mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Florin Andrei <florin@andrei.myip.org>
To: linux-kernel@vger.kernel.org
Subject: generic method to assign IRQs
Date: 13 Jun 2003 21:12:02 -0700	[thread overview]
Message-ID: <1055563922.11874.29.camel@rivendell.home.local> (raw)

Is there any generic method to manually assign IRQs to devices? Not
something that applies to one kernel module or another, but something
that works in general.

It happens quite often, especially on multimedia workstations, when
multiple devices get assigned the same IRQ, the performance goes down
the toilet, and users experience strange things like "my video capture
application stutters when my system sends/receives traffic on the
network card."
In such cases, the usual recommendation is to "shuffle the PCI cards
around." Sometimes that works, sometimes it doesn't. It definitely
doesn't apply to laptops.
Another trick is to enable APIC in the kernel. While this is not a
direct solution, it helps sometimes by providing a larger IRQ space. In
some rare cases it makes the systems less stable.

However, quite often i've heard people saying "i wish i could just
manually assign IRQs to devices, just like i do on That Other Operating
System."

This issue may not matter much on "normal" systems, but it matters a
whole bunch on multimedia machines. Not being able to untangle like five
or six devices assigned to the same IRQ may render an otherwise powerful
system totally unusable for any decent media purpose (i'm talking here
about simple tasks such as watching movies, not necessarily of
professional stuff, which is even more demanding).

Any suggestions?

Thanks,

-- 
Florin Andrei

http://florin.myip.org/


             reply	other threads:[~2003-06-14  3:58 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2003-06-14  4:12 Florin Andrei [this message]
2003-06-14  4:37 ` Mike Dresser
2003-06-14  4:39   ` Trever L. Adams
2003-06-15 22:26   ` Florin Andrei

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=1055563922.11874.29.camel@rivendell.home.local \
    --to=florin@andrei.myip.org \
    --cc=linux-kernel@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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®