btrfs: allocate page arrays more efficiently
v2 cover btrfs: allocate page arrays more efficiently
In several places, btrfs allocates an array of pages, one at a time. In addition to duplicating code, the mm subsystem provides a helper to allocate multiple pages at once into an array which is suited for our usecase. In the fast path, the batching can result in better allocation decisions and less locking. This changeset first adjusts the users to call a common array-of-pages allocation function, then adjusts that common function to use the batch page allocator.
v2: moved new helper to extent_io.[ch]. Fixed title format.
v1: https://lore.kernel.org/linux-btrfs/[email protected]/
Sweet Tea Dorminy (2):
btrfs: factor out allocating an array of pages
btrfs: allocate page arrays using bulk page allocator
fs/btrfs/check-integrity.c | 8 ++--- fs/btrfs/compression.c | 37 +++++++++----------- fs/btrfs/extent_io.c | 72 +++++++++++++++++++++++++++++--------- fs/btrfs/extent_io.h | 2 ++ fs/btrfs/inode.c | 10 +++--- fs/btrfs/raid56.c | 30 +++------------- 6 files changed, 85 insertions(+), 74 deletions(-)
Signature · 1 line
2.35.1
PATCH v2 1/2 btrfs: factor out allocating an array of pages
Several functions currently populate an array of page pointers one allocated page at a time; factor out the common code so as to allow improvements to all of the sites at once.
---
Changes in v2:
- moved the new btrfs_alloc_page_array() function to extent_io.[ch]
--- fs/btrfs/check-integrity.c | 8 ++--- fs/btrfs/compression.c | 37 ++++++++++------------ fs/btrfs/extent_io.c | 65 ++++++++++++++++++++++++++++---------- fs/btrfs/extent_io.h | 2 ++ fs/btrfs/inode.c | 10 +++--- fs/btrfs/raid56.c | 30 +++--------------- 6 files changed, 78 insertions(+), 74 deletions(-)
fs/btrfs/check-integrity.c +3 -5
@@ -1553,11 +1553,9 @@ static int btrfsic_read_block(struct btrfsic_state *state,return -ENOMEM ; block_ctx->datav = block_ctx->mem_to_free; block_ctx->pagev = (struct page **)(block_ctx->datav + num_pages); -for (i =0 ; i < num_pages; i++) { - block_ctx->pagev[i] =alloc_page (GFP_NOFS ); -if (!block_ctx->pagev[i]) -return -1 ; - } + ret =btrfs_alloc_page_array (num_pages, block_ctx->pagev); +if (ret) +return ret; dev_bytenr = block_ctx->dev_bytenr;for (i =0 ; i < num_pages;) {
fs/btrfs/compression.c +16 -21
@@ -801,8 +801,6 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,struct extent_map_tree *em_tree;struct compressed_bio *cb;unsigned int compressed_len; -unsigned int nr_pages; -unsigned int pg_index;struct bio *comp_bio =NULL ;const u64 disk_bytenr = bio->bi_iter.bi_sector <<SECTOR_SHIFT ;u64 cur_disk_byte = disk_bytenr;
@@ -812,7 +810,8 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,u64 em_start;struct extent_map *em;blk_status_t ret; -int faili =0 ; +int r; +int i;u8 *sums; em_tree = &BTRFS_I (inode)->extent_tree;
@@ -855,25 +854,20 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, cb->compress_type =extent_compress_type (bio_flags); cb->orig_bio = bio; - nr_pages =DIV_ROUND_UP (compressed_len,PAGE_SIZE ); - cb->compressed_pages =kcalloc (nr_pages,sizeof (struct page *), + cb->nr_pages =DIV_ROUND_UP (compressed_len,PAGE_SIZE ); + cb->compressed_pages =kcalloc (cb->nr_pages,sizeof (struct page *),GFP_NOFS );if (!cb->compressed_pages) { ret =BLK_STS_RESOURCE ; - goto fail1; + goto fail; } -for (pg_index =0 ; pg_index < nr_pages; pg_index++) { - cb->compressed_pages[pg_index] =alloc_page (GFP_NOFS ); -if (!cb->compressed_pages[pg_index]) { - faili = pg_index -1 ; - ret =BLK_STS_RESOURCE ; - goto fail2; - } + r =btrfs_alloc_page_array (cb->nr_pages, cb->compressed_pages); +if (r) { + ret =BLK_STS_RESOURCE ; + goto fail; } - faili = nr_pages -1 ; - cb->nr_pages = nr_pages; - +add_ra_bio_pages (inode, em_start + em_len, cb);/* include any pages we added in add_ra-bio_pages */
