valgrind 3.8.1 warning in jemalloc 3.2

[Daniel Mezzatto Rodrigues]

Unfortunately I can't generate a simple test program that makes the 
valgring errors occur. Even inside my system the valgrind error messeges 
don't happen for every HTTP request.

Looks like only memory intense requests, that allocates 64 MB or more in 
a single chunk, triggers the errors. It also appears that it is related 
to reallocs. If I have a HTTP request that somehow generates more than 
64 MB of data in a single chunk of memory and this chunck needs to me 
realloc'd, then valgring starts complaning.

I'm sending the full valgrind report (20K lines, 15k .bz2 file) of one 
of these memory intense requests to jasone at canonware.com so that you can 
have some more details.

best regards,

Daniel Mezzatto

On 12/12/2012 02:52 PM, Jason Evans wrote:
> The bulk of the valgrind error messages is almost certainly a result of valgrind complaining about what jemalloc is doing under the covers with internal data structures.  I'm perplexed as to why valgrind is complaining though.  It's almost as if valgrind knows something about the mmap'ed memory jemalloc manages, where jemalloc expects valgrind not to know anything about it.  Do such valgrind errors occur for a simple test program in your environment?
>
> I'm starting to wonder if there's a change between Valgrind 3.7.x and 3.8.x that jemalloc needs to be updated for.