On 6/26/20, Stefan Eßer <s...@freebsd.org> wrote:
> Am 26.06.20 um 12:23 schrieb Peter Jeremy:
>> On 2020-Jun-25 11:30:31 -0700, Donald Wilde <dwil...@gmail.com> wrote:
>>> Here's 'pstat -s' on the i3 (which registers as cpu HAMMER):
[snip]
> An idea for a better strategy:
>
> It might be better to use an allocation algorithm that assigns a
> swap device to each running process that needs pages written to the
> swap device and only assign another swap device (and use if from
> then on for that process) if there is no free space left on the one
> used until then.
>
> Such a strategy would at least reduce the number of processes that
> need all configured swap devices at the same time in a striped
> configuration.
>
> If all processes start with the first configured swap device assigned
> to them, this will lead to only one of them being used until it fills
> up, then progressing to the next one.
>
> The strategy of whether the initial swap device assigned to a process
> is always the first one configured in the system, or whether after
> that could not be used by some process is moved on to the next one
> (typically the one assigned to that process for further page-outs) is
> not obvious to me.
You're getting over my head, STefan, but that's okay. I suspect that
having somebody be loony -- and desperate enough -- to configure two
swap partitions is a rare occurance.
>
> The behavior could be controlled by a sysctl to allow to adapt the
> strategy to the hardware (e.g. rotating vs. flash disks for swap).
Not to mention Intel and Micron and their fancy fast non-volatile
chips ('Optane'). I do agree that SOMEBODY is going to need this kind
of sysctl guidance for the kernel.
>
[snip]
> And while it does not come up that often in the mail list, it might
> be better for many kinds of application if the default was increased
> (a longer wait for resources might be more acceptable than the loss
> of all results of a long running computation).
Yes. Synth seems to be able to keep going / recover from last-known
success points, but your point is very valid. As we go further into
OOP, the _controllable_ use of heap space, stack space, and recursion
is going to become more crucial. We humans are used to operating
without a "full stack," (sleep DOES help :) ) but I think the whole
point of modern AI is to create systems that actually can master the
logical inference chains proposed by the early LISP guys at MIT, C-M,
and Stanford. The gains from ML have been enough to keep 'the Street'
happy for now but they'll want more soon enough.
> Regards, STefan
Thought-provoking indeed. :D
--
Don Wilde
****************************************************
* What is the Internet of Things but a system *
* of systems including humans? *
****************************************************
_______________________________________________
freebsd-stable@freebsd.org mailing list
https://lists.freebsd.org/mailman/listinfo/freebsd-stable
To unsubscribe, send any mail to "freebsd-stable-unsubscr...@freebsd.org"
