Ocfs2: Online defragmentaion V3.

index b5f9160..19ebc5a 100644
@@ -3228,7 +3228,7 @@ static int ocfs2_make_clusters_writable(struct super_block *sb,
 					u32 num_clusters, unsigned int e_flags)
 {
 	int ret, delete, index, credits =  0;
-	u32 new_bit, new_len;
+	u32 new_bit, new_len, orig_num_clusters;
 	unsigned int set_len;
 	struct ocfs2_super *osb = OCFS2_SB(sb);
 	handle_t *handle;

@@ -3261,6 +3261,8 @@ static int ocfs2_make_clusters_writable(struct super_block *sb,
 		goto out;
 	}
 
+	orig_num_clusters = num_clusters;
+
 	while (num_clusters) {
 		ret = ocfs2_get_refcount_rec(ref_ci, context->ref_root_bh,
 					     p_cluster, num_clusters,

@@ -3348,7 +3350,8 @@ static int ocfs2_make_clusters_writable(struct super_block *sb,
 	 * in write-back mode.
 	 */
 	if (context->get_clusters == ocfs2_di_get_clusters) {
-		ret = ocfs2_cow_sync_writeback(sb, context, cpos, num_clusters);
+		ret = ocfs2_cow_sync_writeback(sb, context, cpos,
+					       orig_num_clusters);
 		if (ret)
 			mlog_errno(ret);
 	}

index 19ebc5a..bd4ca78 100644
@@ -66,7 +66,7 @@ struct ocfs2_cow_context {
 			    u32 *num_clusters,
 			    unsigned int *extent_flags);
 	int (*cow_duplicate_clusters)(handle_t *handle,
-				      struct ocfs2_cow_context *context,
+				      struct file *file,
 				      u32 cpos, u32 old_cluster,
 				      u32 new_cluster, u32 new_len);
 };

@@ -2922,20 +2922,21 @@ static int ocfs2_clear_cow_buffer(handle_t *handle, struct buffer_head *bh)
 	return 0;
 }
 
-static int ocfs2_duplicate_clusters_by_page(handle_t *handle,
-					    struct ocfs2_cow_context *context,
-					    u32 cpos, u32 old_cluster,
-					    u32 new_cluster, u32 new_len)
+int ocfs2_duplicate_clusters_by_page(handle_t *handle,
+				     struct file *file,
+				     u32 cpos, u32 old_cluster,
+				     u32 new_cluster, u32 new_len)
 {
 	int ret = 0, partial;
-	struct ocfs2_caching_info *ci = context->data_et.et_ci;
+	struct inode *inode = file->f_path.dentry->d_inode;
+	struct ocfs2_caching_info *ci = INODE_CACHE(inode);
 	struct super_block *sb = ocfs2_metadata_cache_get_super(ci);
 	u64 new_block = ocfs2_clusters_to_blocks(sb, new_cluster);
 	struct page *page;
 	pgoff_t page_index;
 	unsigned int from, to, readahead_pages;
 	loff_t offset, end, map_end;
-	struct address_space *mapping = context->inode->i_mapping;
+	struct address_space *mapping = inode->i_mapping;
 
 	mlog(0, "old_cluster %u, new %u, len %u at offset %u\n", old_cluster,
 	     new_cluster, new_len, cpos);

@@ -2949,8 +2950,8 @@ static int ocfs2_duplicate_clusters_by_page(handle_t *handle,
 	 * We only duplicate pages until we reach the page contains i_size - 1.
 	 * So trim 'end' to i_size.
 	 */
-	if (end > i_size_read(context->inode))
-		end = i_size_read(context->inode);
+	if (end > i_size_read(inode))
+		end = i_size_read(inode);
 
 	while (offset < end) {
 		page_index = offset >> PAGE_CACHE_SHIFT;

@@ -2973,10 +2974,9 @@ static int ocfs2_duplicate_clusters_by_page(handle_t *handle,
 		if (PAGE_CACHE_SIZE <= OCFS2_SB(sb)->s_clustersize)
 			BUG_ON(PageDirty(page));
 
-		if (PageReadahead(page) && context->file) {
+		if (PageReadahead(page) && file) {
 			page_cache_async_readahead(mapping,
-						   &context->file->f_ra,
-						   context->file,
+						   &file->f_ra, file,
 						   page, page_index,
 						   readahead_pages);
 		}

@@ -3000,8 +3000,7 @@ static int ocfs2_duplicate_clusters_by_page(handle_t *handle,
 			}
 		}
 
-		ocfs2_map_and_dirty_page(context->inode,
-					 handle, from, to,
+		ocfs2_map_and_dirty_page(inode, handle, from, to,
 					 page, 0, &new_block);
 		mark_page_accessed(page);
 unlock:

