Commit 677b9752 authored by Tao Ma's avatar Tao Ma Committed by Mark Fasheh

ocfs2: Add support for cross extent block

In ocfs2_merge_rec_left, when we find the merge extent is "CONTIG_RIGHT"
with the first extent record of the next extent block, we will merge it to
the next extent block and change all the related extent blocks accordingly.

In ocfs2_merge_rec_right, when we find the merge extent is "CONTIG_LEFT"
with the last extent record of the previous extent block, we will merge
it to the prevoius extent block and change all the related extent blocks
accordingly.

As for CONTIG_LEFTRIGHT, we will handle CONTIG_RIGHT first so that when
the index is zero, the merge process will be more efficient and easier.
Signed-off-by: default avatarTao Ma <tao.ma@oracle.com>
Signed-off-by: default avatarMark Fasheh <mfasheh@suse.com>
parent 52f7c21b
...@@ -1450,6 +1450,8 @@ static void ocfs2_adjust_root_records(struct ocfs2_extent_list *root_el, ...@@ -1450,6 +1450,8 @@ static void ocfs2_adjust_root_records(struct ocfs2_extent_list *root_el,
* - When our insert into the right path leaf is at the leftmost edge * - When our insert into the right path leaf is at the leftmost edge
* and requires an update of the path immediately to it's left. This * and requires an update of the path immediately to it's left. This
* can occur at the end of some types of rotation and appending inserts. * can occur at the end of some types of rotation and appending inserts.
* - When we've adjusted the last extent record in the left path leaf and the
* 1st extent record in the right path leaf during cross extent block merge.
*/ */
static void ocfs2_complete_edge_insert(struct inode *inode, handle_t *handle, static void ocfs2_complete_edge_insert(struct inode *inode, handle_t *handle,
struct ocfs2_path *left_path, struct ocfs2_path *left_path,
...@@ -2712,24 +2714,147 @@ static void ocfs2_cleanup_merge(struct ocfs2_extent_list *el, ...@@ -2712,24 +2714,147 @@ static void ocfs2_cleanup_merge(struct ocfs2_extent_list *el,
} }
} }
static int ocfs2_get_right_path(struct inode *inode,
struct ocfs2_path *left_path,
struct ocfs2_path **ret_right_path)
{
int ret;
u32 right_cpos;
struct ocfs2_path *right_path = NULL;
struct ocfs2_extent_list *left_el;
*ret_right_path = NULL;
/* This function shouldn't be called for non-trees. */
BUG_ON(left_path->p_tree_depth == 0);
left_el = path_leaf_el(left_path);
BUG_ON(left_el->l_next_free_rec != left_el->l_count);
ret = ocfs2_find_cpos_for_right_leaf(inode->i_sb, left_path,
&right_cpos);
if (ret) {
mlog_errno(ret);
goto out;
}
/* This function shouldn't be called for the rightmost leaf. */
BUG_ON(right_cpos == 0);
right_path = ocfs2_new_path(path_root_bh(left_path),
path_root_el(left_path));
if (!right_path) {
ret = -ENOMEM;
mlog_errno(ret);
goto out;
}
ret = ocfs2_find_path(inode, right_path, right_cpos);
if (ret) {
mlog_errno(ret);
goto out;
}
*ret_right_path = right_path;
out:
if (ret)
ocfs2_free_path(right_path);
return ret;
}
/* /*
* Remove split_rec clusters from the record at index and merge them * Remove split_rec clusters from the record at index and merge them
* onto the beginning of the record at index + 1. * onto the beginning of the record "next" to it.
* For index < l_count - 1, the next means the extent rec at index + 1.
* For index == l_count - 1, the "next" means the 1st extent rec of the
* next extent block.
