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. > http://i.imgur.com/Z24MQ.png
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? Thanks, Jason _______________________________________________ jemalloc-discuss mailing list [email protected] http://www.canonware.com/mailman/listinfo/jemalloc-discuss
