From: Peter Zijlstra <a.p.zijlstra@chello.nl>
To: linux-kernel <linux-kernel@vger.kernel.org>
Cc: Fengguang Wu <wfg@mail.ustc.edu.cn>, riel <riel@redhat.com>,
Andrew Morton <akpm@linux-foundation.org>,
Rusty Russell <rusty@rustcorp.com.au>,
Tim Pepper <lnxninja@us.ibm.com>, Chris Snook <csnook@redhat.com>,
Peter Zijlstra <a.p.zijlstra@chello.nl>
Subject: [PATCH 3/3] readahead: scale max readahead size depending on memory size
Date: Sat, 21 Jul 2007 23:00:08 +0200 [thread overview]
Message-ID: <20070721210052.497469000@chello.nl> (raw)
In-Reply-To: 20070721210005.000228000@chello.nl
[-- Attachment #1: ra_pages.patch --]
[-- Type: text/plain, Size: 2488 bytes --]
Scale the default max readahead size with the system memory size.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
block/ll_rw_blk.c | 2 +-
include/linux/fs.h | 1 +
mm/readahead.c | 32 ++++++++++++++++++++++++++++++++
3 files changed, 34 insertions(+), 1 deletion(-)
Index: linux-2.6/block/ll_rw_blk.c
===================================================================
--- linux-2.6.orig/block/ll_rw_blk.c
+++ linux-2.6/block/ll_rw_blk.c
@@ -208,7 +208,7 @@ void blk_queue_make_request(request_queu
blk_queue_max_phys_segments(q, MAX_PHYS_SEGMENTS);
blk_queue_max_hw_segments(q, MAX_HW_SEGMENTS);
q->make_request_fn = mfn;
- q->backing_dev_info.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
+ bdi_ra_init(&q->backing_dev_info);
q->backing_dev_info.state = 0;
q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY;
blk_queue_max_sectors(q, SAFE_MAX_SECTORS);
Index: linux-2.6/include/linux/fs.h
===================================================================
--- linux-2.6.orig/include/linux/fs.h
+++ linux-2.6/include/linux/fs.h
@@ -1696,6 +1696,7 @@ extern long do_splice_direct(struct file
extern void
file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping);
+extern void bdi_ra_init(struct backing_dev_info *bdi);
extern loff_t no_llseek(struct file *file, loff_t offset, int origin);
extern loff_t generic_file_llseek(struct file *file, loff_t offset, int origin);
extern loff_t remote_llseek(struct file *file, loff_t offset, int origin);
Index: linux-2.6/mm/readahead.c
===================================================================
--- linux-2.6.orig/mm/readahead.c
+++ linux-2.6/mm/readahead.c
@@ -42,6 +42,38 @@ file_ra_state_init(struct file_ra_state
}
EXPORT_SYMBOL_GPL(file_ra_state_init);
+static unsigned long ra_pages;
+
+static __init int readahead_init(void)
+{
+ /*
+ * Scale the max readahead window with system memory
+ *
+ * 64M: 128K
+ * 128M: 180K
+ * 256M: 256K
+ * 512M: 360K
+ * 1G: 512K
+ * 2G: 724K
+ * 4G: 1024K
+ * 8G: 1448K
+ * 16G: 2048K
+ */
+ ra_pages = int_sqrt(totalram_pages/16);
+ if (ra_pages > (2 << (20 - PAGE_SHIFT)))
+ ra_pages = 2 << (20 - PAGE_SHIFT);
+
+ return 0;
+}
+
+subsys_initcall(readahead_init);
+
+void bdi_ra_init(struct backing_dev_info *bdi)
+{
+ bdi->ra_pages = ra_pages;
+}
+EXPORT_SYMBOL(bdi_ra_init);
+
#define list_to_page(head) (list_entry((head)->prev, struct page, lru))
/**
--
next prev parent reply other threads:[~2007-07-21 19:02 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-07-21 21:00 [PATCH 0/3] readahead drop behind and size adjustment Peter Zijlstra
2007-07-21 21:00 ` [PATCH 1/3] readahead: drop behind Peter Zijlstra
2007-07-21 20:29 ` Eric St-Laurent
2007-07-21 20:37 ` Peter Zijlstra
2007-07-21 20:59 ` Eric St-Laurent
2007-07-21 21:06 ` Peter Zijlstra
2007-07-25 3:55 ` Eric St-Laurent
2007-07-21 21:00 ` [PATCH 2/3] readahead: fadvise drop behind controls Peter Zijlstra
2007-07-21 21:00 ` Peter Zijlstra [this message]
2007-07-22 8:24 ` [PATCH 3/3] readahead: scale max readahead size depending on memory size Jens Axboe
2007-07-22 8:36 ` Peter Zijlstra
2007-07-22 8:50 ` Jens Axboe
2007-07-22 9:17 ` Peter Zijlstra
2007-07-22 16:44 ` Jens Axboe
2007-07-23 10:04 ` Jörn Engel
2007-07-23 10:11 ` Jens Axboe
2007-07-23 22:44 ` Rusty Russell
2007-07-22 23:52 ` Rik van Riel
2007-07-23 5:22 ` Jens Axboe
[not found] ` <20070722084526.GB6317@mail.ustc.edu.cn>
2007-07-22 8:45 ` Fengguang Wu
2007-07-22 8:59 ` Peter Zijlstra
[not found] ` <20070722095313.GA8136@mail.ustc.edu.cn>
2007-07-22 9:53 ` Fengguang Wu
[not found] ` <20070722023923.GA6438@mail.ustc.edu.cn>
2007-07-22 2:39 ` [PATCH 0/3] readahead drop behind and size adjustment Fengguang Wu
2007-07-22 2:44 ` Dave Jones
[not found] ` <20070722081010.GA6317@mail.ustc.edu.cn>
2007-07-22 8:10 ` Fengguang Wu
2007-07-22 8:24 ` Peter Zijlstra
[not found] ` <20070722082923.GA7790@mail.ustc.edu.cn>
2007-07-22 8:29 ` Fengguang Wu
2007-07-22 8:33 ` Rusty Russell
2007-07-22 8:45 ` Peter Zijlstra
2007-07-23 9:00 ` Nick Piggin
[not found] ` <20070723142457.GA10130@mail.ustc.edu.cn>
2007-07-23 14:24 ` Fengguang Wu
2007-07-23 19:40 ` Andrew Morton
[not found] ` <20070724004728.GA8026@mail.ustc.edu.cn>
2007-07-24 0:47 ` Fengguang Wu
2007-07-24 1:17 ` Andrew Morton
2007-07-24 8:50 ` Andreas Dilger
2007-07-24 4:30 ` Nick Piggin
2007-07-25 4:35 ` Eric St-Laurent
2007-07-25 5:19 ` Nick Piggin
2007-07-25 6:18 ` Eric St-Laurent
2007-07-25 7:09 ` Nick Piggin
2007-07-25 7:48 ` Eric St-Laurent
2007-07-25 15:36 ` Rik van Riel
2007-07-25 15:33 ` Rik van Riel
2007-07-29 7:44 ` Eric St-Laurent
2007-07-25 15:28 ` Rik van Riel
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=20070721210052.497469000@chello.nl \
--to=a.p.zijlstra@chello.nl \
--cc=akpm@linux-foundation.org \
--cc=csnook@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=lnxninja@us.ibm.com \
--cc=riel@redhat.com \
--cc=rusty@rustcorp.com.au \
--cc=wfg@mail.ustc.edu.cn \
/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