Re: regression: 100% io-wait with 2.6.24-rcX

[Fengguang Wu]

On Wed, Jan 16, 2008 at 01:26:41AM -0800, Martin Knoblauch wrote:
> > For those interested in using your writeback improvements in
> > production sooner rather than later (primarily with ext3); what
> > recommendations do you have?  Just heavily test our own 2.6.24 + your
> > evolving "close, but not ready for merge" -mm writeback patchset?
> > 
> Hi Fengguang, Mike,
> 
>  I can add myself to Mikes question. It would be good to know a "roadmap" for the writeback changes. Testing 2.6.24-rcX so far has been showing quite nice improvement of the overall writeback situation and it would be sad to see this [partially] gone in 2.6.24-final. Linus apparently already has reverted  "...2250b". I will definitely repeat my tests with -rc8. and report.

Thank you, Martin. Can you help test this patch on 2.6.24-rc7?
Maybe we can push it to 2.6.24 after your testing.

Fengguang
---
 fs/fs-writeback.c         |   17 +++++++++++++++--
 include/linux/writeback.h |    1 +
 mm/page-writeback.c       |    9 ++++++---
 3 files changed, 22 insertions(+), 5 deletions(-)

--- linux.orig/fs/fs-writeback.c
+++ linux/fs/fs-writeback.c
@@ -284,7 +284,16 @@ __sync_single_inode(struct inode *inode,
 				 * soon as the queue becomes uncongested.
 				 */
 				inode->i_state |= I_DIRTY_PAGES;
-				requeue_io(inode);
+				if (wbc->nr_to_write <= 0)
+					/*
+					 * slice used up: queue for next turn
+					 */
+					requeue_io(inode);
+				else
+					/*
+					 * somehow blocked: retry later
+					 */
+					redirty_tail(inode);
 			} else {
 				/*
 				 * Otherwise fully redirty the inode so that
@@ -479,8 +488,12 @@ sync_sb_inodes(struct super_block *sb, s
 		iput(inode);
 		cond_resched();
 		spin_lock(&inode_lock);
-		if (wbc->nr_to_write <= 0)
+		if (wbc->nr_to_write <= 0) {
+			wbc->more_io = 1;
 			break;
+		}
+		if (!list_empty(&sb->s_more_io))
+			wbc->more_io = 1;
 	}
 	return;		/* Leave any unwritten inodes on s_io */
 }
--- linux.orig/include/linux/writeback.h
+++ linux/include/linux/writeback.h
@@ -62,6 +62,7 @@ struct writeback_control {
 	unsigned for_reclaim:1;		/* Invoked from the page allocator */
 	unsigned for_writepages:1;	/* This is a writepages() call */
 	unsigned range_cyclic:1;	/* range_start is cyclic */
+	unsigned more_io:1;		/* more io to be dispatched */
 };
 
 /*
--- linux.orig/mm/page-writeback.c
+++ linux/mm/page-writeback.c
@@ -558,6 +558,7 @@ static void background_writeout(unsigned
 			global_page_state(NR_UNSTABLE_NFS) < background_thresh
 				&& min_pages <= 0)
 			break;
+		wbc.more_io = 0;
 		wbc.encountered_congestion = 0;
 		wbc.nr_to_write = MAX_WRITEBACK_PAGES;
 		wbc.pages_skipped = 0;
@@ -565,8 +566,9 @@ static void background_writeout(unsigned
 		min_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
 		if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
 			/* Wrote less than expected */
-			congestion_wait(WRITE, HZ/10);
-			if (!wbc.encountered_congestion)
+			if (wbc.encountered_congestion || wbc.more_io)
+				congestion_wait(WRITE, HZ/10);
+			else
 				break;
 		}
 	}
@@ -631,11 +633,12 @@ static void wb_kupdate(unsigned long arg
 			global_page_state(NR_UNSTABLE_NFS) +
 			(inodes_stat.nr_inodes - inodes_stat.nr_unused);
 	while (nr_to_write > 0) {
+		wbc.more_io = 0;
 		wbc.encountered_congestion = 0;
 		wbc.nr_to_write = MAX_WRITEBACK_PAGES;
 		writeback_inodes(&wbc);
 		if (wbc.nr_to_write > 0) {
-			if (wbc.encountered_congestion)
+			if (wbc.encountered_congestion || wbc.more_io)
 				congestion_wait(WRITE, HZ/10);
 			else
 				break;	/* All the old data is written */

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/