Date:	Fri, 24 Sep 2010 17:35:59 +0200
From:	Lukas Czerner <lczerner@...hat.com>
To:	linux-ext4@...r.kernel.org
Cc:	tytso@....edu, rwheeler@...hat.com, sandeen@...hat.com,
	adilger@...ger.ca, lczerner@...hat.com, snitzer@...il.com
Subject: [PATCH 3/3] ext3: Add batched discard support

Walk through allocation groups and trim all free extents. It can be
invoked through FITRIM ioctl on the file system. The main idea is to
provide a way to trim the whole file system if needed, since some SSD's
may suffer from performance loss after the whole device was filled (it
does not mean that fs is full!).

It search for free extents in allocation groups specified by Byte range
start -> start+len. When the free extent is within this range, blocks are
marked as used and then trimmed. Afterwards these blocks are marked as
free in per-group bitmap.

Signed-off-by: Lukas Czerner <lczerner@...hat.com>
Reviewed-by: Jan Kara <jack@...e.cz>
Reviewed-by: Dmitry Monakhov <dmonakhov@...nvz.org>
---
 fs/ext3/balloc.c        |  251 +++++++++++++++++++++++++++++++++++++++++++++++
 fs/ext3/super.c         |    1 +
 include/linux/ext3_fs.h |    1 +
 3 files changed, 253 insertions(+), 0 deletions(-)

diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c
index 4a32511..25fbc2f 100644
--- a/fs/ext3/balloc.c
+++ b/fs/ext3/balloc.c
@@ -20,6 +20,7 @@
 #include <linux/ext3_jbd.h>
 #include <linux/quotaops.h>
 #include <linux/buffer_head.h>
+#include <linux/blkdev.h>
 
 /*
  * balloc.c contains the blocks allocation and deallocation routines
@@ -1882,3 +1883,253 @@ unsigned long ext3_bg_num_gdb(struct super_block *sb, int group)
 	return ext3_bg_num_gdb_meta(sb,group);
 
