Ask stupid questions and you'll get a stupid answers, was: Technological advantages over Linux

Aryeh Friedman aryeh.friedman at gmail.com
Sun Jul 26 13:04:15 UTC 2020


On Sun, Jul 26, 2020 at 8:43 AM Steve O'Hara-Smith <steve at sohara.org> wrote:

>
>         There is system wide performance loss due to pages having been
> pushed out to swap and needing to be pulled in to be used. The more times
> you push the memory over the edge like that the more random things get
> pushed out to swap and the more random delays there will be as they get
> pulled back in. This happens because some of the stuff that got pushed to
> swap the first time round never comes back in (it isn't used often enough)
> and so every time round more and more important stuff gets pushed out to
> swap.
>
>         Here is a variant of your experiment that should demonstrate it.
>
> 1: Reboot machine, measure performance
> 2: Memory stress machine to until swapping reduces performance
> 3: Kill memory stressing process
> 4: Disable swap - which forces all pages back into RAM
> 5: Enable swap
> 6: Loop to 2
>

Since stealing memory  from a running process that counts on it to be
functional will crash the process and odds are that process is something
low level and critical to keeping X running the above variant is not
practical to do and thus my current solution has the same effect -- reboot.

But that being said there is nothing about firefox, libreoffice or just
playing MP3's that should cause swapping on a machine with 24 GB of RAM!
(Yes I run tomcat but that has only one small test webapp on it [debugging
issues for a bigger one I support, the bigger one runs just fine on vm at a
hosting company with 8 GB and 2 cores])

-- 
Aryeh M. Friedman, Lead Developer, http://www.PetiteCloud.org


More information about the freebsd-questions mailing list