From mboxrd@z Thu Jan 1 00:00:00 1970 From: Arnaldo Carvalho de Melo Subject: Re: [RFC 1/2] net: Introduce recvmmsg socket syscall Date: Wed, 3 Jun 2009 22:46:23 -0300 Message-ID: <20090604014622.GI7805@ghostprotocols.net> References: <20090520230652.GB5956@ghostprotocols.net> <20090522200611.GB967@hmsreliant.think-freely.org> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: Neil Horman , Arnaldo Carvalho de Melo , David Miller , netdev@vger.kernel.org, Chris Van Hoof , Clark Williams To: Andrew Grover Return-path: Received: from mx2.redhat.com ([66.187.237.31]:47956 "EHLO mx2.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751186AbZFDBqb (ORCPT ); Wed, 3 Jun 2009 21:46:31 -0400 Content-Disposition: inline In-Reply-To: Sender: netdev-owner@vger.kernel.org List-ID: Em Wed, Jun 03, 2009 at 06:44:22PM -0700, Andrew Grover escreveu: > On Fri, May 22, 2009 at 1:06 PM, Neil Horman = wrote: > > Not to throw more questions into the mix again, but didn't Ingo wri= te a > > batching syscall a while back, which let you issue several syscalls= in one trap > > to kernel space? =A0I understand that your approach has some effici= ency gains over > > that, but did that ever get accepted upstream? =A0Is the overlap th= ere sufficient > > to make this approach redundant? =A0Or are the gains in performance= here > > sufficient to warrant this new call? >=20 > I couldn't find this via Google or any posts to LKML by Ingo on this? >=20 > I'm very interested in multiple send/recvmsg support. So, it's > definitely going to happen? :-) I got sidetracked with some other activities, and was waiting for more comments and reports from some testers, but will be back to implement a v2 patch soon. - Arnaldo