On Sun, Aug 18, 2019 at 2:55 PM Gordan Bobic <gor...@redsleeve.org> wrote:
> On Sun, Aug 18, 2019 at 9:07 PM Kevin Kofler <kevin.kof...@chello.at> wrote:
>> Gordan Bobic wrote:
>> > Right, but is it better that _everything_ else suffers with more memory
>> > pressure for the handful of relatively infrequent use cases for which
>> > ulimit can be used to explicitly raise the limit?
>> Well, as I wrote, a lower limit might actually make sense on ARM. But modern
>> x86 computers have gigabytes of RAM, so 1 MiB is ridiculously small there.
>> So this would have to be an architecture-specific setting for ARM.
> That may be so, but this thread started off with memory pressure also being 
> an issue for regular desktop x86 use.

I think optimizations like this, and including compile time defaults
should get smarter to do such optimizations and have a lot of
intrinsic value. But in any case, I think it's fair to say that we're
in very broad agreement that no matter what options get used or what
optimization do or don't happen, unprivileged processes should not be
able to effectively take down the system. That to me is really
incredible to discover.

Everything else: no swap at all and tolerate abrupt and random
oom-killer killoffs, double the swap or use /dev/zram, or use 1/4 RAM
for swap, or throw a metric f ton of RAM at it, all of those are
different ways of dodging a cannon ball. Dodging the problem doesn't
actually fix the problem.Iff your dodge doesn't work out, you get hit
by a cannon ball. Not OK. It's an unprivileged task! I'm aghast.

Chris Murphy
devel mailing list -- devel@lists.fedoraproject.org
To unsubscribe send an email to devel-le...@lists.fedoraproject.org
Fedora Code of Conduct: 
List Guidelines: https://fedoraproject.org/wiki/Mailing_list_guidelines
List Archives: 

Reply via email to