From: Wang Yugui <wangyugui@e16-tech.com>
To: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: linux-fsdevel@vger.kernel.org, linux-xfs@vger.kernel.org,
Dave Chinner <david@fromorbit.com>,
Christoph Hellwig <hch@infradead.org>,
"Darrick J . Wong" <djwong@kernel.org>
Subject: Re: [PATCH v2 0/7] Create large folios in iomap buffered write path
Date: Sun, 04 Jun 2023 08:19:41 +0800 [thread overview]
Message-ID: <20230604081939.241D.409509F4@e16-tech.com> (raw)
In-Reply-To: <20230602222445.2284892-1-willy@infradead.org>
[-- Attachment #1: Type: text/plain, Size: 3301 bytes --]
Hi,
> Commit ebb7fb1557b1 limited the length of ioend chains to 4096 entries
> to improve worst-case latency. Unfortunately, this had the effect of
> limiting the performance of:
>
> fio -name write-bandwidth -rw=write -bs=1024Ki -size=32Gi -runtime=30 \
> -iodepth 1 -ioengine sync -zero_buffers=1 -direct=0 -end_fsync=1 \
> -numjobs=4 -directory=/mnt/test
>
> The problem ends up being lock contention on the i_pages spinlock as we
> clear the writeback bit on each folio (and propagate that up through
> the tree). By using larger folios, we decrease the number of folios
> to be processed by a factor of 256 for this benchmark, eliminating the
> lock contention.
>
> It's also the right thing to do. This is a project that has been on
> the back burner for years, it just hasn't been important enough to do
> before now.
>
> I think it's probably best if this goes through the iomap tree since
> the changes outside iomap are either to the page cache or they're
> trivial.
>
> v2:
> - Fix misplaced semicolon
> - Rename fgp_order to fgp_set_order
> - Rename FGP_ORDER to FGP_GET_ORDER
> - Add fgp_t
> - Update the documentation for ->release_folio
> - Fix iomap_invalidate_folio()
> - Update iomap_release_folio()
It works well based on 6.4-rc4 here.
fio write bandwidth: about 8000MiB/s
And I tried to backport it to 6.1.y, it works well too.
1) 8 patches are selected as depency.
d7b64041164c :Dave Chinner: iomap: write iomap validity checks
7a70a5085ed0 :Andreas Gruenbacher: iomap: Add __iomap_put_folio helper
80baab88bb93 :Andreas Gruenbacher: iomap/gfs2: Unlock and put folio in page_done handler
40405dddd98a :Andreas Gruenbacher: iomap: Rename page_done handler to put_folio
98321b5139f9 :Andreas Gruenbacher: iomap: Add iomap_get_folio helper
9060bc4d3aca :Andreas Gruenbacher: iomap/gfs2: Get page in page_prepare handler
07c22b56685d :Andreas Gruenbacher: iomap: Add __iomap_get_folio helper
c82abc239464 :Andreas Gruenbacher: iomap: Rename page_prepare handler to get_folio
2) patch 4/5/6 are rebased (see attachment files)
better backport are welcome.
Best Regards
Wang Yugui (wangyugui@e16-tech.com)
2023/06/04
> Matthew Wilcox (Oracle) (7):
> iomap: Remove large folio handling in iomap_invalidate_folio()
> doc: Correct the description of ->release_folio
> iomap: Remove unnecessary test from iomap_release_folio()
> filemap: Add fgp_t typedef
> filemap: Allow __filemap_get_folio to allocate large folios
> iomap: Create large folios in the buffered write path
> iomap: Copy larger chunks from userspace
>
> Documentation/filesystems/locking.rst | 14 ++++--
> fs/btrfs/file.c | 6 +--
> fs/f2fs/compress.c | 2 +-
> fs/f2fs/f2fs.h | 2 +-
> fs/gfs2/bmap.c | 2 +-
> fs/iomap/buffered-io.c | 43 ++++++++--------
> include/linux/iomap.h | 2 +-
> include/linux/pagemap.h | 71 ++++++++++++++++++++++-----
> mm/filemap.c | 61 ++++++++++++-----------
> mm/folio-compat.c | 2 +-
> mm/readahead.c | 13 -----
> 11 files changed, 130 insertions(+), 88 deletions(-)
>
> --
> 2.39.2
[-- Attachment #2: 0006-iomap-Create-large-folios-in-the-buffered-write-path.patch --]
[-- Type: application/octet-stream, Size: 3082 bytes --]
From 6901e07ceeb77f9bfe9b38fc46ff20437d293007 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Fri, 2 Jun 2023 23:24:43 +0100
Subject: [PATCH] iomap: Create large folios in the buffered write path
Use the size of the write as a hint for the size of the folio to create.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
fs/gfs2/bmap.c | 2 +-
fs/iomap/buffered-io.c | 6 ++++--
include/linux/iomap.h | 2 +-
3 files changed, 6 insertions(+), 4 deletions(-)
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index c739b258a2d9..3702e5e47b0f 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -971,7 +971,7 @@ gfs2_iomap_get_folio(struct iomap_iter *iter, loff_t pos, unsigned len)
if (status)
return ERR_PTR(status);
- folio = iomap_get_folio(iter, pos);
+ folio = iomap_get_folio(iter, pos, len);
if (IS_ERR(folio))
gfs2_trans_end(sdp);
return folio;
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 30d53b50ee0f..a10f9c037515 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -461,17 +461,19 @@ EXPORT_SYMBOL_GPL(iomap_is_partially_uptodate);
* iomap_get_folio - get a folio reference for writing
* @iter: iteration structure
* @pos: start offset of write
+ * @len: length of write
*
* Returns a locked reference to the folio at @pos, or an error pointer if the
* folio could not be obtained.
