diff mbox series

[RFC,27/46] e2fsck: merge dx_dir_info

Message ID 1586342714-12536-28-git-send-email-wangshilong1991@gmail.com
State New
Headers show
Series introduce parallel fsck to e2fsck pass1 | expand

Commit Message

Wang Shilong April 8, 2020, 10:44 a.m. UTC
From: Wang Shilong <wshilong@ddn.com>

Change-Id: I250de2d510e3c71974f6c853d5f6ff01229d5573
Signed-off-by: Wang Shilong <wshilong@ddn.com>
---
 e2fsck/dx_dirinfo.c | 67 +++++++++++++++++++++++++++++++++++++++++++++
 e2fsck/e2fsck.h     |  1 +
 e2fsck/pass1.c      | 25 +++++++++++++++++
 3 files changed, 93 insertions(+)
diff mbox series

Patch

diff --git a/e2fsck/dx_dirinfo.c b/e2fsck/dx_dirinfo.c
index c0b0e9a4..cf9849dc 100644
--- a/e2fsck/dx_dirinfo.c
+++ b/e2fsck/dx_dirinfo.c
@@ -80,6 +80,73 @@  void e2fsck_add_dx_dir(e2fsck_t ctx, ext2_ino_t ino, struct ext2_inode *inode,
 
 }
 
+/*
+ * Merge two sorted dir info to @dest
+ */
+void e2fsck_merge_dx_dir(e2fsck_t global_ctx, e2fsck_t thread_ctx)
+{
+	struct dx_dir_info *src_array = thread_ctx->dx_dir_info;
+	struct dx_dir_info *dest_array = global_ctx->dx_dir_info;
+	int size_dx_info = sizeof(struct dx_dir_info);
+	int size = global_ctx->dx_dir_info_size;
+	int src_count = thread_ctx->dx_dir_info_count;
+	int dest_count = global_ctx->dx_dir_info_count;
+	int total_count = src_count + dest_count;
+	struct dx_dir_info *array;
+	struct dx_dir_info *array_ptr;
+	int src_index = 0, dest_index = 0;
+	int i;
+
+	if (thread_ctx->dx_dir_info_count == 0)
+		return;
+
+	if (size < total_count)
+		size = total_count;
+
+	if (size < thread_ctx->dx_dir_info_size > size)
+		size = size;
+
+	array = e2fsck_allocate_memory(global_ctx, size * size_dx_info,
+				       "directory map");
+	array_ptr = array;
+	/*
+	 * This can be improved by binary search and memcpy, but codes
+	 * would be complexer. And if the groups distributed to each
+	 * thread are stided, 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_dx_info);
+			break;
+		}
+		if (dest_index >= dest_count) {
+			memcpy(array_ptr, &src_array[src_index],
+			       (src_count - src_index) * size_dx_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 (global_ctx->dx_dir_info)
+		ext2fs_free_mem(&global_ctx->dx_dir_info);
+	global_ctx->dx_dir_info = array;
+	global_ctx->dx_dir_info_size = size;
+	global_ctx->dx_dir_info_count = total_count;
+}
+
 /*
  * get_dx_dir_info() --- given an inode number, try to find the directory
  * information entry for it.
diff --git a/e2fsck/e2fsck.h b/e2fsck/e2fsck.h
index 61761684..0b449b69 100644
--- a/e2fsck/e2fsck.h
+++ b/e2fsck/e2fsck.h
@@ -545,6 +545,7 @@  extern struct dx_dir_info *e2fsck_get_dx_dir_info(e2fsck_t ctx, ext2_ino_t ino);
 extern void e2fsck_free_dx_dir_info(e2fsck_t ctx);
 extern int e2fsck_get_num_dx_dirinfo(e2fsck_t ctx);
 extern struct dx_dir_info *e2fsck_dx_dir_info_iter(e2fsck_t ctx, int *control);
+extern void e2fsck_merge_dx_dir(e2fsck_t global_ctx, e2fsck_t thread_ctx);
 
 /* ea_refcount.c */
 typedef __u64 ea_key_t;
diff --git a/e2fsck/pass1.c b/e2fsck/pass1.c
index 4bd1f8be..6789b701 100644
--- a/e2fsck/pass1.c
+++ b/e2fsck/pass1.c
@@ -2472,6 +2472,24 @@  static void e2fsck_pass1_merge_dir_info(e2fsck_t global_ctx, e2fsck_t thread_ctx
 			      global_ctx->dir_info);
 }
 
+static void e2fsck_pass1_merge_dx_dir(e2fsck_t global_ctx, e2fsck_t thread_ctx)
+{
+	if (thread_ctx->dx_dir_info == NULL)
+		return;
+
+	if (global_ctx->dx_dir_info == NULL) {
+		/* TODO: tdb needs to be handled properly */
+		global_ctx->dx_dir_info = thread_ctx->dx_dir_info;
+		global_ctx->dx_dir_info_size = thread_ctx->dx_dir_info_size;
+		global_ctx->dx_dir_info_count = thread_ctx->dx_dir_info_count;
+		thread_ctx->dx_dir_info = NULL;
+		return;
+	}
+
+	e2fsck_merge_dx_dir(global_ctx, thread_ctx);
+}
+
+
 #define PASS1_MERGE_CTX_ICOUNT(_dest, _src, _field)			\
 do {									\
     if (_src->_field) {							\
@@ -2503,6 +2521,7 @@  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;
 	struct dir_info_db *dir_info = global_ctx->dir_info;
+	struct dx_dir_info *dx_dir_info = global_ctx->dx_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;
@@ -2532,6 +2551,8 @@  static int e2fsck_pass1_thread_join_one(e2fsck_t global_ctx, e2fsck_t thread_ctx
 	__u32	fs_fragmented = global_ctx->fs_fragmented;
 	__u32	fs_fragmented_dir = global_ctx->fs_fragmented_dir;
 	__u32	large_files = global_ctx->large_files;
+	int dx_dir_info_size = global_ctx->dx_dir_info_size;
+	int dx_dir_info_count = global_ctx->dx_dir_info_count;
 
 #ifdef HAVE_SETJMP_H
 	jmp_buf		 old_jmp;
@@ -2555,6 +2576,10 @@  static int e2fsck_pass1_thread_join_one(e2fsck_t global_ctx, e2fsck_t thread_ctx
 	global_ctx->block_metadata_map = block_metadata_map;
 	global_ctx->dir_info = dir_info;
 	e2fsck_pass1_merge_dir_info(global_ctx, thread_ctx);
+	global_ctx->dx_dir_info = dx_dir_info;
+	global_ctx->dx_dir_info_count = dx_dir_info_count;
+	global_ctx->dx_dir_info_size = dx_dir_info_size;
+	e2fsck_pass1_merge_dx_dir(global_ctx, thread_ctx);
 	global_ctx->inode_count = inode_count;
 	global_ctx->inode_link_info = inode_link_info;
 	PASS1_MERGE_CTX_COUNT(global_ctx, thread_ctx, fs_directory_count);