks again -Message d'origine- De : [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] la part de Emmanuel SIMON Envoyé : jeudi 4 septembre 2003 17:40 À : 'LARTC' Objet : [LARTC] CBQ Rate Hi everyone, This is on a linux box, ingress (eth1) at 100Mb/s and egress (eth0) at 10Mb/s. The purpose is to test CBQ Here is my script --- # Root qdisc tc qdisc add dev eth0 root handle 1:0 cbq bandwidth 9Mbit \ avpkt 1000 cell 8 # Classes tc class add dev eth0 parent 1:0 classid 1:1 cbq bandwidth 9Mbit \ rate 5Mbit weight 0.3 allot 1514 avpkt 1000 bounded prio 1 tc class add dev eth0 parent 1:0 classid 1:2 cbq bandwidth 9Mbit \ rate 5Mbit weight 0.3 allot 1514 avpkt 1000 bounded prio 2 tc class add dev eth0 parent 1:0 classid 1:3 cbq bandwidth 9Mbit \ rate 5Mbit weight 0.3 allot 1514 avpkt 1000 bounded prio 3 # Leaf qdiscs tc qdisc add dev eth0 parent 1:1 handle 10:0 sfq perturb 10 tc qdisc add dev eth0 parent 1:2 handle 20:0 sfq perturb 10 tc qdisc add dev eth0 parent 1:3 handle 30:0 sfq perturb 10 # Filters tc filter add dev eth0 parent 1:0 proto ip prio 0 u32 \ match ip tos 0x10 0xff flowid 1:1 tc filter add dev eth0 parent 1:0 proto ip prio 1 u32 \ match ip tos 0x04 0xff flowid 1:2 tc filter add dev eth0 parent 1:0 proto ip prio 2 u32 \ match ip tos 0x08 0xff flowid 1:3 --- I send some traffic at different rate : 3Mb/s, 3.5Mb/s, 4Mb/s, 4.5Mb/s, 5Mb/s, 6Mb/s 1st in only one class at a time == the result is always 2.35Mb/s then in the 3 classes at the same time with the same rates. == the result rate is close from wanted rate Can someone explain to me why we I send data in only one class the rate is so low ? Thank you Emmanuel ___ LARTC mailing list / [EMAIL PROTECTED] http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://lartc.org/ ___ LARTC mailing list / [EMAIL PROTECTED] http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://lartc.org/
Re: [LARTC] CBQ Rate
On Thursday 04 September 2003 19:07, Emmanuel SIMON wrote: It is me again. is there nos a trouble in my script : ... rate 5Mbit weight 0.3 ... -- is it compatible ?? Yes. But take weight = rate / 10 as a general rule. And your bandwidth parameter should be the real NIC bandwidth. So 10mbit. And it's also better to create a parent class attached to the root qdisc. And different prio's in the filter statement will not change much. It only determines the order the filters are checked. Thanks again -Message d'origine- De : [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] la part de Emmanuel SIMON Envoyé : jeudi 4 septembre 2003 17:40 À : 'LARTC' Objet : [LARTC] CBQ Rate Hi everyone, This is on a linux box, ingress (eth1) at 100Mb/s and egress (eth0) at 10Mb/s. The purpose is to test CBQ Here is my script --- # Root qdisc tc qdisc add dev eth0 root handle 1:0 cbq bandwidth 9Mbit \ avpkt 1000 cell 8 # Classes tc class add dev eth0 parent 1:0 classid 1:1 cbq bandwidth 9Mbit \ rate 5Mbit weight 0.3 allot 1514 avpkt 1000 bounded prio 1 tc class add dev eth0 parent 1:0 classid 1:2 cbq bandwidth 9Mbit \ rate 5Mbit weight 0.3 allot 1514 avpkt 1000 bounded prio 2 tc class add dev eth0 parent 1:0 classid 1:3 cbq bandwidth 9Mbit \ rate 5Mbit weight 0.3 allot 1514 avpkt 1000 bounded prio 3 # Leaf qdiscs tc qdisc add dev eth0 parent 1:1 handle 10:0 sfq perturb 10 tc qdisc add dev eth0 parent 1:2 handle 20:0 sfq perturb 10 tc qdisc add dev eth0 parent 1:3 handle 30:0 sfq perturb 10 # Filters tc filter add dev eth0 parent 1:0 proto ip prio 0 u32 \ match ip tos 0x10 0xff flowid 1:1 tc filter add dev eth0 parent 1:0 proto ip prio 1 u32 \ match ip tos 0x04 0xff flowid 1:2 tc filter add dev eth0 parent 1:0 proto ip prio 2 u32 \ match ip tos 0x08 0xff flowid 1:3 --- I send some traffic at different rate : 3Mb/s, 3.5Mb/s, 4Mb/s, 4.5Mb/s, 5Mb/s, 6Mb/s 1st in only one class at a time == the result is always 2.35Mb/s then in the 3 classes at the same time with the same rates. == the result rate is close from wanted rate Can someone explain to me why we I send data in only one class the rate is so low ? Thank you Emmanuel Stef -- [EMAIL PROTECTED] Using Linux as bandwidth manager http://www.docum.org/ #lartc @ irc.oftc.net ___ LARTC mailing list / [EMAIL PROTECTED] http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://lartc.org/