@@ -946,9 +946,7 @@ static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached,
u64 block_start;
struct extent_map *em;
int ret = 0;
- size_t pg_offset = 0;
- size_t iosize;
- size_t blocksize = fs_info->sectorsize;
+ const size_t blocksize = fs_info->sectorsize;
ret = set_folio_extent_mapped(folio);
if (ret < 0) {
@@ -959,23 +957,22 @@ static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached,
if (folio->index == last_byte >> folio_shift(folio)) {
size_t zero_offset = offset_in_folio(folio, last_byte);
- if (zero_offset) {
- iosize = folio_size(folio) - zero_offset;
- folio_zero_range(folio, zero_offset, iosize);
- }
+ if (zero_offset)
+ folio_zero_range(folio, zero_offset,
+ folio_size(folio) - zero_offset);
}
bio_ctrl->end_io_func = end_bbio_data_read;
begin_folio_read(fs_info, folio);
- while (cur <= end) {
+ for (cur = start; cur <= end; cur += blocksize) {
enum btrfs_compression_type compress_type = BTRFS_COMPRESS_NONE;
+ unsigned long pg_offset = offset_in_folio(folio, cur);
bool force_bio_submit = false;
u64 disk_bytenr;
ASSERT(IS_ALIGNED(cur, fs_info->sectorsize));
if (cur >= last_byte) {
- iosize = folio_size(folio) - pg_offset;
- folio_zero_range(folio, pg_offset, iosize);
- end_folio_read(folio, true, cur, iosize);
+ folio_zero_range(folio, pg_offset, end - cur + 1);
+ end_folio_read(folio, true, cur, end - cur + 1);
break;
}
em = get_extent_map(BTRFS_I(inode), folio, cur, end - cur + 1, em_cached);
@@ -989,8 +986,6 @@ static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached,
compress_type = extent_map_compression(em);
- iosize = min(extent_map_end(em) - cur, end - cur + 1);
- iosize = ALIGN(iosize, blocksize);
if (compress_type != BTRFS_COMPRESS_NONE)
disk_bytenr = em->disk_bytenr;
else
@@ -1046,18 +1041,13 @@ static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached,
/* we've found a hole, just zero and go on */
if (block_start == EXTENT_MAP_HOLE) {
- folio_zero_range(folio, pg_offset, iosize);
-
- end_folio_read(folio, true, cur, iosize);
- cur = cur + iosize;
- pg_offset += iosize;
+ folio_zero_range(folio, pg_offset, blocksize);
+ end_folio_read(folio, true, cur, blocksize);
continue;
}
/* the get_extent function already copied into the folio */
if (block_start == EXTENT_MAP_INLINE) {
- end_folio_read(folio, true, cur, iosize);
- cur = cur + iosize;
- pg_offset += iosize;
+ end_folio_read(folio, true, cur, blocksize);
continue;
}
@@ -1068,12 +1058,9 @@ static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached,
if (force_bio_submit)
submit_one_bio(bio_ctrl);
- submit_extent_folio(bio_ctrl, disk_bytenr, folio, iosize,
+ submit_extent_folio(bio_ctrl, disk_bytenr, folio, blocksize,
pg_offset);
- cur = cur + iosize;
- pg_offset += iosize;
}
-
return 0;
}
Currently if a btrfs has block size (the older sector size) < page size, btrfs_do_readpage() will handle the range extent by extent, this is good for performance as it doesn't need to re-lookup the same extent map again and again. (Although __get_extent_map() already does extra cached em check, thus the optimization is not that obvious) This is totally fine and is a valid optimization, but it has an assumption that, there is no partial uptodate range in the page. Meanwhile there is an incoming feature, requiring btrfs to skip the full page read if a buffered write range covers a full block but not a full page. In that case, we can have a page that is partially uptodate, and the current per-extent lookup can not handle such case. So here we change btrfs_do_readpage() to do block-by-block read, this simplifies the following things: - Remove the need for @iosize variable Because we just use sectorsize as our increment. - Remove @pg_offset, and calculate it inside the loop when needed It's just offset_in_folio(). - Use a for() loop instead of a while() loop This will slightly reduce the read performance for block size < page size cases, but for the future where we can skip a full page read for a lot of cases, it should still be worthy. For block size == page size, this brings no performance change. Signed-off-by: Qu Wenruo <wqu@suse.com> --- fs/btrfs/extent_io.c | 37 ++++++++++++------------------------- 1 file changed, 12 insertions(+), 25 deletions(-)