*/ */
static int ocfs2_merge_rec_right(struct inode *inode, struct buffer_head *bh, static int ocfs2_merge_rec_right(struct inode *inode,
handle_t *handle, struct ocfs2_path *left_path,
struct ocfs2_extent_rec *split_rec, handle_t *handle,
struct ocfs2_extent_list *el, int index) struct ocfs2_extent_rec *split_rec,
int index)
{ {
int ret; int ret, next_free, i;
unsigned int split_clusters = le16_to_cpu(split_rec->e_leaf_clusters); unsigned int split_clusters = le16_to_cpu(split_rec->e_leaf_clusters);
struct ocfs2_extent_rec *left_rec; struct ocfs2_extent_rec *left_rec;
struct ocfs2_extent_rec *right_rec; struct ocfs2_extent_rec *right_rec;
struct ocfs2_extent_list *right_el;
struct ocfs2_path *right_path = NULL;
int subtree_index = 0;
struct ocfs2_extent_list *el = path_leaf_el(left_path);
struct buffer_head *bh = path_leaf_bh(left_path);
struct buffer_head *root_bh = NULL;
BUG_ON(index >= le16_to_cpu(el->l_next_free_rec)); BUG_ON(index >= le16_to_cpu(el->l_next_free_rec));
left_rec = &el->l_recs[index]; left_rec = &el->l_recs[index];
right_rec = &el->l_recs[index + 1];
if (index == le16_to_cpu(el->l_next_free_rec - 1) &&
le16_to_cpu(el->l_next_free_rec) == le16_to_cpu(el->l_count)) {
/* we meet with a cross extent block merge. */
ret = ocfs2_get_right_path(inode, left_path, &right_path);
if (ret) {
mlog_errno(ret);
goto out;
}
right_el = path_leaf_el(right_path);
next_free = le16_to_cpu(right_el->l_next_free_rec);
BUG_ON(next_free <= 0);
right_rec = &right_el->l_recs[0];
if (ocfs2_is_empty_extent(right_rec)) {
BUG_ON(le16_to_cpu(next_free) <= 1);
right_rec = &right_el->l_recs[1];
}
BUG_ON(le32_to_cpu(left_rec->e_cpos) +
le16_to_cpu(left_rec->e_leaf_clusters) !=
le32_to_cpu(right_rec->e_cpos));
subtree_index = ocfs2_find_subtree_root(inode,
left_path, right_path);
ret = ocfs2_extend_rotate_transaction(handle, subtree_index,
handle->h_buffer_credits,
right_path);
if (ret) {
mlog_errno(ret);
goto out;
}
root_bh = left_path->p_node[subtree_index].bh;
BUG_ON(root_bh != right_path->p_node[subtree_index].bh);
ret = ocfs2_journal_access(handle, inode, root_bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (ret) {
mlog_errno(ret);
goto out;
}
for (i = subtree_index + 1;
i < path_num_items(right_path); i++) {
ret = ocfs2_journal_access(handle, inode,
right_path->p_node[i].bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (ret) {
mlog_errno(ret);
goto out;
}
ret = ocfs2_journal_access(handle, inode,
left_path->p_node[i].bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (ret) {
mlog_errno(ret);
goto out;
}
}
} else {
BUG_ON(index == le16_to_cpu(el->l_next_free_rec) - 1);
right_rec = &el->l_recs[index + 1];
}
ret = ocfs2_journal_access(handle, inode, bh, ret = ocfs2_journal_access(handle, inode, bh,
OCFS2_JOURNAL_ACCESS_WRITE); OCFS2_JOURNAL_ACCESS_WRITE);
...@@ -2751,30 +2876,156 @@ static int ocfs2_merge_rec_right(struct inode *inode, struct buffer_head *bh, ...@@ -2751,30 +2876,156 @@ static int ocfs2_merge_rec_right(struct inode *inode, struct buffer_head *bh,
if (ret) if (ret)
mlog_errno(ret); mlog_errno(ret);
if (right_path) {
ret = ocfs2_journal_dirty(handle, path_leaf_bh(right_path));
if (ret)
mlog_errno(ret);
ocfs2_complete_edge_insert(inode, handle, left_path,
right_path, subtree_index);
}
out:
if (right_path)
ocfs2_free_path(right_path);
return ret;
}
static int ocfs2_get_left_path(struct inode *inode,
struct ocfs2_path *right_path,
struct ocfs2_path **ret_left_path)
{
int ret;
u32 left_cpos;
struct ocfs2_path *left_path = NULL;
*ret_left_path = NULL;
/* This function shouldn't be called for non-trees. */
BUG_ON(right_path->p_tree_depth == 0);
ret = ocfs2_find_cpos_for_left_leaf(inode->i_sb,
right_path, &left_cpos);
if (ret) {
mlog_errno(ret);
goto out;
}
/* This function shouldn't be called for the leftmost leaf. */
BUG_ON(left_cpos == 0);
left_path = ocfs2_new_path(path_root_bh(right_path),
path_root_el(right_path));
if (!left_path) {
ret = -ENOMEM;
mlog_errno(ret);
goto out;
}
ret = ocfs2_find_path(inode, left_path, left_cpos);
if (ret) {
mlog_errno(ret);
goto out;
}
*ret_left_path = left_path;
out: out:
if (ret)
ocfs2_free_path(left_path);
return ret; return ret;
} }
/* /*
* Remove split_rec clusters from the record at index and merge them * Remove split_rec clusters from the record at index and merge them
* onto the tail of the record at index - 1. * onto the tail of the record "before" it.
