Re: memory leak detector, 2.0.32, patch

Chris Adams (cadams@ro.com)
Tue, 2 Dec 1997 13:28:44 -0600 (CST)

Once upon a time, Ingo Molnar wrote
> The algorithms used are extremely fast [O(1) everywhere], so it should
> make no visible speed difference on a running RL system. Memory object
> structures are not touched as well. [i couldnt measure any slowdown on my
> system]. It still contains lots of safety code. The hard work is done in
> the user-space postprocessing script. Currently we waste 10% of real
> memory with this detector. Those 10% are well spent IMO, but if there is
> enough demand then it can be decreased to under 5%.

Well, this patch slowed down my system a lot. 100% in fact. I got this
during boot:

---
Memory: 281056k/286720k available (540k kernel code, 384k reserved, 4740k data)
Bad pmd in pte_alloc: 120000e7
Kernel panic: Failed to allocate buffer hash table


In swapper task - not syncing

---


and then it stopped.


This is a server with 320M of RAM (have to pass mem=320M from LILO).


Really, I'm not trying to break everything I touch!  I just want it to
work.

-- 
Chris Adams - cadams@ro.com
System Administrator - Renaissance Internet Services
I don't speak for anybody but myself - that's enough trouble.