linux-kernel - [PATCH] do_mpage_readpage: don't submit lots of small bios on boundary

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [day] [month] [year] [list]

Message-ID: <20081023161500.GA28181@xs4all.net>
Date:	Thu, 23 Oct 2008 18:15:03 +0200
From:	Miquel van Smoorenburg <mikevs@...all.net>
To:	Jens Axboe <jens.axboe@...cle.com>
Cc:	linux-kernel@...r.kernel.org
Subject: [PATCH] do_mpage_readpage: don't submit lots of small bios on
	boundary

(not really sure who to put in the Cc list here)

While tracing I/O patterns with blktrace (a great tool) a few
weeks ago I identified a minor issue in fs/mpage.c

[PATCH] do_mpage_readpage: don't submit lots of small bios on boundary

As the comment above mpage_readpages() says, a fs's get_block
function will set BH_Boundary when it maps a block just before
a block for which extra I/O is required.

Since get_block() can map a range of pages, for all these pages
the BH_Boundary flag will be set. But we only need to push what
I/O we have accumulated at the last block of this range.

This makes do_mpage_readpage() send out the largest possible
bio instead of a bunch of page-sized ones in the BH_Boundary case.

Signed-off-by: Miquel van Smoorenburg <mikevs@...all.net>

diff -ruN linux-2.6.26.5.orig/fs/mpage.c linux-2.6.26.5/fs/mpage.c
--- linux-2.6.26.5.orig/fs/mpage.c	2008-09-08 19:40:20.000000000 +0200
+++ linux-2.6.26.5/fs/mpage.c	2008-10-23 00:32:11.000000000 +0200
@@ -307,7 +307,10 @@
 		goto alloc_new;
 	}
 
-	if (buffer_boundary(map_bh) || (first_hole != blocks_per_page))
+	relative_block = block_in_file - *first_logical_block;
+	nblocks = map_bh->b_size >> blkbits;
+	if ((buffer_boundary(map_bh) && relative_block == nblocks) ||
+	    (first_hole != blocks_per_page))
 		bio = mpage_bio_submit(READ, bio);
 	else
 		*last_block_in_bio = blocks[blocks_per_page - 1];
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/