From: Wu Fengguang <fengguang.wu@intel.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Andi Kleen <andi@firstfloor.org>,
Quentin Barnes <qbarnes+nfs@yahoo-inc.com>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
linux-fsdevel@vger.kernel.org, Nick Piggin <npiggin@suse.de>,
Steven Whitehouse <swhiteho@redhat.com>
Subject: [RFC][PATCH 1/2] readahead: replace ra->mmap_miss with ra->flags
Date: Wed, 30 Dec 2009 13:17:47 +0800 [thread overview]
Message-ID: <20091230051747.GA26364@localhost> (raw)
In-Reply-To: <20091230051540.GA16308@localhost>
Introduce a readahead flags field and embed the existing mmap_miss in it
(to save space).
It will be possible to lose the flags in race conditions, however the
impact should be limited.
CC: Nick Piggin <npiggin@suse.de>
CC: Andi Kleen <andi@firstfloor.org>
CC: Steven Whitehouse <swhiteho@redhat.com>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
---
include/linux/fs.h | 30 +++++++++++++++++++++++++++++-
mm/filemap.c | 7 ++-----
2 files changed, 31 insertions(+), 6 deletions(-)
--- linux.orig/include/linux/fs.h 2009-12-30 11:07:04.000000000 +0800
+++ linux/include/linux/fs.h 2009-12-30 12:59:28.000000000 +0800
@@ -889,10 +889,38 @@ struct file_ra_state {
there are only # of pages ahead */
unsigned int ra_pages; /* Maximum readahead window */
- unsigned int mmap_miss; /* Cache miss stat for mmap accesses */
+ unsigned int flags;
loff_t prev_pos; /* Cache last read() position */
};
+/* low 16 bits: cache miss stat for mmap accesses */
+#define RA_FLAG_MMAP_MISS 0x0000ffff
+
+/*
+ * Don't do flags++ directly to avoid possible overflow:
+ * the ra fields can be accessed concurrently in a racy way.
+ */
+static inline unsigned int ra_mmap_miss_inc(struct file_ra_state *ra)
+{
+ unsigned int miss = ra->flags & RA_FLAG_MMAP_MISS;
+
+ if (miss < RA_FLAG_MMAP_MISS) {
+ miss++;
+ ra->flags = miss | (ra->flags &~ RA_FLAG_MMAP_MISS);
+ }
+ return miss;
+}
+
+static inline void ra_mmap_miss_dec(struct file_ra_state *ra)
+{
+ unsigned int miss = ra->flags & RA_FLAG_MMAP_MISS;
+
+ if (miss) {
+ miss--;
+ ra->flags = miss | (ra->flags &~ RA_FLAG_MMAP_MISS);
+ }
+}
+
/*
* Check if @index falls in the readahead windows.
*/
--- linux.orig/mm/filemap.c 2009-12-30 11:07:04.000000000 +0800
+++ linux/mm/filemap.c 2009-12-30 11:07:22.000000000 +0800
@@ -1418,14 +1418,12 @@ static void do_sync_mmap_readahead(struc
return;
}
- if (ra->mmap_miss < INT_MAX)
- ra->mmap_miss++;
/*
* Do we miss much more than hit in this file? If so,
* stop bothering with read-ahead. It will only hurt.
*/
- if (ra->mmap_miss > MMAP_LOTSAMISS)
+ if (ra_mmap_miss_inc(ra) > MMAP_LOTSAMISS)
return;
/*
@@ -1455,8 +1453,7 @@ static void do_async_mmap_readahead(stru
/* If we don't want any read-ahead, don't bother */
if (VM_RandomReadHint(vma))
return;
- if (ra->mmap_miss > 0)
- ra->mmap_miss--;
+ ra_mmap_miss_dec(ra);
if (PageReadahead(page))
page_cache_async_readahead(mapping, ra, file,
page, offset, ra->ra_pages);
next prev parent reply other threads:[~2009-12-30 5:17 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20091225000717.GA26949@yahoo-inc.com>
[not found] ` <87aax18xms.fsf@basil.nowhere.org>
2009-12-30 5:15 ` [RFC][PATCH] Disabling read-ahead makes I/O of large reads small Wu Fengguang
2009-12-30 5:17 ` Wu Fengguang [this message]
2009-12-30 5:24 ` [RFC][PATCH 2/2] readahead: avoid page-by-page reads on POSIX_FADV_RANDOM Wu Fengguang
2009-12-30 18:02 ` Andi Kleen
2009-12-31 1:39 ` Wu Fengguang
2009-12-31 2:53 ` Wu Fengguang
2009-12-31 3:03 ` Wu Fengguang
2009-12-31 4:31 ` [RFC][PATCH v2] readahead: introduce O_RANDOM_READ for POSIX_FADV_RANDOM Wu Fengguang
2010-01-08 13:08 ` Christoph Hellwig
2010-01-09 13:59 ` Wu Fengguang
2010-01-09 14:01 ` Wu Fengguang
2010-01-04 4:50 ` [RFC][PATCH v3] readahead: introduce O_RANDOM " Wu Fengguang
2010-01-04 5:17 ` Stephen Rothwell
2010-01-04 7:33 ` Christoph Hellwig
2010-01-04 12:56 ` [RFC][PATCH v4] " Wu Fengguang
2010-01-05 2:03 ` Stephen Rothwell
2010-01-05 2:26 ` Wu Fengguang
2010-01-05 2:28 ` Stephen Rothwell
2010-01-05 2:45 ` Wu Fengguang
2010-01-05 5:21 ` Eric Paris
2010-01-05 3:18 ` [RFC][PATCH v5] " Wu Fengguang
2010-01-05 3:27 ` Wu Fengguang
2010-01-04 16:50 ` [RFC][PATCH v3] " Quentin Barnes
2010-01-04 18:57 ` Andreas Dilger
2010-01-04 5:20 ` Minchan Kim
2010-01-04 12:16 ` Wu Fengguang
2010-01-05 1:46 ` Minchan Kim
2010-01-05 2:16 ` Wu Fengguang
2010-01-05 3:40 ` Minchan Kim
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20091230051747.GA26364@localhost \
--to=fengguang.wu@intel.com \
--cc=akpm@linux-foundation.org \
--cc=andi@firstfloor.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=npiggin@suse.de \
--cc=qbarnes+nfs@yahoo-inc.com \
--cc=swhiteho@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).