@@ -3016,14 +3015,15 @@ unlock:
 	return ret;
 }
 
-static int ocfs2_duplicate_clusters_by_jbd(handle_t *handle,
-					   struct ocfs2_cow_context *context,
-					   u32 cpos, u32 old_cluster,
-					   u32 new_cluster, u32 new_len)
+int ocfs2_duplicate_clusters_by_jbd(handle_t *handle,
+				    struct file *file,
+				    u32 cpos, u32 old_cluster,
+				    u32 new_cluster, u32 new_len)
 {
 	int ret = 0;
-	struct super_block *sb = context->inode->i_sb;
-	struct ocfs2_caching_info *ci = context->data_et.et_ci;
+	struct inode *inode = file->f_path.dentry->d_inode;
+	struct super_block *sb = inode->i_sb;
+	struct ocfs2_caching_info *ci = INODE_CACHE(inode);
 	int i, blocks = ocfs2_clusters_to_blocks(sb, new_len);
 	u64 old_block = ocfs2_clusters_to_blocks(sb, old_cluster);
 	u64 new_block = ocfs2_clusters_to_blocks(sb, new_cluster);

@@ -3146,8 +3146,8 @@ static int ocfs2_replace_clusters(handle_t *handle,
 
 	/*If the old clusters is unwritten, no need to duplicate. */
 	if (!(ext_flags & OCFS2_EXT_UNWRITTEN)) {
-		ret = context->cow_duplicate_clusters(handle, context, cpos,
-						      old, new, len);
+		ret = context->cow_duplicate_clusters(handle, context->file,
+						      cpos, old, new, len);
 		if (ret) {
 			mlog_errno(ret);
 			goto out;

@@ -3163,22 +3163,22 @@ out:
 	return ret;
 }
 
-static int ocfs2_cow_sync_writeback(struct super_block *sb,
-				    struct ocfs2_cow_context *context,
-				    u32 cpos, u32 num_clusters)
+int ocfs2_cow_sync_writeback(struct super_block *sb,
+			     struct inode *inode,
+			     u32 cpos, u32 num_clusters)
 {
 	int ret = 0;
 	loff_t offset, end, map_end;
 	pgoff_t page_index;
 	struct page *page;
 
-	if (ocfs2_should_order_data(context->inode))
+	if (ocfs2_should_order_data(inode))
 		return 0;
 
 	offset = ((loff_t)cpos) << OCFS2_SB(sb)->s_clustersize_bits;
 	end = offset + (num_clusters << OCFS2_SB(sb)->s_clustersize_bits);
 
-	ret = filemap_fdatawrite_range(context->inode->i_mapping,
+	ret = filemap_fdatawrite_range(inode->i_mapping,
 				       offset, end - 1);
 	if (ret < 0) {
 		mlog_errno(ret);

@@ -3191,7 +3191,7 @@ static int ocfs2_cow_sync_writeback(struct super_block *sb,
 		if (map_end > end)
 			map_end = end;
 
-		page = find_or_create_page(context->inode->i_mapping,
+		page = find_or_create_page(inode->i_mapping,
 					   page_index, GFP_NOFS);
 		BUG_ON(!page);
 

@@ -3350,7 +3350,7 @@ static int ocfs2_make_clusters_writable(struct super_block *sb,
 	 * in write-back mode.
 	 */
 	if (context->get_clusters == ocfs2_di_get_clusters) {
-		ret = ocfs2_cow_sync_writeback(sb, context, cpos,
+		ret = ocfs2_cow_sync_writeback(sb, context->inode, cpos,
 					       orig_num_clusters);
 		if (ret)
 			mlog_errno(ret);

index c8ce46f..7754608 100644
@@ -84,6 +84,17 @@ int ocfs2_refcount_cow_xattr(struct inode *inode,
 			     struct buffer_head *ref_root_bh,
 			     u32 cpos, u32 write_len,
 			     struct ocfs2_post_refcount *post);
+int ocfs2_duplicate_clusters_by_page(handle_t *handle,
+				     struct file *file,
+				     u32 cpos, u32 old_cluster,
+				     u32 new_cluster, u32 new_len);
+int ocfs2_duplicate_clusters_by_jbd(handle_t *handle,
+				    struct file *file,
+				    u32 cpos, u32 old_cluster,
+				    u32 new_cluster, u32 new_len);
+int ocfs2_cow_sync_writeback(struct super_block *sb,
+			     struct inode *inode,
+			     u32 cpos, u32 num_clusters);
 int ocfs2_add_refcount_flag(struct inode *inode,
 			    struct ocfs2_extent_tree *data_et,
 			    struct ocfs2_caching_info *ref_ci,

index b46f39b..f2be820 100644
@@ -171,4 +171,33 @@ enum ocfs2_info_type {
 
 #define OCFS2_IOC_INFO		_IOR('o', 5, struct ocfs2_info)
 
