On Dec 12, 2012, at 8:21 AM, Daniel Mezzatto Rodrigues <[email protected]> wrote: > I think jemalloc is configuring itself to support valgrind. Running configure > shows me this: > > ./configure --with-jemalloc-prefix=je_ | grep -i valgrind > checking whether valgrind is compilable... yes > valgrind : 1 > > Looks like the header files you mentioned are in the right place: > > /usr/local/include/valgrind/ | grep -E "(valgrind|memcheck)" > memcheck.h > valgrind.h > > Is it OK for me to just ignore these error messages? If it's just a > missconfiguration of jemalloc's valgrind support, I'm fine with that.
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. Thanks, Jason _______________________________________________ jemalloc-discuss mailing list [email protected] http://www.canonware.com/mailman/listinfo/jemalloc-discuss
