On Wed, Feb 07, 2007 at 12:25:50AM -0800, Mingming Cao wrote:
> On Wed, 2007-02-07 at 13:18 +0530, Amit K. Arora wrote:
> > I plan to test the persistent preallocation patches on a huge sparse
> > device, to know if >32 bit physical block numbers (upto 48bit) behave as
> > expected.
> Thanks!
>
>
> > I have following questions for this and will appreciate
> > suggestions here:
>
> > c) Do I need to put some hack in the filesystem code for above (to
> > allocate >32 bit physical block numbers) ?
> >
>
> I had a ext3 hack patch before to allow application specify which block
> group is the targeted block allocation group,using ioctl command, so to
> allocate >32 bit physical block numbers it just set the target block
> group beyond 2**(32-15) = 2**17. patch is below..
>
> BTW, have you considered
> - move the preallocation code in ioctl to a seperate function, and call
> that function from ioctl? That way we could easily switch to
> posix_falloc later.
Good suggestion.
> - Test preallocation with mapped IO?
> - disable preallocation if the filesystem free blocks is under some low
> watermarks, to save space for near future real block allocation?
A policy decision like this is probably worth a discussion during today's call.
> - is de-preallocation something worth doing?
Wouldn't truncate do that ?
Or you thinking of something like hole punching ?
Regards
Suparna
>
> Mingming
>
> ---
>
> linux-2.6.16-ming/fs/ext3/balloc.c | 24 ++++++++++++++---------
> linux-2.6.16-ming/fs/ext3/ioctl.c | 29
> ++++++++++++++++++++++++++++
> linux-2.6.16-ming/include/linux/ext3_fs.h | 1
> linux-2.6.16-ming/include/linux/ext3_fs_i.h | 1
> 4 files changed, 46 insertions(+), 9 deletions(-)
>
> diff -puN fs/ext3/ioctl.c~ext3_set_alloc_blk_group_hack fs/ext3/ioctl.c
> --- linux-2.6.16/fs/ext3/ioctl.c~ext3_set_alloc_blk_group_hack
> 2006-03-28 15:19:58.000000000 -0800
> +++ linux-2.6.16-ming/fs/ext3/ioctl.c 2006-03-28 15:54:14.507288400 -0800
> @@ -22,6 +22,7 @@ int ext3_ioctl (struct inode * inode, st
> struct ext3_inode_info *ei = EXT3_I(inode);
> unsigned int flags;
> unsigned short rsv_window_size;
> + unsigned int blk_group;
>
> ext3_debug ("cmd = %u, arg = %lu\n", cmd, arg);
>
> @@ -193,6 +194,34 @@ flags_err:
> mutex_unlock(&ei->truncate_mutex);
> return 0;
> }
> + case EXT3_IOC_SETALLOCBLKGRP: {
> +
> + if (!test_opt(inode->i_sb, RESERVATION)
> ||!S_ISREG(inode->i_mode))
> + return -ENOTTY;
> +
> + if (IS_RDONLY(inode))
> + return -EROFS;
> +
> + if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
> + return -EACCES;
> +
> + if (get_user(blk_group, (int __user *)arg))
> + return -EFAULT;
> +
> + /*
> + * need to allocate reservation structure for this inode
> + * before set the window size
> + */
> + mutex_lock(&ei->truncate_mutex);
> + if (!ei->i_block_alloc_info)
> + ext3_init_block_alloc_info(inode);
> +
> + if (ei->i_block_alloc_info){
> + ei->i_block_alloc_info->goal_block_group = blk_group;
> + }
> + mutex_unlock(&ei->truncate_mutex);
> + return 0;
> + }
