Re: measuring swap partition speed

On Fri, 22 Dec 2023, at 20:08, Mark Millard wrote:
> I normally use -j$(sysctl -n hw.ncpu) for installworld but,
> if I gather right, you effectively used -j1 (implicit), so
> I'll do both styles, -j4 being appropriate for RPi4B's.

Interesting. Advice long ago was to not use -j for the installworld part
so I've never used it at that stage.

Other ways of testing, in place of 'make installworld':

git -C /usr/ports pull --ff-only
periodic daily
find / -name "*.core" -mtime +2 -ls

(snip results)

> Compared/contrasted to yours, it again suggests seek-time as a
> potential notable contribution to the results in your context:
> the spinnig rust spends far more overall time between command,
> limiting the command processing rate. Plugging in and using a
> separate USB3 SSD suitable for use as swap might be a help,
> despite the shared bandwidth for the 2 USB3 ports. Even using
> the USB2 port could be useful, and might have a more independent
> bandwidth.

Historically there's been an issue (I didn't delve into it deeply at the time) 
where if both ports on the usb2 bus were occupied (like keyboard+mouse), 
one knocks the other off the bus. Doesn't matter what make/model the keyboard
or bus are. This was last identified when the system was at 13-stable. At present,
there is a wifi module plugged into the usb2 bus (ralink, shows up as run0). 
It'll page down and up when the system gets busy, to the extent i've had to 
take it out of monitoring. It's the only thing plugged into the usb2 bus.
I've avoided having to plug in more than one usb2 device into this bus since
encountering the problem. Having two things plugged into it makes one or the other malfunction. Having one thing plugged into it flaps when the system gets busy.

It's unknown to me at this stage whether anything similar affects the
usb3 bus. Right now, there's the usb3 disk plugged into one port and a usb2
serial cable (for a UPS) into the other. Something might be affecting usb in 
general and I've till now considered it to be usb2-only because that's where 
it was most obvious.

So I'm thinking what I'm seeing might be some effect with usb2 and/or 3 
being the root cause.

Things I'll be trying:

1. creating a swap partition on a usb3 stick plugged into the usb3 bus and 
running the tests
2. take the disk, plug it into an amd64 usb3 bus, try the tests on the plugged-in
disk

thanks for your help, it's appreciated.