Message-Id: <ACF77779-7A44-4ED7-BC49-7658A8DF8514@dilger.ca>
Date:	Mon, 20 Jan 2014 16:25:23 -0700
From:	Andreas Dilger <adilger@...ger.ca>
To:	Theodore Ts'o <tytso@....edu>
Cc:	Ext4 Developers List <linux-ext4@...r.kernel.org>
Subject: Re: [PATCH 12/12] mke2fs: allow metadata blocks to be at the beginning of the file system

On Jan 19, 2014, at 10:54 PM, Theodore Ts'o <tytso@....edu> wrote:
> Add the extended options packed_meta_blocks and journal_location_front
> which causes mke2fs to place the metadata blocks at the beginning of
> the file system.

The "packed_meta_blocks" appears to be equivalent to setting flex_bg
to some large enough factor that all the block and inode bitmaps are
at the start of the filesystem?  It would probably be better to align
the inode and block bitmaps and inode table on a multiple of
s_raid_stride (will this be used to align on SMR erase blocks?) so
that rewrites are at least somewhat efficient and aligned?  That would
also allow reserving some room in the flex_bg packing to allow for
filesystem resizing.

It would also be useful to allow setting the journal goal block
directly, instead of journal_location_front only allowing to specify
goal == 0 (i.e. add "-E journal_start_goal=N" instead of adding
"-E journal_location_front", which implied by packed_meta_blocks).
I've wanted to be able to do this for a long time, but the stumbling
block is that write_journal_inode() doesn't have any parameter to
specify the goal journal block without storing it in the superblock.
I suppose it would be possible to pass the journal goal block in
s_jnl_blocks[0..1] or something?

