Skip to contentSkip to conversation

beta-release of H-FSC port for Linux 2.6

LARTC Patrick McHardy 5 participants 7 messages Oct 26, 2003 – Nov 13, 2003

lore
Share & tools
lore
#0 lore raw

I've done a port of the altq H-FSC packet scheduler for linux 2.6. It's still in beta stage but it's running for about two weeks here without problems (and excellent shaping results). There is no documentation, so it's at best for the playful at the moment. The patches are available at http://trash.net/~kaber/hfsc
If you are looking for 2.4 patches, there are none at the moment but it's a 5 minute effort so if you need them please ask.

Please note due to a lack of time I will only answer basic usage questions at this point and for sure I won't review tc scripts without detailed bug reports.

Have Fun,
Patrick

BTW: on a related issue, IMQ is looking for a new maintainer.
If you are interested please contact me.

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

#1 lore raw

Hello Patrick,

I read the abstract and introduction to original H-FSC paper. I believe it was mostly about decoupling bw and delay. It seems to me HTB does this well. When and/or why would I would want to use H-FSC versus HTB or are they direct competitors?

Curious,

Torsten

-----Original Message-----
From: Patrick McHardy [mailto:[email protected]]
Sent: Sunday, October 26, 2003 10:05 AM
To: [email protected]
Subject: [LARTC] beta-release of H-FSC port for Linux 2.6

I've done a port of the altq H-FSC packet scheduler for linux 2.6. It's still in beta stage but it's running for about two weeks here without problems (and excellent shaping results). There is no documentation, so it's at best for the playful at the moment. The patches are available at http://trash.net/~kaber/hfsc
If you are looking for 2.4 patches, there are none at the moment but it's a 5 minute effort so if you need them please ask.

Please note due to a lack of time I will only answer basic usage questions at this point and for sure I won't review tc scripts without detailed bug reports.

Have Fun,
Patrick

BTW: on a related issue, IMQ is looking for a new maintainer.
If you are interested please contact me.

_______________________________________________
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/

#2 lore raw
In reply to Patrick McHardy

Hi Torsten,

Quoted 4 lines · Hans T

I read the abstract and introduction to original H-FSC paper. I believe it was mostly about decoupling bw and delay. It seems to me HTB does this well. When and/or why would I would want to use H-FSC versus HTB or are they direct competitors?

Not sure what you mean with "competitors", I made this port for fun after happily discovering that the code was very nicely written (unlike the version mentioned in the paper). This should not be understood as dissatisfaction with HTB, I was perfectly happy with the entire time I used it.

So why would you want to use H-FSC .. you're right, a major feature of H-FSC is decoupling of bandwidth and delay, but it also offers delay _guarantees_ if configured correctly. This is very important for streaming, VoIP, .. (and gamers of course). I don't know if my understanding of HTB's algorithm is correct, but it is basically a chained token bucket, so delay is directly coupled to bandwidth. Also I believe it always tries to dequeue "quantum" bytes at once so classes might go overlimits for a limited period of time. This hurts delay. On the other hand, HTB is more expressive due to priorites. So I'd say it basically comes down to expressiveness vs. delay guarantees. However I was able to convert my HTB config to something very similar with H-FSC depite using priorites with HTB.

I hope that anwers your question.

Best regards,
Patrick

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

#3 lore raw
In reply to Patrick McHardy

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

Quoted 4 lines · Patrick McHardy

So why would you want to use H-FSC .. you're right, a major feature of H-FSC is decoupling of bandwidth and delay, but it also offers delay _guarantees_ if configured correctly. This is very important for streaming, VoIP, .. (and gamers of course).

Exactly. I was able to shape the ping latency down from 2000 ms on large uploads to 60-150 ms using HTB, this is good for ssh - but not good enough for quake3.

- --
- Thilo Schulz

My public GnuPG key is available at http://home.bawue.de/~arny/public_key.asc
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.2.3 (GNU/Linux)

iD8DBQE/pCESZx4hBtWQhl4RAvJPAJ4m+J+B2o2LSeaOKbykGoHyiWIgRgCg6enN 1oYZvSyTYC1sQgk2MBfqMEU=WKzh
-----END PGP SIGNATURE-----

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

#4 lore raw
In reply to Patrick McHardy
Quoted 20 lines · On Sat, 01 Nov 2003 15:45:04 +0100 Patrick McHardy <[email protected]> wrote:

Not sure what you mean with "competitors", I made this port for fun after happily discovering that the code was very nicely written (unlike the version mentioned in the paper). This should not be understood as dissatisfaction with HTB, I was perfectly happy with the entire time I used it.

So why would you want to use H-FSC .. you're right, a major feature of H-FSC is decoupling of bandwidth and delay, but it also offers delay _guarantees_ if configured correctly. This is very important for streaming, VoIP, .. (and gamers of course). I don't know if my understanding of HTB's algorithm is correct, but it is basically a chained token bucket, so delay is directly coupled to bandwidth. Also I believe it always tries to dequeue "quantum" bytes at once so classes might go overlimits for a limited period of time. This hurts delay. On the other hand, HTB is more expressive due to priorites. So I'd say it basically comes down to expressiveness vs. delay guarantees. However I was able to convert my HTB config to something very similar with H-FSC depite using priorites with HTB.

Quoted 6 lines

I hope that anwers your question.

Best regards,
Patrick

Sound interesting, but where I can find samples of hfsc usage ? I want to try my htb setup and hfsc.

Quoted 4 lines

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

Signature · 4 lines
PGP key : http://pgp.dtype.org:11371/pks/lookup?op=get&search=0x0BE90515
_______________________________________________
LARTC mailing list / [email protected]
http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://lartc.org/
#5 lore raw
In reply to Patrick McHardy

Hi Alexey,

Quoted 4 lines · Alexey Sheshka

Sound interesting, but where I can find samples of hfsc usage ? I want to try my htb setup and hfsc.

There is no documentation yet. Since H-FSC is currently approaching stability I will concentrate on this in the next time. If you don't like to wait that long I can also send you the script I use to shape my DSL connection.

Best regards,
Patrick

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

#6 lore raw
In reply to Patrick McHardy

On Tue, 04 Nov 2003 15:19:01 +0100
Patrick McHardy <[email protected]> wrote:

I would be interested in seeing that script, if possible

Quoted 21 lines

Hi Alexey,

Quoted 5 lines · Alexey Sheshka

Sound interesting, but where I can find samples of hfsc usage ? I want to try my htb setup and hfsc.

There is no documentation yet. Since H-FSC is currently approaching stability I will concentrate on this in the next time. If you don't like to wait that long I can also send you the script I use to shape my DSL connection.

Best regards,
Patrick

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

Signature · 8 lines
Cezar ATANASIU
GMB Computers
Departamentul Internet
Tel/fax: +40 241 619222/673199     

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