e2fsck: When repacking directories, leave slack space for more efficiency

If the directory is packed with no slack space, as soon as any new
directory entries are added, leaf nodes end up getting split and
directory ends up getting very inefficient.

Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

diff --git a/e2fsck/e2fsck.c b/e2fsck/e2fsck.c
index 9f862ff..26f7b5e 100644 (file)
--- a/e2fsck/e2fsck.c
+++ b/e2fsck/e2fsck.c
@@ -32,6 +32,7 @@ errcode_t e2fsck_allocate_context(e2fsck_t *ret)
        context->process_inode_size = 256;
        context->ext_attr_ver = 2;
        context->blocks_per_page = 1;
+       context->htree_slack_percentage = 255;
 
        time_env = getenv("E2FSCK_TIME");
        if (time_env)

diff --git a/e2fsck/e2fsck.conf.5.in b/e2fsck/e2fsck.conf.5.in
index c66a769..6638a39 100644 (file)
--- a/e2fsck/e2fsck.conf.5.in
+++ b/e2fsck/e2fsck.conf.5.in
@@ -100,6 +100,13 @@ buggy distributions do not correct this before running e2fsck.  If this
 option is set to a boolean value of true, we attempt to work around this
 situation by allowing the superblock last write time, last mount time,
 and last check time to be in the future by up to 24 hours.
+.TP
+.I clear_test_fs_flag
+This boolean relation controls whether or not 
+.BR e2fsck (8)
+will offer to clear
+the test_fs flag if the ext4 filesystem is available on the system.  It
+defaults to true.
 .TP 
 .I defer_check_on_battery
 This boolean relation controls whether or not the interval between 
@@ -107,10 +114,15 @@ filesystem checks (either based on time or number of mounts) should
 be doubled if the system is running on battery.  It defaults to 
 true.
 .TP
-.I clear_test_fs_flag
-This boolean relation controls whether or not e2fsck will offer to clear
-the test_fs flag if the ext4 filesystem is available on the system.  It
-defaults to true.
+.I indexed_dir_slack_percentage
+When
+.BR e2fsck (8)
+repacks a indexed directory, reserve the specified percentage of
+empty space in each leaf nodes so that a few new entries can
+be added to the directory without splitting leaf nodes, so that
+the average fill ratio of directories can be maintained at a
+higher, more efficient level.  This relation defaults to 20
+percent.
 .SH THE [problems] STANZA
 Each tag in the
 .I [problems] 

diff --git a/e2fsck/e2fsck.h b/e2fsck/e2fsck.h
index 9b91615..a159f2a 100644 (file)
--- a/e2fsck/e2fsck.h
+++ b/e2fsck/e2fsck.h
@@ -289,6 +289,7 @@ struct e2fsck_struct {
         */
        int process_inode_size;
        int inode_buffer_blocks;
+       unsigned int htree_slack_percentage;
 
        /*
         * ext3 journal support

diff --git a/e2fsck/rehash.c b/e2fsck/rehash.c
index 6c24bdd..51c2993 100644 (file)
--- a/e2fsck/rehash.c
+++ b/e2fsck/rehash.c
@@ -397,17 +397,27 @@ static int duplicate_search_and_fix(e2fsck_t ctx, ext2_filsys fs,
 }
 
 
-static errcode_t copy_dir_entries(ext2_filsys fs,
+static errcode_t copy_dir_entries(e2fsck_t ctx,
                                  struct fill_dir_struct *fd,
                                  struct out_dir *outdir)
 {
+       ext2_filsys             fs = ctx->fs;
        errcode_t               retval;
        char                    *block_start;
        struct hash_entry       *ent;
        struct ext2_dir_entry   *dirent;
        int                     i, rec_len, left;
        ext2_dirhash_t          prev_hash;
-       int                     offset;
+       int                     offset, slack;
+
+       if (ctx->htree_slack_percentage == 255) {
+               profile_get_uint(ctx->profile, "options",
+                                "indexed_dir_slack_percentage",
+                                0, 20,
+                                &ctx->htree_slack_percentage);
+               if (ctx->htree_slack_percentage > 100)
+                       ctx->htree_slack_percentage = 20;
+       }
 
