Re: [PATCH v3 14/15] dax: dirty extent notification

2015-11-03 Thread Dan Williams
On Tue, Nov 3, 2015 at 1:37 PM, Ross Zwisler wrote: > On Wed, Nov 04, 2015 at 07:51:31AM +1100, Dave Chinner wrote: >> On Mon, Nov 02, 2015 at 11:20:49PM -0800, Dan Williams wrote: >> > On Mon, Nov 2, 2015 at 9:40 PM, Dave Chinner wrote: >> > > On Mon, Nov 02, 2015 at 08:56:24PM -0800, Dan Willia

Re: [PATCH v3 14/15] dax: dirty extent notification

2015-11-03 Thread Ross Zwisler
On Wed, Nov 04, 2015 at 07:51:31AM +1100, Dave Chinner wrote: > On Mon, Nov 02, 2015 at 11:20:49PM -0800, Dan Williams wrote: > > On Mon, Nov 2, 2015 at 9:40 PM, Dave Chinner wrote: > > > On Mon, Nov 02, 2015 at 08:56:24PM -0800, Dan Williams wrote: > > >> No, we definitely can't do that. I thin

Re: [PATCH v3 14/15] dax: dirty extent notification

2015-11-03 Thread Dan Williams
On Tue, Nov 3, 2015 at 1:18 PM, Ross Zwisler wrote: > On Mon, Nov 02, 2015 at 08:56:24PM -0800, Dan Williams wrote: >> On Mon, Nov 2, 2015 at 5:16 PM, Dave Chinner wrote: >> > On Sun, Nov 01, 2015 at 11:30:58PM -0500, Dan Williams wrote: > <> >> > Yes, that's a basic feature of Ross's patches. He

Re: [PATCH v3 14/15] dax: dirty extent notification

2015-11-03 Thread Dan Williams
On Tue, Nov 3, 2015 at 12:51 PM, Dave Chinner wrote: > On Mon, Nov 02, 2015 at 11:20:49PM -0800, Dan Williams wrote: >> On Mon, Nov 2, 2015 at 9:40 PM, Dave Chinner wrote: >> > On Mon, Nov 02, 2015 at 08:56:24PM -0800, Dan Williams wrote: >> >> No, we definitely can't do that. I think your ment

Re: [PATCH v3 14/15] dax: dirty extent notification

2015-11-03 Thread Ross Zwisler
On Mon, Nov 02, 2015 at 08:56:24PM -0800, Dan Williams wrote: > On Mon, Nov 2, 2015 at 5:16 PM, Dave Chinner wrote: > > On Sun, Nov 01, 2015 at 11:30:58PM -0500, Dan Williams wrote: <> > > Yes, that's a basic feature of Ross's patches. Hence I think this > > special case DAX<->bdev interface is th

Re: [PATCH v3 14/15] dax: dirty extent notification

2015-11-03 Thread Dave Chinner
On Mon, Nov 02, 2015 at 11:20:49PM -0800, Dan Williams wrote: > On Mon, Nov 2, 2015 at 9:40 PM, Dave Chinner wrote: > > On Mon, Nov 02, 2015 at 08:56:24PM -0800, Dan Williams wrote: > >> No, we definitely can't do that. I think your mental model of the > >> cache flushing is similar to the disk

Re: [PATCH v3 14/15] dax: dirty extent notification

2015-11-02 Thread Dan Williams
On Mon, Nov 2, 2015 at 9:40 PM, Dave Chinner wrote: > On Mon, Nov 02, 2015 at 08:56:24PM -0800, Dan Williams wrote: >> No, we definitely can't do that. I think your mental model of the >> cache flushing is similar to the disk model where a small buffer is >> flushed after a large streaming write

Re: [PATCH v3 14/15] dax: dirty extent notification

2015-11-02 Thread Dave Chinner
On Mon, Nov 02, 2015 at 08:56:24PM -0800, Dan Williams wrote: > On Mon, Nov 2, 2015 at 5:16 PM, Dave Chinner wrote: > > On Sun, Nov 01, 2015 at 11:30:58PM -0500, Dan Williams wrote: > >> DAX-enabled block device drivers can use hints from fs/dax.c to > >> optimize their internal tracking of potent

Re: [PATCH v3 14/15] dax: dirty extent notification

2015-11-02 Thread Dan Williams
On Mon, Nov 2, 2015 at 5:16 PM, Dave Chinner wrote: > On Sun, Nov 01, 2015 at 11:30:58PM -0500, Dan Williams wrote: >> DAX-enabled block device drivers can use hints from fs/dax.c to >> optimize their internal tracking of potentially dirty cpu cache lines. >> If a DAX mapping is being used for syn

Re: [PATCH v3 14/15] dax: dirty extent notification

2015-11-02 Thread Dave Chinner
On Sun, Nov 01, 2015 at 11:30:58PM -0500, Dan Williams wrote: > DAX-enabled block device drivers can use hints from fs/dax.c to > optimize their internal tracking of potentially dirty cpu cache lines. > If a DAX mapping is being used for synchronous operations, dax_do_io(), > a dax-enabled block-dr