From: Tom Verbeek <tom@designobjekt.de>
To: lartc@vger.kernel.org
Subject: Re[2]: [LARTC] QOS and gameserver lags
Date: Tue, 26 Aug 2003 21:25:18 +0000 [thread overview]
Message-ID: <marc-lartc-106193319610829@msgid-missing> (raw)
Monday, August 25, 2003, 7:25:39 PM, Stef wrote:
SC> Can you check the bandwidth used in the different classes? I have a script on
SC> www.docum.org that can do this for you. I ask this because you have
SC> different prio's and you have to be sure you never overlimit a class (send
SC> more then the rate) or the latency can go up.
OK, I checked the bandwidth with monitor_tc.pl: everythings looks
okay. The increased latenca does not come from different prios. But I
still put every class on prio 0.
SC> You also have to check the quantum values. For the 10 kbit class, quantum =
10kbit / 8 (bit ->> byte) / 10 (r2q) = 12.5 byte and this < mtu = 1500 byte.
SC> So add quantum 1500 if you create that class.
OK. I set quantum 1500 on the small class.
But the solution to my problem is much simpler:
my Provider says I get 192 kbits upstream.
When I do an ftp upload to a close server I get 175 kbits.
But to make my linux router the bottleneck I need to limit the rate to
160 kbits!!!!
Can anybody explain the difference in the numbers?
Please see the current version of my shaper here:
http://www.designobjekt.de/test/rc.trafficshaper
Now I only get minimally increased latency when playing
online games and having 100% upstream traffic at the same time.
Cheers,
Tom.
--
Word Perfect isn't, Excel doesn't, Works won't.
_______________________________________________
LARTC mailing list / LARTC@mailman.ds9a.nl
http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://lartc.org/
next reply other threads:[~2003-08-26 21:25 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-08-26 21:25 Tom Verbeek [this message]
2003-08-27 18:10 ` Re[2]: [LARTC] QOS and gameserver lags Stef Coene
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=marc-lartc-106193319610829@msgid-missing \
--to=tom@designobjekt.de \
--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.