* For index > 0, the "before" means the extent rec at index - 1.
*
* For index == 0, the "before" means the last record of the previous
* extent block. And there is also a situation that we may need to
* remove the rightmost leaf extent block in the right_path and change
* the right path to indicate the new rightmost path.
*/ */
static int ocfs2_merge_rec_left(struct inode *inode, struct buffer_head *bh, static int ocfs2_merge_rec_left(struct inode *inode,
struct ocfs2_path *right_path,
handle_t *handle, handle_t *handle,
struct ocfs2_extent_rec *split_rec, struct ocfs2_extent_rec *split_rec,
struct ocfs2_extent_list *el, int index) struct ocfs2_cached_dealloc_ctxt *dealloc,
int index)
{ {
int ret, has_empty_extent = 0; int ret, i, subtree_index = 0, has_empty_extent = 0;
unsigned int split_clusters = le16_to_cpu(split_rec->e_leaf_clusters); unsigned int split_clusters = le16_to_cpu(split_rec->e_leaf_clusters);
struct ocfs2_extent_rec *left_rec; struct ocfs2_extent_rec *left_rec;
struct ocfs2_extent_rec *right_rec; struct ocfs2_extent_rec *right_rec;
struct ocfs2_extent_list *el = path_leaf_el(right_path);
struct buffer_head *bh = path_leaf_bh(right_path);
struct buffer_head *root_bh = NULL;
struct ocfs2_path *left_path = NULL;
struct ocfs2_extent_list *left_el;
BUG_ON(index <= 0); BUG_ON(index < 0);
left_rec = &el->l_recs[index - 1];
right_rec = &el->l_recs[index]; right_rec = &el->l_recs[index];
if (ocfs2_is_empty_extent(&el->l_recs[0])) if (index == 0) {
has_empty_extent = 1; /* we meet with a cross extent block merge. */
ret = ocfs2_get_left_path(inode, right_path, &left_path);
if (ret) {
mlog_errno(ret);
goto out;
}
left_el = path_leaf_el(left_path);
BUG_ON(le16_to_cpu(left_el->l_next_free_rec) !=
le16_to_cpu(left_el->l_count));
left_rec = &left_el->l_recs[
le16_to_cpu(left_el->l_next_free_rec) - 1];
BUG_ON(le32_to_cpu(left_rec->e_cpos) +
le16_to_cpu(left_rec->e_leaf_clusters) !=
le32_to_cpu(split_rec->e_cpos));
subtree_index = ocfs2_find_subtree_root(inode,
left_path, right_path);
ret = ocfs2_extend_rotate_transaction(handle, subtree_index,
handle->h_buffer_credits,
left_path);
if (ret) {
mlog_errno(ret);
goto out;
}
root_bh = left_path->p_node[subtree_index].bh;
BUG_ON(root_bh != right_path->p_node[subtree_index].bh);
ret = ocfs2_journal_access(handle, inode, root_bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (ret) {
mlog_errno(ret);
goto out;
}
for (i = subtree_index + 1;
i < path_num_items(right_path); i++) {
ret = ocfs2_journal_access(handle, inode,
right_path->p_node[i].bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (ret) {
mlog_errno(ret);
goto out;
}
ret = ocfs2_journal_access(handle, inode,
left_path->p_node[i].bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (ret) {
mlog_errno(ret);
goto out;
}
}
} else {
left_rec = &el->l_recs[index - 1];
if (ocfs2_is_empty_extent(&el->l_recs[0]))
has_empty_extent = 1;
}
ret = ocfs2_journal_access(handle, inode, bh, ret = ocfs2_journal_access(handle, inode, bh,
OCFS2_JOURNAL_ACCESS_WRITE); OCFS2_JOURNAL_ACCESS_WRITE);
...@@ -2790,9 +3041,8 @@ static int ocfs2_merge_rec_left(struct inode *inode, struct buffer_head *bh, ...@@ -2790,9 +3041,8 @@ static int ocfs2_merge_rec_left(struct inode *inode, struct buffer_head *bh,
*left_rec = *split_rec; *left_rec = *split_rec;
has_empty_extent = 0; has_empty_extent = 0;
} else { } else
le16_add_cpu(&left_rec->e_leaf_clusters, split_clusters); le16_add_cpu(&left_rec->e_leaf_clusters, split_clusters);
}
le32_add_cpu(&right_rec->e_cpos, split_clusters); le32_add_cpu(&right_rec->e_cpos, split_clusters);
le64_add_cpu(&right_rec->e_blkno, le64_add_cpu(&right_rec->e_blkno,
...@@ -2805,13 +3055,44 @@ static int ocfs2_merge_rec_left(struct inode *inode, struct buffer_head *bh, ...@@ -2805,13 +3055,44 @@ static int ocfs2_merge_rec_left(struct inode *inode, struct buffer_head *bh,
if (ret) if (ret)
mlog_errno(ret); mlog_errno(ret);
if (left_path) {
ret = ocfs2_journal_dirty(handle, path_leaf_bh(left_path));
if (ret)
mlog_errno(ret);
/*
* In the situation that the right_rec is empty and the extent
* block is empty also, ocfs2_complete_edge_insert can't handle
* it and we need to delete the right extent block.
