On Wed, Jul 29, 2015 at 6:08 PM, Dave Chinner wrote:
> On Wed, Jul 29, 2015 at 07:21:47AM -0400, Ming Lei wrote:
>> On Wed, Jul 29, 2015 at 4:41 AM, Dave Chinner wrote:
>> > On Wed, Jul 29, 2015 at 03:33:52AM -0400, Ming Lei wrote:
>> >> On Mon, Jul 27, 2015 at 1:33 PM, Christoph Hellwig
>> >>
On Wed, Jul 29, 2015 at 6:08 PM, Dave Chinner da...@fromorbit.com wrote:
On Wed, Jul 29, 2015 at 07:21:47AM -0400, Ming Lei wrote:
On Wed, Jul 29, 2015 at 4:41 AM, Dave Chinner da...@fromorbit.com wrote:
On Wed, Jul 29, 2015 at 03:33:52AM -0400, Ming Lei wrote:
On Mon, Jul 27, 2015 at 1:33
On Wed, Jul 29, 2015 at 07:21:47AM -0400, Ming Lei wrote:
> On Wed, Jul 29, 2015 at 4:41 AM, Dave Chinner wrote:
> > On Wed, Jul 29, 2015 at 03:33:52AM -0400, Ming Lei wrote:
> >> On Mon, Jul 27, 2015 at 1:33 PM, Christoph Hellwig
> >> wrote:
> >> > On Mon, Jul 27, 2015 at 05:53:33AM -0400,
On Wed, Jul 29, 2015 at 4:41 AM, Dave Chinner wrote:
> On Wed, Jul 29, 2015 at 03:33:52AM -0400, Ming Lei wrote:
>> On Mon, Jul 27, 2015 at 1:33 PM, Christoph Hellwig
>> wrote:
>> > On Mon, Jul 27, 2015 at 05:53:33AM -0400, Ming Lei wrote:
>> >> Because size has to be 4k aligned too.
>> >
>> >
On Wed, Jul 29, 2015 at 03:33:52AM -0400, Ming Lei wrote:
> On Mon, Jul 27, 2015 at 1:33 PM, Christoph Hellwig wrote:
> > On Mon, Jul 27, 2015 at 05:53:33AM -0400, Ming Lei wrote:
> >> Because size has to be 4k aligned too.
> >
> > Yes. But again I don't see any reason to limit us to a hardcoded
On Mon, Jul 27, 2015 at 1:33 PM, Christoph Hellwig wrote:
> On Mon, Jul 27, 2015 at 05:53:33AM -0400, Ming Lei wrote:
>> Because size has to be 4k aligned too.
>
> Yes. But again I don't see any reason to limit us to a hardcoded 512
> byte block size here, especially considering the patches to
On Wed, Jul 29, 2015 at 07:21:47AM -0400, Ming Lei wrote:
On Wed, Jul 29, 2015 at 4:41 AM, Dave Chinner da...@fromorbit.com wrote:
On Wed, Jul 29, 2015 at 03:33:52AM -0400, Ming Lei wrote:
On Mon, Jul 27, 2015 at 1:33 PM, Christoph Hellwig h...@infradead.org
wrote:
On Mon, Jul 27, 2015
On Mon, Jul 27, 2015 at 1:33 PM, Christoph Hellwig h...@infradead.org wrote:
On Mon, Jul 27, 2015 at 05:53:33AM -0400, Ming Lei wrote:
Because size has to be 4k aligned too.
Yes. But again I don't see any reason to limit us to a hardcoded 512
byte block size here, especially considering the
On Wed, Jul 29, 2015 at 03:33:52AM -0400, Ming Lei wrote:
On Mon, Jul 27, 2015 at 1:33 PM, Christoph Hellwig h...@infradead.org wrote:
On Mon, Jul 27, 2015 at 05:53:33AM -0400, Ming Lei wrote:
Because size has to be 4k aligned too.
Yes. But again I don't see any reason to limit us to a
On Wed, Jul 29, 2015 at 4:41 AM, Dave Chinner da...@fromorbit.com wrote:
On Wed, Jul 29, 2015 at 03:33:52AM -0400, Ming Lei wrote:
On Mon, Jul 27, 2015 at 1:33 PM, Christoph Hellwig h...@infradead.org
wrote:
On Mon, Jul 27, 2015 at 05:53:33AM -0400, Ming Lei wrote:
Because size has to be
On Mon, Jul 27, 2015 at 05:53:33AM -0400, Ming Lei wrote:
> On Mon, Jul 27, 2015 at 5:45 AM, Christoph Hellwig wrote:
> > On Mon, Jul 27, 2015 at 05:41:57AM -0400, Ming Lei wrote:
> >> > Why the hardcoded value? I suspect this should be more like:
> >> >
> >> > if (dio &&
On Mon, Jul 27, 2015 at 05:53:33AM -0400, Ming Lei wrote:
> Because size has to be 4k aligned too.
