Re: Memory fragmentation?

Stuart Parmenter wrote:
> On Oct 26, 7:25 pm, Mike Schroepfer <[email protected]> wrote:
>> [email protected] wrote:
>>> On Oct 19, 1:17 pm, Boris Zbarsky <[email protected]> wrote:
>>>> Well.  In that bug the "problem" is "top reports high memory usage".
>>> Which is typically what people complain about, too. "I closed all my
>>> pages and tabs and Firefox is still using 10GB of memory!" We may have
>>> free()ed almost all of it, but the library won't give it back to the
>>> OS.
>> yep - really big perceptual problem.  Just hitting spacbar in google
>> reader can start to chew through ram...  Closing all tabs and having a
>> very different memory number than when you first start is very hard to
>> explain.  As I asked on another reply is there an easy way to get modern
>> numbers on windows for this?
>>
>> Cheers,
>>
>> Schrep
> 
> I've done several tests to look in to this today.  I found an easily
> reproducable testcase and ran it through purify checking memory in use
> before and after (with bfcache disabled as well as images) and while
> the app grows 20mb in task manager, memory in use only grows by about
> 1.2mb.  This leads me to believe that at least some of the numbers are
> in fact due to memory fragmentation.  I did some further work to force
> us to page out and back in our app which results in us landing back at
> about the same amount of memory as before we loaded the page.
> 
> All that said, I have a hard time believing that we're losing 20mb to
> fragmentation by loading gmail and searching and loading a message.
> I'll continue to poke at this and see if I can come up with more info.
> 
> stuart
> 

Have we ever tried the windows low-fragmentation heap? Added some info to:

https://bugzilla.mozilla.org/show_bug.cgi?id=276342

about it. Avail on XP+ but might be worth a shot to see if it makes a 
difference.

Schrep