Received-SPF: pass (google.com: domain of linux-ext4-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   "Ritesh Harjani (IBM)" <ritesh.list@gmail.com>
To:     Theodore Ts'o <tytso@mit.edu>
Cc:     linux-ext4@vger.kernel.org,
        Harshad Shirwadkar <harshadshirwadkar@gmail.com>,
        Wang Shilong <wshilong@ddn.com>,
        Andreas Dilger <adilger.kernel@dilger.ca>,
        Li Xi <lixi@ddn.com>, Ritesh Harjani <ritesh.list@gmail.com>
Subject: [RFCv1 39/72] e2fsck: merge dx_dir_info after threads finish
Date:   Mon,  7 Nov 2022 17:51:27 +0530
Message-Id: <ce0d19896608c68e0e2adabc754961f9ffeb8e27.1667822611.git.ritesh.list@gmail.com>
In-Reply-To: <cover.1667822611.git.ritesh.list@gmail.com>
References: <cover.1667822611.git.ritesh.list@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Wang Shilong <wshilong@ddn.com>

Merge properly.

Signed-off-by: Wang Shilong <wshilong@ddn.com>
Signed-off-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
---
 e2fsck/dx_dirinfo.c | 64 +++++++++++++++++++++++++++++++++++++++++++++
 e2fsck/e2fsck.h     |  1 +
 e2fsck/pass1.c      | 23 ++++++++++++++++
 3 files changed, 88 insertions(+)

diff --git a/e2fsck/dx_dirinfo.c b/e2fsck/dx_dirinfo.c
index caca3e30..91954572 100644
--- a/e2fsck/dx_dirinfo.c
+++ b/e2fsck/dx_dirinfo.c
@@ -5,6 +5,7 @@
  * under the terms of the GNU Public License.
  */
 
+#include <assert.h>
 #include "config.h"
 #include "e2fsck.h"
 
@@ -79,6 +80,69 @@ void e2fsck_add_dx_dir(e2fsck_t ctx, ext2_ino_t ino, struct ext2_inode *inode,
 				       "dx_block info array");
 }
 
+/*
+ * 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;
+	size_t size_dx_info = sizeof(struct dx_dir_info);
+	ext2_ino_t size = global_ctx->dx_dir_info_size;
+	ext2_ino_t src_count = thread_ctx->dx_dir_info_count;
+	ext2_ino_t dest_count = global_ctx->dx_dir_info_count;
+	ext2_ino_t total_count = src_count + dest_count;
+	struct dx_dir_info *array;
+	struct dx_dir_info *array_ptr;
+	ext2_ino_t src_index = 0, dest_index = 0;
+
+	if (thread_ctx->dx_dir_info_count == 0)
+		return;
+
+	if (size < total_count)
+		size = total_count;
+
+	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 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_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);
+	if (thread_ctx->dx_dir_info)
+		ext2fs_free_mem(&thread_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 9b0f5067..26c3b8a5 100644
--- a/e2fsck/e2fsck.h
+++ b/e2fsck/e2fsck.h
@@ -578,6 +578,7 @@ extern int e2fsck_dir_info_get_parent(e2fsck_t ctx, ext2_ino_t ino,
 				      ext2_ino_t *parent);
 extern int e2fsck_dir_info_get_dotdot(e2fsck_t ctx, ext2_ino_t ino,
 				      ext2_ino_t *dotdot);
+extern void e2fsck_merge_dx_dir(e2fsck_t global_ctx, e2fsck_t thread_ctx);
 
 /* dx_dirinfo.c */
 extern void e2fsck_add_dx_dir(e2fsck_t ctx, ext2_ino_t ino,
diff --git a/e2fsck/pass1.c b/e2fsck/pass1.c
index 8b502307..f998590e 100644
--- a/e2fsck/pass1.c
+++ b/e2fsck/pass1.c
@@ -2341,6 +2341,22 @@ 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) {
+		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);
+}
+
 static inline errcode_t
 e2fsck_pass1_merge_icount(ext2_icount_t *dest_icount,
 			  ext2_icount_t *src_icount)
@@ -2386,6 +2402,7 @@ static int e2fsck_pass1_thread_join_one(e2fsck_t global_ctx, e2fsck_t thread_ctx
 	ext2_filsys global_fs = global_ctx->fs;
 	ext2fs_inode_bitmap inode_bad_map = global_ctx->inode_bad_map;
 	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;
@@ -2415,6 +2432,8 @@ 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;
+	ext2_ino_t dx_dir_info_size = global_ctx->dx_dir_info_size;
+	ext2_ino_t dx_dir_info_count = global_ctx->dx_dir_info_count;
 
 #ifdef HAVE_SETJMP_H
 	jmp_buf old_jmp;
@@ -2439,6 +2458,10 @@ 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;
 	global_ctx->fs_directory_count += fs_directory_count;
-- 
2.37.3