linux-btrfs.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: David Sterba <dsterba@suse.cz>
To: Qu Wenruo <wqu@suse.com>
Cc: linux-btrfs@vger.kernel.org
Subject: Re: [PATCH v2 4/4] btrfs: subpage: pack all subpage bitmaps into a larger bitmap
Date: Mon, 23 Aug 2021 18:57:46 +0200	[thread overview]
Message-ID: <20210823165746.GH5047@twin.jikos.cz> (raw)
In-Reply-To: <20210817093852.48126-5-wqu@suse.com>

On Tue, Aug 17, 2021 at 05:38:52PM +0800, Qu Wenruo wrote:
> Currently we use u16 bitmap to make 4k sectorsize work for 64K page
> size.
> 
> But this u16 bitmap is not large enough to contain larger page size like
> 128K, nor is space efficient for 16K page size.
> 
> To handle both cases, here we pack all subpage bitmaps into a larger
> bitmap, now btrfs_subpage::bitmaps[] will be the ultimate bitmap for
> subpage usage.
> 
> Each sub-bitmap will has its start bit number recorded in
> btrfs_subpage_info::*_start, and its bitmap length will be recorded in
> btrfs_subpage_info::bitmap_nr_bits.
> 
> All subpage bitmap operations will be converted from using direct u16
> operations to bitmap operations, with above *_start calculated.
> 
> For 64K page size with 4K sectorsize, this should not cause much
> difference.
> 
> While for 16K page size, we will only need 1 unsigned long (u32) to
> store all the bitmaps, which saves quite some space.
> 
> Furthermore, this allows us to support larger page size like 128K and
> 258K.
> 
> Signed-off-by: Qu Wenruo <wqu@suse.com>
> ---
>  fs/btrfs/extent_io.c |  59 +++++++++++--------
>  fs/btrfs/subpage.c   | 136 +++++++++++++++++++++++++++++--------------
>  fs/btrfs/subpage.h   |  19 +-----
>  3 files changed, 129 insertions(+), 85 deletions(-)
> 
> diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
> index 3c5770d47a95..fcb25ff86ea9 100644
> --- a/fs/btrfs/extent_io.c
> +++ b/fs/btrfs/extent_io.c
> @@ -3856,10 +3856,9 @@ static void find_next_dirty_byte(struct btrfs_fs_info *fs_info,
>  	struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
>  	u64 orig_start = *start;
>  	/* Declare as unsigned long so we can use bitmap ops */
> -	unsigned long dirty_bitmap;
>  	unsigned long flags;
> -	int nbits = (orig_start - page_offset(page)) >> fs_info->sectorsize_bits;
> -	int range_start_bit = nbits;
> +	int range_start_bit = fs_info->subpage_info->dirty_offset +
> +		(offset_in_page(orig_start) >> fs_info->sectorsize_bits);

There are several instances of fs_info->subpage_info so that warrants a
temporary variable.

