Skip to contentSkip to conversation

htb & bandwidth sharing

LARTC Albert Martorell 3 participants 8 messages Jun 16, 2003 – Jun 18, 2003

lore
Share & tools
lore
#0 lore raw

Hi everybody!

I've been trying with htb and tc filter. It seemed to work fine, but after testing with ethloop I've realized that traffic is not being distributed through the leaves as I thought. When sending packets to 1:10 and 1:11 at the same time, there's no bandwidth sharing. There's no traffic through 1:11 until traffic through 1:10 has finished. Though I've tried assigning different prio's, 1:10 always gets more bandwidth...

Here's the script that reproduces this behaviour:

tc qdisc add dev eth0 root handle 1: htb default 12 r2q 10 tc class add dev eth0 parent 1: classid 1:1 htb rate 600kbit ceil 600kbit
tc class add dev eth0 parent 1:1 classid 1:10 htb rate 200kbit ceil 600kbit
tc class add dev eth0 parent 1:1 classid 1:11 htb rate 200kbit ceil 600kbit
tc class add dev eth0 parent 1:1 classid 1:12 htb rate 200kbit ceil 600kbit
tc qdisc add dev eth0 parent 1:10 handle 20: sfq perturb 10 tc qdisc add dev eth0 parent 1:11 handle 21: sfq perturb 10 tc qdisc add dev eth0 parent 1:12 handle 22: sfq perturb 10

tc filter add dev eth0 protocol ip parent 1: u32 match ip sport 53 0xffff flowid 1:10
tc filter add dev eth0 protocol ip parent 1: u32 match ip src 1.2.3.4 match ip sport 80 0xffff flowid 1:11

Thanks in advance!

Albert

_______________________________________________
LARTC mailing list / [email protected]
http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://lartc.org/

#1 lore raw
Quoted 9 lines · Albert Martorell

Hi everybody!

I've been trying with htb and tc filter. It seemed to work fine, but after testing with ethloop I've realized that traffic is not being distributed through the leaves as I thought. When sending packets to 1:10 and 1:11 at the same time, there's no bandwidth sharing. There's no traffic through 1:11 until traffic through 1:10 has finished. Though I've tried assigning different prio's, 1:10 always gets more bandwidth...

I also did some test and used ethloop But I had good restults. You can find more info on
http://www.docum.org/stef.coene/qos/tests/htb/parent/

Quoted 15 lines

Here's the script that reproduces this behaviour:

tc qdisc add dev eth0 root handle 1: htb default 12 r2q 10 tc class add dev eth0 parent 1: classid 1:1 htb rate 600kbit ceil 600kbit
tc class add dev eth0 parent 1:1 classid 1:10 htb rate 200kbit ceil 600kbit
tc class add dev eth0 parent 1:1 classid 1:11 htb rate 200kbit ceil 600kbit
tc class add dev eth0 parent 1:1 classid 1:12 htb rate 200kbit ceil 600kbit
tc qdisc add dev eth0 parent 1:10 handle 20: sfq perturb 10 tc qdisc add dev eth0 parent 1:11 handle 21: sfq perturb 10 tc qdisc add dev eth0 parent 1:12 handle 22: sfq perturb 10

Quoted 4 lines

tc filter add dev eth0 protocol ip parent 1: u32 match ip sport 53 0xffff flowid 1:10
tc filter add dev eth0 protocol ip parent 1: u32 match ip src 1.2.3.4 match ip sport 80 0xffff flowid 1:11

I did my tests with ethloop on lo and you used eth0. Do you have a loopback connecter installed on eth0?

Stef

Signature · 8 lines
[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/
#2 lore raw
In reply to Albert Martorell

We noted this problem that the first subclass got all the extra bandwidth when the subclasses should be sharing the extra bandwidth equally. We were able to get it working better by lowering the quantum to 1600.

I think what is happening with a larger quantum is that the first subclass is getting all the extra bandwidth in one quantum.

Orlie

Quoted 31 lines · On Monday 2003.06.16 10:07 Albert Martorell wrote:

Hi everybody!

I've been trying with htb and tc filter. It seemed to work fine, but after testing with ethloop I've realized that traffic is not being distributed through the leaves as I thought. When sending packets to 1:10 and 1:11 at the same time, there's no bandwidth sharing. There's no traffic through 1:11 until traffic through 1:10 has finished. Though I've tried assigning different prio's, 1:10 always gets more bandwidth...

Here's the script that reproduces this behaviour:

tc qdisc add dev eth0 root handle 1: htb default 12 r2q 10 tc class add dev eth0 parent 1: classid 1:1 htb rate 600kbit ceil 600kbit
tc class add dev eth0 parent 1:1 classid 1:10 htb rate 200kbit ceil 600kbit
tc class add dev eth0 parent 1:1 classid 1:11 htb rate 200kbit ceil 600kbit
tc class add dev eth0 parent 1:1 classid 1:12 htb rate 200kbit ceil 600kbit
tc qdisc add dev eth0 parent 1:10 handle 20: sfq perturb 10 tc qdisc add dev eth0 parent 1:11 handle 21: sfq perturb 10 tc qdisc add dev eth0 parent 1:12 handle 22: sfq perturb 10

tc filter add dev eth0 protocol ip parent 1: u32 match ip sport 53 0xffff flowid 1:10
tc filter add dev eth0 protocol ip parent 1: u32 match ip src 1.2.3.4 match ip sport 80 0xffff flowid 1:11

Quoted 9 lines

Thanks in advance!

