Re: Break 2.4 VM in five easy steps

[Mike Galbraith]

On Thu, 7 Jun 2001, Bulent Abali wrote:

> I happened to saw this one with debugger attached serial port.
> The system was alive.  I think I was watching the free page count and
> it was decreasing very slowly may be couple pages per second.  Bigger
> the swap usage longer it takes to do swapoff.  For example, if I had
> 1GB in the swap space then it would take may be an half hour to shutdown...

I took a ~300ms ktrace snapshot of the no IO spot with 2.4.4.ikd..

  % TOTAL    TOTAL USECS    AVG/CALL   NCALLS
  0.0693%         208.54        0.40      517 c012d4b9 __free_pages
  0.0755%         227.34        1.01      224 c012cb67 __free_pages_ok
  ...
 34.7195%      104515.15        0.95   110049 c012de73 unuse_vma
 53.3435%      160578.37      303.55      529 c012dd38 __swap_free
Total entries: 131051  Total usecs:    301026.93 Idle: 0.00%

Andrew Morton could be right about that loop not being wonderful.

	-Mike