Greg Stark <gsstark@mit.edu> writes:
> Two mallocs can work fine alongside each other. They each call mmap or
> sbrk to allocate new pages and they each manage the pages they've
> received. They won't have any idea why the allocator seems to be
> skipping pages, but they should be careful not to touch those pages.
However, it's quite likely that such a setup will fail to release memory
back to the OS very effectively, and it could easily suffer bad
fragmentation problems even without thinking about whether the program
break address can be moved back. I think what Sven is seeing is exactly
fragmentation inefficiency.
regards, tom lane