        outdir->max = 0;
        retval = alloc_size_dir(fs, outdir,
@@ -422,6 +432,10 @@ static errcode_t copy_dir_entries(ext2_filsys fs,
                return retval;
        dirent = (struct ext2_dir_entry *) block_start;
        left = fs->blocksize;
+       slack = fd->compress ? 12 :
+               (fs->blocksize * ctx->htree_slack_percentage)/100;
+       if (slack < 12)
+               slack = 12;
        for (i=0; i < fd->num_array; i++) {
                ent = fd->harray + i;
                if (ent->dir->inode == 0)
@@ -449,7 +463,7 @@ static errcode_t copy_dir_entries(ext2_filsys fs,
                memcpy(dirent->name, ent->dir->name, dirent->name_len & 0xFF);
                offset += rec_len;
                left -= rec_len;
-               if (left < 12) {
+               if (left < slack) {
                        dirent->rec_len += left;
                        offset += left;
                        left = 0;
@@ -750,7 +764,7 @@ resort:
         * Copy the directory entries.  In a htree directory these
         * will become the leaf nodes.
         */
-       retval = copy_dir_entries(fs, &fd, &outdir);
+       retval = copy_dir_entries(ctx, &fd, &outdir);
        if (retval)
                goto errout;
 

diff --git a/tests/f_h_badnode/expect.1 b/tests/f_h_badnode/expect.1
index 44d4a7c..5aa3cda 100644 (file)
--- a/tests/f_h_badnode/expect.1
+++ b/tests/f_h_badnode/expect.1
@@ -14,5 +14,5 @@ Pass 4: Checking reference counts
 Pass 5: Checking group summary information
 
 test_filesys: ***** FILE SYSTEM WAS MODIFIED *****
-test_filesys: 47730/100192 files (0.0% non-contiguous), 13377/31745 blocks
+test_filesys: 47730/100192 files (0.0% non-contiguous), 13551/31745 blocks
 Exit status is 1

diff --git a/tests/f_h_badnode/expect.2 b/tests/f_h_badnode/expect.2
index 8a21997..b9dadb7 100644 (file)
--- a/tests/f_h_badnode/expect.2
+++ b/tests/f_h_badnode/expect.2
@@ -3,5 +3,5 @@ Pass 2: Checking directory structure
 Pass 3: Checking directory connectivity
 Pass 4: Checking reference counts
 Pass 5: Checking group summary information
-test_filesys: 47730/100192 files (0.0% non-contiguous), 13377/31745 blocks
+test_filesys: 47730/100192 files (0.0% non-contiguous), 13551/31745 blocks
 Exit status is 0

diff --git a/tests/f_h_badroot/expect.1 b/tests/f_h_badroot/expect.1
index 261000d..037942d 100644 (file)
--- a/tests/f_h_badroot/expect.1
+++ b/tests/f_h_badroot/expect.1
@@ -36,5 +36,5 @@ Pass 4: Checking reference counts
 Pass 5: Checking group summary information
 
 test_filesys: ***** FILE SYSTEM WAS MODIFIED *****
-test_filesys: 1921/100080 files (0.0% non-contiguous), 13642/15361 blocks
+test_filesys: 1921/100080 files (0.0% non-contiguous), 13646/15361 blocks
 Exit status is 1

diff --git a/tests/f_h_badroot/expect.2 b/tests/f_h_badroot/expect.2
index 28f1d2a..d5772c1 100644 (file)
--- a/tests/f_h_badroot/expect.2
+++ b/tests/f_h_badroot/expect.2
@@ -3,5 +3,5 @@ Pass 2: Checking directory structure
 Pass 3: Checking directory connectivity
 Pass 4: Checking reference counts
 Pass 5: Checking group summary information
-test_filesys: 1921/100080 files (0.0% non-contiguous), 13642/15361 blocks
+test_filesys: 1921/100080 files (0.0% non-contiguous), 13646/15361 blocks
 Exit status is 0

diff --git a/tests/f_h_reindex/expect.1 b/tests/f_h_reindex/expect.1
index 4511893..a2324d7 100755 (executable)
--- a/tests/f_h_reindex/expect.1
+++ b/tests/f_h_reindex/expect.1
@@ -954,5 +954,5 @@ Pass 4: Checking reference counts
 Pass 5: Checking group summary information
 
 test_filesys: ***** FILE SYSTEM WAS MODIFIED *****
-test_filesys: 30514/32000 files (0.0% non-contiguous), 5558/8000 blocks
+test_filesys: 30514/32000 files (0.0% non-contiguous), 5669/8000 blocks
 Exit status is 1

diff --git a/tests/f_h_reindex/expect.2 b/tests/f_h_reindex/expect.2
index 99de4cf..7f785af 100644 (file)
--- a/tests/f_h_reindex/expect.2
+++ b/tests/f_h_reindex/expect.2
@@ -3,5 +3,5 @@ Pass 2: Checking directory structure
 Pass 3: Checking directory connectivity
 Pass 4: Checking reference counts
 Pass 5: Checking group summary information
-test_filesys: 30514/32000 files (0.0% non-contiguous), 5558/8000 blocks
+test_filesys: 30514/32000 files (0.0% non-contiguous), 5669/8000 blocks
 Exit status is 0