ext4: journal credits reservation fixes for extent file writepage

This patch modified the writepage/write_begin credit calculation for
extent files, to use the credits caculation helper function.

The current calculation of how many index/leaf blocks should be
accounted is too conservetive, it always considered the worse case,
where the tree level is 5, and in the case of multiple chunk
allocations, it always assumed no blocks were dirtied in common across
the allocations. This path uses the accurate depth of the inode with
some extras to calculate the index blocks, and also less conservative in
the case of multiple allocation accounting.

Signed-off-by: Mingming Cao <cmm@us.ibm.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

3 files changed, 49 insertions, 62 deletions

diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index 6c166c0a54b7..d33dc56d6986 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -216,7 +216,9 @@ extern int ext4_ext_calc_metadata_amount(struct inode *inode, int blocks);
 extern ext4_fsblk_t idx_pblock(struct ext4_extent_idx *);
 extern void ext4_ext_store_pblock(struct ext4_extent *, ext4_fsblk_t);
 extern int ext4_extent_tree_init(handle_t *, struct inode *);
-extern int ext4_ext_calc_credits_for_insert(struct inode *, struct ext4_ext_path *);
+extern int ext4_ext_calc_credits_for_single_extent(struct inode *inode,
+                                                   int num,
+                                                   struct ext4_ext_path *path);
 extern int ext4_ext_try_to_merge(struct inode *inode,
                                  struct ext4_ext_path *path,
                                  struct ext4_extent *);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 7212947a8ca3..5c5dd3a1d657 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -1747,54 +1747,61 @@ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
 }
 
 /*
- * ext4_ext_calc_credits_for_insert:
- * This routine returns max. credits that the extent tree can consume.
- * It should be OK for low-performance paths like ->writepage()
- * To allow many writing processes to fit into a single transaction,
- * the caller should calculate credits under i_data_sem and
- * pass the actual path.
+ * ext4_ext_calc_credits_for_single_extent:
+ * This routine returns max. credits that needed to insert an extent
+ * to the extent tree.
+ * When pass the actual path, the caller should calculate credits
+ * under i_data_sem.
  */
-int ext4_ext_calc_credits_for_insert(struct inode *inode,
+int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int num,
                                                 struct ext4_ext_path *path)
 {
-        int depth, needed;
-
         if (path) {
+                int depth = ext_depth(inode);
+                int ret;
+
                 /* probably there is space in leaf? */
-                depth = ext_depth(inode);
                 if (le16_to_cpu(path[depth].p_hdr->eh_entries)
-                                < le16_to_cpu(path[depth].p_hdr->eh_max))
-                        return 1;
-        }
+                                < le16_to_cpu(path[depth].p_hdr->eh_max)) {
 
-        /*
-         * given 32-bit logical block (4294967296 blocks), max. tree
-         * can be 4 levels in depth -- 4 * 340^4 == 53453440000.
-         * Let's also add one more level for imbalance.
-         */
-        depth = 5;
-
-        /* allocation of new data block(s) */
-        needed = 2;
+                        /*
+                         *  There are some space in the leaf tree, no
+                         *  need to account for leaf block credit
+                         *
+                         *  bitmaps and block group descriptor blocks
+                         *  and other metadat blocks still need to be
+                         *  accounted.
+                         */
+                        /* 1 one bitmap, 1 block group descriptor */
+                        ret = 2 + EXT4_META_TRANS_BLOCKS(inode->i_sb);
+                }
+        }
 
-        /*
-         * tree can be full, so it would need to grow in depth:
-         * we need one credit to modify old root, credits for
-         * new root will be added in split accounting
-         */
-        needed += 1;
+        return ext4_meta_trans_blocks(inode, num, 1);
+}
 
-        /*
-         * Index split can happen, we would need:
-         *    allocate intermediate indexes (bitmap + group)
-         *  + change two blocks at each level, but root (already included)
-         */
-        needed += (depth * 2) + (depth * 2);
+/*
+ * How many index/leaf blocks need to change/allocate to modify nrblocks?
+ *
+ * if nrblocks are fit in a single extent (chunk flag is 1), then
+ * in the worse case, each tree level index/leaf need to be changed
+ * if the tree split due to insert a new extent, then the old tree
+ * index/leaf need to be updated too
+ *
+ * If the nrblocks are discontiguous, they could cause
+ * the whole tree split more than once, but this is really rare.
+ */
+int ext4_ext_index_trans_blocks(struct inode *inode, int num, int chunk)
+{
+        int index;
+        int depth = ext_depth(inode);
 
-        /* any allocation modifies superblock */
-        needed += 1;
+        if (chunk)
+                index = depth * 2;
+        else
+                index = depth * 3;
 
-        return needed;
+        return index;
 }
 
 static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
@@ -1921,9 +1928,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
                         correct_index = 1;
                         credits += (ext_depth(inode)) + 1;
                 }
-#ifdef CONFIG_QUOTA
                 credits += 2 * EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb);
-#endif
 
                 err = ext4_ext_journal_restart(handle, credits);
                 if (err)
@@ -2858,27 +2863,6 @@ out_stop:
         ext4_journal_stop(handle);
 }
 
-/*
- * ext4_ext_writepage_trans_blocks:
- * calculate max number of blocks we could modify
- * in order to allocate new block for an inode
- */
-int ext4_ext_writepage_trans_blocks(struct inode *inode, int num)
-{
-        int needed;
-
-        needed = ext4_ext_calc_credits_for_insert(inode, NULL);
-
-        /* caller wants to allocate num blocks, but note it includes sb */
-        needed = needed * num - (num - 1);
-
-#ifdef CONFIG_QUOTA
-        needed += 2 * EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb);
-#endif
-
-        return needed;
-}
-
 static void ext4_falloc_update_inode(struct inode *inode,
                                 int mode, loff_t new_size, int update_ctime)
 {
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index b9e077ba07e9..46fc0b5b12ba 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -53,7 +53,8 @@ static int finish_range(handle_t *handle, struct inode *inode,
          * credit. But below we try to not accumalate too much
          * of them by restarting the journal.
          */
-        needed = ext4_ext_calc_credits_for_insert(inode, path);
+        needed = ext4_ext_calc_credits_for_single_extent(inode,
+                    lb->last_block - lb->first_block + 1, path);
 
         /*
          * Make sure the credit we accumalated is not really high