+struct ocfs2_move_extents {
+/* All values are in bytes */
+	/* in */
+	__u64 me_start;		/* Virtual start in the file to move */
+	__u64 me_len;		/* Length of the extents to be moved */
+	__u64 me_goal;		/* Physical offset of the goal,
+				   it's in block unit */
+	__u64 me_thresh;	/* Maximum distance from goal or threshold
+				   for auto defragmentation */
+	__u64 me_flags;		/* Flags for the operation:
+				 * - auto defragmentation.
+				 * - refcount,xattr cases.
+				 */
+	/* out */
+	__u64 me_moved_len;	/* Moved/defraged length */
+	__u64 me_new_offset;	/* Resulting physical location */
+	__u32 me_reserved[2];	/* Reserved for futhure */
+};
+
+#define OCFS2_MOVE_EXT_FL_AUTO_DEFRAG	(0x00000001)	/* Kernel manages to
+							   claim new clusters
+							   as the goal place
+							   for extents moving */
+#define OCFS2_MOVE_EXT_FL_COMPLETE	(0x00000002)	/* Move or defragmenation
+							   completely gets done.
+							 */
+
+#define OCFS2_IOC_MOVE_EXT	_IOW('o', 6, struct ocfs2_move_extents)
+
 #endif /* OCFS2_IOCTL_H */

index ea2ed9f..36f1cb2 100644
@@ -121,6 +121,7 @@
 #define ML_KTHREAD	0x0000000400000000ULL /* kernel thread activity */
 #define ML_RESERVATIONS	0x0000000800000000ULL /* ocfs2 alloc reservations */
 #define ML_CLUSTER	0x0000001000000000ULL /* cluster stack */
+#define ML_MOVE_EXT	0x0000002000000000ULL /* move extents */
 
 #define MLOG_INITIAL_AND_MASK (ML_ERROR|ML_NOTICE)
 #define MLOG_INITIAL_NOT_MASK (ML_ENTRY|ML_EXIT)

57 lines not on this page · raw message

new file mode 100644
index 0000000..eba4044
@@ -0,0 +1,20 @@
+/* -*- mode: c; c-basic-offset: 8; -*-
+ * vim: noexpandtab sw=8 ts=8 sts=0:
+ *
+ * move_extents.h
+ *
+ * Copyright (C) 2010 Oracle.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+#ifndef OCFS2_MOVE_EXTENTS_H
+#define OCFS2_MOVE_EXTENTS_H
+
+#endif /* OCFS2_MOVE_EXTENTS_H */

index b79c2d3..9b30636 100644
@@ -55,3 +55,64 @@ struct ocfs2_move_extents_context {
 	struct ocfs2_alloc_context *data_ac;
 	struct ocfs2_cached_dealloc_ctxt dealloc;
 };
+
+/*
+ * lock allocators, and reserving appropriate number of bits for
+ * meta blocks and data clusters.
+ *
+ * in some cases, we don't need to reserve clusters, just let data_ac
+ * be NULL.
+ */
+static int ocfs2_lock_allocators_move_extents(struct inode *inode,
+					struct ocfs2_extent_tree *et,
+					u32 clusters_to_move,
+					u32 extents_to_split,
+					struct ocfs2_alloc_context **meta_ac,
+					struct ocfs2_alloc_context **data_ac,
+					int extra_blocks,
+					int *credits)
+{
+	int ret, num_free_extents;
+	unsigned int max_recs_needed = 2 * extents_to_split + clusters_to_move;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+
+	num_free_extents = ocfs2_num_free_extents(osb, et);
+	if (num_free_extents < 0) {
+		ret = num_free_extents;
+		mlog_errno(ret);
+		goto out;
+	}
+
+	if (!num_free_extents ||
+	    (ocfs2_sparse_alloc(osb) && num_free_extents < max_recs_needed))
+		extra_blocks += ocfs2_extend_meta_needed(et->et_root_el);
+
+	ret = ocfs2_reserve_new_metadata_blocks(osb, extra_blocks, meta_ac);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	if (data_ac) {
+		ret = ocfs2_reserve_clusters(osb, clusters_to_move, data_ac);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+	}
+
+	*credits += ocfs2_calc_extend_credits(osb->sb, et->et_root_el,
+					      clusters_to_move + 2);
+
+	mlog(0, "reserve metadata_blocks: %d, data_clusters: %u, credits: %d\n",
+	     extra_blocks, clusters_to_move, *credits);
+out:
+	if (ret) {
+		if (*meta_ac) {
+			ocfs2_free_alloc_context(*meta_ac);
+			*meta_ac = NULL;
+		}
+	}
+
+	return ret;
+}

index 9b30636..e28bd7d 100644
@@ -56,6 +56,110 @@ struct ocfs2_move_extents_context {
 	struct ocfs2_cached_dealloc_ctxt dealloc;
 };
 
