All of lore.kernel.org
 help / color / mirror / Atom feed
From: Wu Fengguang <fengguang.wu@intel.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Andi Kleen <andi@firstfloor.org>, Wu Fengguang <fengguang.wu@intel.com>
Cc: Linux Memory Management List <linux-mm@kvack.org>,
	<linux-fsdevel@vger.kernel.org>
Cc: LKML <linux-kernel@vger.kernel.org>
Subject: [PATCH 2/9] readahead: snap readahead request to EOF
Date: Tue, 29 Nov 2011 21:09:02 +0800	[thread overview]
Message-ID: <20111129131456.145362960@intel.com> (raw)
In-Reply-To: 20111129130900.628549879@intel.com

[-- Attachment #1: readahead-eof --]
[-- Type: text/plain, Size: 1524 bytes --]

If the file size is 20kb and readahead request is [0, 16kb),
it's better to expand the readahead request to [0, 20kb), which will
likely save one followup I/O for [16kb, 20kb).

If the readahead request already covers EOF, trimm it down to EOF.
Also don't set the PG_readahead mark to avoid an unnecessary future
invocation of the readahead code.

This special handling looks worthwhile because small to medium sized
files are pretty common.

Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
---
 mm/readahead.c |    8 ++++++++
 1 file changed, 8 insertions(+)

--- linux-next.orig/mm/readahead.c	2011-11-29 11:28:56.000000000 +0800
+++ linux-next/mm/readahead.c	2011-11-29 11:29:05.000000000 +0800
@@ -251,8 +251,16 @@ unsigned long max_sane_readahead(unsigne
 unsigned long ra_submit(struct file_ra_state *ra,
 		       struct address_space *mapping, struct file *filp)
 {
+	pgoff_t eof = ((i_size_read(mapping->host)-1) >> PAGE_CACHE_SHIFT) + 1;
+	pgoff_t start = ra->start;
 	int actual;
 
+	/* snap to EOF */
+	if (start + ra->size + ra->size / 2 > eof) {
+		ra->size = eof - start;
+		ra->async_size = 0;
+	}
+
 	actual = __do_page_cache_readahead(mapping, filp,
 					ra->start, ra->size, ra->async_size);
 


--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

WARNING: multiple messages have this Message-ID (diff)
From: Wu Fengguang <fengguang.wu@intel.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Andi Kleen <andi@firstfloor.org>,
	Wu Fengguang <fengguang.wu@intel.com>,
	Linux Memory Management List <linux-mm@kvack.org>,
	linux-fsdevel@vger.kernel.org,
	LKML <linux-kernel@vger.kernel.org>
Subject: [PATCH 2/9] readahead: snap readahead request to EOF
Date: Tue, 29 Nov 2011 21:09:02 +0800	[thread overview]
Message-ID: <20111129131456.145362960@intel.com> (raw)
In-Reply-To: 20111129130900.628549879@intel.com

[-- Attachment #1: readahead-eof --]
[-- Type: text/plain, Size: 1524 bytes --]

If the file size is 20kb and readahead request is [0, 16kb),
it's better to expand the readahead request to [0, 20kb), which will
likely save one followup I/O for [16kb, 20kb).

If the readahead request already covers EOF, trimm it down to EOF.
Also don't set the PG_readahead mark to avoid an unnecessary future
invocation of the readahead code.

This special handling looks worthwhile because small to medium sized
files are pretty common.

Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
---
 mm/readahead.c |    8 ++++++++
 1 file changed, 8 insertions(+)

--- linux-next.orig/mm/readahead.c	2011-11-29 11:28:56.000000000 +0800
+++ linux-next/mm/readahead.c	2011-11-29 11:29:05.000000000 +0800
@@ -251,8 +251,16 @@ unsigned long max_sane_readahead(unsigne
 unsigned long ra_submit(struct file_ra_state *ra,
 		       struct address_space *mapping, struct file *filp)
 {
+	pgoff_t eof = ((i_size_read(mapping->host)-1) >> PAGE_CACHE_SHIFT) + 1;
+	pgoff_t start = ra->start;
 	int actual;
 
