Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755268AbYFXAb0 (ORCPT ); Mon, 23 Jun 2008 20:31:26 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751930AbYFXAbN (ORCPT ); Mon, 23 Jun 2008 20:31:13 -0400 Received: from e6.ny.us.ibm.com ([32.97.182.146]:59922 "EHLO e6.ny.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751822AbYFXAbL (ORCPT ); Mon, 23 Jun 2008 20:31:11 -0400 Subject: Re: Performance of ext4 From: Mingming To: "Aneesh Kumar K.V" Cc: Holger Kiehl , Theodore Tso , Eric Sandeen , Jan Kara , Solofo.Ramangalahy@bull.net, Nick Dokos , linux-ext4@vger.kernel.org, linux-kernel In-Reply-To: <20080623174508.GA7216@skywalker> References: <20080616175408.GF3279@atrey.karlin.mff.cuni.cz> <20080616181353.GA20686@skywalker> <20080619155645.GA8582@mit.edu> <485A8C2D.1090806@redhat.com> <20080619174211.GB9119@mit.edu> <20080620085922.GH9119@mit.edu> <20080623174508.GA7216@skywalker> Content-Type: text/plain Date: Mon, 23 Jun 2008 17:31:32 -0700 Message-Id: <1214267492.27507.285.camel@BVR-FS.beaverton.ibm.com> Mime-Version: 1.0 X-Mailer: Evolution 2.12.0 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 4507 Lines: 144 On Mon, 2008-06-23 at 23:15 +0530, Aneesh Kumar K.V wrote: > I found one place where we fail to update i_disksize. Can you try this > patch ? > > diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c > index 33f940b..9fa737f 100644 > --- a/fs/ext4/inode.c > +++ b/fs/ext4/inode.c > @@ -1620,7 +1620,10 @@ static int ext4_da_writepage(struct page *page, > loff_t size; > unsigned long len; > handle_t *handle = NULL; > + ext4_lblk_t block; > + loff_t disksize; > struct buffer_head *page_bufs; > + struct buffer_head *bh, *head; > struct inode *inode = page->mapping->host; > > handle = ext4_journal_current_handle(); > @@ -1662,6 +1665,38 @@ static int ext4_da_writepage(struct page *page, > else > ret = block_write_full_page(page, ext4_da_get_block_write, wbc); > > + if (ret) > + return ret; > + /* > + * When called via shrink_page_list and if we don't have any unmapped > + * buffer_head we still could have written some new content in an > + * already mapped buffer. That means we need to extent i_disksize here > + */ In this case(when extend the file without need block allocation), wouldn't make sense to update the i_disksize at write_end() time? So that the window of i_size different from i_disksize could be much smaller in this case. Something like below? (untested) Signed-off-by: Mingming Cao --- fs/ext4/inode.c | 66 ++++++++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 60 insertions(+), 6 deletions(-) Index: linux-2.6.26-rc6/fs/ext4/inode.c =================================================================== --- linux-2.6.26-rc6.orig/fs/ext4/inode.c 2008-06-23 17:28:01.000000000 -0700 +++ linux-2.6.26-rc6/fs/ext4/inode.c 2008-06-23 17:28:10.000000000 -0700 @@ -1573,6 +1573,65 @@ static int ext4_da_write_begin(struct fi return ret; } +static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh) +{ + return !buffer_mapped(bh) || buffer_delay(bh); +} + +static int ext4_da_write_end(struct file *file, + struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata) +{ + handle_t *handle = NULL; + struct inode *inode = mapping->host; + int needed_blocks = ext4_writepage_trans_blocks(inode); + unsigned from, to; + int ret = 0, ret2; + + from = pos & (PAGE_CACHE_SIZE - 1); + to = from + len; + + if (ret == 0) { + /* + * generic_write_end() will run mark_inode_dirty() if i_size + * changes. So let's piggyback the i_disksize mark_inode_dirty + * into that. + */ + loff_t new_i_size; + + new_i_size = pos + copied; + if (new_i_size > EXT4_I(inode)->i_disksize) + if (!walk_page_buffers(NULL, page_buffers(page), + 0, len, NULL, ext4_bh_unmapped_or_delay)){ + /* + * Updating i_disksize when extending file without + * need block allocation + */ + handle = ext4_journal_start(inode, needed_blocks); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + return ret; + } + if (ext4_should_order_data(inode)) + ret = ext4_jbd2_file_inode(handle, inode); + + EXT4_I(inode)->i_disksize = new_i_size; + } + ret2 = generic_write_end(file, mapping, pos, len, copied, + page, fsdata); + copied = ret2; + if (ret2 < 0) + ret = ret2; + } + if (handle) + ret2 = ext4_journal_stop(handle); + if (!ret) + ret = ret2; + + return ret ? ret : copied; +} + static void ext4_da_invalidatepage(struct page *page, unsigned long offset) { struct buffer_head *head, *bh; @@ -1682,11 +1741,6 @@ static int bput_one(handle_t *handle, st return 0; } -static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh) -{ - return !buffer_mapped(bh) || buffer_delay(bh); -} - /* * Note that we don't need to start a transaction unless we're journaling data * because we should have holes filled from ext4_page_mkwrite(). We even don't @@ -2050,7 +2104,7 @@ static const struct address_space_operat .writepages = ext4_da_writepages, .sync_page = block_sync_page, .write_begin = ext4_da_write_begin, - .write_end = generic_write_end, + .write_end = ext4_da_write_end, .bmap = ext4_bmap, .invalidatepage = ext4_da_invalidatepage, .releasepage = ext4_releasepage, -- 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/