Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S965724AbXFGV5o (ORCPT ); Thu, 7 Jun 2007 17:57:44 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S935230AbXFGV5g (ORCPT ); Thu, 7 Jun 2007 17:57:36 -0400 Received: from x35.xmailserver.org ([64.71.152.41]:1684 "EHLO x35.xmailserver.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S936440AbXFGV5f (ORCPT ); Thu, 7 Jun 2007 17:57:35 -0400 X-AuthUser: davidel@xmailserver.org Date: Thu, 7 Jun 2007 14:57:33 -0700 (PDT) From: Davide Libenzi X-X-Sender: davide@alien.or.mcafeemobile.com To: Eric Dumazet cc: Kyle Moffett , Alan Cox , Ulrich Drepper , Linux Kernel Mailing List , Linus Torvalds , Andrew Morton , Ingo Molnar Subject: Re: [patch 7/8] fdmap v2 - implement sys_socket2 In-Reply-To: <466864F8.2050903@cosmosbay.com> Message-ID: References: <20070606235906.72439d16@the-village.bc.nu> <20070607001932.35c9591c@the-village.bc.nu> <466741BD.20106@redhat.com> <20070607110432.73be7960@the-village.bc.nu> <20070607151243.22caab9e.dada1@cosmosbay.com> <466864F8.2050903@cosmosbay.com> X-GPG-FINGRPRINT: CFAE 5BEE FD36 F65E E640 56FE 0974 BF23 270F 474E X-GPG-PUBLIC_KEY: http://www.xmailserver.org/davidel.asc MIME-Version: 1.0 Content-Type: MULTIPART/MIXED; BOUNDARY="1795850513-1008335502-1181253453=:6445" Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2028 Lines: 53 This message is in MIME format. The first part should be readable text, while the remaining parts are likely unreadable without MIME-aware tools. --1795850513-1008335502-1181253453=:6445 Content-Type: TEXT/PLAIN; charset=ISO-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE On Thu, 7 Jun 2007, Eric Dumazet wrote: > Davide Libenzi a =E9crit : > > On Thu, 7 Jun 2007, Eric Dumazet wrote: > >=20 > > > Davide, are you sure we want FIFO for non sequential allocations ? > > >=20 > > > This tends to use all the fmap slots, and not very cache friendly > > > if an app does a lot of [open(),...,close()] things. We already got a= perf > > > drop because of RCUification of file freeing (FIFO mode instead of LI= FO > > > given by kmalloc()/kfree()) > > >=20 > > > If the idea behind this FIFO was security (ie not easy for an app to > > > predict next glibc file handle), we/glibc might use yet another > > > FD_SECUREMODE flag, wich ORed with O_NONSEQFD would ask to fdmap_newf= d() > > > to take the tail of fmap->slist, not head. > >=20 > > Uli, would it be OK to rely only on base randomization and use a LIFO > > instead? We have base randomization, plus LIFO does not mean strictly > > sequential like legacy allocator, just more compatc and cache friendly. > >=20 >=20 > I am afraid randomization wont really work if /sbin/init or /bin/bash for > example uses one (or more) unseq fd : > The 'random base' will be propagated at fork()/exec() time ? As I said to Uli, we can't move the base while fds are in there. We can=20 re-randomize it when it's empty. This can also be done (it's a trivial and= =20 fast operation - just set fmap->base to a new value) even every time the=20 fd count on the map touches zero. - Davide --1795850513-1008335502-1181253453=:6445-- - 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/