+static int __ocfs2_move_extent(handle_t *handle,
+			       struct ocfs2_move_extents_context *context,
+			       u32 cpos, u32 len, u32 p_cpos, u32 new_p_cpos,
+			       int ext_flags)
+{
+	int ret = 0, index;
+	struct inode *inode = context->inode;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct ocfs2_extent_rec *rec, replace_rec;
+	struct ocfs2_path *path = NULL;
+	struct ocfs2_extent_list *el;
+	u64 ino = ocfs2_metadata_cache_owner(context->et.et_ci);
+	u64 old_blkno = ocfs2_clusters_to_blocks(inode->i_sb, p_cpos);
+
+	ret = ocfs2_duplicate_clusters_by_page(handle, context->file, cpos,
+					       p_cpos, new_p_cpos, len);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	memset(&replace_rec, 0, sizeof(replace_rec));
+	replace_rec.e_cpos = cpu_to_le32(cpos);
+	replace_rec.e_leaf_clusters = cpu_to_le16(len);
+	replace_rec.e_blkno = cpu_to_le64(ocfs2_clusters_to_blocks(inode->i_sb,
+								   new_p_cpos));
+
+	path = ocfs2_new_path_from_et(&context->et);
+	if (!path) {
+		ret = -ENOMEM;
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = ocfs2_find_path(INODE_CACHE(inode), path, cpos);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	el = path_leaf_el(path);
+
+	index = ocfs2_search_extent_list(el, cpos);
+	if (index == -1 || index >= le16_to_cpu(el->l_next_free_rec)) {
+		ocfs2_error(inode->i_sb,
+			    "Inode %llu has an extent at cpos %u which can no "
+			    "longer be found.\n",
+			    (unsigned long long)ino, cpos);
+		ret = -EROFS;
+		goto out;
+	}
+
+	rec = &el->l_recs[index];
+
+	BUG_ON(ext_flags != rec->e_flags);
+	/*
+	 * after moving/defraging to new location, the extent is not going
+	 * to be refcounted anymore.
+	 */
+	if (ext_flags & OCFS2_EXT_REFCOUNTED)
+		replace_rec.e_flags = ext_flags & ~OCFS2_EXT_REFCOUNTED;
+	else
+		replace_rec.e_flags = ext_flags;
+
+	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode),
+				      context->et.et_root_bh,
+				      OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = ocfs2_split_extent(handle, &context->et, path, index,
+				 &replace_rec, context->meta_ac,
+				 &context->dealloc);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ocfs2_journal_dirty(handle, context->et.et_root_bh);
+
+	context->new_phys_cpos = new_p_cpos;
+
+	/*
+	 * need I to append truncate log for old clusters?
+	 */
+	if (old_blkno) {
+		if (ext_flags & OCFS2_EXT_REFCOUNTED)
+			ret = ocfs2_decrease_refcount(inode, handle,
+					ocfs2_blocks_to_clusters(osb->sb,
+								 old_blkno),
+					len, context->meta_ac,
+					&context->dealloc, 1);
+			
+		else
+			ret = ocfs2_truncate_log_append(osb, handle,
+							old_blkno, len);
+	}
+
+out:
+	return ret;
+}
+
 /*
  * lock allocators, and reserving appropriate number of bits for
  * meta blocks and data clusters.

index e28bd7d..071bb12 100644
@@ -220,3 +220,139 @@ out:
 
 	return ret;
 }
+
+/*
+ * Using one journal handle to guarantee the data consistency in case
+ * crash happens anywhere.
+ */
+static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context,
+			       u32 cpos, u32 phys_cpos, u32 len, int ext_flags)
+{
+	int ret, credits = 0, extra_blocks = 0;
+	handle_t *handle;
+	struct inode *inode = context->inode;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct inode *tl_inode = osb->osb_tl_inode;
+	struct ocfs2_refcount_tree *ref_tree = NULL;
+	u32 new_phys_cpos, new_len;
+	u64 phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, phys_cpos);
+
+	if ((ext_flags & OCFS2_EXT_REFCOUNTED) && len) {
+
+		BUG_ON(!(OCFS2_I(inode)->ip_dyn_features &
+			 OCFS2_HAS_REFCOUNT_FL));
+
+		BUG_ON(!context->refcount_loc);
+
+		ret = ocfs2_lock_refcount_tree(osb, context->refcount_loc, 1,
+					       &ref_tree, NULL);
+		if (ret) {
+			mlog_errno(ret);
+			return ret;
+		}
+		
+		ret = ocfs2_prepare_refcount_change_for_del(inode,
+							context->refcount_loc,
+							phys_blkno,
+							len,
+							&credits,
+							&extra_blocks);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+	}
+
+	ret = ocfs2_lock_allocators_move_extents(inode, &context->et, len, 1,
+						 &context->meta_ac,
+						 &context->data_ac,
+						 extra_blocks, &credits);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	/*
+	 * should be using allocation reservation strategy there?
+	 *
+	 * if (context->data_ac)
+	 *	context->data_ac->ac_resv = &OCFS2_I(inode)->ip_la_data_resv;
+	 */
+
+	mutex_lock(&tl_inode->i_mutex);
+
+	if (ocfs2_truncate_log_needs_flush(osb)) {
+		ret = __ocfs2_flush_truncate_log(osb);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto out_unlock_mutex;
+		}
+	}
+
+	handle = ocfs2_start_trans(osb, credits);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		mlog_errno(ret);
+		goto out_unlock_mutex;
+	}
+
+	ret = __ocfs2_claim_clusters(handle, context->data_ac, 1, len,
+				     &new_phys_cpos, &new_len);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_commit;
+	}
+
+	/*
+	 * we're not quite patient here to make multiple attempts for claiming
+	 * enough clusters, failure to claim clusters per-requested is not a
+	 * disaster though, it can only mean partial range of defragmentation
+	 * or extent movements gets gone, users anyway is able to have another
+	 * try as they wish anytime, since they're going to be returned a
+	 * '-ENOSPC' and completed length of this movement.
+	 */
+	if (new_len != len) {
+		mlog(0, "len_claimed: %u, len: %u\n", new_len, len);
+		context->range->me_flags &= ~OCFS2_MOVE_EXT_FL_COMPLETE;
+		ret = -ENOSPC;
+		goto out_commit;
+	}
+
+	mlog(0, "cpos: %u, phys_cpos: %u, new_phys_cpos: %u\n", cpos,
+	     phys_cpos, new_phys_cpos);
+
+	ret = __ocfs2_move_extent(handle, context, cpos, len, phys_cpos,
+				  new_phys_cpos, ext_flags);
+	if (ret)
+		mlog_errno(ret);
+
+	/*
+	 * Here we should write the new page out first if we are
+	 * in write-back mode.
+	 */
+	ret = ocfs2_cow_sync_writeback(inode->i_sb, context->inode, cpos, len);
+	if (ret)
+		mlog_errno(ret);
+
+out_commit:
+	ocfs2_commit_trans(osb, handle);
+
+out_unlock_mutex:
+	mutex_unlock(&tl_inode->i_mutex);
+
+	if (context->data_ac) {
+		ocfs2_free_alloc_context(context->data_ac);
+		context->data_ac = NULL;
+	}
+
+	if (context->meta_ac) {
+		ocfs2_free_alloc_context(context->meta_ac);
+		context->meta_ac = NULL;
+	}
+
+out:
+	if (ref_tree)
+		ocfs2_unlock_refcount_tree(osb, ref_tree, 1);
+
+	return ret;
+}