*/
if (le16_to_cpu(right_rec->e_leaf_clusters) == 0 &&
le16_to_cpu(el->l_next_free_rec) == 1) {
ret = ocfs2_remove_rightmost_path(inode, handle,
right_path, dealloc);
if (ret) {
mlog_errno(ret);
goto out;
}
/* Now the rightmost extent block has been deleted.
* So we use the new rightmost path.
*/
ocfs2_mv_path(right_path, left_path);
left_path = NULL;
} else
ocfs2_complete_edge_insert(inode, handle, left_path,
right_path, subtree_index);
}
out: out:
if (left_path)
ocfs2_free_path(left_path);
return ret; return ret;
} }
static int ocfs2_try_to_merge_extent(struct inode *inode, static int ocfs2_try_to_merge_extent(struct inode *inode,
handle_t *handle, handle_t *handle,
struct ocfs2_path *left_path, struct ocfs2_path *path,
int split_index, int split_index,
struct ocfs2_extent_rec *split_rec, struct ocfs2_extent_rec *split_rec,
struct ocfs2_cached_dealloc_ctxt *dealloc, struct ocfs2_cached_dealloc_ctxt *dealloc,
...@@ -2819,7 +3100,7 @@ static int ocfs2_try_to_merge_extent(struct inode *inode, ...@@ -2819,7 +3100,7 @@ static int ocfs2_try_to_merge_extent(struct inode *inode,
{ {
int ret = 0; int ret = 0;
struct ocfs2_extent_list *el = path_leaf_el(left_path); struct ocfs2_extent_list *el = path_leaf_el(path);
struct ocfs2_extent_rec *rec = &el->l_recs[split_index]; struct ocfs2_extent_rec *rec = &el->l_recs[split_index];
BUG_ON(ctxt->c_contig_type == CONTIG_NONE); BUG_ON(ctxt->c_contig_type == CONTIG_NONE);
...@@ -2832,7 +3113,7 @@ static int ocfs2_try_to_merge_extent(struct inode *inode, ...@@ -2832,7 +3113,7 @@ static int ocfs2_try_to_merge_extent(struct inode *inode,
* extents - having more than one in a leaf is * extents - having more than one in a leaf is
* illegal. * illegal.
*/ */
ret = ocfs2_rotate_tree_left(inode, handle, left_path, ret = ocfs2_rotate_tree_left(inode, handle, path,
dealloc); dealloc);
if (ret) { if (ret) {
mlog_errno(ret); mlog_errno(ret);
...@@ -2847,7 +3128,6 @@ static int ocfs2_try_to_merge_extent(struct inode *inode, ...@@ -2847,7 +3128,6 @@ static int ocfs2_try_to_merge_extent(struct inode *inode,
* Left-right contig implies this. * Left-right contig implies this.
*/ */
BUG_ON(!ctxt->c_split_covers_rec); BUG_ON(!ctxt->c_split_covers_rec);
BUG_ON(split_index == 0);
/* /*
* Since the leftright insert always covers the entire * Since the leftright insert always covers the entire
...@@ -2858,9 +3138,14 @@ static int ocfs2_try_to_merge_extent(struct inode *inode, ...@@ -2858,9 +3138,14 @@ static int ocfs2_try_to_merge_extent(struct inode *inode,
* Since the adding of an empty extent shifts * Since the adding of an empty extent shifts
* everything back to the right, there's no need to * everything back to the right, there's no need to
* update split_index here. * update split_index here.
