All of lore.kernel.org
 help / color / mirror / Atom feed
* rmap patches for 2.4.30(or 31)
@ 2005-06-03 22:53 Masoud Sharbiani
  0 siblings, 0 replies; only message in thread
From: Masoud Sharbiani @ 2005-06-03 22:53 UTC (permalink / raw)
  To: riel; +Cc: linux-kernel

Hello Rik,

It seems that I have successfully hacked 2.4.25 rmap patch so that it 
applies cleanly to 2.4.30 (that is, it compiles, boots and runs great 
under normal conditions); How would I go for testing it and stress 
testing it? It does survive the make -j of kernel (with lots of swap), 
but, when I want to try and run ltp tests, it goes to a bad mood (i.e. 
swapping out massively at first, then a dead silence)

Here is my ltp test run command:
./runltplite.sh -i 1024 -m 128 -p -q -l /tmp/result-rmap -d /home/0tmp/
It ends up forking a lot of loadgen processes that simply allocate 
memory and use it (and CPU), so the system becomes unresponsive; It also 
starts killing processes since it runs out of memory. I don't see any 
hangs or panics, and the system responds to pings and Keyboard dump 
commands, such as right-Alt+Scroll lock and similar ones, and looks it 
is spending most of its time in page_launder() or thereabouts, swap and 
physical memory both become full.
How do you test the rmap patches for correctness before offering them to 
the people out there?
The patch is available from http://masoud.ir/patches/2.4.30-rmap15.patch

Thanks in advance,
Masoud Sharbiani


^ permalink raw reply	[flat|nested] only message in thread

only message in thread, other threads:[~2005-06-03 22:53 UTC | newest]

Thread overview: (only message) (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2005-06-03 22:53 rmap patches for 2.4.30(or 31) Masoud Sharbiani

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.