[PATCH] btrfs: lower the dirty balance poll interval

[PATCH] btrfs: lower the dirty balance poll interval

[Wu Fengguang]

Tests show that the original large intervals can easily make the dirty
limit exceeded on 100 concurrent dd's. So adapt to as large as the
next check point selected by the dirty throttling algorithm.

Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
---
 fs/btrfs/file.c |    2 ++
 1 file changed, 2 insertions(+)

--- linux-next.orig/fs/btrfs/file.c	2011-11-17 20:18:51.000000000 +0800
+++ linux-next/fs/btrfs/file.c	2011-11-17 20:18:55.000000000 +0800
@@ -1168,6 +1168,8 @@ static noinline ssize_t __btrfs_buffered
 	nrptrs = min((iov_iter_count(i) + PAGE_CACHE_SIZE - 1) /
 		     PAGE_CACHE_SIZE, PAGE_CACHE_SIZE /
 		     (sizeof(struct page *)));
+	nrptrs = min(nrptrs, current->nr_dirtied_pause - current->nr_dirtied);
+	nrptrs = max(nrptrs, 8);
 	pages = kmalloc(nrptrs * sizeof(struct page *), GFP_KERNEL);
 	if (!pages)
 		return -ENOMEM;

Re: [PATCH] btrfs: lower the dirty balance poll interval

[Chris Mason]

On Thu, Nov 17, 2011 at 08:24:03PM +0800, Wu Fengguang wrote:
> Tests show that the original large intervals can easily make the dirty
> limit exceeded on 100 concurrent dd's. So adapt to as large as the
> next check point selected by the dirty throttling algorithm.

Thanks Wu, were you planning on pushing this through your tree or should
I take it?

-chris

Re: [PATCH] btrfs: lower the dirty balance poll interval

[Wu Fengguang]

On Tue, Nov 22, 2011 at 04:36:14AM +0800, Chris Mason wrote:
> On Thu, Nov 17, 2011 at 08:24:03PM +0800, Wu Fengguang wrote:
> > Tests show that the original large intervals can easily make the dirty
> > limit exceeded on 100 concurrent dd's. So adapt to as large as the
> > next check point selected by the dirty throttling algorithm.
> 
> Thanks Wu, were you planning on pushing this through your tree or should
> I take it?

Will you take it please?

Thanks,
Fengguang