spurious out of swap kills
bob prohaska
fbsd at www.zefox.net
Sat Sep 14 16:10:20 UTC 2019
On Fri, Sep 13, 2019 at 10:59:58PM -0700, Mark Millard wrote:
> bob prohaska fbsd at www.zefox.net wrote on
> Fri Sep 13 16:24:57 UTC 2019 :
>
> > Not sure this is relevant, but in compiling chromium on a Pi3 with 6 GB
> > of swap the job completed successfully some months ago, with peak swap
> > use around 3.5 GB. The swap layout was sub-optimal, with a 2 GB partition
> > combined with a 4 GB partition. A little over 4GB total seems usable.
> >
> > A few days ago the same attempt stopped with a series of OOMA kills,
> > but in each case simply restarting allowed the compile to pick up
> > where it left off and continue, eventually finishing with a runnable
> > version of chromium. In this case swap use peaked a little over 4 GB.
> >
> > Might this suggest the machine isn't freeing swap in a timely manner?
>
> Are you saying that your increases to:
>
> vm.pageout_oom_seq
>
> no longer prove sufficient? What value for vm.pageout_oom_seq were
> you using that got the recent failures?
>
Correct. Initial value was 2048, later raised to 4096. Far as I could
tell the change didn't help. No explict j value was set for make, but
no more than four jobs were observed in top
A log of storage activity along with swap total and the last two
console messages is at
http://www.zefox.net/~fbsd/rpi3/swaptests/r351586/swapscript.log
along with a sorted list of total swap use, which can be used as
a sort of index to the log file.
The initial "out of swap space" at the very beginning
is a relic from before logging started.
Da0 is a Sandisk SDCZ80 usb 3.0 device, mmcsd0 is a Samsung
Evo + 128 GB device.
The two points of curiosity to me are:
1. Why did swap use increase from 3.5 GB months ago to 4.2 GB now?
2. Why does stopping and restarting make (which would seem to free
un-needed swap) allow the job to finish?
> If more or different configuration/tuning is required, I'm going to
> eventually want to learn about it as well.
>
You will have some company.
Thanks for reading,
bob prohaska
More information about the freebsd-current
mailing list