*/
-struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos)
+struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos, size_t len)
{
fgp_t fgp = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE | FGP_NOFS;
struct folio *folio;
if (iter->flags & IOMAP_NOWAIT)
fgp |= FGP_NOWAIT;
+ fgp |= fgp_set_order(len);
folio = __filemap_get_folio(iter->inode->i_mapping, pos >> PAGE_SHIFT,
fgp, mapping_gfp_mask(iter->inode->i_mapping));
@@ -596,7 +598,7 @@ static struct folio *__iomap_get_folio(struct iomap_iter *iter, loff_t pos,
if (page_ops && page_ops->get_folio)
return page_ops->get_folio(iter, pos, len);
else
- return iomap_get_folio(iter, pos);
+ return iomap_get_folio(iter, pos, len);
}
static void __iomap_put_folio(struct iomap_iter *iter, loff_t pos, size_t ret,
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index e2b836c2e119..80facb9c9e5b 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -261,7 +261,7 @@ int iomap_file_buffered_write_punch_delalloc(struct inode *inode,
int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops);
void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops);
bool iomap_is_partially_uptodate(struct folio *, size_t from, size_t count);
-struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos);
+struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos, size_t len);
bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags);
void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len);
int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
--
2.36.2
[-- Attachment #3: 0004-filemap-Add-fgp_t-typedef.patch --]
[-- Type: application/octet-stream, Size: 7780 bytes --]
From 22b61cbd1429c25dbcd0548034894be2011e1544 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Fri, 2 Jun 2023 23:24:41 +0100
Subject: [PATCH] filemap: Add fgp_t typedef
Similarly to gfp_t, define fgp_t as its own type to prevent various
misuses and confusion. Move the documentation to the definition of the
type insted of burying it in the __filemap_get_folio() documentation.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
fs/btrfs/file.c | 6 +++---
fs/f2fs/compress.c | 2 +-
fs/f2fs/f2fs.h | 2 +-
fs/iomap/buffered-io.c | 2 +-
include/linux/pagemap.h | 32 +++++++++++++++++++++++++++++---
mm/filemap.c | 21 ++-------------------
mm/folio-compat.c | 2 +-
7 files changed, 46 insertions(+), 35 deletions(-)
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index f649647392e0..4bbbbdafb472 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -876,9 +876,9 @@ static int prepare_uptodate_page(struct inode *inode,
return 0;
}
-static unsigned int get_prepare_fgp_flags(bool nowait)
+static fgp_t get_prepare_fgp_flags(bool nowait)
{
- unsigned int fgp_flags = FGP_LOCK | FGP_ACCESSED | FGP_CREAT;
+ fgp_t fgp_flags = FGP_LOCK | FGP_ACCESSED | FGP_CREAT;
if (nowait)
fgp_flags |= FGP_NOWAIT;
@@ -910,7 +910,7 @@ static noinline int prepare_pages(struct inode *inode, struct page **pages,
int i;
unsigned long index = pos >> PAGE_SHIFT;
gfp_t mask = get_prepare_gfp_flags(inode, nowait);
- unsigned int fgp_flags = get_prepare_fgp_flags(nowait);
+ fgp_t fgp_flags = get_prepare_fgp_flags(nowait);
int err = 0;
int faili;
diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
index 11653fa79289..ee358f5f2a86 100644
--- a/fs/f2fs/compress.c
+++ b/fs/f2fs/compress.c
@@ -1019,7 +1019,7 @@ static int prepare_compress_overwrite(struct compress_ctx *cc,
struct address_space *mapping = cc->inode->i_mapping;
struct page *page;
sector_t last_block_in_bio;
- unsigned fgp_flag = FGP_LOCK | FGP_WRITE | FGP_CREAT;
+ fgp_t fgp_flag = FGP_LOCK | FGP_WRITE | FGP_CREAT;
