Re: Overcommitable memory??

From: James Sutherland (jas88@cam.ac.uk)
Date: Mon Mar 20 2000 - 07:33:34 EST


On Sun, 19 Mar 2000 22:17:04 -0400, you wrote:

>James Sutherland <jas88@cam.ac.uk> said:
>
>[...]
>
>> However it is handled, you now know that your memory allocation
>> succeeded and you have real memory on your hands, not just an IOU. If
>> there isn't any memory available, you get SIGBUSed - but then OOM
>> conditions usually lead to death anyway.
>
>You can hand out a IOU when you don't have the cash at hand, so you can go
>farther that way. That is why IOUs are around in the first place: They
>_are_ useful, even if more dangerous than hard cash.

Yes. If we find ourselves having handed out more IOUs than than we
have money, it means we have already run out of memory - and a
non-overcommit system would have started killing processes already.
Overcommit has delayed the problem but not avoided it in this specific
case - in other cases, we could have survived unscathed thanks to
overcommit.

James.

-
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 : Thu Mar 23 2000 - 21:00:29 EST