Memory corruptions near 32 bit limits

[Jason Evans]

On Nov 6, 2012, at 3:01 AM, Salvatore Sanfilippo wrote:
> in the Redis community it was observed multiple times that when a 32
> bit instance using Jemalloc (<= 3.0) is very near to be out of memory
> because the whole available address space was used, it can happen that
> the server crashes because memory gets corrupted instead of malloc
> returning NULL.
> 
> Is this a known issues?

This is the first I've heard of such an issue.  If you are able to narrow down the failure mode, please let me know so that we can get this fixed ASAP.

Thanks,
Jason