 }
+
+/**
+ * ext3_trim_all_free -- function to trim all free space in alloc. group
+ * @sb:			super block for file system
+ * @group:		allocation group to trim
+ * @start:		first group block to examine
+ * @max:		last group block to examine
+ * @gdp:		allocation group description structure
+ * @minblocks:		minimum extent block count
+ *
+ * ext3_trim_all_free walks through group's block bitmap searching for free
+ * blocks. When the free block is found, it tries to allocate this block and
+ * consequent free block to get the biggest free extent possible, until it
+ * reaches any used block. Then issue a TRIM command on this extent and free
+ * the extent in the block bitmap. This is done until whole group is scanned.
+ */
+ext3_grpblk_t ext3_trim_all_free(struct super_block *sb, unsigned int group,
+				ext3_grpblk_t start, ext3_grpblk_t max,
+				ext3_grpblk_t minblocks)
+{
+	handle_t *handle;
+	ext3_grpblk_t next, count = 0, bit;
+	struct ext3_sb_info *sbi;
+	ext3_fsblk_t discard_block;
+	struct buffer_head *bitmap_bh = NULL;
+	struct buffer_head *gdp_bh;
+	ext3_grpblk_t free_blocks;
+	struct ext3_group_desc *gdp;
+	int err = 0, ret = 0;
+	ext3_grpblk_t freed;
+
+	/*
+	 * We will update one block bitmap, and one group descriptor
+	 */
+	handle = ext3_journal_start_sb(sb, 2);
+	if (IS_ERR(handle)) {
+		err = PTR_ERR(handle);
+		return err;
+	}
+
+	bitmap_bh = read_block_bitmap(sb, group);
+	if (!bitmap_bh)
+		goto err_out;
+
+	BUFFER_TRACE(bitmap_bh, "getting undo access");
+	err = ext3_journal_get_undo_access(handle, bitmap_bh);
+	if (err)
+		goto err_out;
+
+	gdp = ext3_get_group_desc(sb, group, &gdp_bh);
+	if (!gdp)
+		goto err_out;
+
+	BUFFER_TRACE(gdp_bh, "get_write_access");
+	err = ext3_journal_get_write_access(handle, gdp_bh);
+	if (err)
+		goto err_out;
+
+	free_blocks = le16_to_cpu(gdp->bg_free_blocks_count);
+	sbi = EXT3_SB(sb);
+
+	 /* Walk through the whole group */
+	while (start < max) {
+
+		start = bitmap_search_next_usable_block(start, bitmap_bh, max);
+		if (start < 0)
+			break;
+		next = start;
+
+		/*
+		 * Allocate contiguous free extents by setting bits in the
+		 * block bitmap
+		 */
+		while (next < max
+			&& claim_block(sb_bgl_lock(sbi, group),
+					next, bitmap_bh)) {
+			next++;
+		}
+
+		 /* We did not claim any blocks */
+		if (next == start)
+			continue;
+
+		discard_block = (ext3_fsblk_t)start +
+				ext3_group_first_block_no(sb, group);
+
+		/* Update counters */
+		spin_lock(sb_bgl_lock(sbi, group));
+		le16_add_cpu(&gdp->bg_free_blocks_count, start - next);
+		spin_unlock(sb_bgl_lock(sbi, group));
+		percpu_counter_sub(&sbi->s_freeblocks_counter, next - start);
+
+		/* Do not issue a TRIM on extents smaller than minblocks */
+		if ((next - start) < minblocks)
+			goto free_extent;
+
+		 /* Send the TRIM command down to the device */
+		ret = sb_issue_discard(sb, discard_block, next - start,
+				       GFP_NOFS, 0);
+		count += (next - start);
+
+free_extent:
+		freed = 0;
+
+		/*
+		 * Clear bits in the bitmap
+		 */
+		for (bit = start; bit < next; bit++) {
+			BUFFER_TRACE(bitmap_bh, "clear bit");
+			if (!ext3_clear_bit_atomic(sb_bgl_lock(sbi, group),
+						bit, bitmap_bh->b_data)) {
+				ext3_error(sb, __func__,
+					"bit already cleared for block "E3FSBLK,
+					 (unsigned long)bit);
+				BUFFER_TRACE(bitmap_bh, "bit already cleared");
+			} else {
+				freed++;
+			}
+		}
+
+		/* Update couters */
+		spin_lock(sb_bgl_lock(sbi, group));
+		le16_add_cpu(&gdp->bg_free_blocks_count, freed);
+		spin_unlock(sb_bgl_lock(sbi, group));
+		percpu_counter_add(&sbi->s_freeblocks_counter, next - start);
+
+		start = next;
+
+		if (ret < 0) {
+			if (ret == -EOPNOTSUPP) {
+				ext3_warning(sb, __func__,
+					"discard not supported!");
+				count = ret;
+				break;
+			}
+			err = ret;
+			break;
+		}
+
+		if (fatal_signal_pending(current)) {