index 071bb12..2678605 100644
@@ -356,3 +356,107 @@ out:
 
 	return ret;
 }
+
+/*
+ * find the victim alloc group, where #blkno fits.
+ */
+static int ocfs2_find_victim_alloc_group(struct inode *inode,
+					 u64 vict_blkno,
+					 int type, int slot,
+					 int *vict_bit,
+					 struct buffer_head **ret_bh)
+{
+	int ret, i, blocks_per_unit = 1;
+	u64 blkno;
+	char namebuf[40];
+
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct buffer_head *ac_bh = NULL, *gd_bh = NULL;
+	struct ocfs2_chain_list *cl;
+	struct ocfs2_chain_rec *rec;
+	struct ocfs2_dinode *ac_dinode;
+	struct ocfs2_group_desc *bg;
+
+	ocfs2_sprintf_system_inode_name(namebuf, sizeof(namebuf), type, slot);
+	ret = ocfs2_lookup_ino_from_name(osb->sys_root_inode, namebuf,
+					 strlen(namebuf), &blkno);
+	if (ret) {
+		ret = -ENOENT;
+		goto out;
+	}
+
+	ret = ocfs2_read_blocks_sync(osb, blkno, 1, &ac_bh);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ac_dinode = (struct ocfs2_dinode *)ac_bh->b_data;
+	cl = &(ac_dinode->id2.i_chain);
+	rec = &(cl->cl_recs[0]);
+
+	if (type == GLOBAL_BITMAP_SYSTEM_INODE)
+		blocks_per_unit <<= (osb->s_clustersize_bits -
+						inode->i_sb->s_blocksize_bits);
+	/*
+	 * 'vict_blkno' was out of the valid range.
+	 */
+	if ((vict_blkno < le64_to_cpu(rec->c_blkno)) ||
+	    (vict_blkno >= (le32_to_cpu(ac_dinode->id1.bitmap1.i_total) *
+				blocks_per_unit))) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	for (i = 0; i < le16_to_cpu(cl->cl_next_free_rec); i++) {
+
+		rec = &(cl->cl_recs[i]);
+		if (!rec)
+			continue;
+
+		bg = NULL;
+
+		do {
+			if (!bg)
+				blkno = le64_to_cpu(rec->c_blkno);
+			else
+				blkno = le64_to_cpu(bg->bg_next_group);
+
+			if (gd_bh) {
+				brelse(gd_bh);
+				gd_bh = NULL;
+			}
+
+			ret = ocfs2_read_blocks_sync(osb, blkno, 1, &gd_bh);
+			if (ret) {
+				mlog_errno(ret);
+				goto out;
+			}
+
+			bg = (struct ocfs2_group_desc *)gd_bh->b_data;
+
+			if (vict_blkno < (le64_to_cpu(bg->bg_blkno) +
+						le16_to_cpu(bg->bg_bits))) {
+
+				*ret_bh = gd_bh;
+				*vict_bit = (vict_blkno - blkno) /
+							blocks_per_unit;
+				mlog(0, "find the victim group: #%llu, "
+				     "total_bits: %u, vict_bit: %u\n",
+				     blkno, le16_to_cpu(bg->bg_bits),
+				     *vict_bit);
+				goto out;
+			}
+
+		} while (le64_to_cpu(bg->bg_next_group));
+	}
+
+	ret = -EINVAL;
+out:
+	brelse(ac_bh);
+
+	/*
+	 * caller has to release the gd_bh properly.
+	 */
+	return ret;
+}