Cheers, Andreas

> Signed-off-by: "Theodore Ts'o" <tytso@....edu>
> ---
> lib/ext2fs/ext2fs.h    |  1 +
> lib/ext2fs/mkjournal.c |  5 +++-
> misc/mke2fs.8.in       | 14 +++++++++++
> misc/mke2fs.c          | 65 +++++++++++++++++++++++++++++++++++++++++++++++++-
> misc/mke2fs.conf.5.in  |  4 ++++
> 5 files changed, 87 insertions(+), 2 deletions(-)
> 
> diff --git a/lib/ext2fs/ext2fs.h b/lib/ext2fs/ext2fs.h
> index efe0964..fed6410 100644
> --- a/lib/ext2fs/ext2fs.h
> +++ b/lib/ext2fs/ext2fs.h
> @@ -204,6 +204,7 @@ typedef struct ext2_file *ext2_file_t;
> #define EXT2_MKJOURNAL_V1_SUPER	0x0000001 /* create V1 superblock (deprecated) */
> #define EXT2_MKJOURNAL_LAZYINIT	0x0000002 /* don't zero journal inode before use*/
> #define EXT2_MKJOURNAL_NO_MNT_CHECK 0x0000004 /* don't check mount status */
> +#define EXT2_MKJOURNAL_LOCATION_FRONT 0x0000004 /* journal at the beginning */
> 
> struct opaque_ext2_group_desc;
> 
> diff --git a/lib/ext2fs/mkjournal.c b/lib/ext2fs/mkjournal.c
> index d09c458..aa6d9af 100644
> --- a/lib/ext2fs/mkjournal.c
> +++ b/lib/ext2fs/mkjournal.c
> @@ -360,7 +360,10 @@ static errcode_t write_journal_inode(ext2_filsys fs, ext2_ino_t journal_ino,
> 		    ext2fs_bg_free_blocks_count(fs, group))
> 			group = i;
> 
> -	es.goal = ext2fs_group_first_block2(fs, group);
> +	if (flags & EXT2_MKJOURNAL_LOCATION_FRONT)
> +		es.goal = 0;
> +	else
> +		es.goal = ext2fs_group_first_block2(fs, group);
> 	retval = ext2fs_block_iterate3(fs, journal_ino, BLOCK_FLAG_APPEND,
> 				       0, mkjournal_proc, &es);
> 	if (es.err) {
> diff --git a/misc/mke2fs.8.in b/misc/mke2fs.8.in
> index 483fb1c..9f8c9f6 100644
> --- a/misc/mke2fs.8.in
> +++ b/misc/mke2fs.8.in
> @@ -280,6 +280,20 @@ If the
> file system feature is enabled this option controls whether there will
> be 0, 1, or 2 backup superblocks created in the file system.
> .TP
> +.B packed_meta_blocks\fR[\fB= \fI<0 to disable, 1 to enable>\fR]
> +Place the allocation bitmaps and the inode table at the beginning of the
> +disk.  This option requires that the flex_bg file system feature to be
> +enabled in order for it to have effect, and also implies the
> +extended option
> +.IR journal_location_front .
> +This option is useful for flash devices that use SLC flash at the beginning of
> +the disk.   It also maximizes the range of contiguous data blocks, which
> +can be useful for certain specialized use cases, such as supported
> +Shingled Drives.
> +.TP
> +.B journal_location_front\fR[\fB= \fI<0 to disable, 1 to enable>\fR]
> +Place the journal at the beginning of the file system.
> +.TP
> .BI root_owner [=uid:gid]
> Specify the numeric user and group ID of the root directory.  If no UID:GID
> is specified, use the user and group ID of the user running \fBmke2fs\fR.
> diff --git a/misc/mke2fs.c b/misc/mke2fs.c
> index efb068a..363e96b 100644
> --- a/misc/mke2fs.c
> +++ b/misc/mke2fs.c
> @@ -94,6 +94,7 @@ static gid_t	root_gid;
> int	journal_size;
> int	journal_flags;
> static int	lazy_itable_init;
> +static int	packed_meta_blocks;
> static char	*bad_blocks_filename = NULL;
> static __u32	fs_stride;
> static int	quotatype = -1;  /* Initialize both user and group quotas by default */
> @@ -310,6 +311,40 @@ _("Warning: the backup superblock/group descriptors at block %u contain\n"
> 	ext2fs_badblocks_list_iterate_end(bb_iter);
> }
> 
> +static errcode_t packed_allocate_tables(ext2_filsys fs)
> +{
> +	errcode_t	retval;
> +	dgrp_t		i;
> +	blk64_t		goal = 0;
> +
> +	for (i = 0; i < fs->group_desc_count; i++) {
> +		retval = ext2fs_new_block2(fs, goal, NULL, &goal);
> +		if (retval)
> +			return retval;
> +		ext2fs_block_alloc_stats2(fs, goal, +1);
> +		ext2fs_block_bitmap_loc_set(fs, i, goal);
> +	}
> +	for (i = 0; i < fs->group_desc_count; i++) {
> +		retval = ext2fs_new_block2(fs, goal, NULL, &goal);
> +		if (retval)
> +			return retval;
> +		ext2fs_block_alloc_stats2(fs, goal, +1);
> +		ext2fs_inode_bitmap_loc_set(fs, i, goal);
> +	}
> +	for (i = 0; i < fs->group_desc_count; i++) {
