On Thu, Jun 09, 2022 at 09:10:04PM +0200, Sedat Dilek wrote:
> On Wed, Jun 8, 2022 at 10:39 PM Al Viro <viro@xxxxxxxxxxxxxxxxxx> wrote:
> >
> > On Wed, Jun 08, 2022 at 09:28:18PM +0200, Sedat Dilek wrote:
> >
> > > I have pulled this on top of Linux v5.19-rc1... plus assorted patches
> > > to fix issues with LLVM/Clang version 14.
> > > No (new) warnings in my build-log.
> > > Boots fine on bare metal on my Debian/unstable AMD64 system.
> > >
> > > Any hints for testing - to see improvements?
> >
> > Profiling, basically... A somewhat artificial microbenchmark would be
> > to remove read_null()/write_null()/read_zero()/write_zero(), along with
> > the corresponding .read and .write initializers in drivers/char/mem.c
> > and see how dd to/from /dev/zero and friends behaves. On the mainline
> > it gives a noticable regression, due to overhead in new_sync_{read,write}().
> > With this series it should get better; pipe reads/writes also should see
> > reduction of overhead.
> >
> > There'd been a thread regarding /dev/random stuff; look for
> > "random: convert to using iters" and things nearby...
>
> Hmm, I did not find it...
>
> I bookmarked Ingo's reply on Boris x86-usercopy patch.
> There is a vague description without (for me at least) concrete instructions.
It's not really that. This is more about per-IO overhead, so you'd want
to do a lot of 1-byte writes to maximise your chance of seeing a
difference.