+			count = -ERESTARTSYS;
+			break;
+		}
+
+		cond_resched();
+
+		/* No more suitable extents */
+		if ((free_blocks - count) < minblocks)
+			break;
+	}
+
+	/* We dirtied the bitmap block */
+	BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
+	err = ext3_journal_dirty_metadata(handle, bitmap_bh);
+
+	/* And the group descriptor block */
+	BUFFER_TRACE(gdp_bh, "dirtied group descriptor block");
+	ret = ext3_journal_dirty_metadata(handle, gdp_bh);
+	if (!err)
+		err = ret;
+
+	ext3_debug("trimmed %d blocks in the group %d\n",
+		count, group);
+
+err_out:
+	if (err) {
+		ext3_std_error(sb, err);
+		count = err;
+	}
+
+	ext3_journal_stop(handle);
+	brelse(bitmap_bh);
+
+	return count;
+}
+
+/**
+ * ext3_trim_fs() -- trim ioctl handle function
+ * @sb:			superblock for filesystem
+ * @start:		First Byte to trim
+ * @len:		number of Bytes to trim from start
+ * @minlen:		minimum extent length in Bytes
+ *
+ * ext3_trim_fs goes through all allocation groups containing Bytes from
+ * start to start+len. For each such a group ext3_trim_all_free function
+ * is invoked to trim all free space.
+ */
+int ext3_trim_fs(struct super_block *sb, uint64_t start, uint64_t len,
+		uint64_t minlen)
+{
+	ext3_grpblk_t last_block, first_block, free_blocks;
+	unsigned long long first_group, last_group;
+	unsigned long group, ngroups;
+	struct ext3_group_desc *gdp;
+	struct ext3_super_block *es;
+	int ret = 0;
+
+	start >>= sb->s_blocksize_bits;
+	len >>= sb->s_blocksize_bits;
+	minlen >>= sb->s_blocksize_bits;
+
+	if (unlikely(minlen > EXT3_BLOCKS_PER_GROUP(sb)))
+		return -EINVAL;
+
+	es = EXT3_SB(sb)->s_es;
+	ngroups = EXT3_SB(sb)->s_groups_count;
+	smp_rmb();
+
+	/* Determine first and last group to examine based on start and len */
+	first_group = (start - le32_to_cpu(es->s_first_data_block)) /
+		      EXT3_BLOCKS_PER_GROUP(sb);
+	last_group = (start + len - le32_to_cpu(es->s_first_data_block)) /
+		     EXT3_BLOCKS_PER_GROUP(sb);
+	last_group = (last_group > ngroups - 1) ? ngroups - 1 : last_group;
+
+	if (first_group > last_group)
+		return -EINVAL;
+
+	first_block = (start - le32_to_cpu(es->s_first_data_block)) %
+			EXT3_BLOCKS_PER_GROUP(sb);
+	last_block = EXT3_BLOCKS_PER_GROUP(sb);
+
+	for (group = first_group; group <= last_group; group++) {
+
+		gdp = ext3_get_group_desc(sb, group, NULL);
+		if (!gdp)
+			break;
+
+		free_blocks = le16_to_cpu(gdp->bg_free_blocks_count);
+		if (free_blocks < minlen)
+			continue;
+
+		if (len >= EXT3_BLOCKS_PER_GROUP(sb))
+			len -= (EXT3_BLOCKS_PER_GROUP(sb) - first_block);
+		else
+			last_block = len;
+
+		ret = ext3_trim_all_free(sb, group, first_block,
+					last_block, minlen);
+		if (ret < 0)
+			break;
+
+		first_block = 0;
+	}
+
+	if (ret >= 0)
+		ret = 0;
+
+	return ret;
+}
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 5dbf4db..2e095db 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -782,6 +782,7 @@ static const struct super_operations ext3_sops = {
 	.quota_write	= ext3_quota_write,
 #endif
 	.bdev_try_to_free_page = bdev_try_to_free_page,
+	.trim_fs	= ext3_trim_fs,
 };
 
 static const struct export_operations ext3_export_ops = {
diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h
index 6ce1bca..07040dc 100644
--- a/include/linux/ext3_fs.h
+++ b/include/linux/ext3_fs.h
@@ -856,6 +856,7 @@ extern struct ext3_group_desc * ext3_get_group_desc(struct super_block * sb,
 extern int ext3_should_retry_alloc(struct super_block *sb, int *retries);
 extern void ext3_init_block_alloc_info(struct inode *);
 extern void ext3_rsv_window_add(struct super_block *sb, struct ext3_reserve_window_node *rsv);
+extern int ext3_trim_fs(struct super_block *sb, uint64_t *args);
 
 /* dir.c */
 extern int ext3_check_dir_entry(const char *, struct inode *,
-- 
1.7.2.3

--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Powered by blists - more mailing lists