On Mon, Jul 18, 2011 at 10:32 AM, John Reiser <[email protected]> wrote:
>> Is there a reason for assuming that syscalls won't block by default?
>
> There is substantial overhead to allow for the possibility that a syscall
> might block.  This wakes up valgrind's internal machinery for threads,
> which is not spry.  chdir and fchdir are used infrequently enough that
> it might not matter too much; but stat64 and close are used quite often.

Ok, makes sense. Tom Hughes suggested that I create a bug and attach
my patch, so that's what I did. If it is going to be a significant
performance hit, maybe it would be better to have an option that can
turn this on for all syscalls? That way when debugging a fuse
file-system, the syscalls won't deadlock, but it won't slow things
down for the general user. Also I imagine there are other filesystem
related syscalls that would have the same issue - I only patched the
ones that were causing me trouble.

Thanks for the help,
-Mike

------------------------------------------------------------------------------
Storage Efficiency Calculator
This modeling tool is based on patent-pending intellectual property that
has been used successfully in hundreds of IBM storage optimization engage-
ments, worldwide.  Store less, Store more with what you own, Move data to 
the right place. Try It Now! http://www.accelacomm.com/jaw/sfnl/114/51427378/
_______________________________________________
Valgrind-users mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/valgrind-users

Reply via email to