Albert

_______________________________________________
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/

#3 lore raw
In reply to Albert Martorell
Quoted 10 lines · Stef Coene
Quoted 9 lines · Albert Martorell

Hi everybody!

I've been trying with htb and tc filter. It seemed to work fine, but after testing with ethloop I've realized that traffic is not being distributed through the leaves as I thought. When sending packets to 1:10 and 1:11 at the same time, there's no bandwidth sharing. There's no traffic through 1:11 until traffic through 1:10 has finished. Though I've tried assigning different prio's, 1:10 always gets more bandwidth...

Quoted 3 lines

I also did some test and used ethloop But I had good restults. You can find more info on
http://www.docum.org/stef.coene/qos/tests/htb/parent/

Thanks, I'll take a look.

Quoted 17 lines
Quoted 17 lines

Here's the script that reproduces this behaviour:

tc qdisc add dev eth0 root handle 1: htb default 12 r2q 10 tc class add dev eth0 parent 1: classid 1:1 htb rate 600kbit ceil 600kbit
tc class add dev eth0 parent 1:1 classid 1:10 htb rate 200kbit ceil 600kbit
tc class add dev eth0 parent 1:1 classid 1:11 htb rate 200kbit ceil 600kbit
tc class add dev eth0 parent 1:1 classid 1:12 htb rate 200kbit ceil 600kbit
tc qdisc add dev eth0 parent 1:10 handle 20: sfq perturb 10 tc qdisc add dev eth0 parent 1:11 handle 21: sfq perturb 10 tc qdisc add dev eth0 parent 1:12 handle 22: sfq perturb 10

Quoted 6 lines
Quoted 4 lines

tc filter add dev eth0 protocol ip parent 1: u32 match ip sport 53 0xffff flowid 1:10
tc filter add dev eth0 protocol ip parent 1: u32 match ip src 1.2.3.4 match ip sport 80 0xffff flowid 1:11

I did my tests with ethloop on lo and you used eth0. Do you have a loopback connecter installed on eth0?

I see my first mistake has been testing directly on ethernet devices without a loopback connector... Anyway I've tried with ethloop on lo and the results are the same.

Thx.

Albert

_______________________________________________
LARTC mailing list / [email protected]
http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://lartc.org/

#4 lore raw
In reply to Albert Martorell
Quoted 3 lines · Albert Martorell

I see my first mistake has been testing directly on ethernet devices without a loopback connector... Anyway I've tried with ethloop on lo and the results are the same.

Did you execute
ifconfig lo mtu 1500
?

Stef

Signature · 8 lines
[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/
#5 lore raw
In reply to Albert Martorell
Quoted 8 lines · Stef Coene
Quoted 3 lines · Albert Martorell

I see my first mistake has been testing directly on ethernet devices without a loopback connector... Anyway I've tried with ethloop on lo and the results are the same.

Did you execute
ifconfig lo mtu 1500
?

Yes I did. I've seen that for low rates in ethloop it behaves as expected. When I increase rates to 50% of ceil rate, traffic only goes through the first leaf class. I've tried lowering the quantum, as suggested by Orlie Brewer, but it has not worked for me..

Albert

_______________________________________________
LARTC mailing list / [email protected]
http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://lartc.org/

#6 lore raw
In reply to Albert Martorell
Quoted 6 lines · Albert Martorell
Quoted 5 lines · Stef Coene
Quoted 3 lines · Albert Martorell

I see my first mistake has been testing directly on ethernet devices without a loopback connector... Anyway I've tried with ethloop on lo and the results are the same.

Quoted 8 lines
Quoted 3 lines

Did you execute
ifconfig lo mtu 1500
?

Yes I did. I've seen that for low rates in ethloop it behaves as expected. When I increase rates to 50% of ceil rate, traffic only goes through the first leaf class. I've tried lowering the quantum, as suggested by Orlie Brewer, but it has not worked for me..

Can send me the scripts and ethloop commands you use? So I can try it myself.

Stef

Signature · 8 lines
[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/
#7 lore raw
In reply to Albert Martorell

When I was going to send you my scripts I discovered where the mistake was. In ethloop 'k' rates are kbps instead of kbits, so I was supplying very high rates...

I'm sorry for this. Anyway, thanks a lot for your help.

Albert

Quoted 17 lines · Stef Coene
Quoted 6 lines · Albert Martorell
Quoted 5 lines · Stef Coene
Quoted 3 lines · Albert Martorell

I see my first mistake has been testing directly on ethernet devices without a loopback connector... Anyway I've tried with ethloop on lo and the results are the same.

Quoted 8 lines
Quoted 3 lines

Did you execute
ifconfig lo mtu 1500
?

Yes I did. I've seen that for low rates in ethloop it behaves as expected. When I increase rates to 50% of ceil rate, traffic only goes through the first leaf class. I've tried lowering the quantum, as suggested by Orlie Brewer, but it has not worked for me..

Can send me the scripts and ethloop commands you use? So I can try it myself.

Quoted 8 lines

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/