Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel…

…/git/tytso/ext4 * 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: ext4: Remove automatic enabling of the HUGE_FILE feature flag ext4: Replace hackish ext4_mb_poll_new_transaction with commit callback ext4: Update Documentation/filesystems/ext4.txt ext4: Remove unused mount options: nomballoc, mballoc, nocheck ext4: Remove compile warnings when building w/o CONFIG_PROC_FS ext4: Add missing newlines to printk messages ext4: Fix file fragmentation during large file write. vfs: Add no_nrwrite_index_update writeback control flag vfs: Remove the range_cont writeback mode. ext4: Use tag dirty lookup during mpage_da_submit_io ext4: let the block device know when unused blocks can be discarded ext4: Don't reuse released data blocks until transaction commits ext4: Use an rbtree for tracking blocks freed during transaction. ext4: Do mballoc init before doing filesystem recovery ext4: Free ext4_prealloc_space using kmem_cache_free ext4: Fix Kconfig typo for ext4dev ext4: Remove an old reference to ext4dev in Makefile comment
mariux64 · Oct 17, 2008 · 58617d5 · 58617d5
2 parents 26e9a39 + f287a1a
commit 58617d5
Show file tree

Hide file tree

Showing 15 changed files with 320 additions and 336 deletions.
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
@@ -2,19 +2,24 @@
 Ext4 Filesystem
 ===============
 
-This is a development version of the ext4 filesystem, an advanced level
-of the ext3 filesystem which incorporates scalability and reliability
-enhancements for supporting large filesystems (64 bit) in keeping with
-increasing disk capacities and state-of-the-art feature requirements.
+Ext4 is an an advanced level of the ext3 filesystem which incorporates
+scalability and reliability enhancements for supporting large filesystems
+(64 bit) in keeping with increasing disk capacities and state-of-the-art
+feature requirements.
 
-Mailing list: linux-ext4@vger.kernel.org
+Mailing list:	linux-ext4@vger.kernel.org
+Web site:	http://ext4.wiki.kernel.org
 
 
 1. Quick usage instructions:
 ===========================
 
+Note: More extensive information for getting started with ext4 can be
+      found at the ext4 wiki site at the URL:
+      http://ext4.wiki.kernel.org/index.php/Ext4_Howto
+
   - Compile and install the latest version of e2fsprogs (as of this
-    writing version 1.41) from:
+    writing version 1.41.3) from:
 
     http://sourceforge.net/project/showfiles.php?group_id=2406
 
@@ -36,11 +41,9 @@ Mailing list: linux-ext4@vger.kernel.org
 
     	# mke2fs -t ext4 /dev/hda1
 
-    Or configure an existing ext3 filesystem to support extents and set
-    the test_fs flag to indicate that it's ok for an in-development
-    filesystem to touch this filesystem:
+    Or to configure an existing ext3 filesystem to support extents: 
 
-	# tune2fs -O extents -E test_fs /dev/hda1
+	# tune2fs -O extents /dev/hda1
 
     If the filesystem was created with 128 byte inodes, it can be
     converted to use 256 byte for greater efficiency via:
@@ -104,8 +107,8 @@ exist yet so I'm not sure they're in the near-term roadmap.
 The big performance win will come with mballoc, delalloc and flex_bg
 grouping of bitmaps and inode tables.  Some test results available here:
 
- - http://www.bullopensource.org/ext4/20080530/ffsb-write-2.6.26-rc2.html
- - http://www.bullopensource.org/ext4/20080530/ffsb-readwrite-2.6.26-rc2.html
+ - http://www.bullopensource.org/ext4/20080818-ffsb/ffsb-write-2.6.27-rc1.html
+ - http://www.bullopensource.org/ext4/20080818-ffsb/ffsb-readwrite-2.6.27-rc1.html
 
 3. Options
 ==========
@@ -214,9 +217,6 @@ noreservation
 bsddf		(*)	Make 'df' act like BSD.
 minixdf			Make 'df' act like Minix.
 
-check=none		Don't do extra checking of bitmaps on mount.
-nocheck
-
 debug			Extra debugging information is sent to syslog.
 
 errors=remount-ro(*)	Remount the filesystem read-only on an error.
@@ -253,8 +253,6 @@ nobh			(a) cache disk block mapping information
 			"nobh" option tries to avoid associating buffer
 			heads (supported only for "writeback" mode).
 
