We're hoping that upgrading to jemalloc 4.1 might resolve #5348 .

However it also introduces a regression on #3516.

I posted a message to the jemalloc-discuss mailing list describing the issue: http://www.canonware.com/pipermail/jemalloc-discuss/2016-April/001285.html