Hello,
On Tue 19-08-14 15:52:38, Gioh Kim wrote:
> A buffer cache is allocated from movable area
> because it is referred for a while and released soon.
> But some filesystems are taking buffer cache for a long time
> and it can disturb page migration.
>
> A new API should be introduced to allocate buffer cache
> with user specific flag.
> For instance if user set flag to zero, buffer cache is allocated from
> non-movable area.
>
> Signed-off-by: Gioh Kim <gioh.kim@xxxxxxx>
> ---
> fs/buffer.c | 52 +++++++++++++++++++++++++++++--------------
> include/linux/buffer_head.h | 12 +++++++++-
> 2 files changed, 46 insertions(+), 18 deletions(-)
>
> diff --git a/fs/buffer.c b/fs/buffer.c
> index 8f05111..14f2f21 100644
> --- a/fs/buffer.c
> +++ b/fs/buffer.c
> @@ -993,7 +993,7 @@ init_page_buffers(struct page *page, struct block_device *bdev,
> */
> static int
> grow_dev_page(struct block_device *bdev, sector_t block,
> - pgoff_t index, int size, int sizebits)
> + pgoff_t index, int size, int sizebits, gfp_t gfp)
> {
> struct inode *inode = bdev->bd_inode;
> struct page *page;
> @@ -1002,10 +1002,10 @@ grow_dev_page(struct block_device *bdev, sector_t block,
> int ret = 0; /* Will call free_more_memory() */
> gfp_t gfp_mask;
>
> - gfp_mask = mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS;
> - gfp_mask |= __GFP_MOVABLE;
> + gfp_mask = (mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS) | gfp;
> +
Hum, it seems a bit misleading that the 'gfp' flags are just or-ed to
mapping_gfp_mask(inode->i_mapping). Usually, passed gfp mask is just
directly used. There are also interfaces like pagecache_get_page() which
play more complex tricks with mapping_gfp_mask(). This would be yet another
convention which I don't think is desirable. I know Andrew suggested what
you wrote so I guess I have to settle this with him. Andrew?
> /*
> - * XXX: __getblk_slow() can not really deal with failure and
> + * XXX: __getblk_gfp() can not really deal with failure and
> * will endlessly loop on improvised global reclaim. Prefer
> * looping in the allocator rather than here, at least that
> * code knows what it's doing.
> @@ -1058,7 +1058,7 @@ failed:
> * that page was dirty, the buffers are set dirty also.
> */
> static int
> -grow_buffers(struct block_device *bdev, sector_t block, int size)
> +grow_buffers(struct block_device *bdev, sector_t block, int size, gfp_t gfp)
> {
> pgoff_t index;
> int sizebits;
> @@ -1085,11 +1085,12 @@ grow_buffers(struct block_device *bdev, sector_t block, int size)
> }
>
> /* Create a page with the proper size buffers.. */
> - return grow_dev_page(bdev, block, index, size, sizebits);
> + return grow_dev_page(bdev, block, index, size, sizebits, gfp);
> }
>
> -static struct buffer_head *
> -__getblk_slow(struct block_device *bdev, sector_t block, int size)
> +struct buffer_head *
> +__getblk_gfp(struct block_device *bdev, sector_t block,
> + unsigned size, gfp_t gfp)
> {
> /* Size must be multiple of hard sectorsize */
> if (unlikely(size & (bdev_logical_block_size(bdev)-1) ||
> @@ -1111,13 +1112,14 @@ __getblk_slow(struct block_device *bdev, sector_t block, int size)
> if (bh)
> return bh;
>
> - ret = grow_buffers(bdev, block, size);
> + ret = grow_buffers(bdev, block, size, gfp);
> if (ret < 0)
> return NULL;
> if (ret == 0)
> free_more_memory();
> }
> }
> +EXPORT_SYMBOL(__getblk_gfp);
>
> /*
> * The relationship between dirty buffers and dirty pages:
> @@ -1381,12 +1383,7 @@ EXPORT_SYMBOL(__find_get_block);
> struct buffer_head *
> __getblk(struct block_device *bdev, sector_t block, unsigned size)
> {
> - struct buffer_head *bh = __find_get_block(bdev, block, size);
> -
> - might_sleep();
> - if (bh == NULL)
> - bh = __getblk_slow(bdev, block, size);
> - return bh;
> + return __getblk_gfp(bdev, block, size, __GFP_MOVABLE);
> }
> EXPORT_SYMBOL(__getblk);
Why did you remove the __find_get_block() call? That looks like a bug.
