On Sun, Oct 1, 2017 at 2:59 PM, Dave Chinner wrote:
[..]
> The "capacity tax" had nothing to do with it - the major problem
> with self hosting struct pages was that page locks can be hot and
> contention on them will rapidly burn through write cycles on the
> pmem. That's still a problem, yes?
I
On Sun, Oct 01, 2017 at 02:22:08PM -0700, Dan Williams wrote:
> On Sun, Oct 1, 2017 at 2:11 PM, Dave Chinner wrote:
> > On Sun, Oct 01, 2017 at 10:58:06AM -0700, Dan Williams wrote:
> >> On Sun, Oct 1, 2017 at 12:57 AM, Christoph Hellwig wrote:
> >> > While this looks like a really nice cleanup o
On Sun, Oct 1, 2017 at 2:22 PM, Dan Williams wrote:
> On Sun, Oct 1, 2017 at 2:11 PM, Dave Chinner wrote:
>> On Sun, Oct 01, 2017 at 10:58:06AM -0700, Dan Williams wrote:
>>> On Sun, Oct 1, 2017 at 12:57 AM, Christoph Hellwig wrote:
>>> > While this looks like a really nice cleanup of the code a
On Sun, Oct 1, 2017 at 2:11 PM, Dave Chinner wrote:
> On Sun, Oct 01, 2017 at 10:58:06AM -0700, Dan Williams wrote:
>> On Sun, Oct 1, 2017 at 12:57 AM, Christoph Hellwig wrote:
>> > While this looks like a really nice cleanup of the code and removes
>> > nasty race conditions I'd like to understa
On Sun, Oct 01, 2017 at 10:58:06AM -0700, Dan Williams wrote:
> On Sun, Oct 1, 2017 at 12:57 AM, Christoph Hellwig wrote:
> > While this looks like a really nice cleanup of the code and removes
> > nasty race conditions I'd like to understand the tradeoffs.
> >
> > This now requires every dax devi
On Sun, Oct 1, 2017 at 12:57 AM, Christoph Hellwig wrote:
> While this looks like a really nice cleanup of the code and removes
> nasty race conditions I'd like to understand the tradeoffs.
>
> This now requires every dax device that is used with a file system
> to have a struct page backing, whic
On Tue, Sep 26, 2017 at 11:11:55AM -0700, Dan Williams wrote:
> I think we'll always need an explicit override available, but yes we
> need to think about what the override looks like in the context of a
> kernel that is able to automatically pick the right I/O policy
> relative to the media type.
On Wed, Sep 27, 2017 at 10:15:10AM -0600, Ross Zwisler wrote:
> Well, I don't know if platforms that support HMAT + PMEM are widely available,
> but we have all the details in the ACPI spec, so we could begin to code it up
> and things will "just work" when platforms arrive.
Then again currently a
While this looks like a really nice cleanup of the code and removes
nasty race conditions I'd like to understand the tradeoffs.
This now requires every dax device that is used with a file system
to have a struct page backing, which means not only means we'd
break existing setups, but also a sharp