From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751977Ab3KTF43 (ORCPT ); Wed, 20 Nov 2013 00:56:29 -0500 Received: from mailout3.samsung.com ([203.254.224.33]:43448 "EHLO mailout3.samsung.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750776Ab3KTF40 (ORCPT ); Wed, 20 Nov 2013 00:56:26 -0500 X-AuditID: cbfee61a-b7f836d0000025d7-9c-528c4efe161b From: Chao Yu To: ??? Cc: linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org, linux-f2fs-devel@lists.sourceforge.net, =?gb2312?B?zLfmrQ==?= Subject: [f2fs-dev] [PATCH V2 1/2 RESEND] f2fs: add a new function to support for merging contiguous read Date: Wed, 20 Nov 2013 13:54:35 +0800 Message-id: <001901cee5b5$2e28a520$8a79ef60$@samsung.com> MIME-version: 1.0 Content-type: text/plain; charset=gb2312 Content-transfer-encoding: 7bit X-Mailer: Microsoft Outlook 14.0 Thread-index: Ac7lry7hQeiwBW3hTziushnsetuPhw== Content-language: zh-cn X-Brightmail-Tracker: H4sIAAAAAAAAA+NgFrrMLMWRmVeSWpSXmKPExsVy+t9jAd1/fj1BBof7zSyu7/rLZHFpkbvF nr0nWSwu75rDZtG68DyzA6vH7gWfmTz6tqxi9Pi8SS6AOYrLJiU1J7MstUjfLoEr48R6iYLl UhV9aw4wNzAeEO1i5OSQEDCRmDPlGDOELSZx4d56ti5GLg4hgUWMEu8PHodyfjBKLOvczghS xSagIrG84z8TiC0ioCix4f0GdpAiZoEZjBKH5/5jBUkIC2RLTP70gQXEZhFQlTi45zNYnFfA UuLBqxfMELagxI/J98BqmAU0JPoXbWCDsOUlNq95C3WSgsSOs68ZIZbpSZy+MJEVokZcYuOR WywTGAVmIRk1C8moWUhGzULSsoCRZRWjaGpBckFxUnquoV5xYm5xaV66XnJ+7iZGcFA/k9rB uLLB4hCjAAejEg+vxILuICHWxLLiytxDjBIczEoivLfce4KEeFMSK6tSi/Lji0pzUosPMUpz sCiJ8x5otQ4UEkhPLEnNTk0tSC2CyTJxcEo1MG6/IyJ9+tesH69vFGs/urRTweLswYJ+9+q6 PtZ26fA+gTNPvyd+3eB9PKlD67hZOduPz1M6Ze71Ku8+znk+/YHzASbFZQ+uK0qzX7X5ozzj JBt373XuJzcYWB+x1cU7aPvrbG078f+xjsXzdx59T1IuvW5J////+/Kc9c9DLhhdEL+969TM h4uUWIozEg21mIuKEwFmYjvoZgIAAA== Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org For better read performance, we add a new function to support for merging contiguous read as the one for write. v1-->v2: o add declarations here as Gu Zheng suggested. o use new structure f2fs_bio_info introduced by Jaegeuk Kim. Signed-off-by: Chao Yu Acked-by: Gu Zheng --- fs/f2fs/data.c | 50 ++++++++++++++++++++++++++++++++++++++++++++++++++ fs/f2fs/f2fs.h | 3 +++ fs/f2fs/super.c | 1 + 3 files changed, 54 insertions(+) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index b4e4c7e..9cf3f6c 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -400,6 +400,56 @@ int f2fs_readpage(struct f2fs_sb_info *sbi, struct page *page, return 0; } +void f2fs_submit_read_bio(struct f2fs_sb_info *sbi, int rw) +{ + struct f2fs_bio_info *io = &sbi->read_io; + + if (!io->bio) + return; + + mutex_lock(&io->io_mutex); + if (io->bio) { + submit_bio(rw, io->bio); + io->bio = NULL; + } + mutex_unlock(&io->io_mutex); +} + +void submit_read_page(struct f2fs_sb_info *sbi, struct page *page, + block_t blk_addr, int rw) +{ + struct block_device *bdev = sbi->sb->s_bdev; + struct f2fs_bio_info *io = &sbi->read_io; + int bio_blocks; + + verify_block_addr(sbi, blk_addr); + + mutex_lock(&io->io_mutex); + + if (io->bio && io->last_block_in_bio != blk_addr - 1) { + submit_bio(rw, io->bio); + io->bio = NULL; + } +alloc_new: + if (io->bio == NULL) { + bio_blocks = MAX_BIO_BLOCKS(max_hw_blocks(sbi)); + io->bio = f2fs_bio_alloc(bdev, bio_blocks); + io->bio->bi_sector = SECTOR_FROM_BLOCK(sbi, blk_addr); + io->bio->bi_end_io = read_end_io; + } + + if (bio_add_page(io->bio, page, PAGE_CACHE_SIZE, 0) < + PAGE_CACHE_SIZE) { + submit_bio(rw, io->bio); + io->bio = NULL; + goto alloc_new; + } + + io->last_block_in_bio = blk_addr; + + mutex_unlock(&io->io_mutex); +} + /* * This function should be used by the data read flow only where it * does not check the "create" flag that indicates block allocation. diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index a54fac2..e2cb920 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -368,6 +368,7 @@ struct f2fs_sb_info { struct f2fs_sm_info *sm_info; /* segment manager */ /* for bio operations */ + struct f2fs_bio_info read_io; /* for read bios */ struct f2fs_bio_info write_io[NR_PAGE_TYPE]; /* for write bios */ /* for checkpoint */ @@ -1118,6 +1119,8 @@ struct page *find_data_page(struct inode *, pgoff_t, bool); struct page *get_lock_data_page(struct inode *, pgoff_t); struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool); int f2fs_readpage(struct f2fs_sb_info *, struct page *, block_t, int); +void f2fs_submit_read_bio(struct f2fs_sb_info *, int); +void submit_read_page(struct f2fs_sb_info *, struct page *, block_t, int); int do_write_data_page(struct page *); /* diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 344fb86..6d78fff 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -876,6 +876,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) sbi->por_doing = false; spin_lock_init(&sbi->stat_lock); + mutex_init(&sbi->read_io.io_mutex); for (i = 0; i < NR_PAGE_TYPE; i++) mutex_init(&sbi->write_io[i].io_mutex); -- 1.7.9.5