[Pvfs2-users] Question about behavior of locking (or lack of it) in PVFS2

[Murali Vilayannur]

Avery,
Thanks for the links!
Any chance of it being crossported to TRUNK?
Were there any philosophical objections to the design etc?
I can take a stab at integration with the VFS.
thanks,
Murali

On Jan 4, 2008 10:34 AM, Avery Ching <aching at ece.northwestern.edu> wrote:
> I have implemented a DLM for locking at the byte-range level in the
> version-lock-actual-branch.  A link to the relevant paper is
>
> http://cholera.ece.northwestern.edu/~aching/research_webpage/publications/20
> 07sc_2.pdf
>
> You would also need my MPI-IO PVFS2 driver to support MPI-IO atomic mode.  I
> have not integrated these locks with the PVFS kernel interface (although it
> would be an important building block for consistent client side caching in
> PVFS).  If you are interested in this, feel free to contact me.
>
> Avery
>
>
> On 1/4/08 8:01 AM, "Robert Latham" <robl at mcs.anl.gov> wrote:
>
> > On Fri, Jan 04, 2008 at 12:01:50AM -0800, Murali Vilayannur wrote:
> >> Craig,
> >>
> >>> I know that PVFS2 does not support locking and understand the
> >>> benefits of this design.  However, I have a question about what
> >>> happens to file writes for contiguous, non-overlapping writes.
> >>
> >> I think Avery has patches to support locking at the file/byte range level.
> >> I am not sure if they are in some private branch though and it is
> >> likely they may
> >> need some additional work to integrate with the VFS...Avery, Rob?
> >
> > for the curious, that work lives in 'version-lock-actual-branch'
> >
> > Thanks for the detailed answer, Murali!
> > ==rob
>
>
>