Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754313Ab0AEBNI (ORCPT ); Mon, 4 Jan 2010 20:13:08 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754212Ab0AEBM7 (ORCPT ); Mon, 4 Jan 2010 20:12:59 -0500 Received: from mga03.intel.com ([143.182.124.21]:60582 "EHLO mga03.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754189Ab0AEBMw (ORCPT ); Mon, 4 Jan 2010 20:12:52 -0500 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.47,316,1257148800"; d="scan'208";a="229176907" Date: Mon, 4 Jan 2010 20:56:20 +0800 From: Wu Fengguang To: Christoph Hellwig Cc: Stephen Rothwell , Andi Kleen , Andrew Morton , Quentin Barnes , "linux-kernel@vger.kernel.org" , "linux-fsdevel@vger.kernel.org" , Nick Piggin , Steven Whitehouse , David Howells , Al Viro , Jonathan Corbet Subject: [RFC][PATCH v4] readahead: introduce O_RANDOM for POSIX_FADV_RANDOM Message-ID: <20100104125620.GB12266@localhost> References: <20091225000717.GA26949@yahoo-inc.com> <87aax18xms.fsf@basil.nowhere.org> <20091230051540.GA16308@localhost> <20091230052402.GB26364@localhost> <873a2s8hmp.fsf@basil.nowhere.org> <20100104045020.GA21021@localhost> <20100104161719.a0bb35ad.sfr@canb.auug.org.au> <20100104073328.GA3422@infradead.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20100104073328.GA3422@infradead.org> User-Agent: Mutt/1.5.18 (2008-05-17) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 5193 Lines: 149 On Mon, Jan 04, 2010 at 03:33:28PM +0800, Christoph Hellwig wrote: > On Mon, Jan 04, 2010 at 04:17:19PM +1100, Stephen Rothwell wrote: > > > @@ -80,6 +80,10 @@ > > > #define O_NDELAY O_NONBLOCK > > > #endif > > > > > > +#ifndef O_RANDOM > > > +#define O_RANDOM 010000000 /* random access pattern hint */ > > > +#endif > > > > This value conflicts with O_CLOEXEC on alpha and parisc and O_NOATIME on > > sparc. Ah thanks! For now I'll use bit 040000000, which happen to equal to FMODE_NONOTIFY and will be masked out by __dentry_open() in the very beginning. So there's no way to call open(O_RANDOM). > Also when I tried to use this value for O_RSYNC and tested it I could > not actually see it getting propagated by the open code. > > Eitherway I don't think an O_ value is a good idea for a simple access > pattern hint. Hmm, I don't really care adding open(O_RANDOM) support. O_RANDOM is used in the code mainly because the file_ra_state fields are racy, so the f_lock protected file->f_flags is convenient for saving the random hint bit. If necessary, we can further mask out O_RANDOM for fcntl(F_GETFL). Thanks, Fengguang --- readahead: introduce O_RANDOM for POSIX_FADV_RANDOM This fixes inefficient page-by-page reads on POSIX_FADV_RANDOM. POSIX_FADV_RANDOM used to set ra_pages=0, which leads to poor performance: a 16K read will be carried out in 4 _sync_ 1-page reads. In other places, ra_pages==0 means - it's ramfs/tmpfs/hugetlbfs/sysfs/configfs - some IO error happened where multi-page read IO won't help or should be avoided. POSIX_FADV_RANDOM actually want a different semantics: to disable the *heuristic* readahead algorithm, and to use a dumb one which faithfully submit read IO for whatever application requests. So introduce a flag O_RANDOM for POSIX_FADV_RANDOM. It will be visible to fcntl(F_GETFL), but open(O_RANDOM) is disabled for now. Note that the random hint is not likely to help random reads performance noticeably. And it may be too permissive on huge request size (its IO size is not limited by read_ahead_kb). In Quentin's report (http://lkml.org/lkml/2009/12/24/145), the overall (NFS read) performance of the application increased by 313%! v4: resolve bit conflicts with sparc and parisc; use bit 040000000(=FMODE_NONOTIFY), which will be masked out by __dentry_open(), so that open(O_RANDOM) is disabled (Stephen Rothwell and Christoph Hellwig) v3: use O_RANDOM to indicate both read/write access pattern as in posix_fadvise(), although it only takes effect for read() now (proposed by Quentin) v2: use O_RANDOM_READ to avoid race conditions (pointed out by Andi) CC: Nick Piggin CC: Andi Kleen CC: Steven Whitehouse CC: David Howells CC: Al Viro CC: Jonathan Corbet CC: Christoph Hellwig Tested-by: Quentin Barnes Signed-off-by: Wu Fengguang --- include/asm-generic/fcntl.h | 8 ++++++++ mm/fadvise.c | 10 +++++++++- mm/readahead.c | 6 ++++++ 3 files changed, 23 insertions(+), 1 deletion(-) --- linux.orig/include/asm-generic/fcntl.h 2010-01-04 12:39:29.000000000 +0800 +++ linux/include/asm-generic/fcntl.h 2010-01-04 20:50:41.000000000 +0800 @@ -80,6 +80,14 @@ #define O_NDELAY O_NONBLOCK #endif +/* + * don't support open(O_RANDOM) for now: + * __dentry_open() will nuke this bit implicitly + */ +#ifndef O_RANDOM +#define O_RANDOM 040000000 /* random access pattern hint */ +#endif + #define F_DUPFD 0 /* dup */ #define F_GETFD 1 /* get close_on_exec */ #define F_SETFD 2 /* set/clear close_on_exec */ --- linux.orig/mm/fadvise.c 2010-01-04 12:39:29.000000000 +0800 +++ linux/mm/fadvise.c 2010-01-04 12:39:30.000000000 +0800 @@ -77,12 +77,20 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, lof switch (advice) { case POSIX_FADV_NORMAL: file->f_ra.ra_pages = bdi->ra_pages; + spin_lock(&file->f_lock); + file->f_flags &= ~O_RANDOM; + spin_unlock(&file->f_lock); break; case POSIX_FADV_RANDOM: - file->f_ra.ra_pages = 0; + spin_lock(&file->f_lock); + file->f_flags |= O_RANDOM; + spin_unlock(&file->f_lock); break; case POSIX_FADV_SEQUENTIAL: file->f_ra.ra_pages = bdi->ra_pages * 2; + spin_lock(&file->f_lock); + file->f_flags &= ~O_RANDOM; + spin_unlock(&file->f_lock); break; case POSIX_FADV_WILLNEED: if (!mapping->a_ops->readpage) { --- linux.orig/mm/readahead.c 2010-01-04 12:39:29.000000000 +0800 +++ linux/mm/readahead.c 2010-01-04 12:39:30.000000000 +0800 @@ -501,6 +501,12 @@ void page_cache_sync_readahead(struct ad if (!ra->ra_pages) return; + /* be dumb */ + if (filp->f_flags & O_RANDOM) { + force_page_cache_readahead(mapping, filp, offset, req_size); + return; + } + /* do read-ahead */ ondemand_readahead(mapping, ra, filp, false, offset, req_size); } -- 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/