All of lore.kernel.org
 help / color / mirror / Atom feed
From: Oswin Budiman <armahalma@gmail.com>
To: lartc@vger.kernel.org
Subject: [LARTC] HTB - ethloop - overlimits?
Date: Thu, 30 Dec 2004 04:50:06 +0000	[thread overview]
Message-ID: <67137473041229205078f134fd@mail.gmail.com> (raw)

Hi all,

I'm trying to setup htb on a box with the following class configuration:

class htb 1:2 root rate 4Mbit ceil 4Mbit burst 2099b/8 mpu 0b overhead
0b cburst 2099b/8 mpu 0b overhead 0b level 7
 Sent 0 bytes 0 pkts (dropped 0, overlimits 0 requeues 0) 
 lended: 0 borrowed: 0 giants: 0
 tokens: 4300 ctokens: 4300

class htb 1:4 parent 1:2 leaf 4: prio 7 quantum 1000 rate 1Kbit ceil
1Kbit burst 1599b/8 mpu 0b overhead 0b cburst 1599b/8 mpu 0b overhead
0b level 0
 Sent 0 bytes 0 pkts (dropped 0, overlimits 0 requeues 0) 
 lended: 0 borrowed: 0 giants: 0
 tokens: 13107200 ctokens: 13107200

class htb 1:6 parent 1:2 leaf 6: prio 0 quantum 12500 rate 1Mbit ceil
1Mbit burst 1724b/8 mpu 0b overhead 0b cburst 1724b/8 mpu 0b overhead
0b level 0
 Sent 0 bytes 0 pkts (dropped 0, overlimits 0 requeues 0) 
 lended: 0 borrowed: 0 giants: 0
 tokens: 14131 ctokens: 14131

class htb 1:7 parent 1:2 leaf 7: prio 0 quantum 37500 rate 3Mbit ceil
3Mbit burst 1974b/8 mpu 0b overhead 0b cburst 1974b/8 mpu 0b overhead
0b level 0
 Sent 0 bytes 0 pkts (dropped 0, overlimits 0 requeues 0) 
 lended: 0 borrowed: 0 giants: 0
 tokens: 5392 ctokens: 5392

and then I try to simulate the traffic using ethloop to see it it's work.
I use the following script to generate the packet on ethloop. I'm
using loopback interface.

# Set interface
0       i       0       lo
0       i       1       lo
# Set packet size
0       S       0       1k
0       S       1       1k
# Determine flow id
0       P       0       0x10006
0       P       1       0x10007
# Start flow...
0       R       0       4000k
0       R       1       4000k
# Finish it. 
10000   X       0       0  

Foxtrot ethloop # ethloop < input > output

When it finish, I got weird output. When I see the tc stat, the flow
enters the right class but the rate is terribly wrong... I wonder what
happen to it? Here's the output file and tc stat.

Foxtrot ethloop # cat output

0.5 173183 98004 443 0 55401 57802 3 0
1.0 136001 118161 734 0 13147 13717 3 0
1.5 128969 124736 735 0 3120 3255 3 0
2.0 125141 124136 735 0 740 772 3 0
2.5 125825 125586 735 0 176 183 3 0
3.0 124266 129381 735 0 42 44 3 0
3.5 125977 125555 736 0 10 10 3 0
4.0 129326 127894 735 0 2 3 3 0
4.5 125209 124869 737 0 1 1 3 0
5.0 124410 129449 128 0 0 0 3 0
5.5 125842 125418 417 0 0 0 3 0
6.0 128815 128714 706 0 0 0 3 0
6.5 125021 124997 736 0 0 0 3 0
7.0 127941 127936 735 0 0 0 3 0
7.5 124749 124748 736 0 0 0 3 0
8.0 128248 127326 735 0 1113 1113 2 0
8.5 125319 125100 735 0 264 264 2 0
9.0 127961 126230 735 0 63 63 2 0
9.5 124722 124311 735 0 15 15 2 0
10.0 127203 127105 736 0 4 4 2 0

Foxtrot ethloop # qd lo

qdisc htb 1: r2q 10 default 4 direct_packets_stat 0 ver 3.17
 Sent 2728960 bytes 2665 pkts (dropped 0, overlimits 3996 requeues 0) 
qdisc sfq 4: parent 1:4 limit 128p quantum 16450b flows 128/1024 perturb 10sec 
 Sent 0 bytes 0 pkts (dropped 0, overlimits 0 requeues 0) 
qdisc sfq 6: parent 1:6 limit 128p quantum 16450b flows 128/1024 perturb 10sec 
 Sent 2297856 bytes 2244 pkts (dropped 0, overlimits 0 requeues 0) 
qdisc sfq 7: parent 1:7 limit 128p quantum 16450b flows 128/1024 perturb 10sec 
 Sent 431104 bytes 421 pkts (dropped 0, overlimits 0 requeues 0)
_______________________________________________
LARTC mailing list / LARTC@mailman.ds9a.nl
http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://lartc.org/

             reply	other threads:[~2004-12-30  4:50 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2004-12-30  4:50 Oswin Budiman [this message]
2004-12-30 15:46 ` [LARTC] HTB - ethloop - overlimits? Stef Coene
2005-01-03  3:04 ` Oswin Budiman

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=67137473041229205078f134fd@mail.gmail.com \
    --to=armahalma@gmail.com \
    --cc=lartc@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.