RPI3 swap experiments ["was killed: out of swap space" with: "v_free_count: 5439, v_inactive_count: 1"]

[Warner Losh]

On Wed, Aug 8, 2018 at 2:48 PM, Mark Johnston <markj at freebsd.org> wrote:

> On Wed, Aug 08, 2018 at 08:38:00AM -0700, bob prohaska wrote:
> > The patched kernel ran longer than default but OOMA still halted
> buildworld around
> > 13 MB. That's considerably farther than a default build world have run
> but less than
> > observed when setting vm.pageout_oom_seq=120 alone. Log files are at
> > http://www.zefox.net/~fbsd/rpi3/swaptests/r337226M/
> 1gbsdflash_1gbusbflash/batchqueue/
> >
> > Both changes are now in place and -j4 buildworld has been restarted.
>
> Looking through the gstat output, I'm seeing some pretty abysmal average
> write latencies for da0, the flash drive.  I also realized that my
> reference to r329882 lowering the pagedaemon sleep period was wrong -
> things have been this way for much longer than that.  Moreover, as you
> pointed out, bumping oom_seq to a much larger value wasn't quite
> sufficient.
>



> I'm curious as to what the worst case swap I/O latencies are in your
> test, since the average latencies reported in your logs are high enough
> to trigger OOM kills even with the increased oom_seq value.  When the
> current test finishes, could you try repeating it with this patch
> applied on top? https://people.freebsd.org/~markj/patches/slow_swap.diff
> That is, keep the non-default oom_seq setting and modification to
> VM_BATCHQUEUE_SIZE, and apply this patch on top.  It'll cause the kernel
> to print messages to the console under certain conditions, so a log of
> console output will be interesting.


Experience tells me that worst case is about 10x-50x median (which kinda
tracks the average that gstat reports). For SD cards, it may be much much
worse. Like seconds to tens of seconds worst case.

I don't think the swapper is well tuned to devices that have such a large
dynamic range and suck so bad when driven to the brink.

Warner