From: Rasmus Villemoes Subject: Re: [RFC] vfs: don't bother clearing close_on_exec bit for unused fds Date: Wed, 04 Nov 2015 00:13:41 +0100 Message-ID: <878u6ed6ca.fsf@rasmusvillemoes.dk> References: <1446543679-28849-1-git-send-email-linux@rasmusvillemoes.dk> Mime-Version: 1.0 Content-Type: text/plain Cc: Alexander Viro , linux-fsdevel , Linux Kernel Mailing List To: Linus Torvalds Return-path: Received: from mail-wi0-f170.google.com ([209.85.212.170]:35804 "EHLO mail-wi0-f170.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S965128AbbKCXNo (ORCPT ); Tue, 3 Nov 2015 18:13:44 -0500 Received: by wicll6 with SMTP id ll6so79469795wic.0 for ; Tue, 03 Nov 2015 15:13:43 -0800 (PST) In-Reply-To: (Linus Torvalds's message of "Tue, 3 Nov 2015 14:45:01 -0800") Sender: linux-fsdevel-owner@vger.kernel.org List-ID: On Tue, Nov 03 2015, Linus Torvalds wrote: > On Tue, Nov 3, 2015 at 1:41 AM, Rasmus Villemoes > wrote: >> >> I'm sure I've missed something, hence the RFC. But if not, there's >> probably also a few memsets which become redundant. And the >> __set_close_on_exec part should probably be its own patch... > > The patch looks fine to me. I'm not sure the __set_close_on_exec part > even makes sense, because if you set that bit, it usually really *is* > clear before, so testing it beforehand is just pointless. And if > somebody really keeps setting the bit, they are doing something stupid > anyway.. So that's true for the lifetime of a single fd where no-one of course does fcntl(fd, FD_CLOEXEC) more than once. But the scenario I was thinking of was when fds get recycled. open(, O_CLOEXEC) => 5, close(5), open(, O_CLOEXEC) => 5; in that case, letting the close_on_exec bit keep its value avoids dirtying the cache line on all subsequent allocations of fd 5 (for example, had Eric's app been using *_CLOEXEC for all its open's, socket's etc. there wouldn't have been any gain by adding the conditional to __clear_close_on_exec, but I'd expect to see a similar gain by doing the symmetric thing). Again, this is assuming that almost all fd allocations either do or do not apply CLOEXEC - after a while, ->close_on_exec would reach a steady-state where no bits get flipped anymore. The "usually really *is* clear" only holds when we do "bother clearing close_on_exec bit for unused fds", which is what I suggest we don't :-) I don't think either state of the bit in close_on_exec is more or less 'up-to-date' when its buddy in open_fds is not set. Rasmus