index 2678605..f4410e3 100644
@@ -460,3 +460,64 @@ out:
 	 */
 	return ret;
 }
+
+/*
+ * XXX: helper to validate and adjust moving goal.
+ */
+static int ocfs2_validate_and_adjust_move_goal(struct inode *inode,
+					       struct ocfs2_move_extents *range)
+{
+	int ret, goal_bit = 0;
+
+	struct buffer_head *gd_bh = NULL;
+	struct ocfs2_group_desc *bg;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	int c_to_b = 1 << (osb->s_clustersize_bits -
+					inode->i_sb->s_blocksize_bits);
+
+	/*
+	 * validate goal sits within global_bitmap, and return the victim
+	 * group desc
+	 */
+	ret = ocfs2_find_victim_alloc_group(inode, range->me_goal,
+					    GLOBAL_BITMAP_SYSTEM_INODE,
+					    OCFS2_INVALID_SLOT,
+					    &goal_bit, &gd_bh);
+	if (ret)
+		goto out;
+
+	bg = (struct ocfs2_group_desc *)gd_bh->b_data;
+
+	/*
+	 * make goal become cluster aligned.
+	 */
+	if (range->me_goal % c_to_b)
+		range->me_goal = range->me_goal / c_to_b * c_to_b;
+
+	/*
+	 * moving goal is not allowd to start with a group desc blok(#0 blk)
+	 * let's compromise to the latter cluster.
+	 */
+	if (range->me_goal == le64_to_cpu(bg->bg_blkno))
+		range->me_goal += c_to_b;
+
+	/*
+	 * movement is not gonna cross two groups.
+	 */
+	if ((le16_to_cpu(bg->bg_bits) - goal_bit) * osb->s_clustersize <
+								range->me_len) {
+		ret = -EINVAL;
+		goto out;
+	}
+	/*
+	 * more exact validations/adjustments will be performed later during
+	 * moving operation for each extent range.
+	 */
+	mlog(0, "extents get ready to be moved to #%llu block\n",
+	     range->me_goal);
+
+out:
+	brelse(gd_bh);
+
+	return ret;
+}

index f4410e3..61b2871 100644
@@ -521,3 +521,42 @@ out:
 
 	return ret;
 }
+
+static void ocfs2_probe_alloc_group(struct inode *inode, struct buffer_head *bh,
+				    int *goal_bit, u32 move_len, u32 max_hop,
+				    u32 *phys_cpos)
+{
+	int i, used, last_free_bits = 0, base_bit = *goal_bit;
+	struct ocfs2_group_desc *gd = (struct ocfs2_group_desc *)bh->b_data;
+	u32 base_cpos = ocfs2_blocks_to_clusters(inode->i_sb,
+						 le64_to_cpu(gd->bg_blkno));
+
+	for (i = base_bit; i < le16_to_cpu(gd->bg_bits); i++) {
+
+		used = ocfs2_test_bit(i, (unsigned long *)gd->bg_bitmap);
+		if (used) {
+			/*
+			 * we even tried searching the free chunk by jumping
+			 * a 'max_hop' distance, but still failed.
+			 */
+			if ((i - base_bit) > max_hop) {
+				*phys_cpos = 0;
+				break;
+			}
+
+			if (last_free_bits)
+				last_free_bits = 0;
+
+			continue;
+		} else
+			last_free_bits++;
+
+		if (last_free_bits == move_len) {
+			*goal_bit = i;
+			*phys_cpos = base_cpos + i;
+			break;
+		}
+	}
+
+	mlog(0, "found phys_cpos: %u to fit the wanted moving.\n", *phys_cpos);
+}

index 61b2871..2ee74cd 100644
@@ -560,3 +560,83 @@ static void ocfs2_probe_alloc_group(struct inode *inode, struct buffer_head *bh,
 
