mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: "Randy.Dunlap" <rdunlap@xenotime.net>
To: ebiederm@xmission.com (Eric W. Biederman)
Cc: Andrew Morton <akpm@osdl.org>, Andi Kleen <ak@suse.de>,
	"Protasevich, Natalie" <Natalie.Protasevich@UNISYS.com>,
	<linux-kernel@vger.kernel.org>
Subject: Re: [PATCH] x86_64: Make NR_IRQS configurable in Kconfig
Date: Mon, 7 Aug 2006 08:59:24 -0700	[thread overview]
Message-ID: <20060807085924.72f832af.rdunlap@xenotime.net> (raw)
In-Reply-To: <m1irl4ftya.fsf@ebiederm.dsl.xmission.com>

On Mon, 07 Aug 2006 09:26:21 -0600 Eric W. Biederman wrote:

> Currrently on a SMP system we can theoretically support
> NR_CPUS*224 irqs.  Unfortunately our data structures
> don't cope will with that many irqs, nor does hardware
> typically provide that many irq sources.
> 
> With the number of cores starting to follow Moores
> law, and the apicid limits being raised beyond an 8bit
> number trying to track our current maximum with our
> current data structures would be fatal and wasteful.
> 
> So this patch decouples the number of irqs we support
> from the number of cpus.  We can revisit this decision
> once someone reworks the current data structures.
> 
> Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
> ---
>  arch/x86_64/Kconfig      |   13 +++++++++++++
>  include/asm-x86_64/irq.h |    3 ++-
>  2 files changed, 15 insertions(+), 1 deletions(-)
> 
> diff --git a/arch/x86_64/Kconfig b/arch/x86_64/Kconfig
> index 7598d99..d744e5b 100644
> --- a/arch/x86_64/Kconfig
> +++ b/arch/x86_64/Kconfig
> @@ -384,6 +384,19 @@ config NR_CPUS
>  	  This is purely to save memory - each supported CPU requires
>  	  memory in the static kernel configuration.
>  
> +config NR_IRQS
> +	int "Maximum number of IRQs (224-4096)"
> +	range 256 4096
> +	depends on SMP
> +	default "4096"
> +	help
> +	  This allows you to specify the maximum number of IRQs which this
> +	  kernel will support. Current maximum is 4096 IRQs as that
> +	  is slightly larger than has observed in the field.
> +
> +	  This is purely to save memory - each supported IRQ requires
> +	  memory in the static kernel configuration.

If (a) "nor does hardware typically provide that many irq sources"
and (b) "This is purely to save memory", why is the default
4096 instead of something smaller?

---
~Randy

  parent reply	other threads:[~2006-08-07 15:56 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-08-07 15:26 Eric W. Biederman
2006-08-07 15:33 ` Andi Kleen
2006-08-07 15:55   ` Eric W. Biederman
2006-08-07 15:59 ` Randy.Dunlap [this message]
2006-08-07 16:11   ` Protasevich, Natalie
2006-08-07 16:17     ` Andi Kleen
2006-08-07 16:23       ` Protasevich, Natalie
2006-08-07 16:58       ` Eric W. Biederman
2006-08-07 16:44   ` Eric W. Biederman
2006-08-07 17:00     ` H. Peter Anvin
2006-08-07 17:46       ` Eric W. Biederman
2006-08-07 17:52         ` H. Peter Anvin
2006-08-07 17:30   ` Eric W. Biederman
2006-08-07 17:55     ` Randy.Dunlap
2006-08-07 18:16       ` Eric W. Biederman
2006-08-07 18:53       ` Eric W. Biederman
2006-08-07 19:04         ` Randy.Dunlap
2006-08-07 22:10           ` Eric W. Biederman
2006-08-07 23:55             ` Andrew Morton
2006-08-08  2:17               ` Andi Kleen
2006-08-08  2:41                 ` Andrew Morton
2006-08-08  2:47                   ` Arjan van de Ven
2006-08-08  5:47                     ` [PATCH] x86_64: Auto size the per cpu area Eric W. Biederman
2006-08-08  6:01                       ` Andrew Morton
2006-08-08  6:31                         ` Eric W. Biederman
2006-08-08  6:01                       ` Andi Kleen
2006-08-08  6:46                         ` Eric W. Biederman
2006-08-08  6:48                           ` Andi Kleen
2006-08-08  7:29                             ` Eric W. Biederman
2006-08-08  5:09                   ` [PATCH] x86_64: Make NR_IRQS configurable in Kconfig Paul Mackerras
2006-08-08  5:14                     ` Andi Kleen
2006-08-08  8:17                       ` Martin Schwidefsky
2006-08-09 17:58                         ` Luck, Tony
2006-08-09 18:25                           ` Dave Hansen
2006-08-10 12:55                             ` Martin Schwidefsky
2006-08-10 14:40                               ` Andy Whitcroft
2006-08-10 14:53                                 ` Martin Schwidefsky
2006-08-07 19:40         ` Adrian Bunk
2006-08-07 22:26           ` Eric W. Biederman
2006-08-07 23:06             ` Adrian Bunk

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=20060807085924.72f832af.rdunlap@xenotime.net \
    --to=rdunlap@xenotime.net \
    --cc=Natalie.Protasevich@UNISYS.com \
    --cc=ak@suse.de \
    --cc=akpm@osdl.org \
    --cc=ebiederm@xmission.com \
    --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®