netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Ben Greear <greearb@candelatech.com>
To: jamal <hadi@cyberus.ca>
Cc: "'netdev@oss.sgi.com'" <netdev@oss.sgi.com>
Subject: Re: [PATCH]  Break 'budget' dependency on netdev_max_backlog.
Date: Tue, 22 Oct 2002 19:37:02 -0700	[thread overview]
Message-ID: <3DB60B4E.1090004@candelatech.com> (raw)
In-Reply-To: Pine.GSO.4.30.0210222113240.24323-100000@shell.cyberus.ca

jamal wrote:

> I think you misunderstood. Look at the dev->weight.

Yep, I was definately confused.  I don't see how changing the
value as I did could affect anything in a good way, but I definately
saw changes in dropped packets...maybe it was too late at night :)

So, after further looking at the code, it appears that the dev->weight
is basically hard-coded in the tulip driver, and the weight_p value
in dev.c (and settable though sysctl) is not used anywhere except
netdev_init (ie, not soon enough to actually set via sysctl).

Think we should add an IOCTL to change the weight of a device
dynamically?  (I want my e1000 and tg3 to have higher weight than
the tulip nics, I imagine)

Is there a ready-built proc interface to do things to individual devices?

Thanks,
Ben

-- 
Ben Greear <greearb@candelatech.com>       <Ben_Greear AT excite.com>
President of Candela Technologies Inc      http://www.candelatech.com
ScryMUD:  http://scry.wanfear.com     http://scry.wanfear.com/~greear

  reply	other threads:[~2002-10-23  2:37 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2002-10-21  6:46 [PATCH] Break 'budget' dependency on netdev_max_backlog Ben Greear
2002-10-21 12:51 ` jamal
2002-10-21 16:25   ` Ben Greear
2002-10-23  0:47     ` jamal
2002-10-23  1:06       ` Ben Greear
2002-10-23  1:18         ` jamal
2002-10-23  2:37           ` Ben Greear [this message]
2002-10-23  3:21             ` jamal
2002-10-23  3:43               ` Ben Greear
2002-10-23  3:44                 ` jamal
2002-10-23  4:00                   ` Ben Greear
2002-10-23  3:58                     ` jamal

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=3DB60B4E.1090004@candelatech.com \
    --to=greearb@candelatech.com \
    --cc=hadi@cyberus.ca \
    --cc=netdev@oss.sgi.com \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).