 	mlog(0, "found phys_cpos: %u to fit the wanted moving.\n", *phys_cpos);
 }
+
+static int ocfs2_alloc_dinode_update_counts(struct inode *inode,
+				       handle_t *handle,
+				       struct buffer_head *di_bh,
+				       u32 num_bits,
+				       u16 chain)
+{
+	int ret;
+	u32 tmp_used;
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *) di_bh->b_data;
+	struct ocfs2_chain_list *cl =
+				(struct ocfs2_chain_list *) &di->id2.i_chain;
+
+	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
+				      OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret < 0) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	tmp_used = le32_to_cpu(di->id1.bitmap1.i_used);
+	di->id1.bitmap1.i_used = cpu_to_le32(num_bits + tmp_used);
+	le32_add_cpu(&cl->cl_recs[chain].c_free, -num_bits);
+	ocfs2_journal_dirty(handle, di_bh);
+
+out:
+	return ret;
+}
+
+static inline int ocfs2_block_group_set_bits(handle_t *handle,
+					     struct inode *alloc_inode,
+					     struct ocfs2_group_desc *bg,
+					     struct buffer_head *group_bh,
+					     unsigned int bit_off,
+					     unsigned int num_bits)
+{
+	int status;
+	void *bitmap = bg->bg_bitmap;
+	int journal_type = OCFS2_JOURNAL_ACCESS_WRITE;
+
+	mlog_entry_void();
+
+	/* All callers get the descriptor via
+	 * ocfs2_read_group_descriptor().  Any corruption is a code bug. */
+	BUG_ON(!OCFS2_IS_VALID_GROUP_DESC(bg));
+	BUG_ON(le16_to_cpu(bg->bg_free_bits_count) < num_bits);
+
+	mlog(0, "block_group_set_bits: off = %u, num = %u\n", bit_off,
+	     num_bits);
+
+	if (ocfs2_is_cluster_bitmap(alloc_inode))
+		journal_type = OCFS2_JOURNAL_ACCESS_UNDO;
+
+	status = ocfs2_journal_access_gd(handle,
+					 INODE_CACHE(alloc_inode),
+					 group_bh,
+					 journal_type);
+	if (status < 0) {
+		mlog_errno(status);
+		goto bail;
+	}
+
+	le16_add_cpu(&bg->bg_free_bits_count, -num_bits);
+	if (le16_to_cpu(bg->bg_free_bits_count) > le16_to_cpu(bg->bg_bits)) {
+		ocfs2_error(alloc_inode->i_sb, "Group descriptor # %llu has bit"
+			    " count %u but claims %u are freed. num_bits %d",
+			    (unsigned long long)le64_to_cpu(bg->bg_blkno),
+			    le16_to_cpu(bg->bg_bits),
+			    le16_to_cpu(bg->bg_free_bits_count), num_bits);
+		return -EROFS;
+	}
+	while (num_bits--)
+		ocfs2_set_bit(bit_off++, bitmap);
+
+	ocfs2_journal_dirty(handle, group_bh);
+
+bail:
+	mlog_exit(status);
+	return status;
+}

index 2ee74cd..c2b7638 100644
@@ -640,3 +640,168 @@ bail:
 	mlog_exit(status);
 	return status;
 }
+
+static int ocfs2_move_extent(struct ocfs2_move_extents_context *context,
+			     u32 cpos, u32 phys_cpos, u32 *new_phys_cpos,
+			     u32 len, int ext_flags)
+{
+	int ret, credits = 0, extra_blocks = 0, goal_bit = 0;
+	handle_t *handle;
+	struct inode *inode = context->inode;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct inode *tl_inode = osb->osb_tl_inode;
+	struct inode *gb_inode = NULL;
+	struct buffer_head *gb_bh = NULL;
+	struct buffer_head *gd_bh = NULL;
+	struct ocfs2_group_desc *gd;
+	struct ocfs2_refcount_tree *ref_tree = NULL;
+	u32 move_max_hop = ocfs2_blocks_to_clusters(inode->i_sb,
+						    context->range->me_thresh);
+	u64 phys_blkno, new_phys_blkno;
+
+	phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, phys_cpos);
+
+	if ((ext_flags & OCFS2_EXT_REFCOUNTED) && len) {
+
+		BUG_ON(!(OCFS2_I(inode)->ip_dyn_features &
+			 OCFS2_HAS_REFCOUNT_FL));
+
+		BUG_ON(!context->refcount_loc);
+
+		ret = ocfs2_lock_refcount_tree(osb, context->refcount_loc, 1,
+					       &ref_tree, NULL);
+		if (ret) {
+			mlog_errno(ret);
+			return ret;
+		}
+		
+		ret = ocfs2_prepare_refcount_change_for_del(inode,
+							context->refcount_loc,
+							phys_blkno,
+							len,
+							&credits,
+							&extra_blocks);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+	}
+
+	ret = ocfs2_lock_allocators_move_extents(inode, &context->et, len, 1,
+						 &context->meta_ac,
+						 NULL, extra_blocks, &credits);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	/*
+	 * need to count 2 extra credits for global_bitmap inode and
+	 * group descriptor.
+	 */
+	credits += OCFS2_INODE_UPDATE_CREDITS + 1;
+
+	/*
+	 * ocfs2_move_extent() didn't reserve any clusters in lock_allocators()
+	 * logic, while we still need to lock the global_bitmap.
+	 */
+	gb_inode = ocfs2_get_system_file_inode(osb, GLOBAL_BITMAP_SYSTEM_INODE,
+					       OCFS2_INVALID_SLOT);
+	if (!gb_inode) {
+		mlog(ML_ERROR, "unable to get global_bitmap inode\n");
+		ret = -EIO;
+		goto out;
+	}
+
+	mutex_lock(&gb_inode->i_mutex);
+
+	ret = ocfs2_inode_lock(gb_inode, &gb_bh, 1);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_unlock_gb_mutex;
+	}
+
+	mutex_lock(&tl_inode->i_mutex);
+
+	handle = ocfs2_start_trans(osb, credits);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		mlog_errno(ret);
+		goto out_unlock_tl_inode;
+	}
+
+	new_phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, *new_phys_cpos);
+	ret = ocfs2_find_victim_alloc_group(inode, new_phys_blkno,
+					    GLOBAL_BITMAP_SYSTEM_INODE,
+					    OCFS2_INVALID_SLOT,
+					    &goal_bit, &gd_bh);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_commit;
+	}
+
+	/*
+	 * probe the victim cluster group to find a proper
+	 * region to fit wanted movement, it even will perfrom
+	 * a best-effort attempt by compromising to a threshold
+	 * around the goal.
+	 */
+	ocfs2_probe_alloc_group(inode, gd_bh, &goal_bit, len, move_max_hop,
+				new_phys_cpos);
+	if (!new_phys_cpos) {
+		ret = -ENOSPC;
+		goto out_commit;
+	}
+
+	ret = __ocfs2_move_extent(handle, context, cpos, len, phys_cpos,
+				  *new_phys_cpos, ext_flags);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_commit;
+	}
+
+	gd = (struct ocfs2_group_desc *)gd_bh->b_data;
+	ret = ocfs2_alloc_dinode_update_counts(gb_inode, handle, gb_bh, len,
+					       le16_to_cpu(gd->bg_chain));
+	if (ret) {
+		mlog_errno(ret);
+		goto out_commit;
+	}
+
+	ret = ocfs2_block_group_set_bits(handle, gb_inode, gd, gd_bh,
+					 goal_bit, len);
+	if (ret)
+		mlog_errno(ret);
+
+	/*
+	 * Here we should write the new page out first if we are
+	 * in write-back mode.
+	 */
+	ret = ocfs2_cow_sync_writeback(inode->i_sb, context->inode, cpos, len);
+	if (ret)
+		mlog_errno(ret);
+
+out_commit:
+	ocfs2_commit_trans(osb, handle);
+	brelse(gd_bh);
+
+out_unlock_tl_inode:
+	mutex_unlock(&tl_inode->i_mutex);
+
+	ocfs2_inode_unlock(gb_inode, 1);
+out_unlock_gb_mutex:
+	mutex_unlock(&gb_inode->i_mutex);
+	brelse(gb_bh);
+	iput(gb_inode);
+
+out:
+	if (context->meta_ac) {
+		ocfs2_free_alloc_context(context->meta_ac);
+		context->meta_ac = NULL;
+	}
+
+	if (ref_tree)
+		ocfs2_unlock_refcount_tree(osb, ref_tree, 1);
+
+	return ret;
+}