pgoff_t start_idx = start_idx_of_cluster(cc);
int i, ret;
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index d211ee89c158..a03c3df75f7c 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -2715,7 +2715,7 @@ static inline struct page *f2fs_grab_cache_page(struct address_space *mapping,
static inline struct page *f2fs_pagecache_get_page(
struct address_space *mapping, pgoff_t index,
- int fgp_flags, gfp_t gfp_mask)
+ fgp_t fgp_flags, gfp_t gfp_mask)
{
if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_GET)) {
f2fs_show_injection_info(F2FS_M_SB(mapping), FAULT_PAGE_GET);
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 2054b85c9d9b..30d53b50ee0f 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -467,7 +467,7 @@ EXPORT_SYMBOL_GPL(iomap_is_partially_uptodate);
*/
struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos)
{
- unsigned fgp = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE | FGP_NOFS;
+ fgp_t fgp = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE | FGP_NOFS;
struct folio *folio;
if (iter->flags & IOMAP_NOWAIT)
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index a56308a9d1a4..7ab57a2bb576 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -497,6 +497,32 @@ pgoff_t page_cache_next_miss(struct address_space *mapping,
pgoff_t page_cache_prev_miss(struct address_space *mapping,
pgoff_t index, unsigned long max_scan);
+/**
+ * typedef fgp_t - Flags for getting folios from the page cache.
+ *
+ * Most users of the page cache will not need to use these flags;
+ * there are convenience functions such as filemap_get_folio() and
+ * filemap_lock_folio(). For users which need more control over exactly
+ * what is done with the folios, these flags to __filemap_get_folio()
+ * are available.
+ *
+ * * %FGP_ACCESSED - The folio will be marked accessed.
+ * * %FGP_LOCK - The folio is returned locked.
+ * * %FGP_CREAT - If no folio is present then a new folio is allocated,
+ * added to the page cache and the VM's LRU list. The folio is
+ * returned locked.
+ * * %FGP_FOR_MMAP - The caller wants to do its own locking dance if the
+ * folio is already in cache. If the folio was allocated, unlock it
+ * before returning so the caller can do the same dance.
+ * * %FGP_WRITE - The folio will be written to by the caller.
+ * * %FGP_NOFS - __GFP_FS will get cleared in gfp.
+ * * %FGP_NOWAIT - Don't block on the folio lock.
+ * * %FGP_STABLE - Wait for the folio to be stable (finished writeback)
+ * * %FGP_WRITEBEGIN - The flags to use in a filesystem write_begin()
+ * implementation.
+ */
+typedef unsigned int fgp_t;
+
#define FGP_ACCESSED 0x00000001
#define FGP_LOCK 0x00000002
#define FGP_CREAT 0x00000004
@@ -509,9 +535,9 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping,
#define FGP_STABLE 0x00000200
struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
- int fgp_flags, gfp_t gfp);
+ fgp_t fgp_flags, gfp_t gfp);
struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index,
- int fgp_flags, gfp_t gfp);
+ fgp_t fgp_flags, gfp_t gfp);
/**
* filemap_get_folio - Find and get a folio.
@@ -586,7 +612,7 @@ static inline struct page *find_get_page(struct address_space *mapping,
}
static inline struct page *find_get_page_flags(struct address_space *mapping,
- pgoff_t offset, int fgp_flags)
+ pgoff_t offset, fgp_t fgp_flags)
{
return pagecache_get_page(mapping, offset, fgp_flags, 0);
}
diff --git a/mm/filemap.c b/mm/filemap.c
index b4c9bd368b7e..eb89a815f2f8 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1882,32 +1882,15 @@ static void *mapping_get_entry(struct address_space *mapping, pgoff_t index)
*
* Looks up the page cache entry at @mapping & @index.