-mballoc		(*)	Use the multiple block allocator for block allocation
-nomballoc		disabled multiple block allocator for block allocation.
 stripe=n		Number of filesystem blocks that mballoc will try
 			to use for allocation size and alignment. For RAID5/6
 			systems this should be the number of data

diff --git a/fs/Kconfig b/fs/Kconfig
@@ -160,7 +160,7 @@ config EXT4_FS
 	  filesystem initially.
 
 	  To compile this file system support as a module, choose M here. The
-	  module will be called ext4dev.
+	  module will be called ext4.
 
 	  If unsure, say N.
 

diff --git a/fs/Makefile b/fs/Makefile
@@ -71,7 +71,7 @@ obj-$(CONFIG_DLM)		+= dlm/
 # Do not add any filesystems before this line
 obj-$(CONFIG_REISERFS_FS)	+= reiserfs/
 obj-$(CONFIG_EXT3_FS)		+= ext3/ # Before ext2 so root fs can be ext3
-obj-$(CONFIG_EXT4_FS)		+= ext4/ # Before ext2 so root fs can be ext4dev
+obj-$(CONFIG_EXT4_FS)		+= ext4/ # Before ext2 so root fs can be ext4
 obj-$(CONFIG_JBD)		+= jbd/
 obj-$(CONFIG_JBD2)		+= jbd2/
 obj-$(CONFIG_EXT2_FS)		+= ext2/

diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
@@ -568,8 +568,16 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 
 	/* this isn't the right place to decide whether block is metadata
 	 * inode.c/extents.c knows better, but for safety ... */
-	if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode) ||
-			ext4_should_journal_data(inode))
+	if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+		metadata = 1;
+
+	/* We need to make sure we don't reuse
+	 * block released untill the transaction commit.
+	 * writeback mode have weak data consistency so
+	 * don't force data as metadata when freeing block
+	 * for writeback mode.
+	 */
+	if (metadata == 0 && !ext4_should_writeback_data(inode))
 		metadata = 1;
 
 	sb = inode->i_sb;

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
@@ -511,7 +511,6 @@ do {									       \
 /*
  * Mount flags
  */
-#define EXT4_MOUNT_CHECK		0x00001	/* Do mount-time checks */
 #define EXT4_MOUNT_OLDALLOC		0x00002  /* Don't use the new Orlov allocator */
 #define EXT4_MOUNT_GRPID		0x00004	/* Create files with directory's group */
 #define EXT4_MOUNT_DEBUG		0x00008	/* Some debugging messages */

diff --git a/fs/ext4/ext4_sb.h b/fs/ext4/ext4_sb.h
@@ -99,9 +99,6 @@ struct ext4_sb_info {
 	struct inode *s_buddy_cache;
 	long s_blocks_reserved;
 	spinlock_t s_reserve_lock;
-	struct list_head s_active_transaction;
-	struct list_head s_closed_transaction;
-	struct list_head s_committed_transaction;
 	spinlock_t s_md_lock;
 	tid_t s_last_transaction;
 	unsigned short *s_mb_offsets, *s_mb_maxs;

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
@@ -1648,27 +1648,38 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd)
 	int ret = 0, err, nr_pages, i;
 	unsigned long index, end;
 	struct pagevec pvec;
+	long pages_skipped;
 
 	BUG_ON(mpd->next_page <= mpd->first_page);
 	pagevec_init(&pvec, 0);
 	index = mpd->first_page;
 	end = mpd->next_page - 1;
 
