From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Mosberger Date: Fri, 04 Jun 2004 06:29:19 +0000 Subject: Re: Scalability enhancements for gettimeofday Message-Id: <16576.5823.37997.996516@napali.hpl.hp.com> List-Id: References: <200405201205.57930.clameter@sgi.com> In-Reply-To: <200405201205.57930.clameter@sgi.com> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: linux-ia64@vger.kernel.org >>>>> On Thu, 3 Jun 2004 13:04:12 -0700, Chris Wedgwood said: Chris> On Wed, Jun 02, 2004 at 10:33:39AM -0700, David Mosberger wrote: >> Does this really make a substantial difference? My guess is no and, >> if so, I'd rather not add any more #ifdefs. Chris> How about have the sn2 init code stomp over this value and point to Chris> some local code as required? Do you know about the "nolwsys" option? It already patches the fsyscall-table at boot time. Now this isn't something that we should go overboard with, but in a few select cases, it may indeed be reasonable (and the patch would have to be limited to boot-time, to avoid races etc.). It would, however, be good to share as much source code as possible between the different implementations. For example, me thinks the HPET-version of fsys_gettimeofday() would look almost identical to the SN2-version and some of the existing fsys_gettimeofday() source code should be sharable as well. So if someone wants to pursue this in earnest, it might make sense to move fsys_gettimeofday() into a separate file. --david