On Tue, Jun 02, 2020 at 07:51:52AM +0200, Christoph Hellwig wrote:
> On Mon, Jun 01, 2020 at 10:44:26AM +0200, Greg KH wrote:
> > But does this code path actually show up anywhere that is actually
> > measurable as mattering?
> >
> > If so, please show that benchmark results.
>
> I think the
On Mon, Jun 01, 2020 at 10:44:26AM +0200, Greg KH wrote:
> But does this code path actually show up anywhere that is actually
> measurable as mattering?
>
> If so, please show that benchmark results.
I think the requests are starting to be a bit unreasonable. Tao is
replacing a reimplementation
On Mon, Jun 01, 2020 at 03:22:01PM +0800, Tao pilgrim wrote:
> On Fri, May 29, 2020 at 10:13 PM Jens Axboe wrote:
> >
> > On 5/29/20 8:11 AM, Kaitao Cheng wrote:
> > > There is a function named ilog2() exist which can replace blksize.
> > > The generated code will be shorter and more efficient on
On Fri, May 29, 2020 at 10:13 PM Jens Axboe wrote:
>
> On 5/29/20 8:11 AM, Kaitao Cheng wrote:
> > There is a function named ilog2() exist which can replace blksize.
> > The generated code will be shorter and more efficient on some
> > architecture, such as arm64. And ilog2() can be optimized
On 5/29/20 4:27 PM, Bart Van Assche wrote:
> On 2020-05-29 13:27, Matthew Wilcox wrote:
>> On Fri, May 29, 2020 at 10:11:00PM +0800, Kaitao Cheng wrote:
>>> There is a function named ilog2() exist which can replace blksize.
>>> The generated code will be shorter and more efficient on some
>>>
On 2020-05-29 13:27, Matthew Wilcox wrote:
> On Fri, May 29, 2020 at 10:11:00PM +0800, Kaitao Cheng wrote:
>> There is a function named ilog2() exist which can replace blksize.
>> The generated code will be shorter and more efficient on some
>> architecture, such as arm64. And ilog2() can be
On Fri, May 29, 2020 at 10:11:00PM +0800, Kaitao Cheng wrote:
> There is a function named ilog2() exist which can replace blksize.
> The generated code will be shorter and more efficient on some
> architecture, such as arm64. And ilog2() can be optimized according
> to different architecture.
On 5/29/20 8:11 AM, Kaitao Cheng wrote:
> There is a function named ilog2() exist which can replace blksize.
> The generated code will be shorter and more efficient on some
> architecture, such as arm64. And ilog2() can be optimized according
> to different architecture.
When you posted this last
> ns->size = i_size_read(ns->bdev->bd_inode);
> - ns->blksize_shift = blksize_bits(bdev_logical_block_size(ns->bdev));
> + ns->blksize_shift = ilog2(bdev_logical_block_size(ns->bdev));
This should just be:
ns->blksize_shift = ns->bdev->bd_inode->i_blkbits;
> diff --git
There is a function named ilog2() exist which can replace blksize.
The generated code will be shorter and more efficient on some
architecture, such as arm64. And ilog2() can be optimized according
to different architecture.
Signed-off-by: Kaitao Cheng
---
changes in v2:
Remove all
10 matches
Mail list logo