Re: [PATCH 5/5] writeback: introduce writeback_control.more_io to indicate more io

2007-10-05 Thread Fengguang Wu
On Fri, Oct 05, 2007 at 05:41:03PM +1000, David Chinner wrote: > On Fri, Oct 05, 2007 at 11:36:52AM +0800, Fengguang Wu wrote: > > On Thu, Oct 04, 2007 at 03:03:44PM +1000, David Chinner wrote: > > > On Thu, Oct 04, 2007 at 10:21:33AM +0800, Fengguang Wu wrote: > > if (wbc.nr_to_write > 0 || wbc.p

Re: [PATCH 5/5] writeback: introduce writeback_control.more_io to indicate more io

2007-10-05 Thread David Chinner
On Fri, Oct 05, 2007 at 11:36:52AM +0800, Fengguang Wu wrote: > On Thu, Oct 04, 2007 at 03:03:44PM +1000, David Chinner wrote: > > On Thu, Oct 04, 2007 at 10:21:33AM +0800, Fengguang Wu wrote: > > > OK, I guess it is the focus of all your questions: Why should we sleep > > > in congestion_wait() an

Re: [PATCH 5/5] writeback: introduce writeback_control.more_io to indicate more io

2007-10-04 Thread Fengguang Wu
On Thu, Oct 04, 2007 at 03:03:44PM +1000, David Chinner wrote: > On Thu, Oct 04, 2007 at 10:21:33AM +0800, Fengguang Wu wrote: > > On Wed, Oct 03, 2007 at 12:41:19PM +1000, David Chinner wrote: > > > On Wed, Oct 03, 2007 at 09:34:39AM +0800, Fengguang Wu wrote: > > > > On Wed, Oct 03, 2007 at 07:47

Re: [PATCH 5/5] writeback: introduce writeback_control.more_io to indicate more io

2007-10-03 Thread David Chinner
On Thu, Oct 04, 2007 at 10:21:33AM +0800, Fengguang Wu wrote: > On Wed, Oct 03, 2007 at 12:41:19PM +1000, David Chinner wrote: > > On Wed, Oct 03, 2007 at 09:34:39AM +0800, Fengguang Wu wrote: > > > On Wed, Oct 03, 2007 at 07:47:45AM +1000, David Chinner wrote: > > > > On Tue, Oct 02, 2007 at 04:41

Re: [PATCH 5/5] writeback: introduce writeback_control.more_io to indicate more io

2007-10-03 Thread Fengguang Wu
On Wed, Oct 03, 2007 at 12:41:19PM +1000, David Chinner wrote: > On Wed, Oct 03, 2007 at 09:34:39AM +0800, Fengguang Wu wrote: > > On Wed, Oct 03, 2007 at 07:47:45AM +1000, David Chinner wrote: > > > On Tue, Oct 02, 2007 at 04:41:48PM +0800, Fengguang Wu wrote: > > > > wbc.pages_ski

Re: [PATCH 5/5] writeback: introduce writeback_control.more_io to indicate more io

2007-10-02 Thread David Chinner
On Wed, Oct 03, 2007 at 09:34:39AM +0800, Fengguang Wu wrote: > On Wed, Oct 03, 2007 at 07:47:45AM +1000, David Chinner wrote: > > On Tue, Oct 02, 2007 at 04:41:48PM +0800, Fengguang Wu wrote: > > > wbc.pages_skipped = 0; > > > @@ -560,8 +561,9 @@ static void background_writeout(unsigned

Re: [PATCH 5/5] writeback: introduce writeback_control.more_io to indicate more io

2007-10-02 Thread Fengguang Wu
On Wed, Oct 03, 2007 at 07:47:45AM +1000, David Chinner wrote: > On Tue, Oct 02, 2007 at 04:41:48PM +0800, Fengguang Wu wrote: > > wbc.pages_skipped = 0; > > @@ -560,8 +561,9 @@ static void background_writeout(unsigned > > min_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;

Re: [PATCH 5/5] writeback: introduce writeback_control.more_io to indicate more io

2007-10-02 Thread David Chinner
On Tue, Oct 02, 2007 at 04:41:48PM +0800, Fengguang Wu wrote: > wbc.pages_skipped = 0; > @@ -560,8 +561,9 @@ static void background_writeout(unsigned > min_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write; > if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {

[PATCH 5/5] writeback: introduce writeback_control.more_io to indicate more io

2007-10-02 Thread Fengguang Wu
After making dirty a 100M file, the normal behavior is to start the writeback for all data after 30s delays. But sometimes the following happens instead: - after 30s:~4M - after 5s: ~4M - after 5s: all remaining 92M Some analyze shows that the internal io dispa