>  	int range_end_bit;
>  
>  	/*
> @@ -3874,11 +3873,14 @@ static void find_next_dirty_byte(struct btrfs_fs_info *fs_info,
>  
>  	/* We should have the page locked, but just in case */
>  	spin_lock_irqsave(&subpage->lock, flags);
> -	dirty_bitmap = subpage->dirty_bitmap;
> +	bitmap_next_set_region(subpage->bitmaps, &range_start_bit, &range_end_bit,
> +			       fs_info->subpage_info->dirty_offset +
> +			       fs_info->subpage_info->bitmap_nr_bits);
>  	spin_unlock_irqrestore(&subpage->lock, flags);
>  
> -	bitmap_next_set_region(&dirty_bitmap, &range_start_bit, &range_end_bit,
> -			       BTRFS_SUBPAGE_BITMAP_SIZE);
> +	range_start_bit -= fs_info->subpage_info->dirty_offset;
> +	range_end_bit -= fs_info->subpage_info->dirty_offset;
> +
>  	*start = page_offset(page) + range_start_bit * fs_info->sectorsize;
>  	*end = page_offset(page) + range_end_bit * fs_info->sectorsize;
>  }
> @@ -4602,12 +4604,11 @@ static int submit_eb_subpage(struct page *page,
>  	int submitted = 0;
>  	u64 page_start = page_offset(page);
>  	int bit_start = 0;
> -	const int nbits = BTRFS_SUBPAGE_BITMAP_SIZE;
>  	int sectors_per_node = fs_info->nodesize >> fs_info->sectorsize_bits;
>  	int ret;
>  
>  	/* Lock and write each dirty extent buffers in the range */
> -	while (bit_start < nbits) {
> +	while (bit_start < fs_info->subpage_info->bitmap_nr_bits) {
>  		struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
>  		struct extent_buffer *eb;
>  		unsigned long flags;
> @@ -4623,7 +4624,8 @@ static int submit_eb_subpage(struct page *page,
>  			break;
>  		}
>  		spin_lock_irqsave(&subpage->lock, flags);
> -		if (!((1 << bit_start) & subpage->dirty_bitmap)) {
> +		if (!test_bit(bit_start + fs_info->subpage_info->dirty_offset,
> +			      subpage->bitmaps)) {
>  			spin_unlock_irqrestore(&subpage->lock, flags);
>  			spin_unlock(&page->mapping->private_lock);
>  			bit_start++;
> @@ -7170,32 +7172,41 @@ void memmove_extent_buffer(const struct extent_buffer *dst,
>  	}
>  }
>  
> +#define GANG_LOOKUP_SIZE	16
>  static struct extent_buffer *get_next_extent_buffer(
>  		struct btrfs_fs_info *fs_info, struct page *page, u64 bytenr)
>  {
> -	struct extent_buffer *gang[BTRFS_SUBPAGE_BITMAP_SIZE];
> +	struct extent_buffer *gang[GANG_LOOKUP_SIZE];
>  	struct extent_buffer *found = NULL;
>  	u64 page_start = page_offset(page);
> -	int ret;
> -	int i;
> +	u64 cur = page_start;
>  
>  	ASSERT(in_range(bytenr, page_start, PAGE_SIZE));
> -	ASSERT(PAGE_SIZE / fs_info->nodesize <= BTRFS_SUBPAGE_BITMAP_SIZE);
>  	lockdep_assert_held(&fs_info->buffer_lock);
>  
> -	ret = radix_tree_gang_lookup(&fs_info->buffer_radix, (void **)gang,
> -			bytenr >> fs_info->sectorsize_bits,
> -			PAGE_SIZE / fs_info->nodesize);
> -	for (i = 0; i < ret; i++) {
> -		/* Already beyond page end */
> -		if (gang[i]->start >= page_start + PAGE_SIZE)
> -			break;
> -		/* Found one */
> -		if (gang[i]->start >= bytenr) {
> -			found = gang[i];
> -			break;
> +	while (cur < page_start + PAGE_SIZE) {
> +		int ret;
> +		int i;
> +
> +		ret = radix_tree_gang_lookup(&fs_info->buffer_radix,
> +				(void **)gang, cur >> fs_info->sectorsize_bits,
> +				min_t(unsigned int, GANG_LOOKUP_SIZE,
> +				      PAGE_SIZE / fs_info->nodesize));
> +		if (ret == 0)
> +			goto out;
> +		for (i = 0; i < ret; i++) {
> +			/* Already beyond page end */
> +			if (gang[i]->start >= page_start + PAGE_SIZE)
> +				goto out;
> +			/* Found one */
> +			if (gang[i]->start >= bytenr) {
> +				found = gang[i];
> +				goto out;
> +			}
>  		}
> +		cur = gang[ret - 1]->start + gang[ret - 1]->len;
>  	}
> +out:
>  	return found;
>  }
>  
> diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c
> index c4fb2ce52207..578095c52a0f 100644
> --- a/fs/btrfs/subpage.c
> +++ b/fs/btrfs/subpage.c
> @@ -142,10 +142,13 @@ struct btrfs_subpage *btrfs_alloc_subpage(const struct btrfs_fs_info *fs_info,
>  					  enum btrfs_subpage_type type)
>  {
>  	struct btrfs_subpage *ret;
> +	unsigned int real_size;
>  
>  	ASSERT(fs_info->sectorsize < PAGE_SIZE);
>  
> -	ret = kzalloc(sizeof(struct btrfs_subpage), GFP_NOFS);
> +	real_size = struct_size(ret, bitmaps,
> +			BITS_TO_LONGS(fs_info->subpage_info->total_nr_bits));
> +	ret = kzalloc(real_size, GFP_NOFS);
>  	if (!ret)
>  		return ERR_PTR(-ENOMEM);
>  
> @@ -328,37 +331,60 @@ void btrfs_page_end_writer_lock(const struct btrfs_fs_info *fs_info,
>  		unlock_page(page);
>  }
>  
> -/*
> - * Convert the [start, start + len) range into a u16 bitmap
> - *
> - * For example: if start == page_offset() + 16K, len = 16K, we get 0x00f0.
> - */
> -static u16 btrfs_subpage_calc_bitmap(const struct btrfs_fs_info *fs_info,
> -		struct page *page, u64 start, u32 len)
> +static bool bitmap_test_range_all_set(unsigned long *addr, unsigned int start,
> +				      unsigned int nbits)
>  {
> -	const int bit_start = offset_in_page(start) >> fs_info->sectorsize_bits;
> -	const int nbits = len >> fs_info->sectorsize_bits;
> +	unsigned int found_zero;
>  
> -	btrfs_subpage_assert(fs_info, page, start, len);
> +	found_zero = find_next_zero_bit(addr, start + nbits, start);
> +	if (found_zero == start + nbits)
> +		return true;
> +	return false;
> +}
>  
> -	/*
> -	 * Here nbits can be 16, thus can go beyond u16 range. We make the
> -	 * first left shift to be calculate in unsigned long (at least u32),
> -	 * then truncate the result to u16.
> -	 */
> -	return (u16)(((1UL << nbits) - 1) << bit_start);
> +static bool bitmap_test_range_all_zero(unsigned long *addr, unsigned int start,
> +				       unsigned int nbits)
> +{
> +	unsigned int found_set;
> +
> +	found_set = find_next_bit(addr, start + nbits, start);
> +	if (found_set == start + nbits)
> +		return true;
> +	return false;
>  }
>  
> +#define subpage_calc_start_bit(fs_info, page, name, start, len)		\
> +({									\
> +	unsigned int start_bit;						\
> +									\
> +	btrfs_subpage_assert(fs_info, page, start, len);		\
> +	start_bit = offset_in_page(start) >> fs_info->sectorsize_bits;	\
> +	start_bit += fs_info->subpage_info->name##_offset;		\
> +	start_bit;							\
> +})
> +
> +#define subpage_test_bitmap_all_set(fs_info, subpage, name)		\
> +	bitmap_test_range_all_set(subpage->bitmaps,			\
> +			fs_info->subpage_info->name##_offset,		\
> +			fs_info->subpage_info->bitmap_nr_bits)
> +
> +#define subpage_test_bitmap_all_zero(fs_info, subpage, name)		\
> +	bitmap_test_range_all_zero(subpage->bitmaps,			\
> +			fs_info->subpage_info->name##_offset,		\
> +			fs_info->subpage_info->bitmap_nr_bits)
> +
>  void btrfs_subpage_set_uptodate(const struct btrfs_fs_info *fs_info,
>  		struct page *page, u64 start, u32 len)
>  {
>  	struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
> -	const u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len);
> +	unsigned int start_bit = subpage_calc_start_bit(fs_info, page,
> +							uptodate, start, len);
>  	unsigned long flags;
>  
>  	spin_lock_irqsave(&subpage->lock, flags);
> -	subpage->uptodate_bitmap |= tmp;
> -	if (subpage->uptodate_bitmap == U16_MAX)
> +	bitmap_set(subpage->bitmaps, start_bit,
> +		   len >> fs_info->sectorsize_bits);