index c2b7638..bad4f15 100644
@@ -805,3 +805,33 @@ out:
 
 	return ret;
 }
+
+/*
+ * Helper to calculate the defraging length in one run according to threshold.
+ */
+static void ocfs2_calc_extent_defrag_len(u32 *alloc_size, u32 *len_defraged,
+					 u32 threshold, int *skip)
+{
+	if ((*alloc_size + *len_defraged) < threshold) {
+		/*
+		 * proceed defragmentation until we meet the thresh
+		 */
+		*len_defraged += *alloc_size;
+	} else if (*len_defraged == 0) {
+		/*
+		 * XXX: skip a large extent.
+		 */
+		*skip = 1;
+	} else {
+		/*
+		 * split this extent to coalesce with former pieces as
+		 * to reach the threshold.
+		 *
+		 * we're done here with one cycle of defragmentation
+		 * in a size of 'thresh', resetting 'len_defraged'
+		 * forces a new defragmentation.
+		 */
+		*alloc_size = threshold - *len_defraged;
+		*len_defraged = 0;
+	}
+}

index 7a48681..b8fe7a7 100644
@@ -23,6 +23,7 @@
 #include "ioctl.h"
 #include "resize.h"
 #include "refcounttree.h"
+#include "move_extents.h"
 
 #include <linux/ext2_fs.h>
 

@@ -523,6 +524,8 @@ long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 			return -EFAULT;
 
 		return ocfs2_info_handle(inode, &info, 0);
+	case OCFS2_IOC_MOVE_EXT:
+		return ocfs2_ioctl_move_extents(filp, (void __user *)arg);
 	default:
 		return -ENOTTY;
 	}

@@ -565,6 +568,8 @@ long ocfs2_compat_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 			return -EFAULT;
 
 		return ocfs2_info_handle(inode, &info, 1);
+	case OCFS2_IOC_MOVE_EXT:
+		break;
 	default:
 		return -ENOIOCTLCMD;
 	}

315 lines not on this page · raw message

index eba4044..d9f0f29 100644
@@ -17,4 +17,6 @@
 #ifndef OCFS2_MOVE_EXTENTS_H
 #define OCFS2_MOVE_EXTENTS_H
 
+int ocfs2_ioctl_move_extents(struct file *filp,  void __user *argp);
+
 #endif /* OCFS2_MOVE_EXTENTS_H */