*
- * @fgp_flags can be zero or more of these flags:
- *
- * * %FGP_ACCESSED - The folio will be marked accessed.
- * * %FGP_LOCK - The folio is returned locked.
- * * %FGP_ENTRY - If there is a shadow / swap / DAX entry, return it
- * instead of allocating a new folio to replace it.
- * * %FGP_CREAT - If no page is present then a new page is allocated using
- * @gfp and added to the page cache and the VM's LRU list.
- * The page is returned locked and with an increased refcount.
- * * %FGP_FOR_MMAP - The caller wants to do its own locking dance if the
- * page is already in cache. If the page was allocated, unlock it before
- * returning so the caller can do the same dance.
- * * %FGP_WRITE - The page will be written to by the caller.
- * * %FGP_NOFS - __GFP_FS will get cleared in gfp.
- * * %FGP_NOWAIT - Don't get blocked by page lock.
- * * %FGP_STABLE - Wait for the folio to be stable (finished writeback)
- *
* If %FGP_LOCK or %FGP_CREAT are specified then the function may sleep even
* if the %GFP flags specified for %FGP_CREAT are atomic.
*
- * If there is a page cache page, it is returned with an increased refcount.
+ * If this function returns a folio, it is returned with an increased refcount.
*
* Return: The found folio or %NULL otherwise.
*/
struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
- int fgp_flags, gfp_t gfp)
+ fgp_t fgp_flags, gfp_t gfp)
{
struct folio *folio;
diff --git a/mm/folio-compat.c b/mm/folio-compat.c
index c6f056c20503..ae1a737d2533 100644
--- a/mm/folio-compat.c
+++ b/mm/folio-compat.c
@@ -92,7 +92,7 @@ EXPORT_SYMBOL(add_to_page_cache_lru);
noinline
struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index,
- int fgp_flags, gfp_t gfp)
+ fgp_t fgp_flags, gfp_t gfp)
{
struct folio *folio;
--
2.36.2
[-- Attachment #4: 0005-filemap-Allow-__filemap_get_folio-to-allocate-large-.patch --]
[-- Type: application/octet-stream, Size: 5125 bytes --]
From a11bda0f117bc62a5fadba867a77637caf8100a3 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Fri, 2 Jun 2023 23:24:42 +0100
Subject: [PATCH] filemap: Allow __filemap_get_folio to allocate large folios
Allow callers of __filemap_get_folio() to specify a preferred folio
order in the FGP flags. This is only honoured in the FGP_CREATE path;
if there is already a folio in the page cache that covers the index,
we will return it, no matter what its order is. No create-around is
attempted; we will only create folios which start at the specified index.
Unmodified callers will continue to allocate order 0 folios.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
include/linux/pagemap.h | 23 ++++++++++++++++++++++
mm/filemap.c | 42 ++++++++++++++++++++++++++++-------------
mm/readahead.c | 13 -------------
3 files changed, 52 insertions(+), 26 deletions(-)
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 7ab57a2bb576..667ce668f438 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -466,6 +466,19 @@ static inline void *detach_page_private(struct page *page)
return folio_detach_private(page_folio(page));
}
+/*
+ * There are some parts of the kernel which assume that PMD entries
+ * are exactly HPAGE_PMD_ORDER. Those should be fixed, but until then,
+ * limit the maximum allocation order to PMD size. I'm not aware of any
+ * assumptions about maximum order if THP are disabled, but 8 seems like
+ * a good order (that's 1MB if you're using 4kB pages)
+ */
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define MAX_PAGECACHE_ORDER HPAGE_PMD_ORDER
+#else
+#define MAX_PAGECACHE_ORDER 8
+#endif
+
#ifdef CONFIG_NUMA
struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order);
#else
@@ -533,6 +546,16 @@ typedef unsigned int fgp_t;
#define FGP_HEAD 0x00000080
#define FGP_ENTRY 0x00000100
#define FGP_STABLE 0x00000200
+#define FGP_GET_ORDER(fgp) (((__force unsigned)fgp) >> 26) /* top 6 bits */
+
+static inline fgp_t fgp_set_order(size_t size)
+{
+ unsigned int shift = ilog2(size);
+
+ if (shift <= PAGE_SHIFT)
+ return 0;
+ return (__force fgp_t)((shift - PAGE_SHIFT) << 26);
+}
struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
