Date: Mon, 28 Dec 2009 10:47:07 +0100
From: Ingo Molnar <mingo@elte.hu>
To: Yinghai Lu <yinghai@kernel.org>
Cc: 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>
Subject: Re: [PATCH] x86: increase NR_IRQS and nr_irqs
Message-ID: <20091228094707.GH24690@elte.hu>
References: <4B347AEE.6030705@kernel.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <4B347AEE.6030705@kernel.org>
User-Agent: Mutt/1.5.20 (2009-08-17)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 942
Lines: 23


* 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.
> 
> so try to increase NR_IRQS and nr_irqs to about 8000 and 6000.
> for that system.

could you please provide before/after .data size analysis, expected dynamic 
allocation overhead difference (if any), etc. - so that we can see whether 
there's any (and if yes, how much) cost due to the bumping of the limit.

Also, instead of just upping the limit to a new random limit that works on 
that testbox, could we put some more thought into how much we want to increase 
it, and stay at least 2-3 years ahead of the expected hardware curve?

	Ingo
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/