AFAIK Solaris 11 uses a sparse tree instead of a array. Solves the
scalability problem AND deals with variable page size.
Right - seems like tying the radix tree into the locking instead of using an
array would have these same benefits.
On 10 February 2016 at 23:09, Dave Chinner
> On Wed, Feb 10, 2016 at 11:32:49AM +0100, Jan Kara wrote:
>> On Tue 09-02-16 10:18:53, Dan Williams wrote:
>> > On Tue, Feb 9, 2016 at 9:24 AM, Jan Kara <jack(a)suse.cz> wrote:
>> > > Hello,
>> > >
>> > > I was thinking about current issues with DAX fault locking  (data
>> > > corruption due to racing faults allocating blocks) and also races
>> > > currently don't allow us to clear dirty tags in the radix tree due
>> > > between faults and cache flushing . Both of these exist because we
>> > > have an equivalent of page lock available for DAX. While we have a
>> > > reasonable solution available for problem , so far I'm not
aware of a
>> > > decent solution for . After briefly discussing the issue with Mel
>> > > a bright idea that we could used hashed locks to deal with  (and I
>> > > we can solve  with them as well). So my proposal looks as follows:
>> > >
>> > > DAX will have an array of mutexes (the array can be made per device
>> > > initially a global one should be OK). We will use mutexes in the array
>> > > replacement for page lock - we will use hashfn(mapping, index) to get
>> > > particular mutex protecting our offset in the mapping. On fault /
>> > > mkwrite, we'll grab the mutex similarly to page lock and release
it once we
>> > > are done updating page tables. This deals with races in . When
>> > > caches we grab the mutex before clearing writeable bit in page tables
>> > > and clearing dirty bit in the radix tree and drop it after we have
>> > > caches for the pfn. This deals with races in .
>> > >
>> > > Thoughts?
>> > >
>> > I like the fact that this makes the locking explicit and
>> > straightforward rather than something more tricky. Can we make the
>> > hashfn pfn based? I'm thinking we could later reuse this as part of
>> > the solution for eliminating the need to allocate struct page, and we
>> > don't have the 'mapping' available in all paths...
>> So Mel originally suggested to use pfn for hashing as well. My concern with
>> using pfn is that e.g. if you want to fill a hole, you don't have a pfn to
>> lock. What you really need to protect is a logical offset in the file to
>> serialize allocation of underlying blocks, its mapping into page tables,
>> and flushing the blocks out of caches. So using inode/mapping and offset
>> for the hashing is easier (it isn't obvious to me we can fix hole filling
>> races with pfn-based locking).
> So how does that file+offset hash work when trying to lock different
> ranges? file+offset hashing to determine the lock to use only works
> if we are dealing with fixed size ranges that the locks affect.
> e.g. offset has 4k granularity for a single page faults, but we also
> need to handle 2MB granularity for huge page faults, and IIRC 1GB
> granularity for giant page faults...
> What's the plan here?
> Dave Chinner
> To unsubscribe from this list: send the line "unsubscribe linux-fsdevel"
> the body of a message to majordomo(a)vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
Cedric Blancher <cedric.blancher(a)gmail.com>