netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jesse Brandeburg <jesse.brandeburg@gmail.com>
To: Yinghai Lu <yinghai@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>, Thomas Gleixner <tglx@linutronix.de>,
	"H. Peter Anvin" <hpa@zytor.com>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	NetDEV list <netdev@vger.kernel.org>,
	Jesse Brandeburg <jesse.brandeburg@intel.com>
Subject: Re: [PATCH -v2] x86: increase NR_IRQS and nr_irqs
Date: Sun, 3 Jan 2010 19:06:11 -0800	[thread overview]
Message-ID: <4807377b1001031906s6b1ee576jc021da2642bb4147@mail.gmail.com> (raw)
In-Reply-To: <4B398ECD.1080506@kernel.org>

On Mon, Dec 28, 2009 at 9:08 PM, Yinghai Lu <yinghai@kernel.org> wrote:
> have a system with lots of igb and ixgbe, when iov/vf are enabled for
> them, we hit the limit of 3064.
>
> when system have 20 pcie installed, and one card have 2 functions, and one
> function need 64 msi-x,
>  may need 20 * 2 * 64 = 2560 for msi-x
> but if iov and vf are enabled
>  may need 20 * 2 * 64 * 3 = 7680 for msi-x
> assume system with 5 ioapic, nr_irqs_gsi will be 120.
> NR_CPUS = 512, and nr_cpu_ids = 128
> will have NR_IRQS = 256 + 512 * 64 = 33024
> will have nr_irqs = 120 + 8 * 128 + 120 * 64 = 8824
>
> when SPARSE_IRQ is not set, there is no increase with data
> when NR_CPUS=128, and SPARSE_IRQ is set
>   text            data     bss            dec           hex    filename
> 21837444        4216564 12480736        38534744        24bfe58 vmlinux.before
> 21837442        4216580 12480736        38534758        24bfe66 vmlinux.after
> when NR_CPUS=4096, and SPARSE_IRQ is set
>   text            data     bss            dec           hex    filename
> 21878619        5610244 13415392        40904255        270263f vmlinux.before
> 21878617        5610244 13415392        40904253        270263d vmlinux.after
>
> -v2: update comments to address Ingo's concern
>
> Signed-off-by: Yinghai Lu <yinghai@kernel.org>

I'm not sure this is the best plan, but may be okay for now.  What
happens when all of your slots have 6 port 82599 ixgbe adapters in
them?  They are being made[1], as well as quad port 82576 igb
adapters, however I'm not fully sure of the SRIOV support of the
bridges being used on those adapters.

Is it on the table to (re-)design this subsystem to be a little more
dynamic?  There are probably examples in ppc64 or ia64 directories.
Every time you suggest a limit I can find a case where it won't be
enough.

[1] http://www.hotlavasystems.com/products_10gbe.html

       reply	other threads:[~2010-01-04  3:06 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <4B347AEE.6030705@kernel.org>
     [not found] ` <20091228094707.GH24690@elte.hu>
     [not found]   ` <4B398ECD.1080506@kernel.org>
2010-01-04  3:06     ` Jesse Brandeburg [this message]
2010-01-04  3:20       ` [PATCH -v2] x86: increase NR_IRQS and nr_irqs Yinghai Lu
2010-01-04  6:56         ` Subject: [PATCH 1/2] x86: get back 15 vectors Yinghai Lu
2010-01-04 16:18           ` Eric W. Biederman
2010-01-04 18:40             ` Yinghai Lu
2010-01-04 19:04               ` Eric W. Biederman
2010-01-04 19:14                 ` H. Peter Anvin
2010-01-04 19:01             ` H. Peter Anvin
2010-01-04 19:09               ` Eric W. Biederman
2010-01-04 19:35                 ` Yinghai Lu
2010-01-04 19:45                   ` Suresh Siddha
2010-01-04 19:50                     ` H. Peter Anvin
2010-01-05  0:05                       ` Suresh Siddha
2010-01-05  0:16                         ` Yinghai Lu
2010-01-04 19:48                   ` H. Peter Anvin
2010-01-04 20:06                     ` Yinghai Lu
2010-01-04 20:14                       ` Eric W. Biederman
2010-01-04 20:33                         ` Yinghai Lu
2010-01-04 21:10                           ` H. Peter Anvin
2010-01-04 21:20                             ` Yinghai Lu
2010-01-04 21:33                               ` H. Peter Anvin
2010-01-04 22:01                                 ` Yinghai Lu
2010-01-04 23:03                                   ` H. Peter Anvin
2010-01-04 23:32                                     ` Yinghai Lu
2010-01-04 23:38                                       ` H. Peter Anvin
2010-01-04 23:42                                         ` Yinghai Lu
2010-01-04 23:49                                         ` Yinghai Lu
2010-01-04 23:59                                           ` H. Peter Anvin
2010-01-04 20:08                   ` Eric W. Biederman
2010-01-04  6:58         ` [PATCH 2/2] x86: get more exact nr_irqs Yinghai Lu
2010-01-04 16:55           ` Eric W. Biederman
2010-01-04 19:03             ` Yinghai Lu
2010-01-04 19:16               ` Eric W. Biederman
2010-01-04 19:30                 ` H. Peter Anvin
2010-01-04 19:47                   ` Yinghai Lu
2010-01-04 20:05                   ` Eric W. Biederman
2010-01-04 21:50                     ` H. Peter Anvin
2010-01-04  6:59         ` [PATCH 1/2] x86: get back 15 vectors Yinghai Lu

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=4807377b1001031906s6b1ee576jc021da2642bb4147@mail.gmail.com \
    --to=jesse.brandeburg@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=hpa@zytor.com \
    --cc=jesse.brandeburg@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=netdev@vger.kernel.org \
    --cc=tglx@linutronix.de \
    --cc=yinghai@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;
as well as URLs for NNTP newsgroup(s).