[HEADSUP] Please help test device vnode bypass!

[Gary Jennejohn]

Divacky Roman writes:
> > >  On a 700MHz K7 machine this doubles the speed of
> > >          dd if=/dev/zero of=/dev/null bs=1 count=1000000
> > >  
> > >  This roughly translates to shaving 2usec of each read/write syscall.
> 
> I tried it (no problem yet) and did a bit testing...
> (cp -R /sys/ /tmp/s, dd if=/dev/zero of=smth count=1000000, cp smth smth1 and
> so on)
> 
> and it seems like its actually a bit slower (but everything works properly) -
> did I get anything wrong? should the results be a bit better (I did three run
> s
> every time of each test)
> 

You evidently missed the point that this change benefits accesses to
_devices_. All your tests are using files.

---
Gary Jennejohn / garyj[at]jennejohn.org gj[at]freebsd.org garyj[at]denx.de