All the bitmap_* calls like this and the parameter fit one line.

  parent reply	other threads:[~2021-08-23 17:00 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-17  9:38 [PATCH v2 0/2] btrfs: subpage: pack all subpage bitmaps into a larger bitmap Qu Wenruo
2021-08-17  9:38 ` [PATCH v2 1/4] btrfs: only call btrfs_alloc_subpage() when sectorsize is smaller than PAGE_SIZE Qu Wenruo
2021-08-17  9:38 ` [PATCH v2 2/4] btrfs: make btrfs_alloc_subpage() to return struct btrfs_subpage * directly Qu Wenruo
2021-08-17  9:38 ` [PATCH v2 3/4] btrfs: introduce btrfs_subpage_bitmap_info Qu Wenruo
2021-08-17 10:11   ` Nikolay Borisov
2021-08-23 16:45     ` David Sterba
2021-08-30 14:28       ` Nikolay Borisov
2021-08-23 16:41   ` David Sterba
2021-08-23 23:15     ` Qu Wenruo
2021-08-17  9:38 ` [PATCH v2 4/4] btrfs: subpage: pack all subpage bitmaps into a larger bitmap Qu Wenruo
2021-08-17 13:43   ` Nikolay Borisov
2021-08-23 17:00     ` David Sterba
2021-08-23 16:57   ` David Sterba [this message]
2021-08-23 23:16     ` Qu Wenruo
2021-08-24 14:20       ` David Sterba
2021-08-17 13:44 ` [PATCH v2 0/2] " Nikolay Borisov
2021-08-23 17:05 ` David Sterba

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210823165746.GH5047@twin.jikos.cz \
    --to=dsterba@suse.cz \
    --cc=linux-btrfs@vger.kernel.org \
    --cc=wqu@suse.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).