[Pvfs2-developers] encoding negative responses

[Robert Latham]

On Thu, Oct 19, 2006 at 05:57:02PM -0500, Sam Lang wrote:
> This means if a bunch of jobs all do a create of the same  
> file (stupid sure, but possible), all the ones that got EEXISTS back  
> have to do a lookup.  We could potentially optimize this by sticking  
> the handle into the error response.

Sam brings this up because we were looking at the messy
ADIOI_PVFS2_Open code earlier this week.  mpi-io-test exhibits this
behavior.  It's wierd but not wrong, so ROMIO's got to deal with it.

==rob

-- 
Rob Latham
Mathematics and Computer Science Division    A215 0178 EA2D B059 8CDF
Argonne National Lab, IL USA                 B29D F333 664A 4280 315B