e2fsck: merge dir_info after thread finishes

dir_info need be merged after thread finish.

Signed-off-by: Li Xi <lixi@ddn.com>
Signed-off-by: Wang Shilong <wshilong@ddn.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

3 files changed, 123 insertions, 3 deletions

diff --git a/e2fsck/dirinfo.c b/e2fsck/dirinfo.c
index 28baaca2e..b4adaa6e3 100644
--- a/e2fsck/dirinfo.c
+++ b/e2fsck/dirinfo.c
@@ -170,6 +170,72 @@ e2fsck_dir_info_min_larger_equal(struct dir_info_db *dir_info,
 }
 
 /*
+ * Merge two sorted dir info to @dest
+ */
+void e2fsck_merge_dir_info(e2fsck_t ctx, struct dir_info_db *src,
+			   struct dir_info_db *dest)
+{
+	size_t		 size_dir_info = sizeof(struct dir_info);
+	ext2_ino_t	 size = dest->size;
+	struct dir_info	 *src_array = src->array;
+	struct dir_info	 *dest_array = dest->array;
+	ext2_ino_t	 src_count = src->count;
+	ext2_ino_t	 dest_count = dest->count;
+	ext2_ino_t	 total_count = src_count + dest_count;
+	struct dir_info	*tmp_array;
+	struct dir_info	*array_ptr;
+	ext2_ino_t	 src_index = 0;
+	ext2_ino_t	 dest_index = 0;
+
+	if (src->count == 0)
+		return;
+
+	if (size < total_count)
+		size = total_count;
+
+	if (size < src->size)
+		size = src->size;
+
+	tmp_array = e2fsck_allocate_memory(ctx, size * size_dir_info,
+					    "directory map");
+	array_ptr = tmp_array;
+	/*
+	 * This can be improved by binary search and memcpy, but codes
+	 * would be more complex. And if the groups distributed to each
+	 * thread are strided, this implementation won't be too bad
+	 * comparing to the optimiztion.
+	 */
+	while (src_index < src_count || dest_index < dest_count) {
+		if (src_index >= src_count) {
+			memcpy(array_ptr, &dest_array[dest_index],
+			       (dest_count - dest_index) * size_dir_info);
+			break;
+		}
+		if (dest_index >= dest_count) {
+			memcpy(array_ptr, &src_array[src_index],
+			       (src_count - src_index) * size_dir_info);
+			break;
+		}
+		if (src_array[src_index].ino < dest_array[dest_index].ino) {
+			*array_ptr = src_array[src_index];
+			src_index++;
+		} else {
+			assert(src_array[src_index].ino >
+			       dest_array[dest_index].ino);
+			*array_ptr = dest_array[dest_index];
+			dest_index++;
+		}
+		array_ptr++;
+	}
+
+	if (dest->array)
+		ext2fs_free_mem(&dest->array);
+	dest->array = tmp_array;
+	dest->size = size;
+	dest->count = total_count;
+}
+
+/*
  *
  * Insert an inode into the sorted array. The array should have at least one
  * free slot.
diff --git a/e2fsck/e2fsck.h b/e2fsck/e2fsck.h
index 8576c007f..531a353e9 100644
--- a/e2fsck/e2fsck.h
+++ b/e2fsck/e2fsck.h
@@ -507,6 +507,8 @@ extern void read_bad_blocks_file(e2fsck_t ctx, const char *bad_blocks_file,
 
 /* dirinfo.c */
 extern void e2fsck_add_dir_info(e2fsck_t ctx, ext2_ino_t ino, ext2_ino_t parent);
+void e2fsck_merge_dir_info(e2fsck_t ctx, struct dir_info_db *src,
+                           struct dir_info_db *dest);
 extern void e2fsck_free_dir_info(e2fsck_t ctx);
 extern int e2fsck_get_num_dirinfo(e2fsck_t ctx);
 extern struct dir_info_iter *e2fsck_dir_info_iter_begin(e2fsck_t ctx);
diff --git a/e2fsck/pass1.c b/e2fsck/pass1.c
index 58bcc407a..a1ea487a9 100644
--- a/e2fsck/pass1.c
+++ b/e2fsck/pass1.c
@@ -2363,6 +2363,21 @@ out_context:
 	return retval;
 }
 