 	while (index <= end) {
-		/* XXX: optimize tail */
-		nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE);
+		/*
+		 * We can use PAGECACHE_TAG_DIRTY lookup here because
+		 * even though we have cleared the dirty flag on the page
+		 * We still keep the page in the radix tree with tag
+		 * PAGECACHE_TAG_DIRTY. See clear_page_dirty_for_io.
+		 * The PAGECACHE_TAG_DIRTY is cleared in set_page_writeback
+		 * which is called via the below writepage callback.
+		 */
+		nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
+					PAGECACHE_TAG_DIRTY,
+					min(end - index,
+					(pgoff_t)PAGEVEC_SIZE-1) + 1);
 		if (nr_pages == 0)
 			break;
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 
-			index = page->index;
-			if (index > end)
-				break;
-			index++;
-
+			pages_skipped = mpd->wbc->pages_skipped;
 			err = mapping->a_ops->writepage(page, mpd->wbc);
-			if (!err)
+			if (!err && (pages_skipped == mpd->wbc->pages_skipped))
+				/*
+				 * have successfully written the page
+				 * without skipping the same
+				 */
 				mpd->pages_written++;
 			/*
 			 * In error case, we have to continue because
@@ -2104,7 +2115,6 @@ static int mpage_da_writepages(struct address_space *mapping,
 			       struct writeback_control *wbc,
 			       struct mpage_da_data *mpd)
 {
-	long to_write;
 	int ret;
 
 	if (!mpd->get_block)
@@ -2119,19 +2129,18 @@ static int mpage_da_writepages(struct address_space *mapping,
 	mpd->pages_written = 0;
 	mpd->retval = 0;
 
-	to_write = wbc->nr_to_write;
-
 	ret = write_cache_pages(mapping, wbc, __mpage_da_writepage, mpd);
-
 	/*
 	 * Handle last extent of pages
 	 */
 	if (!mpd->io_done && mpd->next_page != mpd->first_page) {
 		if (mpage_da_map_blocks(mpd) == 0)
 			mpage_da_submit_io(mpd);
-	}
 
-	wbc->nr_to_write = to_write - mpd->pages_written;
+		mpd->io_done = 1;
+		ret = MPAGE_DA_EXTENT_TAIL;
+	}
+	wbc->nr_to_write -= mpd->pages_written;
 	return ret;
 }
 
@@ -2360,12 +2369,14 @@ static int ext4_da_writepages_trans_blocks(struct inode *inode)
 static int ext4_da_writepages(struct address_space *mapping,
 			      struct writeback_control *wbc)
 {
+	pgoff_t	index;
+	int range_whole = 0;
 	handle_t *handle = NULL;
-	loff_t range_start = 0;
 	struct mpage_da_data mpd;
 	struct inode *inode = mapping->host;
+	int no_nrwrite_index_update;
+	long pages_written = 0, pages_skipped;
 	int needed_blocks, ret = 0, nr_to_writebump = 0;
-	long to_write, pages_skipped = 0;
 	struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
 
 	/*
@@ -2385,23 +2396,26 @@ static int ext4_da_writepages(struct address_space *mapping,
 		nr_to_writebump = sbi->s_mb_stream_request - wbc->nr_to_write;
 		wbc->nr_to_write = sbi->s_mb_stream_request;
 	}
+	if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
+		range_whole = 1;
 
-	if (!wbc->range_cyclic)
-		/*
-		 * If range_cyclic is not set force range_cont
-		 * and save the old writeback_index
-		 */
-		wbc->range_cont = 1;
-
-	range_start =  wbc->range_start;
-	pages_skipped = wbc->pages_skipped;
+	if (wbc->range_cyclic)
+		index = mapping->writeback_index;
+	else
+		index = wbc->range_start >> PAGE_CACHE_SHIFT;
 
 	mpd.wbc = wbc;
 	mpd.inode = mapping->host;
 
-restart_loop:
-	to_write = wbc->nr_to_write;
-	while (!ret && to_write > 0) {
+	/*
+	 * we don't want write_cache_pages to update
+	 * nr_to_write and writeback_index
+	 */
+	no_nrwrite_index_update = wbc->no_nrwrite_index_update;
+	wbc->no_nrwrite_index_update = 1;
+	pages_skipped = wbc->pages_skipped;
+
+	while (!ret && wbc->nr_to_write > 0) {
 
 		/*
 		 * we  insert one extent at a time. So we need
@@ -2422,48 +2436,53 @@ static int ext4_da_writepages(struct address_space *mapping,
 			dump_stack();
 			goto out_writepages;
 		}
-		to_write -= wbc->nr_to_write;
-
 		mpd.get_block = ext4_da_get_block_write;
 		ret = mpage_da_writepages(mapping, wbc, &mpd);
 
 		ext4_journal_stop(handle);
 
