> And yeah, I had checked other filesystems too and they seem to follow this
> pattern.  So either I'm looking at the wrong place or this is something
> that is much more likely to be triggered by 9p.
>
> Cheers,
> -- 
> Luis
>
>>> If this theory is correct, I'm not sure what's the best way to close this
>>> race because the v9inode->fscache_lock can't really be used.  But I still
>>> need to proof this is really what's happening.
>>
>> Yes, I think we're going to need proof before thinking of a solution, I
>> can't think of anything simple either.
>>
>>
>> Thanks again for looking into it,
>> -- 
>> Dominique