@@ -949,14 +943,15 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, }return BLK_STS_OK ; -fail2: -while (faili >=0 ) { -__free_page (cb->compressed_pages[faili]); - faili--; +fail: +if (cb->compressed_pages) { +for (i =0 ; i < cb->nr_pages; i++) { +if (cb->compressed_pages[i]) +__free_page (cb->compressed_pages[i]); + } }kfree (cb->compressed_pages); -fail1:kfree (cb); out:free_extent_map (em);
fs/btrfs/extent_io.c +49 -16
117 lines not on this page · raw message
fs/btrfs/extent_io.h +2 -0
@@ -277,6 +277,8 @@ void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end);void extent_clear_unlock_delalloc (struct btrfs_inode *inode,u64 start,u64 end,struct page *locked_page,u32 bits_to_clear,unsigned long page_ops); + +int btrfs_alloc_page_array (unsigned long nr_pages,struct page **page_array);struct bio *btrfs_bio_alloc (unsigned int nr_iovecs);struct bio *btrfs_bio_clone (struct bio *bio);struct bio *btrfs_bio_clone_partial (struct bio *orig,u64 offset,u64 size);
fs/btrfs/inode.c +4 -6
@@ -10427,13 +10427,11 @@ static ssize_t btrfs_encoded_read_regular(struct kiocb *iocb, pages =kcalloc (nr_pages,sizeof (struct page *),GFP_NOFS );if (!pages)return -ENOMEM ; -for (i =0 ; i < nr_pages; i++) { - pages[i] =alloc_page (GFP_NOFS ); -if (!pages[i]) { - ret = -ENOMEM ; - goto out; + ret =btrfs_alloc_page_array (nr_pages, pages); +if (ret) { + ret = -ENOMEM ; + goto out; } - } ret =btrfs_encoded_read_regular_fill_pages (inode, start, disk_bytenr, disk_io_size, pages);
fs/btrfs/raid56.c +4 -26
@@ -1026,37 +1026,15 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_fs_info *fs_info,/* allocate pages for all the stripes in the bio, including parity */ static int alloc_rbio_pages (struct btrfs_raid_bio *rbio) { -int i; -struct page *page; - -for (i =0 ; i < rbio->nr_pages; i++) { -if (rbio->stripe_pages[i]) -continue ; - page =alloc_page (GFP_NOFS ); -if (!page) -return -ENOMEM ; - rbio->stripe_pages[i] = page; - } -return 0 ; +return btrfs_alloc_page_array (rbio->nr_pages, rbio->stripe_pages); }/* only allocate pages for p/q stripes */ static int alloc_rbio_parity_pages (struct btrfs_raid_bio *rbio) { -int i; -struct page *page; - - i =rbio_stripe_page_index (rbio, rbio->nr_data,0 ); - -for (; i < rbio->nr_pages; i++) { -if (rbio->stripe_pages[i]) -continue ; - page =alloc_page (GFP_NOFS ); -if (!page) -return -ENOMEM ; - rbio->stripe_pages[i] = page; - } -return 0 ; +int data_pages =rbio_stripe_page_index (rbio, rbio->nr_data,0 ); +return btrfs_alloc_page_array (rbio->nr_pages - data_pages, + rbio->stripe_pages + data_pages); }/*
Signature · 1 line
2.35.1
PATCH v2 2/2 btrfs: allocate page arrays using bulk page allocator
In reply to Sweet Tea DorminyWhile calling alloc_page() in a loop is an effective way to populate an array of pages, the kernel provides a method to allocate pages in bulk. alloc_pages_bulk_array() populates the NULL slots in a page array, trying to grab more than one page at a time.