+	/* snap to EOF */
+	if (start + ra->size + ra->size / 2 > eof) {
+		ra->size = eof - start;
+		ra->async_size = 0;
+	}
+
 	actual = __do_page_cache_readahead(mapping, filp,
 					ra->start, ra->size, ra->async_size);
 


--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

WARNING: multiple messages have this Message-ID (diff)
From: Wu Fengguang <fengguang.wu@intel.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Andi Kleen <andi@firstfloor.org>, Wu Fengguang <fengguang.wu@intel.com>
Cc: Linux Memory Management List <linux-mm@kvack.org>,
	<linux-fsdevel@vger.kernel.org>
Cc: LKML <linux-kernel@vger.kernel.org>
Subject: [PATCH 2/9] readahead: snap readahead request to EOF
Date: Tue, 29 Nov 2011 21:09:02 +0800	[thread overview]
Message-ID: <20111129131456.145362960@intel.com> (raw)
In-Reply-To: 20111129130900.628549879@intel.com

[-- Attachment #1: readahead-eof --]
[-- Type: text/plain, Size: 1221 bytes --]

If the file size is 20kb and readahead request is [0, 16kb),
it's better to expand the readahead request to [0, 20kb), which will
likely save one followup I/O for [16kb, 20kb).

If the readahead request already covers EOF, trimm it down to EOF.
Also don't set the PG_readahead mark to avoid an unnecessary future
invocation of the readahead code.

This special handling looks worthwhile because small to medium sized
files are pretty common.

Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
---
 mm/readahead.c |    8 ++++++++
 1 file changed, 8 insertions(+)

--- linux-next.orig/mm/readahead.c	2011-11-29 11:28:56.000000000 +0800
+++ linux-next/mm/readahead.c	2011-11-29 11:29:05.000000000 +0800
@@ -251,8 +251,16 @@ unsigned long max_sane_readahead(unsigne
 unsigned long ra_submit(struct file_ra_state *ra,
 		       struct address_space *mapping, struct file *filp)
 {
+	pgoff_t eof = ((i_size_read(mapping->host)-1) >> PAGE_CACHE_SHIFT) + 1;
+	pgoff_t start = ra->start;
 	int actual;
 
+	/* snap to EOF */
+	if (start + ra->size + ra->size / 2 > eof) {
+		ra->size = eof - start;
+		ra->async_size = 0;
+	}
+
 	actual = __do_page_cache_readahead(mapping, filp,
 					ra->start, ra->size, ra->async_size);
 



  parent reply	other threads:[~2011-11-29 13:09 UTC|newest]