> +		blk64_t end = ext2fs_blocks_count(fs->super) - 1;
> +		retval = ext2fs_get_free_blocks2(fs, goal, end,
> +						 fs->inode_blocks_per_group,
> +						 fs->block_map, &goal);
> +		if (retval)
> +			return retval;
> +		ext2fs_block_alloc_stats_range(fs, goal,
> +					       fs->inode_blocks_per_group, +1);
> +		ext2fs_inode_table_loc_set(fs, i, goal);
> +	}
> +	return 0;
> +}
> +
> static void write_inode_tables(ext2_filsys fs, int lazy_flag, int itable_zeroed)
> {
> 	errcode_t	retval;
> @@ -712,6 +747,14 @@ static void parse_extended_opts(struct ext2_super_block *param,
> 				continue;
> 			}
> 			param->s_desc_size = desc_size;
> +		} else if (strcmp(token, "journal_location_front") == 0) {
> +			unsigned long front = 1;
> +			if (arg)
> +				front = strtoul(arg, &p, 0);
> +			if (front)
> +				journal_flags |= EXT2_MKJOURNAL_LOCATION_FRONT;
> +			else
> +				journal_flags &= ~EXT2_MKJOURNAL_LOCATION_FRONT;
> 		} else if (strcmp(token, "offset") == 0) {
> 			if (!arg) {
> 				r_usage++;
> @@ -754,6 +797,15 @@ static void parse_extended_opts(struct ext2_super_block *param,
> 				r_usage++;
> 				continue;
> 			}
> +		} else if (strcmp(token, "packed_meta_blocks") == 0) {
> +			if (arg)
> +				packed_meta_blocks = strtoul(arg, &p, 0);
> +			else
> +				packed_meta_blocks = 1;
> +			if (packed_meta_blocks)
> +				journal_flags |= EXT2_MKJOURNAL_LOCATION_FRONT;
> +			else
> +				journal_flags &= ~EXT2_MKJOURNAL_LOCATION_FRONT;
> 		} else if (strcmp(token, "stride") == 0) {
> 			if (!arg) {
> 				r_usage++;
> @@ -915,8 +967,10 @@ static void parse_extended_opts(struct ext2_super_block *param,
> 			"\tstripe-width=<RAID stride * data disks in blocks>\n"
> 			"\toffset=<offset to create the file system>\n"
> 			"\tresize=<resize maximum size in blocks>\n"
> +			"\tpacked_meta_blocks=<0 to disable, 1 to enable>\n"
> 			"\tlazy_itable_init=<0 to disable, 1 to enable>\n"
> 			"\tlazy_journal_init=<0 to disable, 1 to enable>\n"
> +			"\tjournal_location_front=<0 to disable, 1 to enable>\n"
> 			"\troot_uid=<uid of root directory>\n"
> 			"\troot_gid=<gid of root directory>\n"
> 			"\ttest_fs\n"
> @@ -2030,6 +2084,11 @@ profile_error:
> 					       EXT2_MKJOURNAL_LAZYINIT : 0;
> 	journal_flags |= EXT2_MKJOURNAL_NO_MNT_CHECK;
> 
> +	packed_meta_blocks = get_bool_from_profile(fs_types,
> +						   "packed_meta_blocks", 0);
> +	if (packed_meta_blocks)
> +		journal_flags |= EXT2_MKJOURNAL_LOCATION_FRONT;
> +
> 	/* Get options from profile */
> 	for (cpp = fs_types; *cpp; cpp++) {
> 		tmp = NULL;
> @@ -2624,7 +2683,11 @@ int main (int argc, char *argv[])
> 	fs->stride = fs_stride = fs->super->s_raid_stride;
> 	if (!quiet)
> 		printf("%s", _("Allocating group tables: "));
> -	retval = ext2fs_allocate_tables(fs);
> +	if ((fs->super->s_feature_incompat & EXT4_FEATURE_INCOMPAT_FLEX_BG) &&
> +	    packed_meta_blocks)
> +		retval = packed_allocate_tables(fs);
> +	else
> +		retval = ext2fs_allocate_tables(fs);
> 	if (retval) {
> 		com_err(program_name, retval, "%s",
> 			_("while trying to allocate filesystem tables"));
> diff --git a/misc/mke2fs.conf.5.in b/misc/mke2fs.conf.5.in
> index 43bb91e..1aba87b 100644
> --- a/misc/mke2fs.conf.5.in
> +++ b/misc/mke2fs.conf.5.in
> @@ -362,6 +362,10 @@ This relation indicates whether file systems with the
> .B sparse_super2
> feature enabled should be created with 0, 1, or 2 backup superblocks.
> .TP
> +.I packed_meta_blocks
> +This boolean relation specifes whether the allocation bitmaps, inode
> +table, and journal should be located at the beginning of the file system.
> +.TP
> .I inode_ratio
> This relation specifies the default inode ratio if the user does not
> specify one on the command line.
> -- 
> 1.8.5.rc3.362.gdf10213
> 
> --
> To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
> the body of a message to majordomo@...r.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html


Cheers, Andreas






Download attachment "signature.asc" of type "application/pgp-signature" (834 bytes)

Powered by blists - more mailing lists