Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759697AbXEPWvI (ORCPT ); Wed, 16 May 2007 18:51:08 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1760072AbXEPWsk (ORCPT ); Wed, 16 May 2007 18:48:40 -0400 Received: from smtp.ustc.edu.cn ([202.38.64.16]:50152 "HELO ustc.edu.cn" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with SMTP id S1758534AbXEPWsd (ORCPT ); Wed, 16 May 2007 18:48:33 -0400 Message-ID: <379355696.96896@ustc.edu.cn> X-EYOUMAIL-SMTPAUTH: wfg@mail.ustc.edu.cn Message-Id: <20070516224819.281192313@mail.ustc.edu.cn> References: <20070516224752.500812933@mail.ustc.edu.cn> User-Agent: quilt/0.45-1 Date: Thu, 17 May 2007 06:48:00 +0800 From: Fengguang Wu To: Andrew Morton Cc: linux-kernel@vger.kernel.org Cc: Andi Kleen Cc: Jens Axboe Cc: Oleg Nesterov Cc: Steven Pratt Cc: Ram Pai Subject: [PATCH 8/9] readahead: convert ext3/ext4 invocations Content-Disposition: inline; filename=readahead-invocations-dir.patch Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2351 Lines: 67 Convert ext3/ext4 dir reads to use on-demand readahead. Readahead for dirs operates _not_ on file level, but on blockdev level. This makes a difference when the data blocks are not continuous. And the read routine is somehow opaque: there's no handy info about the status of current page. So a simplified call scheme is employed: to call into readahead whenever the current page falls out of readahead windows. Signed-off-by: Fengguang Wu --- fs/ext3/dir.c | 14 ++++++++------ fs/ext4/dir.c | 14 ++++++++------ 2 files changed, 16 insertions(+), 12 deletions(-) --- linux-2.6.22-rc1-mm1.orig/fs/ext3/dir.c +++ linux-2.6.22-rc1-mm1/fs/ext3/dir.c @@ -136,12 +136,14 @@ static int ext3_readdir(struct file * fi err = ext3_get_blocks_handle(NULL, inode, blk, 1, &map_bh, 0, 0); if (err > 0) { - page_cache_readahead(sb->s_bdev->bd_inode->i_mapping, - &filp->f_ra, - filp, - map_bh.b_blocknr >> - (PAGE_CACHE_SHIFT - inode->i_blkbits), - 1); + pgoff_t index = map_bh.b_blocknr >> + (PAGE_CACHE_SHIFT - inode->i_blkbits); + if (!ra_has_index(&filp->f_ra, index)) + page_cache_readahead_ondemand( + sb->s_bdev->bd_inode->i_mapping, + &filp->f_ra, filp, + NULL, index, 1); + filp->f_ra.prev_index = index; bh = ext3_bread(NULL, inode, blk, 0, &err); } --- linux-2.6.22-rc1-mm1.orig/fs/ext4/dir.c +++ linux-2.6.22-rc1-mm1/fs/ext4/dir.c @@ -135,12 +135,14 @@ static int ext4_readdir(struct file * fi map_bh.b_state = 0; err = ext4_get_blocks_wrap(NULL, inode, blk, 1, &map_bh, 0, 0); if (err > 0) { - page_cache_readahead(sb->s_bdev->bd_inode->i_mapping, - &filp->f_ra, - filp, - map_bh.b_blocknr >> - (PAGE_CACHE_SHIFT - inode->i_blkbits), - 1); + pgoff_t index = map_bh.b_blocknr >> + (PAGE_CACHE_SHIFT - inode->i_blkbits); + if (!ra_has_index(&filp->f_ra, index)) + page_cache_readahead_ondemand( + sb->s_bdev->bd_inode->i_mapping, + &filp->f_ra, filp, + NULL, index, 1); + filp->f_ra.prev_index = index; bh = ext4_bread(NULL, inode, blk, 0, &err); } -- - 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/