Yes. But again I don't see any reason to limit us to a hardcoded 512
byte block size here, especially considering the patches to finally
allow enabling other block sizes from userspace.
--
To
On Mon, Jul 27, 2015 at 5:45 AM, Christoph Hellwig wrote:
> On Mon, Jul 27, 2015 at 05:41:57AM -0400, Ming Lei wrote:
>> > Why the hardcoded value? I suspect this should be more like:
>> >
>> > if (dio && inode->i_sb->s_bdev &&
>> > (lo->lo_offset &
On Mon, Jul 27, 2015 at 05:41:57AM -0400, Ming Lei wrote:
> > Why the hardcoded value? I suspect this should be more like:
> >
> > if (dio && inode->i_sb->s_bdev &&
> > (lo->lo_offset & (bdev_io_min(inode->i_sb->s_bdev) - 1)) != 0)
> > dio = false;
>
> The
On Mon, Jul 27, 2015 at 4:40 AM, Christoph Hellwig wrote:
>> + /*
>> + * loop block's logical block size is 512, now
>> + * we support direct I/O only if the backing
>> + * block devices' minimize I/O size is 512 and
>> + * the offset is aligned with 512.
>> + */
>> +
> + /*
> + * loop block's logical block size is 512, now
> + * we support direct I/O only if the backing
> + * block devices' minimize I/O size is 512 and
> + * the offset is aligned with 512.
> + */
> + if (dio) {
> + if (inode->i_sb->s_bdev &&
> +
On Mon, Jul 27, 2015 at 05:53:33AM -0400, Ming Lei wrote:
Because size has to be 4k aligned too.
Yes. But again I don't see any reason to limit us to a hardcoded 512
byte block size here, especially considering the patches to finally
allow enabling other block sizes from userspace.
--
To
On Mon, Jul 27, 2015 at 05:53:33AM -0400, Ming Lei wrote:
On Mon, Jul 27, 2015 at 5:45 AM, Christoph Hellwig h...@infradead.org wrote:
On Mon, Jul 27, 2015 at 05:41:57AM -0400, Ming Lei wrote:
Why the hardcoded value? I suspect this should be more like:
if (dio
On Mon, Jul 27, 2015 at 4:40 AM, Christoph Hellwig h...@infradead.org wrote:
+ /*
+ * loop block's logical block size is 512, now
+ * we support direct I/O only if the backing
+ * block devices' minimize I/O size is 512 and
+ * the offset is aligned with 512.
+
On Mon, Jul 27, 2015 at 05:41:57AM -0400, Ming Lei wrote:
Why the hardcoded value? I suspect this should be more like:
if (dio inode-i_sb-s_bdev
(lo-lo_offset (bdev_io_min(inode-i_sb-s_bdev) - 1)) != 0)
dio = false;
The above can't work if the
On Mon, Jul 27, 2015 at 5:45 AM, Christoph Hellwig h...@infradead.org wrote:
On Mon, Jul 27, 2015 at 05:41:57AM -0400, Ming Lei wrote:
Why the hardcoded value? I suspect this should be more like:
if (dio inode-i_sb-s_bdev
(lo-lo_offset
+ /*
+ * loop block's logical block size is 512, now
+ * we support direct I/O only if the backing
+ * block devices' minimize I/O size is 512 and
+ * the offset is aligned with 512.
+ */
+ if (dio) {
+ if (inode-i_sb-s_bdev
+
This patches provides one interface for enabling direct IO
from user space:
- userspace(such as losetup) can pass 'file' which is
opened/fcntl as O_DIRECT
Also __loop_update_dio() is introduced to check if direct I/O
can be used on current loop setting.
The last big change is to
This patches provides one interface for enabling direct IO
from user space:
- userspace(such as losetup) can pass 'file' which is
opened/fcntl as O_DIRECT
Also __loop_update_dio() is introduced to check if direct I/O
can be used on current loop setting.
The last big change is to
24 matches
Mail list logo