> @@ -1410,18 +1407,39 @@ EXPORT_SYMBOL(__breadahead);
> * @size: size (in bytes) to read
> *
> * Reads a specified block, and returns buffer head that contains it.
> + * The page cache is allocated from movable area so that it can be migrated.
> * It returns NULL if the block was unreadable.
> */
> struct buffer_head *
> __bread(struct block_device *bdev, sector_t block, unsigned size)
> {
> - struct buffer_head *bh = __getblk(bdev, block, size);
> + return __bread_gfp(bdev, block, size, __GFP_MOVABLE);
> +}
> +EXPORT_SYMBOL(__bread);
> +
> +/**
> + * __bread_gfp() - reads a specified block and returns the bh
> + * @bdev: the block_device to read from
> + * @block: number of block
> + * @size: size (in bytes) to read
> + * @gfp: page allocation flag
> + *
> + * Reads a specified block, and returns buffer head that contains it.
> + * The page cache can be allocated from non-movable area
> + * not to prevent page migration if you set gfp to zero.
> + * It returns NULL if the block was unreadable.
> + */
> +struct buffer_head *
> +__bread_gfp(struct block_device *bdev, sector_t block,
> + unsigned size, gfp_t gfp)
> +{
> + struct buffer_head *bh = __getblk_gfp(bdev, block, size, gfp);
>
> if (likely(bh) && !buffer_uptodate(bh))
> bh = __bread_slow(bh);
> return bh;
> }
> -EXPORT_SYMBOL(__bread);
> +EXPORT_SYMBOL(__bread_gfp);
>
> /*
> * invalidate_bh_lrus() is called rarely - but not only at unmount.
> diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
> index 324329c..a1d73fd 100644
> --- a/include/linux/buffer_head.h
> +++ b/include/linux/buffer_head.h
> @@ -177,10 +177,14 @@ struct buffer_head *__find_get_block(struct block_device *bdev, sector_t block,
> unsigned size);
> struct buffer_head *__getblk(struct block_device *bdev, sector_t block,
> unsigned size);
> +struct buffer_head *__getblk_gfp(struct block_device *bdev, sector_t block,
> + unsigned size, gfp_t gfp);
> void __brelse(struct buffer_head *);
> void __bforget(struct buffer_head *);
> void __breadahead(struct block_device *, sector_t block, unsigned int size);
> struct buffer_head *__bread(struct block_device *, sector_t block, unsigned size);
> +struct buffer_head *__bread_gfp(struct block_device *,
> + sector_t block, unsigned size, gfp_t gfp);
> void invalidate_bh_lrus(void);
> struct buffer_head *alloc_buffer_head(gfp_t gfp_flags);
> void free_buffer_head(struct buffer_head * bh);
> @@ -295,7 +299,13 @@ static inline void bforget(struct buffer_head *bh)
> static inline struct buffer_head *
> sb_bread(struct super_block *sb, sector_t block)
> {
> - return __bread(sb->s_bdev, block, sb->s_blocksize);
> + return __bread_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE);
> +}
> +
> +static inline struct buffer_head *
> +sb_bread_gfp(struct super_block *sb, sector_t block, gfp_t gfp)
> +{
> + return __bread_gfp(sb->s_bdev, block, sb->s_blocksize, gfp);
> }
I think Andrew was suggesting to provide sb_bread_unmovable() and
sb_getblk_unmovable() which would set appropriately. It is then more
obvious what are filesystems trying to do when using those functions...
Honza
--
Jan Kara <jack@xxxxxxx>
SUSE Labs, CR
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
