Re: Bug in kernel 2.6.31, Slow wb_kupdate writeout

[Wu Fengguang <fengguang.wu@intel.com>]

On Fri, Jul 31, 2009 at 04:33:09AM +0800, Martin Bligh wrote:
> (BTW: background ... I'm not picking through this code for fun, I'm
> trying to debug writeback problems introduced in our new kernel
> that are affecting Google production workloads ;-))
> 
> >> Well, I see two problems. One is that we set more_io based on
> >> whether s_more_io is empty or not before we finish the loop.
> >> I can't see how this can be correct, especially as there can be
> >> other concurrent writers. So somehow we need to check when
> >> we exit the loop, not during it.
> >
> > It is correct inside the loop, however with some overheads.
> >
> > We put it inside the loop because sometimes the whole filesystem is
> > skipped and we shall not set more_io on them whether or not s_more_io
> > is empty.
> 
> My point was that you're setting more_io based on a condition
> at a point in time that isn't when you return to the caller.
> 
> By the time you return to the caller (after several more loops
> iterations), that condition may no longer be true.
> 
> One other way to address that would to be only to set if if we're
> about to fall off the end of the loop, ie change it to:
> 
> if (!list_empty(&sb->s_more_io) && list_empty(&sb->s_io))
>        wbc->more_io = 1;

Ah I see it (as the below patch), looks reasonable to me.

Thanks,
Fengguang

---
 fs/fs-writeback.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

--- sound-2.6.orig/fs/fs-writeback.c
+++ sound-2.6/fs/fs-writeback.c
@@ -544,9 +544,9 @@ void generic_sync_sb_inodes(struct super
 			wbc->more_io = 1;
 			break;
 		}
-		if (!list_empty(&sb->s_more_io))
-			wbc->more_io = 1;
 	}
+	if (!list_empty(&sb->s_more_io) && list_empty(&sb->s_io))
+			wbc->more_io = 1;
 
 	if (sync) {
 		struct inode *inode, *old_inode = NULL;