From mboxrd@z Thu Jan 1 00:00:00 1970 From: Arthur Kepner Subject: Re: [PATCH] mlx4_core: module param to limit msix vec allocation Date: Fri, 3 Sep 2010 15:13:03 -0700 Message-ID: <20100903221303.GS2464@sgi.com> References: <20100826170646.GB27157@sgi.com> <20100826.122407.260097270.davem@davemloft.net> <20100903203044.GN2464@sgi.com> <20100903.144658.149830788.davem@davemloft.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: netdev@vger.kernel.org To: David Miller Return-path: Received: from relay3.sgi.com ([192.48.152.1]:37365 "EHLO relay.sgi.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1752993Ab0ICWNF (ORCPT ); Fri, 3 Sep 2010 18:13:05 -0400 Content-Disposition: inline In-Reply-To: <20100903.144658.149830788.davem@davemloft.net> Sender: netdev-owner@vger.kernel.org List-ID: On Fri, Sep 03, 2010 at 02:46:58PM -0700, David Miller wrote: > From: Arthur Kepner > Date: Fri, 3 Sep 2010 13:30:44 -0700 > > > I have that running on a (very small) system and it seems to > > work OK. Will send out the patch in just a minute. > > Failure vs. non-failure of allocation of a kernel managed physical > resource can't be determined by a userland process which may or may > not be running. But even if there's no user process running, it's no worse than what we've got now. > > In fact, if I build all of my drivers built-in and use NFS root which > will activate and bring up network devices, userland won't even be > present when the interrupts are requested. Yep. This only works once the user-level irq balancer is available. > > No, you really can't do it this way, IRQ allocation management has to > be in the kernel. Really? I was specifically trying to avoid that, and let the policy about interrupt assignment be done in a user process. Do you have any specific ideas about how that'd look? -- Arthur