[Ocfs2-devel] [PATCH 8/8] Ocfs2: move extents within a certain range.
Tristan Ye
tristan.ye at oracle.com
Tue Dec 28 03:40:48 PST 2010
The basic logic of moving extents for a file is pretty like punching-hole
sequence, walk the extents within the range as user specified, calculating
an appropriate len to defrag/move, then let ocfs2_defrag/move_extent() to
do the actual moving.
This func ends up setting 'OCFS2_MOVE_EXT_FL_COMPLETE' to userpace if operation
gets done successfully.
Signed-off-by: Tristan Ye <tristan.ye at oracle.com>
---
fs/ocfs2/move_extents.c | 169 +++++++++++++++++++++++++++++++++++++++++++++--
1 files changed, 164 insertions(+), 5 deletions(-)
diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index 02d4d01..b9bc1cf 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -446,6 +446,169 @@ 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;
+ }
+}
+
+static int __ocfs2_move_extents_range(struct buffer_head *di_bh,
+ struct ocfs2_move_extents_context *context)
+{
+ int ret, flags, do_defrag, skip = 0;
+ u32 cpos, phys_cpos, move_start, len_to_move, alloc_size;
+ u32 len_defraged = 0, defrag_thresh, new_phys_cpos = 0;
+
+ struct inode *inode = context->inode;
+ struct ocfs2_move_extents *range = context->range;
+ struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+
+ if ((inode->i_size == 0) || (range->me_len == 0))
+ return 0;
+
+ if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
+ return 0;
+
+ ocfs2_init_dinode_extent_tree(&context->et, INODE_CACHE(inode), di_bh);
+ ocfs2_init_dealloc_ctxt(&context->dealloc);
+
+ /*
+ * TO-DO XXX:
+ *
+ * - refcount tree.
+ * - xattr extents.
+ * - unwritten extents.
+ */
+
+ do_defrag = context->auto_defrag;
+
+ /*
+ * extents moving happens in unit of clusters, for the sake
+ * of simplicity, we may ignore two clusters where 'byte_start'
+ * and 'byte_start + len' were within.
+ */
+ move_start = ocfs2_clusters_for_bytes(osb->sb, range->me_start);
+ len_to_move = (range->me_start + range->me_len) >>
+ osb->s_clustersize_bits;
+ if (len_to_move >= move_start)
+ len_to_move -= move_start;
+ else
+ len_to_move = 0;
+
+ if (do_defrag)
+ defrag_thresh = range->me_thresh >> osb->s_clustersize_bits;
+ else
+ new_phys_cpos = ocfs2_clusters_for_bytes(osb->sb,
+ range->me_goal);
+
+ mlog(0, "Inode: %llu, start: %llu, len: %llu, cstart: %u, clen: %u, "
+ "thresh: %u\n",
+ (unsigned long long)OCFS2_I(inode)->ip_blkno,
+ (unsigned long long)range->me_start,
+ (unsigned long long)range->me_len,
+ move_start, len_to_move, defrag_thresh);
+
+ cpos = move_start;
+ while (len_to_move) {
+ ret = ocfs2_get_clusters(inode, cpos, &phys_cpos, &alloc_size,
+ &flags);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+
+ if (alloc_size > len_to_move)
+ alloc_size = len_to_move;
+
+ /*
+ * XXX: how to deal with a hole:
+ *
+ * - skip the hole of course
+ * - force a new defragmentation
+ */
+ if (!phys_cpos) {
+ if (do_defrag)
+ len_defraged = 0;
+
+ goto next;
+ }
+
+ if (do_defrag) {
+ ocfs2_calc_extent_defrag_len(&alloc_size, &len_defraged,
+ defrag_thresh, &skip);
+ /*
+ * skip large extents
+ */
+ if (skip) {
+ skip = 0;
+ goto next;
+ }
+
+ mlog(0, "#Defrag: cpos: %u, phys_cpos: %u, "
+ "alloc_size: %u, len_defraged: %u\n",
+ cpos, phys_cpos, alloc_size, len_defraged);
+
+ ret = ocfs2_defrag_extent(context, cpos, phys_cpos,
+ alloc_size, flags);
+ } else {
+ ret = ocfs2_move_extent(context, cpos, phys_cpos,
+ new_phys_cpos, alloc_size,
+ flags);
+
+ new_phys_cpos += alloc_size;
+ }
+
+ if (ret < 0) {
+ mlog_errno(ret);
+ goto out;
+ }
+
+ context->clusters_moved += alloc_size;
+next:
+ cpos += alloc_size;
+ len_to_move -= alloc_size;
+ }
+
+ range->me_flags |= OCFS2_MOVE_EXT_FL_COMPLETE;
+
+out:
+ range->me_moved_len = ocfs2_clusters_to_bytes(osb->sb,
+ context->clusters_moved);
+ /*
+ * also need to return 'me_new_offset' for none-defragmentation case
+ */
+
+ ocfs2_schedule_truncate_log_flush(osb, 1);
+ ocfs2_run_deallocs(osb, &context->dealloc);
+
+ return ret;
+}
+
+
static int ocfs2_move_extents(struct ocfs2_move_extents_context *context)
{
int status;
@@ -482,11 +645,7 @@ static int ocfs2_move_extents(struct ocfs2_move_extents_context *context)
*/
down_write(&OCFS2_I(inode)->ip_alloc_sem);
- /*
- * real extents moving codes will be fulfilled later.
- *
- * status = __ocfs2_move_extents_range(di_bh, context);
- */
+ status = __ocfs2_move_extents_range(di_bh, context);
up_write(&OCFS2_I(inode)->ip_alloc_sem);
if (status) {
--
1.5.5
More information about the Ocfs2-devel
mailing list