[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20131220071820.GC4571@gchen.bj.intel.com>
Date: Fri, 20 Dec 2013 02:18:20 -0500
From: "Chen, Gong" <gong.chen@...ux.intel.com>
To: Prarit Bhargava <prarit@...hat.com>
Cc: Tony Luck <tony.luck@...il.com>,
Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...hat.com>,
"H. Peter Anvin" <hpa@...or.com>, X86-ML <x86@...nel.org>,
Michel Lespinasse <walken@...gle.com>,
Andi Kleen <ak@...ux.intel.com>,
Seiji Aguchi <seiji.aguchi@....com>,
Yang Zhang <yang.z.zhang@...el.com>,
Paul Gortmaker <paul.gortmaker@...driver.com>,
janet.morgan@...el.com, "Yu, Fenghua" <fenghua.yu@...el.com>
Subject: Re: [PATCH] x86: Add check for number of available vectors before
CPU down [v2]
On Thu, Dec 19, 2013 at 01:11:32PM -0500, Prarit Bhargava wrote:
>
> Yep. The question really is this: is the irq mapped to a single vector or
> multiple vectors. (I think)
>
> P.
>
Yes, this is the original thought I want to express on the bugzilla. On an
ideal environment, without irq balance, all vector_irq should own same
values, say, 0xffffffff. So when one CPU is off-lined, your patch will
considers no places to contain these to-be-migrated irqs but the fact is
they are shared on different CPUs. So if we can answer this question,
the answer will be clear :-).
Download attachment "signature.asc" of type "application/pgp-signature" (837 bytes)
Powered by blists - more mailing lists