[Systems] Sunjammer Swapping

[Samuel Cantero]

It was my mistake to only look at the static result from the free -m
command. However, according to munin, sometimes we have some pages swapped
out to disk (I guess this is related to the swap-so column in the vmstat
result). Of course, it is almost insignificant the size swapped out.

Anyway, just for curiosity and learning purposes: is it expected and
desirable to have even few pages swapped out to disk? I always thought that
the swap partition or swap file was created to avoid an OOM error in case
of physical memory saturation. I have seen even some systems without a swap
partition. One example: freedom.

Thanks and Happy New Year for all! :)

Best regards,

Samuel C.


On Fri, Jan 1, 2016 at 5:21 AM, Bernie Innocenti <bernie at codewiz.org> wrote:

> On 01/01/2016 09:20 AM, Bernie Innocenti wrote:
> > My guess is that an unusual event occurred in the past (perhaps months
> > ago) caused the system to swap out a lot of stuff.
> >
> > After the errant process got OOM-killed, some of the memory got swapped
> > back in, leaving in swap just the pages that were not referenced ever
> since.
> >
> > There should be a munin graph showing swap I/O... and if it stays flat,
> > we're good.
>
> The big swap event was in mid-July:
>
>
> http://munin.sugarlabs.org/static/dynazoom.html?cgiurl_graph=/munin-cgi/munin-cgi-graph&plugin_name=sugarlabs.org/sunjammer.sugarlabs.org/swap&size_x=800&size_y=400&start_epoch=1417076284&stop_epoch=1451636284
>
> --
>  _ // Bernie Innocenti
>  \X/  http://codewiz.org
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.sugarlabs.org/archive/systems/attachments/20160101/b56bcd38/attachment.html>