Unfortunately, it doesn't guarantee allocating all slots in the array, but it's easy to call it in a loop and return an error if no progress occurs. Similar code can be found in xfs/xfs_buf.c:xfs_buf_alloc_pages().
---
Changes in v2:
- Moved from ctree.c to extent_io.c
--- fs/btrfs/extent_io.c | 25 ++++++++++++++++--------- 1 file changed, 16 insertions(+), 9 deletions(-)
fs/btrfs/extent_io.c +16 -9
@@ -3144,17 +3144,24 @@ static void end_bio_extent_readpage(struct bio *bio)*/ int btrfs_alloc_page_array (unsigned long nr_pages,struct page **page_array) { -int i; -for (i =0 ; i < nr_pages; i++) { -struct page *page; -if (page_array[i]) +long allocated =0 ; +for (;;) { +long last = allocated; + + allocated =alloc_pages_bulk_array (GFP_NOFS , nr_pages, + page_array); +if (allocated == nr_pages) +return 0 ; + +if (allocated != last)continue ; - page =alloc_page (GFP_NOFS ); -if (!page) -return -ENOMEM ; - page_array[i] = page; +/* +* During this iteration, no page could be allocated, even +* though alloc_pages_bulk_array() falls back to alloc_page() +* if it could not bulk-allocate. So we must be out of memory. +*/ +return -ENOMEM ; } -return 0 ; }/*
Signature · 1 line
2.35.1
Quoted 9 lines · Sweet Tea Dorminy
In several places, btrfs allocates an array of pages, one at a time. In addition to duplicating code, the mm subsystem provides a helper to allocate multiple pages at once into an array which is suited for our usecase. In the fast path, the batching can result in better allocation decisions and less locking. This changeset first adjusts the users to call a common array-of-pages allocation function, then adjusts that common function to use the batch page allocator.
v2: moved new helper to extent_io.[ch]. Fixed title format.
It does not address comments from
https://lore.kernel.org/linux-btrfs/[email protected]
Quoted 9 lines · David Sterba
Quoted 8 lines · Sweet Tea Dorminy
In several places, btrfs allocates an array of pages, one at a time. In addition to duplicating code, the mm subsystem provides a helper to allocate multiple pages at once into an array which is suited for our usecase. In the fast path, the batching can result in better allocation decisions and less locking. This changeset first adjusts the users to call a common array-of-pages allocation function, then adjusts that common function to use the batch page allocator.
Quoted 4 lines
Quoted 1 line
v2: moved new helper to extent_io.[ch]. Fixed title format.
It does not address comments from
https://lore.kernel.org/linux-btrfs/[email protected]
I apologize, I completely missed the inline comments even though I thought something was missing and reread it a couple times... v3 soon.
Quoted 12 lines · Sweet Tea Dorminy
Quoted 9 lines · David Sterba
Quoted 8 lines · Sweet Tea Dorminy
In several places, btrfs allocates an array of pages, one at a time. In addition to duplicating code, the mm subsystem provides a helper to allocate multiple pages at once into an array which is suited for our usecase. In the fast path, the batching can result in better allocation decisions and less locking. This changeset first adjusts the users to call a common array-of-pages allocation function, then adjusts that common function to use the batch page allocator.
Quoted 6 lines
Quoted 4 lines
Quoted 1 line
v2: moved new helper to extent_io.[ch]. Fixed title format.
It does not address comments from
https://lore.kernel.org/linux-btrfs/[email protected]I apologize, I completely missed the inline comments even though I thought something was missing and reread it a couple times... v3 soon.
Yeah it's common to not trim a patch and write comments right next to the code, trimming to just a piece of code is also done if it's just the one thing to comment, but for example I go through the patch several times so trimming would not work very well.
If you're using mutt, there's a command (bound to T by default) that hides any quoted text.