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 [email protected] 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.
_______________________________________________
jemalloc-discuss mailing list
[email protected]
http://www.canonware.com/mailman/listinfo/jemalloc-discuss
