From: "Matthew Wilcox (Oracle)" <willy@xxxxxxxxxxxxx>
By definition, an extent covers a range of consecutive blocks, so
it would be quite rare to be able to just add pages to the BIO from
a previous range. The only case we can think of is a mapped extent
followed by a hole extent, followed by another mapped extent which has
been allocated immediately after the first extent. We believe this to
be an unlikely layout for a filesystem to choose and, since the queue
is plugged, those two BIOs would be merged by the block layer.
The reason we care is that ext2/ext4 choose to lay out blocks 0-11
consecutively, followed by the indirect block, and we want to merge those
two BIOs. If we don't submit the data BIO before asking the filesystem
for the next extent, then the indirect BIO will be submitted first,
and waited for, leading to inefficient I/O patterns. Buffer heads solve
this with the BH_boundary flag, but iomap doesn't need that as long as
we submit the bio here.
Signed-off-by: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
---
fs/iomap/buffered-io.c | 12 ++++++++++--
1 file changed, 10 insertions(+), 2 deletions(-)
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index f080f542911b..417115bfaf6b 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -420,6 +420,16 @@ iomap_readpages_actor(struct inode *inode, loff_t pos, loff_t length,
ctx, iomap, srcmap);
}
+ /*
+ * Submitting the bio here leads to better I/O patterns for
+ * filesystems which need to do metadata reads to find the
+ * next extent.
+ */
+ if (ctx->bio) {
+ submit_bio(ctx->bio);
+ ctx->bio = NULL;
+ }
+
return done;
}
@@ -449,8 +459,6 @@ iomap_readpages(struct address_space *mapping, struct list_head *pages,
}
ret = 0;
done:
- if (ctx.bio)
- submit_bio(ctx.bio);
if (ctx.cur_page) {
if (!ctx.cur_page_in_bio)
unlock_page(ctx.cur_page);
--
2.25.1
