From: Matthew Wilcox <willy@infradead.org>
To: linux-fsdevel@vger.kernel.org
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org,
linux-btrfs@vger.kernel.org, linux-erofs@lists.ozlabs.org,
linux-ext4@vger.kernel.org,
linux-f2fs-devel@lists.sourceforge.net, cluster-devel@redhat.com,
ocfs2-devel@oss.oracle.com, linux-xfs@vger.kernel.org
Subject: [PATCH v6 11/19] btrfs: Convert from readpages to readahead
Date: Mon, 17 Feb 2020 10:45:59 -0800 [thread overview]
Message-ID: <20200217184613.19668-19-willy@infradead.org> (raw)
In-Reply-To: <20200217184613.19668-1-willy@infradead.org>
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Use the new readahead operation in btrfs. Add a
readahead_for_each_batch() iterator to optimise the loop in the XArray.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
fs/btrfs/extent_io.c | 46 +++++++++++++----------------------------
fs/btrfs/extent_io.h | 3 +--
fs/btrfs/inode.c | 16 +++++++-------
include/linux/pagemap.h | 27 ++++++++++++++++++++++++
4 files changed, 49 insertions(+), 43 deletions(-)
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index c0f202741e09..e97a6acd6f5d 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4278,52 +4278,34 @@ int extent_writepages(struct address_space *mapping,
return ret;
}
-int extent_readpages(struct address_space *mapping, struct list_head *pages,
- unsigned nr_pages)
+void extent_readahead(struct readahead_control *rac)
{
struct bio *bio = NULL;
unsigned long bio_flags = 0;
struct page *pagepool[16];
struct extent_map *em_cached = NULL;
- struct extent_io_tree *tree = &BTRFS_I(mapping->host)->io_tree;
- int nr = 0;
+ struct extent_io_tree *tree = &BTRFS_I(rac->mapping->host)->io_tree;
u64 prev_em_start = (u64)-1;
+ int nr;
- while (!list_empty(pages)) {
- u64 contig_end = 0;
-
- for (nr = 0; nr < ARRAY_SIZE(pagepool) && !list_empty(pages);) {
- struct page *page = lru_to_page(pages);
-
- prefetchw(&page->flags);
- list_del(&page->lru);
- if (add_to_page_cache_lru(page, mapping, page->index,
- readahead_gfp_mask(mapping))) {
- put_page(page);
- break;
- }
-
- pagepool[nr++] = page;
- contig_end = page_offset(page) + PAGE_SIZE - 1;
- }
+ readahead_for_each_batch(rac, pagepool, ARRAY_SIZE(pagepool), nr) {
+ u64 contig_start = page_offset(pagepool[0]);
+ u64 contig_end = page_offset(pagepool[nr - 1]) + PAGE_SIZE - 1;
- if (nr) {
- u64 contig_start = page_offset(pagepool[0]);
+ ASSERT(contig_start + nr * PAGE_SIZE - 1 == contig_end);
- ASSERT(contig_start + nr * PAGE_SIZE - 1 == contig_end);
-
- contiguous_readpages(tree, pagepool, nr, contig_start,
- contig_end, &em_cached, &bio, &bio_flags,
- &prev_em_start);
- }
+ contiguous_readpages(tree, pagepool, nr, contig_start,
+ contig_end, &em_cached, &bio, &bio_flags,
+ &prev_em_start);
}
if (em_cached)
free_extent_map(em_cached);
- if (bio)
- return submit_one_bio(bio, 0, bio_flags);
- return 0;
+ if (bio) {
+ if (submit_one_bio(bio, 0, bio_flags))
+ return;
+ }
}
/*
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 5d205bbaafdc..bddac32948c7 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -198,8 +198,7 @@ int extent_writepages(struct address_space *mapping,
struct writeback_control *wbc);
int btree_write_cache_pages(struct address_space *mapping,
struct writeback_control *wbc);
-int extent_readpages(struct address_space *mapping, struct list_head *pages,
- unsigned nr_pages);
+void extent_readahead(struct readahead_control *rac);
int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len);
void set_page_extent_mapped(struct page *page);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 7d26b4bfb2c6..61d5137ce4e9 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4802,8 +4802,8 @@ static void evict_inode_truncate_pages(struct inode *inode)
/*
* Keep looping until we have no more ranges in the io tree.
- * We can have ongoing bios started by readpages (called from readahead)
- * that have their endio callback (extent_io.c:end_bio_extent_readpage)
+ * We can have ongoing bios started by readahead that have
+ * their endio callback (extent_io.c:end_bio_extent_readpage)
* still in progress (unlocked the pages in the bio but did not yet
* unlocked the ranges in the io tree). Therefore this means some
* ranges can still be locked and eviction started because before
@@ -7004,11 +7004,11 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
* for it to complete) and then invalidate the pages for
* this range (through invalidate_inode_pages2_range()),
* but that can lead us to a deadlock with a concurrent
- * call to readpages() (a buffered read or a defrag call
+ * call to readahead (a buffered read or a defrag call
* triggered a readahead) on a page lock due to an
* ordered dio extent we created before but did not have
* yet a corresponding bio submitted (whence it can not
- * complete), which makes readpages() wait for that
+ * complete), which makes readahead wait for that
* ordered extent to complete while holding a lock on
* that page.
*/
@@ -8247,11 +8247,9 @@ static int btrfs_writepages(struct address_space *mapping,
return extent_writepages(mapping, wbc);
}
-static int
-btrfs_readpages(struct file *file, struct address_space *mapping,
- struct list_head *pages, unsigned nr_pages)
+static void btrfs_readahead(struct readahead_control *rac)
{
- return extent_readpages(mapping, pages, nr_pages);
+ extent_readahead(rac);
}
static int __btrfs_releasepage(struct page *page, gfp_t gfp_flags)
@@ -10456,7 +10454,7 @@ static const struct address_space_operations btrfs_aops = {
.readpage = btrfs_readpage,
.writepage = btrfs_writepage,
.writepages = btrfs_writepages,
- .readpages = btrfs_readpages,
+ .readahead = btrfs_readahead,
.direct_IO = btrfs_direct_IO,
.invalidatepage = btrfs_invalidatepage,
.releasepage = btrfs_releasepage,
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 4f36c06d064d..1bbb60a0bf16 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -669,6 +669,33 @@ static inline void readahead_next(struct readahead_control *rac)
#define readahead_for_each(rac, page) \
for (; (page = readahead_page(rac)); readahead_next(rac))
+static inline unsigned int readahead_page_batch(struct readahead_control *rac,
+ struct page **array, unsigned int size)
+{
+ unsigned int batch = 0;
+ XA_STATE(xas, &rac->mapping->i_pages, rac->_start);
+ struct page *page;
+
+ rac->_batch_count = 0;
+ xas_for_each(&xas, page, rac->_start + rac->_nr_pages - 1) {
+ VM_BUG_ON_PAGE(!PageLocked(page), page);
+ VM_BUG_ON_PAGE(PageTail(page), page);
+ array[batch++] = page;
+ rac->_batch_count += hpage_nr_pages(page);
+ if (PageHead(page))
+ xas_set(&xas, rac->_start + rac->_batch_count);
+
+ if (batch == size)
+ break;
+ }
+
+ return batch;
+}
+
+#define readahead_for_each_batch(rac, array, size, nr) \
+ for (; (nr = readahead_page_batch(rac, array, size)); \
+ readahead_next(rac))
+
/* The byte offset into the file of this readahead block */
static inline loff_t readahead_offset(struct readahead_control *rac)
{
--
2.25.0
next prev parent reply other threads:[~2020-02-17 18:47 UTC|newest]
Thread overview: 111+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-02-17 18:45 [PATCH v6 00/19] Change readahead API Matthew Wilcox
2020-02-17 18:45 ` [PATCH v6 01/19] mm: Return void from various readahead functions Matthew Wilcox
2020-02-18 4:47 ` Dave Chinner
2020-02-18 21:05 ` John Hubbard
2020-02-18 21:21 ` Matthew Wilcox
2020-02-18 21:52 ` John Hubbard
2020-02-17 18:45 ` [PATCH v6 02/19] mm: Ignore return value of ->readpages Matthew Wilcox
2020-02-18 4:48 ` Dave Chinner
2020-02-18 21:33 ` John Hubbard
2020-02-17 18:45 ` [PATCH v6 03/19] mm: Use readahead_control to pass arguments Matthew Wilcox
2020-02-18 5:03 ` Dave Chinner
2020-02-18 13:56 ` Matthew Wilcox
2020-02-18 22:46 ` Dave Chinner
2020-02-18 22:52 ` Matthew Wilcox
2020-02-18 22:22 ` John Hubbard
2020-02-17 18:45 ` [PATCH v6 04/19] mm: Rearrange readahead loop Matthew Wilcox
2020-02-18 5:08 ` Dave Chinner
2020-02-18 13:57 ` Matthew Wilcox
2020-02-18 22:48 ` Dave Chinner
2020-02-18 22:33 ` John Hubbard
2020-02-17 18:45 ` [PATCH v6 04/16] mm: Tweak readahead loop slightly Matthew Wilcox
2020-02-18 22:57 ` John Hubbard
2020-02-18 23:00 ` John Hubbard
2020-02-17 18:45 ` [PATCH v6 05/16] mm: Put readahead pages in cache earlier Matthew Wilcox
2020-02-17 18:45 ` [PATCH v6 05/19] mm: Remove 'page_offset' from readahead loop Matthew Wilcox
2020-02-18 5:14 ` Dave Chinner
2020-02-18 23:08 ` John Hubbard
2020-02-17 18:45 ` [PATCH v6 06/16] mm: Add readahead address space operation Matthew Wilcox
2020-02-17 18:45 ` [PATCH v6 06/19] mm: rename readahead loop variable to 'i' Matthew Wilcox
2020-02-18 5:33 ` Dave Chinner
2020-02-18 23:11 ` John Hubbard
2020-02-17 18:45 ` [PATCH v6 07/16] mm: Add page_cache_readahead_limit Matthew Wilcox
2020-02-17 18:45 ` [PATCH v6 07/19] mm: Put readahead pages in cache earlier Matthew Wilcox
2020-02-18 6:14 ` Dave Chinner
2020-02-18 15:42 ` Matthew Wilcox
2020-02-19 0:59 ` Dave Chinner
2020-02-19 0:01 ` John Hubbard
2020-02-19 1:02 ` Matthew Wilcox
2020-02-19 1:13 ` John Hubbard
2020-02-19 3:24 ` John Hubbard
2020-02-19 14:41 ` Matthew Wilcox
2020-02-19 14:52 ` Christoph Hellwig
2020-02-19 15:01 ` Matthew Wilcox
2020-02-19 20:24 ` John Hubbard
2020-02-17 18:45 ` [PATCH v6 08/16] fs: Convert mpage_readpages to mpage_readahead Matthew Wilcox
2020-02-17 18:45 ` [PATCH v6 08/19] mm: Add readahead address space operation Matthew Wilcox
2020-02-18 6:21 ` Dave Chinner
2020-02-18 16:10 ` Matthew Wilcox
2020-02-19 1:04 ` Dave Chinner
2020-02-19 0:12 ` John Hubbard
2020-02-19 3:10 ` Eric Biggers
2020-02-19 3:35 ` Eric Biggers
2020-02-19 16:52 ` Matthew Wilcox
2020-02-17 18:45 ` [PATCH v6 09/16] btrfs: Convert from readpages to readahead Matthew Wilcox
2020-02-17 18:45 ` [PATCH v6 09/19] mm: Add page_cache_readahead_limit Matthew Wilcox
2020-02-18 6:31 ` Dave Chinner
2020-02-18 19:54 ` Matthew Wilcox
2020-02-19 1:08 ` Dave Chinner
2020-02-19 1:32 ` John Hubbard
2020-02-19 2:23 ` Matthew Wilcox
2020-02-19 2:46 ` John Hubbard
2020-02-17 18:45 ` [PATCH v6 10/16] erofs: Convert uncompressed files from readpages to readahead Matthew Wilcox
2020-02-17 18:45 ` [PATCH v6 10/19] fs: Convert mpage_readpages to mpage_readahead Matthew Wilcox
2020-02-18 1:51 ` [Ocfs2-devel] " Joseph Qi
2020-02-18 6:37 ` Dave Chinner
2020-02-19 2:48 ` John Hubbard
2020-02-19 3:28 ` Eric Biggers
2020-02-19 3:47 ` Matthew Wilcox
2020-02-19 3:55 ` Eric Biggers
2020-02-17 18:45 ` Matthew Wilcox [this message]
2020-02-18 6:57 ` [PATCH v6 11/19] btrfs: Convert from readpages to readahead Dave Chinner
2020-02-18 21:12 ` Matthew Wilcox
2020-02-19 1:23 ` Dave Chinner
2020-02-17 18:46 ` [PATCH v6 11/16] erofs: Convert compressed files " Matthew Wilcox
2020-02-19 2:34 ` Gao Xiang
2020-02-17 18:46 ` [PATCH v6 12/19] erofs: Convert uncompressed " Matthew Wilcox
2020-02-19 2:39 ` Gao Xiang
2020-02-19 3:04 ` Dave Chinner
2020-02-17 18:46 ` [PATCH v6 12/16] ext4: Convert " Matthew Wilcox
2020-02-17 18:46 ` [PATCH v6 13/19] erofs: Convert compressed files " Matthew Wilcox
2020-02-19 3:08 ` Dave Chinner
2020-02-17 18:46 ` [PATCH v6 13/16] f2fs: Convert " Matthew Wilcox
2020-02-17 18:46 ` [PATCH v6 14/19] ext4: " Matthew Wilcox
2020-02-19 3:16 ` Dave Chinner
2020-02-19 3:29 ` Eric Biggers
2020-02-17 18:46 ` [PATCH v6 14/16] fuse: " Matthew Wilcox
2020-02-17 18:46 ` [PATCH v6 15/19] f2fs: " Matthew Wilcox
2020-02-17 18:46 ` [PATCH v6 15/16] iomap: " Matthew Wilcox
2020-02-17 18:46 ` [PATCH v6 16/19] fuse: " Matthew Wilcox
2020-02-19 3:22 ` Dave Chinner
2020-02-17 18:46 ` [PATCH v6 16/16] mm: Use memalloc_nofs_save in readahead path Matthew Wilcox
2020-02-17 18:46 ` [PATCH v6 17/19] iomap: Restructure iomap_readpages_actor Matthew Wilcox
2020-02-19 3:17 ` John Hubbard
2020-02-19 5:35 ` Matthew Wilcox
2020-02-19 3:29 ` Dave Chinner
2020-02-19 6:04 ` Matthew Wilcox
2020-02-19 6:40 ` Dave Chinner
2020-02-19 17:06 ` Matthew Wilcox
2020-02-17 18:46 ` [PATCH v6 18/19] iomap: Convert from readpages to readahead Matthew Wilcox
2020-02-19 3:40 ` Dave Chinner
2020-02-17 18:46 ` [PATCH v6 19/19] mm: Use memalloc_nofs_save in readahead path Matthew Wilcox
2020-02-19 3:43 ` Dave Chinner
2020-02-19 5:22 ` Matthew Wilcox
2020-02-17 18:48 ` [PATCH v6 00/19] Change readahead API Matthew Wilcox
2020-02-18 4:56 ` Dave Chinner
2020-02-18 13:42 ` Matthew Wilcox
2020-02-18 21:26 ` Dave Chinner
2020-02-19 3:45 ` Dave Chinner
2020-02-19 3:48 ` Matthew Wilcox
2020-02-19 3:57 ` Dave Chinner
2020-02-18 20:49 ` John Hubbard
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=20200217184613.19668-19-willy@infradead.org \
--to=willy@infradead.org \
--cc=cluster-devel@redhat.com \
--cc=linux-btrfs@vger.kernel.org \
--cc=linux-erofs@lists.ozlabs.org \
--cc=linux-ext4@vger.kernel.org \
--cc=linux-f2fs-devel@lists.sourceforge.net \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-xfs@vger.kernel.org \
--cc=ocfs2-devel@oss.oracle.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).