understanding page/chunk reclaim algorithm

[Sideropoulos, Alexander]

Hey all. We are trying to understand how Jemalloc reclaims free runs and chunks.
Specifically for small allocation sizes, what are the heuristics for

1) free runs being reclaimed within the chunk to be reused for a different size and
2) free chunks being released back to the OS?

Could someone kindly point us to a web page, man page, white paper, or source code which explains this?

Thanks!
----------
Alexander P. Sideropoulos
NetApp -- Performance Engineering
siderop1 at netapp.com<mailto:siderop1 at netapp.com>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://jemalloc.net/mailman/jemalloc-discuss/attachments/20140811/95624838/attachment.html>