ext4: Allow ext4 to run without a journal
A few weeks ago I posted a patch for discussion that allowed ext4 to run
without a journal. Since that time I've integrated the excellent
comments from Andreas and fixed several serious bugs. We're currently
running with this patch and generating some performance numbers against
both ext2 (with backported reservations code) and ext4 with and without
a journal. It just so happens that running without a journal is
slightly faster for most everything.
We did
iozone -T -t 4 s 2g -r 256k -T -I -i0 -i1 -i2
which creates 4 threads, each of which create and do reads and writes on
a 2G file, with a buffer size of 256K, using O_DIRECT for all file opens
to bypass the page cache. Results:
ext2 ext4, default ext4, no journal
initial writes 13.0 MB/s 15.4 MB/s 15.7 MB/s
rewrites 13.1 MB/s 15.6 MB/s 15.9 MB/s
reads 15.2 MB/s 16.9 MB/s 17.2 MB/s
re-reads 15.3 MB/s 16.9 MB/s 17.2 MB/s
random readers 5.6 MB/s 5.6 MB/s 5.7 MB/s
random writers 5.1 MB/s 5.3 MB/s 5.4 MB/s
So it seems that, so far, this was a useful exercise.
Signed-off-by: Frank Mayhar <fmayhar@google.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index d448eb1..1665aa1 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -149,7 +149,7 @@
{
int err;
- if (handle->h_buffer_credits >= thresh)
+ if (ext4_handle_has_enough_credits(handle, thresh))
return 0;
err = ext4_journal_extend(handle, EXT4_MAX_TRANS_DATA);
@@ -232,7 +232,7 @@
memcpy(gdb->b_data, sbi->s_group_desc[i]->b_data, gdb->b_size);
set_buffer_uptodate(gdb);
unlock_buffer(gdb);
- ext4_journal_dirty_metadata(handle, gdb);
+ ext4_handle_dirty_metadata(handle, NULL, gdb);
ext4_set_bit(bit, bh->b_data);
brelse(gdb);
}
@@ -251,7 +251,7 @@
err = PTR_ERR(bh);
goto exit_bh;
}
- ext4_journal_dirty_metadata(handle, gdb);
+ ext4_handle_dirty_metadata(handle, NULL, gdb);
ext4_set_bit(bit, bh->b_data);
brelse(gdb);
}
@@ -276,7 +276,7 @@
err = PTR_ERR(it);
goto exit_bh;
}
- ext4_journal_dirty_metadata(handle, it);
+ ext4_handle_dirty_metadata(handle, NULL, it);
brelse(it);
ext4_set_bit(bit, bh->b_data);
}
@@ -286,7 +286,7 @@
mark_bitmap_end(input->blocks_count, EXT4_BLOCKS_PER_GROUP(sb),
bh->b_data);
- ext4_journal_dirty_metadata(handle, bh);
+ ext4_handle_dirty_metadata(handle, NULL, bh);
brelse(bh);
/* Mark unused entries in inode bitmap used */
@@ -299,7 +299,7 @@
mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), EXT4_BLOCKS_PER_GROUP(sb),
bh->b_data);
- ext4_journal_dirty_metadata(handle, bh);
+ ext4_handle_dirty_metadata(handle, NULL, bh);
exit_bh:
brelse(bh);
@@ -486,12 +486,12 @@
* reserved inode, and will become GDT blocks (primary and backup).
*/
data[gdb_num % EXT4_ADDR_PER_BLOCK(sb)] = 0;
- ext4_journal_dirty_metadata(handle, dind);
+ ext4_handle_dirty_metadata(handle, NULL, dind);
brelse(dind);
inode->i_blocks -= (gdbackups + 1) * sb->s_blocksize >> 9;
ext4_mark_iloc_dirty(handle, inode, &iloc);
memset((*primary)->b_data, 0, sb->s_blocksize);
- ext4_journal_dirty_metadata(handle, *primary);
+ ext4_handle_dirty_metadata(handle, NULL, *primary);
o_group_desc = EXT4_SB(sb)->s_group_desc;
memcpy(n_group_desc, o_group_desc,
@@ -502,7 +502,7 @@
kfree(o_group_desc);
le16_add_cpu(&es->s_reserved_gdt_blocks, -1);
- ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
+ ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
return 0;
@@ -618,7 +618,7 @@
primary[i]->b_blocknr, gdbackups,
blk + primary[i]->b_blocknr); */
data[gdbackups] = cpu_to_le32(blk + primary[i]->b_blocknr);
- err2 = ext4_journal_dirty_metadata(handle, primary[i]);
+ err2 = ext4_handle_dirty_metadata(handle, NULL, primary[i]);
if (!err)
err = err2;
}
@@ -676,7 +676,8 @@
struct buffer_head *bh;
/* Out of journal space, and can't get more - abort - so sad */
- if (handle->h_buffer_credits == 0 &&
+ if (ext4_handle_valid(handle) &&
+ handle->h_buffer_credits == 0 &&
ext4_journal_extend(handle, EXT4_MAX_TRANS_DATA) &&
(err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA)))
break;
@@ -696,7 +697,7 @@
memset(bh->b_data + size, 0, rest);
set_buffer_uptodate(bh);
unlock_buffer(bh);
- ext4_journal_dirty_metadata(handle, bh);
+ ext4_handle_dirty_metadata(handle, NULL, bh);
brelse(bh);
}
if ((err2 = ext4_journal_stop(handle)) && !err)
@@ -916,7 +917,7 @@
/* Update the global fs size fields */
sbi->s_groups_count++;
- ext4_journal_dirty_metadata(handle, primary);
+ ext4_handle_dirty_metadata(handle, NULL, primary);
/* Update the reserved block counts only once the new group is
* active. */
@@ -938,7 +939,7 @@
EXT4_INODES_PER_GROUP(sb);
}
- ext4_journal_dirty_metadata(handle, sbi->s_sbh);
+ ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
sb->s_dirt = 1;
exit_journal:
@@ -1072,7 +1073,7 @@
goto exit_put;
}
ext4_blocks_count_set(es, o_blocks_count + add);
- ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
+ ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
sb->s_dirt = 1;
unlock_super(sb);
ext4_debug("freeing blocks %llu through %llu\n", o_blocks_count,