Memory usage regression

Jason Evans jasone at
Tue Nov 6 01:16:10 PST 2012

On Nov 4, 2012, at 11:17 PM, Mike Hommey wrote:
> This patch works quite well. The result is still above mozjemalloc, but
> the leak is plugged. Thanks.

I made a few more refinements, and pushed the change on the dev branch.  Hopefully the effect will be similar for Firefox.

> BTW, an interesting fact, if I didn't botch my stats: at the end of
> the 5 iterations, while 17MB are allocated, sucking 68MB of RSS, only
> 40MB worth of pages have allocated data in them. The number is similar
> to what I get with mozjemalloc (mozjemalloc is actually about 100K
> higher than jemalloc3 on that metric, while RSS is 6MB higher with
> jemalloc3) Which means (if my stats are not broken) that there is still
> room for improving RSS.

I've been puzzling over this for a while, and still don't completely understand.  Is one of the numbers missing a digit, perhaps?


More information about the jemalloc-discuss mailing list