fgp_t fgp_flags, gfp_t gfp);
diff --git a/mm/filemap.c b/mm/filemap.c
index eb89a815f2f8..10ea9321c36e 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1937,7 +1937,9 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
folio_wait_stable(folio);
no_page:
if (!folio && (fgp_flags & FGP_CREAT)) {
+ unsigned order = FGP_GET_ORDER(fgp_flags);
int err;
+
if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping))
gfp |= __GFP_WRITE;
if (fgp_flags & FGP_NOFS)
@@ -1946,26 +1948,40 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
gfp &= ~GFP_KERNEL;
gfp |= GFP_NOWAIT | __GFP_NOWARN;
}
-
- folio = filemap_alloc_folio(gfp, 0);
- if (!folio)
- return NULL;
-
if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP))))
fgp_flags |= FGP_LOCK;
- /* Init accessed so avoid atomic mark_page_accessed later */
- if (fgp_flags & FGP_ACCESSED)
- __folio_set_referenced(folio);
+ if (!mapping_large_folio_support(mapping))
+ order = 0;
+ if (order > MAX_PAGECACHE_ORDER)
+ order = MAX_PAGECACHE_ORDER;
+ /* If we're not aligned, allocate a smaller folio */
+ if (index & ((1UL << order) - 1))
+ order = __ffs(index);
- err = filemap_add_folio(mapping, folio, index, gfp);
- if (unlikely(err)) {
+ do {
+ err = -ENOMEM;
+ if (order == 1)
+ order = 0;
+ folio = filemap_alloc_folio(gfp, order);
+ if (!folio)
+ continue;
+
+ /* Init accessed so avoid atomic mark_page_accessed later */
+ if (fgp_flags & FGP_ACCESSED)
+ __folio_set_referenced(folio);
+
+ err = filemap_add_folio(mapping, folio, index, gfp);
+ if (!err)
+ break;
folio_put(folio);
folio = NULL;
- if (err == -EEXIST)
- goto repeat;
- }
+ } while (order-- > 0);
+ if (err == -EEXIST)
+ goto repeat;
+ if (err)
+ return ERR_PTR(err);
/*
* filemap_add_folio locks the page, and for mmap
* we expect an unlocked page.
diff --git a/mm/readahead.c b/mm/readahead.c
index 47afbca1d122..59a071badb90 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -462,19 +462,6 @@ static int try_context_readahead(struct address_space *mapping,
return 1;
}
-/*
- * There are some parts of the kernel which assume that PMD entries
- * are exactly HPAGE_PMD_ORDER. Those should be fixed, but until then,
- * limit the maximum allocation order to PMD size. I'm not aware of any
- * assumptions about maximum order if THP are disabled, but 8 seems like
- * a good order (that's 1MB if you're using 4kB pages)
- */
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-#define MAX_PAGECACHE_ORDER HPAGE_PMD_ORDER
-#else
-#define MAX_PAGECACHE_ORDER 8
-#endif
-
static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index,
pgoff_t mark, unsigned int order, gfp_t gfp)
{
--
2.36.2
[-- Attachment #5: 0006-iomap-Create-large-folios-in-the-buffered-write-path.patch --]
[-- Type: application/octet-stream, Size: 3082 bytes --]
From 6901e07ceeb77f9bfe9b38fc46ff20437d293007 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Fri, 2 Jun 2023 23:24:43 +0100
Subject: [PATCH] iomap: Create large folios in the buffered write path
Use the size of the write as a hint for the size of the folio to create.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
fs/gfs2/bmap.c | 2 +-
fs/iomap/buffered-io.c | 6 ++++--
include/linux/iomap.h | 2 +-
3 files changed, 6 insertions(+), 4 deletions(-)
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index c739b258a2d9..3702e5e47b0f 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -971,7 +971,7 @@ gfs2_iomap_get_folio(struct iomap_iter *iter, loff_t pos, unsigned len)
if (status)
return ERR_PTR(status);
- folio = iomap_get_folio(iter, pos);
+ folio = iomap_get_folio(iter, pos, len);
if (IS_ERR(folio))
gfs2_trans_end(sdp);
return folio;
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 30d53b50ee0f..a10f9c037515 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -461,17 +461,19 @@ EXPORT_SYMBOL_GPL(iomap_is_partially_uptodate);
* iomap_get_folio - get a folio reference for writing
* @iter: iteration structure
* @pos: start offset of write
+ * @len: length of write
*
* Returns a locked reference to the folio at @pos, or an error pointer if the
* folio could not be obtained.
