On 23 May, Jesse Pollard wrote:
> t.n.vanderleeuw@chello.nl
>>
>> On 23 May, Juan J. Quintela wrote:
>> >>>>>> "tim" == t n vanderleeuw <t.n.vanderleeuw@chello.nl> writes:
>> >
>> > tim> Hi,
>> > tim> with pre9-3 and pre9-4 I'm experiencing lockups when OOM.
>> > tim> A random process will be killed (NOT the runaway process) and the
>> > tim> computer hangs solid after that (still pingable, but nothing else
>> > tim> works, not even VT switching or capslock toggle).
>> >
[...]
>>
>> I have the following memory-eater which can repeatedly kill my box.
>>
[...]
> Yup - you die unless you have a large memory system, or you get very
> lucky. The OOM handler kills processes that are seen as being pigs, but
> that assumes that only a few are actually doing so. klogd got killed
> trying to allocate buffers/IO space to log the messages faster than the
> IO system could write them out. The actual hogs were probably mostly swapped
> out already, and idle - waiting for memory.
>
The program is most certainly meant to thrash your machine. But your
computer shouldn't *die* because of it.
I tested it against 2.2.16pre3 and the computer survived; several
random 'innocent' processes got killed by the VM but mostly eatmem hogs
got killed. The most important thing is that it stayed alive, survived
the attack, still took keyboard-input, allowed me to log in, and was
useable afterwards.
The only time when it went wrong in 2.2.16pre3 was when the X server
got killed and thus the graphics card was left in an unpredictable
state. In the next test I shut down X first and all was mostly fine.
In 2.3.99pre9-x I will for sure have to hit the reset-button.
> Nice program though.
Thanks <g>
I wrote it during late 2.1.xxx for similar testing. It used to kill my
box on 2.1.xxx but make it merely unusable under 2.0.xx
When I pulled it out now for VM testing I'd forgotten about the fork()s
and I just increased the arraysize to make sure it would exceed all
memory.
How many UNIXen will actually survive this program, given that the user
running it has no resource limits on memory consumption?
--Tim
> -------------------------------------------------------------------------
> Jesse I Pollard, II
> Email: pollard@navo.hpc.mil
>
> Any opinions expressed are solely my own.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Tue May 23 2000 - 21:00:25 EST