> case EXT3_IOC_GROUP_EXTEND: {
> unsigned long n_blocks_count;
> struct super_block *sb = inode->i_sb;
> diff -puN include/linux/ext3_fs.h~ext3_set_alloc_blk_group_hack
> include/linux/ext3_fs.h
> --- linux-2.6.16/include/linux/ext3_fs.h~ext3_set_alloc_blk_group_hack
> 2006-03-28 15:42:51.000000000 -0800
> +++ linux-2.6.16-ming/include/linux/ext3_fs.h 2006-03-28 15:51:48.321237417
> -0800
> @@ -238,6 +238,7 @@ struct ext3_new_group_data {
> #endif
> #define EXT3_IOC_GETRSVSZ _IOR('f', 5, long)
> #define EXT3_IOC_SETRSVSZ _IOW('f', 6, long)
> +#define EXT3_IOC_SETALLOCBLKGRP _IOW('f', 9, long)
>
> /*
> * Mount options
> diff -puN include/linux/ext3_fs_i.h~ext3_set_alloc_blk_group_hack
> include/linux/ext3_fs_i.h
> --- linux-2.6.16/include/linux/ext3_fs_i.h~ext3_set_alloc_blk_group_hack
> 2006-03-28 15:43:59.000000000 -0800
> +++ linux-2.6.16-ming/include/linux/ext3_fs_i.h 2006-03-28
> 15:47:54.274367219 -0800
> @@ -51,6 +51,7 @@ struct ext3_block_alloc_info {
> * allocation when we detect linearly ascending requests.
> */
> __u32 last_alloc_physical_block;
> + __u32 goal_block_group;
> };
>
> #define rsv_start rsv_window._rsv_start
> diff -puN fs/ext3/balloc.c~ext3_set_alloc_blk_group_hack fs/ext3/balloc.c
> --- linux-2.6.16/fs/ext3/balloc.c~ext3_set_alloc_blk_group_hack
> 2006-03-28 15:45:30.000000000 -0800
> +++ linux-2.6.16-ming/fs/ext3/balloc.c 2006-03-28 16:03:55.770850040
> -0800
> @@ -285,6 +285,7 @@ void ext3_init_block_alloc_info(struct i
> rsv->rsv_alloc_hit = 0;
> block_i->last_alloc_logical_block = 0;
> block_i->last_alloc_physical_block = 0;
> + block_i->goal_block_group = 0;
> }
> ei->i_block_alloc_info = block_i;
> }
> @@ -1263,15 +1264,20 @@ unsigned long ext3_new_blocks(handle_t *
> *errp = -ENOSPC;
> goto out;
> }
> -
> - /*
> - * First, test whether the goal block is free.
> - */
> - if (goal < le32_to_cpu(es->s_first_data_block) ||
> - goal >= le32_to_cpu(es->s_blocks_count))
> - goal = le32_to_cpu(es->s_first_data_block);
> - group_no = (goal - le32_to_cpu(es->s_first_data_block)) /
> - EXT3_BLOCKS_PER_GROUP(sb);
> + if (block_i->goal_block_group) {
> + group_no = block_i->goal_block_group;
> + goal = le32_to_cpu(EXT3_SB(sb)->s_es->s_first_data_block) +
> group_no * EXT3_BLOCKS_PER_GROUP(sb);
> + block_i->goal_block_group = 0;
> + } else {
> + /*
> + * First, test whether the goal block is free.
> + */
> + if (goal < le32_to_cpu(es->s_first_data_block) ||
> + goal >= le32_to_cpu(es->s_blocks_count))
> + goal = le32_to_cpu(es->s_first_data_block);
> + group_no = (goal - le32_to_cpu(es->s_first_data_block)) /
> + EXT3_BLOCKS_PER_GROUP(sb);
> + }
> gdp = ext3_get_group_desc(sb, group_no, &gdp_bh);
> if (!gdp)
> goto io_error;
>
> _
>
>
> -
> To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
> the body of a message to [EMAIL PROTECTED]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
Suparna Bhattacharya ([EMAIL PROTECTED])
Linux Technology Center
IBM Software Lab, India
-
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