*/
-struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos)
+struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos, size_t len)
{
fgp_t fgp = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE | FGP_NOFS;
struct folio *folio;
if (iter->flags & IOMAP_NOWAIT)
fgp |= FGP_NOWAIT;
+ fgp |= fgp_set_order(len);
folio = __filemap_get_folio(iter->inode->i_mapping, pos >> PAGE_SHIFT,
fgp, mapping_gfp_mask(iter->inode->i_mapping));
@@ -596,7 +598,7 @@ static struct folio *__iomap_get_folio(struct iomap_iter *iter, loff_t pos,
if (page_ops && page_ops->get_folio)
return page_ops->get_folio(iter, pos, len);
else
- return iomap_get_folio(iter, pos);
+ return iomap_get_folio(iter, pos, len);
}
static void __iomap_put_folio(struct iomap_iter *iter, loff_t pos, size_t ret,
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index e2b836c2e119..80facb9c9e5b 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -261,7 +261,7 @@ int iomap_file_buffered_write_punch_delalloc(struct inode *inode,
int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops);
void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops);
bool iomap_is_partially_uptodate(struct folio *, size_t from, size_t count);
-struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos);
+struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos, size_t len);
bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags);
void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len);
int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
--
2.36.2
prev parent reply other threads:[~2023-06-04 0:19 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-06-02 22:24 [PATCH v2 0/7] Create large folios in iomap buffered write path Matthew Wilcox (Oracle)
2023-06-02 22:24 ` [PATCH v2 1/7] iomap: Remove large folio handling in iomap_invalidate_folio() Matthew Wilcox (Oracle)
2023-06-04 17:58 ` Darrick J. Wong
2023-06-05 7:11 ` Christoph Hellwig
2023-06-02 22:24 ` [PATCH v2 2/7] doc: Correct the description of ->release_folio Matthew Wilcox (Oracle)
2023-06-04 17:55 ` Darrick J. Wong
2023-06-04 20:10 ` Matthew Wilcox
2023-06-04 20:33 ` Darrick J. Wong
2023-06-05 13:11 ` Matthew Wilcox
2023-06-05 15:07 ` Darrick J. Wong
2023-06-05 7:12 ` Christoph Hellwig
2023-06-02 22:24 ` [PATCH v2 3/7] iomap: Remove unnecessary test from iomap_release_folio() Matthew Wilcox (Oracle)
2023-06-04 18:01 ` Darrick J. Wong
2023-06-04 21:39 ` Matthew Wilcox
2023-06-05 21:10 ` Ritesh Harjani
2023-06-05 7:13 ` Christoph Hellwig
2023-06-02 22:24 ` [PATCH v2 4/7] filemap: Add fgp_t typedef Matthew Wilcox (Oracle)
2023-06-04 18:02 ` Darrick J. Wong
2023-06-05 7:14 ` Christoph Hellwig
2023-06-02 22:24 ` [PATCH v2 5/7] filemap: Allow __filemap_get_folio to allocate large folios Matthew Wilcox (Oracle)
2023-06-04 18:09 ` Darrick J. Wong
2023-06-04 21:48 ` Matthew Wilcox
2023-06-05 15:21 ` Darrick J. Wong
2023-06-05 7:16 ` Christoph Hellwig
2023-06-02 22:24 ` [PATCH v2 6/7] iomap: Create large folios in the buffered write path Matthew Wilcox (Oracle)
2023-06-04 18:10 ` Darrick J. Wong
2023-06-05 7:16 ` Christoph Hellwig
2023-06-02 22:24 ` [PATCH v2 7/7] iomap: Copy larger chunks from userspace Matthew Wilcox (Oracle)
2023-06-04 18:29 ` Darrick J. Wong
2023-06-04 22:11 ` Matthew Wilcox
2023-06-05 8:25 ` Yin, Fengwei
2023-06-06 18:07 ` Matthew Wilcox
2023-06-07 2:21 ` Yin Fengwei
2023-06-07 5:33 ` Yin, Fengwei
2023-06-07 15:55 ` Matthew Wilcox
2023-06-08 1:22 ` Yin Fengwei
2023-06-07 6:40 ` Yin Fengwei
2023-06-07 15:56 ` Matthew Wilcox
2023-06-04 0:19 ` Wang Yugui [this message]
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=20230604081939.241D.409509F4@e16-tech.com \
--to=wangyugui@e16-tech.com \
--cc=david@fromorbit.com \
--cc=djwong@kernel.org \
--cc=hch@infradead.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-xfs@vger.kernel.org \
--cc=willy@infradead.org \
/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).