+static void e2fsck_pass1_merge_dir_info(e2fsck_t global_ctx, e2fsck_t thread_ctx)
+{
+	if (thread_ctx->dir_info == NULL)
+		return;
+
+	if (global_ctx->dir_info == NULL) {
+		global_ctx->dir_info = thread_ctx->dir_info;
+		thread_ctx->dir_info = NULL;
+		return;
+	}
+
+	e2fsck_merge_dir_info(global_ctx, thread_ctx->dir_info,
+			      global_ctx->dir_info);
+}
+
 static int e2fsck_pass1_thread_join_one(e2fsck_t global_ctx, e2fsck_t thread_ctx)
 {
 	errcode_t	 retval;
@@ -2372,6 +2387,7 @@ static int e2fsck_pass1_thread_join_one(e2fsck_t global_ctx, e2fsck_t thread_ctx
 	FILE		*global_logf = global_ctx->logf;
 	FILE		*global_problem_logf = global_ctx->problem_logf;
 	ext2fs_inode_bitmap inode_bad_map = global_ctx->inode_bad_map;
+	struct dir_info_db *dir_info = global_ctx->dir_info;
 	ext2fs_inode_bitmap inode_used_map = global_ctx->inode_used_map;
 	ext2fs_inode_bitmap inode_dir_map = global_ctx->inode_dir_map;
 	ext2fs_inode_bitmap inode_bb_map = global_ctx->inode_bb_map;
@@ -2404,6 +2420,8 @@ static int e2fsck_pass1_thread_join_one(e2fsck_t global_ctx, e2fsck_t thread_ctx
 	global_ctx->block_dup_map = block_dup_map;
 	global_ctx->block_ea_map = block_ea_map;
 	global_ctx->block_metadata_map = block_metadata_map;
+	global_ctx->dir_info = dir_info;
+	e2fsck_pass1_merge_dir_info(global_ctx, thread_ctx);
 
 	/* Keep the global singal flags*/
 	global_ctx->flags |= (flags & E2F_FLAG_SIGNAL_MASK) |
@@ -2503,6 +2521,7 @@ static int e2fsck_pass1_thread_join(e2fsck_t global_ctx, e2fsck_t thread_ctx)
 	e2fsck_pass1_free_bitmap(&thread_ctx->block_dup_map);
 	e2fsck_pass1_free_bitmap(&thread_ctx->block_ea_map);
 	e2fsck_pass1_free_bitmap(&thread_ctx->block_metadata_map);
+	e2fsck_free_dir_info(thread_ctx);
 	ext2fs_free_mem(&thread_ctx);
 
 	return retval;
@@ -2667,15 +2686,48 @@ out_abort:
 }
 #endif
 
+/* TODO: tdb needs to be handled properly for multiple threads*/
+static int multiple_threads_supported(e2fsck_t ctx)
+{
+#ifdef	CONFIG_TDB
+	unsigned int		threshold;
+	ext2_ino_t		num_dirs;
+	errcode_t		retval;
+	char			*tdb_dir;
+	int			enable;
+
+	profile_get_string(ctx->profile, "scratch_files", "directory", 0, 0,
+			   &tdb_dir);
+	profile_get_uint(ctx->profile, "scratch_files",
+			 "numdirs_threshold", 0, 0, &threshold);
+	profile_get_boolean(ctx->profile, "scratch_files",
+			    "icount", 0, 1, &enable);
+
+	retval = ext2fs_get_num_dirs(ctx->fs, &num_dirs);
+	if (retval)
+		num_dirs = 1024;	/* Guess */
+
+	/* tdb is unsupported now */
+	if (enable && tdb_dir && !access(tdb_dir, W_OK) &&
+	    (!threshold || num_dirs > threshold))
+		return 0;
+ #endif
+	return 1;
+}
+
 void e2fsck_pass1(e2fsck_t ctx)
 {
 
 	init_ext2_max_sizes();
 #ifdef HAVE_PTHREAD
-	e2fsck_pass1_multithread(ctx);
-#else
-	e2fsck_pass1_run(ctx);
+	if (multiple_threads_supported(ctx)) {
+		e2fsck_pass1_multithread(ctx);
+		return;
+	}
+	fprintf(stderr, "Fall through single thread for pass1 "
+			"because tdb could not handle properly\n");
 #endif
+	e2fsck_pass1_run(ctx);
 }
 
 #undef FINISH_INODE_LOOP