Re: KDE 3.5.0 seems much chubbier than 3.4.2



> Yes, I'd expect the memory usage to decrease if you build with
> NO_MALLOC_EXTRAS, since redzone overhead is 32 bytes per object. Do
> you see any evidence of unbounded X memory usage though?

Hmm, not sure it was unbounded, but it was certainly consuming a lot of extra
memory. Note that with the debugging off top shows it as..
PID USERNAME THR PRI NICE SIZE RES STATE TIME WCPU COMMAND
19876 root 1 100 0 315M 136M select 18:16 13.67% Xorg

so it's hardly small.

> Why not just append to CFLAGS in make.conf? NO_MALLOC_EXTRAS is a
> development-only flag, since the malloc debug features will be
> disabled for releases, so a make.conf knob would have no relevance to
> releases. Unless there's serious worry about cpp namespace
> pollution, I don't understand the need for the patch you provided.

Hmm, I thought touching CFLAGS in make.conf was verboten..
If not then I will use it.

--
Daniel O'Connor software and network engineer
for Genesis Software - http://www.gsoft.com.au
"The nice thing about standards is that there
are so many of them to choose from."
-- Andrew Tanenbaum
GPG Fingerprint - 5596 B766 97C0 0E94 4347 295E E593 DC20 7B3F CE8C

Attachment:pgpAGESa70j1d.pgp
Description: PGP signature



Relevant Pages

  • Re: Ocfs2 performance bugs of doom
    ... you might want to calculate that hash outside the spinlock. ... Hmm, good catch. ... That could be an avenue to explore. ... actual lookup and memory usage before looking at that. ...
    (Linux-Kernel)
  • Re: Cello/OS X update
    ... >> I will try the glDeleteLists trick to see if this clears up the ... >> pause. ... Hmm, no change in memory usage at all? ...
    (comp.lang.lisp)