*
* When the split_index is zero, we need to merge it to the
* prevoius extent block. It is more efficient and easier
* if we do merge_right first and merge_left later.
*/ */
ret = ocfs2_merge_rec_left(inode, path_leaf_bh(left_path), ret = ocfs2_merge_rec_right(inode, path,
handle, split_rec, el, split_index); handle, split_rec,
split_index);
if (ret) { if (ret) {
mlog_errno(ret); mlog_errno(ret);
goto out; goto out;
...@@ -2871,32 +3156,30 @@ static int ocfs2_try_to_merge_extent(struct inode *inode, ...@@ -2871,32 +3156,30 @@ static int ocfs2_try_to_merge_extent(struct inode *inode,
*/ */
BUG_ON(!ocfs2_is_empty_extent(&el->l_recs[0])); BUG_ON(!ocfs2_is_empty_extent(&el->l_recs[0]));
/* /* The merge left us with an empty extent, remove it. */
* The left merge left us with an empty extent, remove ret = ocfs2_rotate_tree_left(inode, handle, path, dealloc);
* it.
*/
ret = ocfs2_rotate_tree_left(inode, handle, left_path, dealloc);
if (ret) { if (ret) {
mlog_errno(ret); mlog_errno(ret);
goto out; goto out;
} }
split_index--;
rec = &el->l_recs[split_index]; rec = &el->l_recs[split_index];
/* /*
* Note that we don't pass split_rec here on purpose - * Note that we don't pass split_rec here on purpose -
* we've merged it into the left side. * we've merged it into the rec already.
*/ */
ret = ocfs2_merge_rec_right(inode, path_leaf_bh(left_path), ret = ocfs2_merge_rec_left(inode, path,
handle, rec, el, split_index); handle, rec,
dealloc,
split_index);
if (ret) { if (ret) {
mlog_errno(ret); mlog_errno(ret);
goto out; goto out;
} }
BUG_ON(!ocfs2_is_empty_extent(&el->l_recs[0])); ret = ocfs2_rotate_tree_left(inode, handle, path,
ret = ocfs2_rotate_tree_left(inode, handle, left_path,
dealloc); dealloc);
/* /*
* Error from this last rotate is not critical, so * Error from this last rotate is not critical, so
...@@ -2915,8 +3198,9 @@ static int ocfs2_try_to_merge_extent(struct inode *inode, ...@@ -2915,8 +3198,9 @@ static int ocfs2_try_to_merge_extent(struct inode *inode,
*/ */
if (ctxt->c_contig_type == CONTIG_RIGHT) { if (ctxt->c_contig_type == CONTIG_RIGHT) {
ret = ocfs2_merge_rec_left(inode, ret = ocfs2_merge_rec_left(inode,
path_leaf_bh(left_path), path,
handle, split_rec, el, handle, split_rec,
dealloc,
split_index); split_index);
if (ret) { if (ret) {
mlog_errno(ret); mlog_errno(ret);
...@@ -2924,8 +3208,8 @@ static int ocfs2_try_to_merge_extent(struct inode *inode, ...@@ -2924,8 +3208,8 @@ static int ocfs2_try_to_merge_extent(struct inode *inode,
} }
} else { } else {
ret = ocfs2_merge_rec_right(inode, ret = ocfs2_merge_rec_right(inode,
path_leaf_bh(left_path), path,
handle, split_rec, el, handle, split_rec,
split_index); split_index);
if (ret) { if (ret) {
mlog_errno(ret); mlog_errno(ret);
...@@ -2938,7 +3222,7 @@ static int ocfs2_try_to_merge_extent(struct inode *inode, ...@@ -2938,7 +3222,7 @@ static int ocfs2_try_to_merge_extent(struct inode *inode,
* The merge may have left an empty extent in * The merge may have left an empty extent in
* our leaf. Try to rotate it away. * our leaf. Try to rotate it away.
*/ */
ret = ocfs2_rotate_tree_left(inode, handle, left_path, ret = ocfs2_rotate_tree_left(inode, handle, path,
dealloc); dealloc);
if (ret) if (ret)
mlog_errno(ret); mlog_errno(ret);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment