[04/13] mm: split ->readpages calls to avoid non-contiguous pages lists

Commit Message

Christoph Hellwig May 30, 2018, 9:58 a.m. UTC

That way file systems don't have to go spotting for non-contiguous pages
and work around them.  It also kicks off I/O earlier, allowing it to
finish earlier and reduce latency.

Signed-off-by: Christoph Hellwig <[e-mail]>
Reviewed-by: Darrick J. Wong <[e-mail]>
---
 mm/readahead.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

Comments

Dave Chinner May 30, 2018, 11:02 p.m. UTC | #1

On Wed, May 30, 2018 at 11:58:04AM +0200, Christoph Hellwig wrote:
> That way file systems don't have to go spotting for non-contiguous pages
> and work around them.  It also kicks off I/O earlier, allowing it to
> finish earlier and reduce latency.
> 
> Signed-off-by: Christoph Hellwig <[e-mail]>
> Reviewed-by: Darrick J. Wong <[e-mail]>

Looks fine.

Reviewed-by: Dave Chinner <[e-mail]>

Patch

diff --git a/mm/readahead.c b/mm/readahead.c
index fa4d4b767130..e273f0de3376 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -140,8 +140,8 @@  static int read_pages(struct address_space *mapping, struct file *filp,
 }
 
 /*
- * __do_page_cache_readahead() actually reads a chunk of disk.  It allocates all
- * the pages first, then submits them all for I/O. This avoids the very bad
+ * __do_page_cache_readahead() actually reads a chunk of disk.  It allocates
+ * the pages first, then submits them for I/O. This avoids the very bad
  * behaviour which would occur if page allocations are causing VM writeback.
  * We really don't want to intermingle reads and writes like that.
  *
@@ -177,8 +177,18 @@  unsigned int __do_page_cache_readahead(struct address_space *mapping,
 		rcu_read_lock();
 		page = radix_tree_lookup(&mapping->i_pages, page_offset);
 		rcu_read_unlock();
-		if (page && !radix_tree_exceptional_entry(page))
+		if (page && !radix_tree_exceptional_entry(page)) {
+			/*
+			 * Page already present?  Kick off the current batch of
+			 * contiguous pages before continuing with the next
+			 * batch.
+			 */
+			if (nr_pages)
+				read_pages(mapping, filp, &page_pool, nr_pages,
+						gfp_mask);
+			nr_pages = 0;
 			continue;
+		}
 
 		page = __page_cache_alloc(gfp_mask);
 		if (!page)