[PVFS2-users] Timestamp metadata, heterogenous architecture

[Rob Ross]

By disappears you mean that the timestamp appears normal, right?

Sounds like there's something amiss in how we copy the stat results into 
the user buffer.

Thanks, we'll do some investigating.

Rob

Number Cruncher wrote:
> Number Cruncher wrote:
> 
>> Rob Ross wrote:
>>
>>> Hi,
>>>
>>> Does the system exhibit this behavior if you use a "-a 0" argument to 
>>> pvfs2-client instead?
>>>
>>> Thanks,
>>>
>>> Rob
>>
>>
>>
>> Yes.
>> What I don't understand is that 'touch'ing the file clearly changes 
>> some timestamp but not the true date. Is this some 32/64 bit 
>> truncation problem?
>>
> Having now tested with the pvfs2-servers on a 32bit cluster with the 
> same OS (Fedora Core 2) as the pvfs2-client, I'm still getting the same 
> problem, so I guess it's not 32/64 bit truncation. It definitely 
> disappears when the pvfs2-client{-core} is restarted.
> 
> Simon.
>