-		if (mpd.retval == -ENOSPC)
+		if (mpd.retval == -ENOSPC) {
+			/* commit the transaction which would
+			 * free blocks released in the transaction
+			 * and try again
+			 */
 			jbd2_journal_force_commit_nested(sbi->s_journal);
-
-		/* reset the retry count */
-		if (ret == MPAGE_DA_EXTENT_TAIL) {
+			wbc->pages_skipped = pages_skipped;
+			ret = 0;
+		} else if (ret == MPAGE_DA_EXTENT_TAIL) {
 			/*
 			 * got one extent now try with
 			 * rest of the pages
 			 */
-			to_write += wbc->nr_to_write;
+			pages_written += mpd.pages_written;
+			wbc->pages_skipped = pages_skipped;
 			ret = 0;
-		} else if (wbc->nr_to_write) {
+		} else if (wbc->nr_to_write)
 			/*
 			 * There is no more writeout needed
 			 * or we requested for a noblocking writeout
 			 * and we found the device congested
 			 */
-			to_write += wbc->nr_to_write;
 			break;
-		}
-		wbc->nr_to_write = to_write;
-	}
-
-	if (wbc->range_cont && (pages_skipped != wbc->pages_skipped)) {
-		/* We skipped pages in this loop */
-		wbc->range_start = range_start;
-		wbc->nr_to_write = to_write +
-				wbc->pages_skipped - pages_skipped;
-		wbc->pages_skipped = pages_skipped;
-		goto restart_loop;
 	}
+	if (pages_skipped != wbc->pages_skipped)
+		printk(KERN_EMERG "This should not happen leaving %s "
+				"with nr_to_write = %ld ret = %d\n",
+				__func__, wbc->nr_to_write, ret);
+
+	/* Update index */
+	index += pages_written;
+	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
+		/*
+		 * set the writeback_index so that range_cyclic
+		 * mode will write it back later
+		 */
+		mapping->writeback_index = index;
 
 out_writepages:
-	wbc->nr_to_write = to_write - nr_to_writebump;
-	wbc->range_start = range_start;
+	if (!no_nrwrite_index_update)
+		wbc->no_nrwrite_index_update = 0;
+	wbc->nr_to_write -= nr_to_writebump;
 	return ret;
 }
 
@@ -4175,7 +4194,6 @@ static int ext4_inode_blocks_set(handle_t *handle,
 	struct inode *inode = &(ei->vfs_inode);
 	u64 i_blocks = inode->i_blocks;
 	struct super_block *sb = inode->i_sb;
-	int err = 0;
 
 	if (i_blocks <= ~0U) {
 		/*
@@ -4185,36 +4203,27 @@ static int ext4_inode_blocks_set(handle_t *handle,
 		raw_inode->i_blocks_lo   = cpu_to_le32(i_blocks);
 		raw_inode->i_blocks_high = 0;
 		ei->i_flags &= ~EXT4_HUGE_FILE_FL;
-	} else if (i_blocks <= 0xffffffffffffULL) {
+		return 0;
+	}
+	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_HUGE_FILE))
+		return -EFBIG;
+
+	if (i_blocks <= 0xffffffffffffULL) {
 		/*
 		 * i_blocks can be represented in a 48 bit variable
 		 * as multiple of 512 bytes
 		 */
-		err = ext4_update_rocompat_feature(handle, sb,
-					    EXT4_FEATURE_RO_COMPAT_HUGE_FILE);
-		if (err)
-			goto  err_out;
-		/* i_block is stored in the split  48 bit fields */
 		raw_inode->i_blocks_lo   = cpu_to_le32(i_blocks);
 		raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32);
 		ei->i_flags &= ~EXT4_HUGE_FILE_FL;
 	} else {
-		/*
-		 * i_blocks should be represented in a 48 bit variable
-		 * as multiple of  file system block size
-		 */
-		err = ext4_update_rocompat_feature(handle, sb,
-					    EXT4_FEATURE_RO_COMPAT_HUGE_FILE);
-		if (err)
-			goto  err_out;
 		ei->i_flags |= EXT4_HUGE_FILE_FL;
 		/* i_block is stored in file system block size */
 		i_blocks = i_blocks >> (inode->i_blkbits - 9);
 		raw_inode->i_blocks_lo   = cpu_to_le32(i_blocks);
 		raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32);
 	}
-err_out:
-	return err;
+	return 0;
 }
 
 /*