Thread overview: 93+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-11-29 13:09 [PATCH 0/9] readahead stats/tracing, backwards prefetching and more (v2) Wu Fengguang
2011-11-29 13:09 ` Wu Fengguang
2011-11-29 13:09 ` [PATCH 1/9] block: limit default readahead size for small devices Wu Fengguang
2011-11-29 13:09   ` Wu Fengguang
2011-11-29 13:09   ` Wu Fengguang
2011-11-29 13:09 ` Wu Fengguang [this message]
2011-11-29 13:09   ` [PATCH 2/9] readahead: snap readahead request to EOF Wu Fengguang
2011-11-29 13:09   ` Wu Fengguang
2011-11-29 14:29   ` Jan Kara
2011-11-29 14:29     ` Jan Kara
2011-11-30  1:06     ` Wu Fengguang
2011-11-30  1:06       ` Wu Fengguang
2011-11-30 11:37       ` Jan Kara
2011-11-30 11:37         ` Jan Kara
2011-11-30 12:06         ` Wu Fengguang
2011-11-30 12:06           ` Wu Fengguang
2011-11-29 13:09 ` [PATCH 3/9] readahead: record readahead patterns Wu Fengguang
2011-11-29 13:09   ` Wu Fengguang
2011-11-29 13:09   ` Wu Fengguang
2011-11-29 14:40   ` Jan Kara
2011-11-29 14:40     ` Jan Kara
2011-11-29 17:57   ` Andi Kleen
2011-11-29 17:57     ` Andi Kleen
2011-11-30  1:18     ` Wu Fengguang
2011-11-30  1:18       ` Wu Fengguang
2011-12-15  8:55     ` [PATCH] proc: show readahead state in fdinfo Wu Fengguang
2011-12-15  8:55       ` Wu Fengguang
2011-12-15  9:49       ` Ingo Molnar
2011-12-15  9:49         ` Ingo Molnar
2011-11-29 13:09 ` [PATCH 4/9] readahead: tag mmap page fault call sites Wu Fengguang
2011-11-29 13:09   ` Wu Fengguang
2011-11-29 13:09   ` Wu Fengguang
2011-11-29 14:41   ` Jan Kara
2011-11-29 14:41     ` Jan Kara
2011-11-29 13:09 ` [PATCH 5/9] readahead: tag metadata " Wu Fengguang
2011-11-29 13:09   ` Wu Fengguang
2011-11-29 13:09   ` Wu Fengguang
2011-11-29 14:45   ` Jan Kara
2011-11-29 14:45     ` Jan Kara
2011-11-29 13:09 ` [PATCH 6/9] readahead: add /debug/readahead/stats Wu Fengguang
2011-11-29 13:09   ` Wu Fengguang
2011-11-29 13:09   ` Wu Fengguang
2011-11-29 15:21   ` Jan Kara
2011-11-29 15:21     ` Jan Kara
2011-11-30  0:44     ` Wu Fengguang
2011-11-30  0:44       ` Wu Fengguang
2011-12-14  6:36     ` Wu Fengguang
2011-12-14  6:36       ` Wu Fengguang
2011-12-19 16:32       ` Jan Kara
2011-12-19 16:32         ` Jan Kara
2011-12-21  1:29         ` Wu Fengguang
2011-12-21  1:29           ` Wu Fengguang
2011-12-21  4:06           ` Dave Chinner
2011-12-21  4:06             ` Dave Chinner
2011-12-23  3:33             ` Wu Fengguang
2011-12-23  3:33               ` Wu Fengguang
2011-12-23 11:16               ` Jan Kara
2011-12-23 11:16                 ` Jan Kara
2011-11-29 13:09 ` [PATCH 7/9] readahead: add vfs/readahead tracing event Wu Fengguang
2011-11-29 13:09   ` Wu Fengguang
2011-11-29 13:09   ` Wu Fengguang
2011-11-29 15:22   ` Jan Kara
2011-11-29 15:22     ` Jan Kara
2011-11-30  0:42     ` Wu Fengguang
2011-11-30  0:42       ` Wu Fengguang
2011-11-30 11:44       ` Jan Kara
2011-11-30 11:44         ` Jan Kara
2011-11-30 12:06         ` Wu Fengguang
2011-11-30 12:06           ` Wu Fengguang
2011-12-06 15:30   ` Christoph Hellwig
2011-12-06 15:30     ` Christoph Hellwig
2011-12-07  9:18     ` Wu Fengguang
2011-12-07  9:18       ` Wu Fengguang
2011-12-08  9:03     ` [PATCH] writeback: show writeback reason with __print_symbolic Wu Fengguang
2011-12-08  9:03       ` Wu Fengguang
2011-11-29 13:09 ` [PATCH 8/9] readahead: basic support for backwards prefetching Wu Fengguang
2011-11-29 13:09   ` Wu Fengguang
2011-11-29 13:09   ` Wu Fengguang
2011-11-29 15:35   ` Jan Kara
2011-11-29 15:35     ` Jan Kara
2011-11-29 16:37     ` Pádraig Brady
2011-11-29 16:37       ` Pádraig Brady
2011-11-29 16:37       ` Pádraig Brady
2011-11-30  0:24       ` Wu Fengguang
2011-11-30  0:24         ` Wu Fengguang
2011-11-30  0:24         ` Wu Fengguang
2011-11-30  0:37     ` Wu Fengguang
2011-11-30  0:37       ` Wu Fengguang
2011-11-30 11:21       ` Jan Kara
2011-11-30 11:21         ` Jan Kara
2011-11-29 13:09 ` [PATCH 9/9] readahead: dont do start-of-file readahead after lseek() Wu Fengguang
2011-11-29 13:09   ` Wu Fengguang
2011-11-29 13:09   ` Wu Fengguang

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=20111129131456.145362960@intel.com \
    --to=fengguang.wu@intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=andi@firstfloor.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.