If wbc.sync_mode is WBC_SYNC_ALL, then in the page writeback paths we
will be waiting for the write to complete. So the I/O should be
submitted via submit_bh() with WRITE_SYNC so the block layer should
properly prioritize the I/O.
Signed-off-by: "Theodore Ts'o" <tytso@xxxxxxx>
Cc: linux-mm@xxxxxxxxxxxxxxx
---
Following up with an e-mail thread started by Arjan two months ago,
(subject: [PATCH] Give kjournald a IOPRIO_CLASS_RT io priority), I have
a patch, just sent to linux-ext4@xxxxxxxxxxxxxxx, which fixes the jbd2
layer to submit journal writes via submit_bh() with WRITE_SYNC.
Hopefully this might be enough of a priority boost so we don't have to
force a higher I/O priority level via a buffer_head flag. However,
while looking through the code paths, in ordered data mode, we end up
flushing data pages via the page writeback paths on a per-inode basis,
and I noticed that even though we are passing in
wbc.sync_mode=WBC_SYNC_ALL, __block_write_full_page() is using
submit_bh(WRITE, bh) instead of submit_bh(WRITE_SYNC).
I'm not completely confident in my understanding of the page writeback
code paths --- does this change make sense?
- Ted
fs/buffer.c | 6 ++++--
1 files changed, 4 insertions(+), 2 deletions(-)
diff --git a/fs/buffer.c b/fs/buffer.c
index 10179cf..392b1b3 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1741,7 +1741,8 @@ static int __block_write_full_page(struct inode *inode, struct page *page,
do {
struct buffer_head *next = bh->b_this_page;
if (buffer_async_write(bh)) {
- submit_bh(WRITE, bh);
+ submit_bh((wbc->sync_mode == WB_SYNC_ALL) ?
+ WRITE_SYNC : WRITE, bh);
nr_underway++;
}
bh = next;
@@ -1795,7 +1796,8 @@ recover:
struct buffer_head *next = bh->b_this_page;
if (buffer_async_write(bh)) {
clear_buffer_dirty(bh);
- submit_bh(WRITE, bh);
+ submit_bh((wbc->sync_mode == WB_SYNC_ALL) ?
+ WRITE_SYNC : WRITE, bh);
nr_underway++;
}
bh = next;
--
1.6.0.4.8.g36f27.dirty
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
