Re: [PATCH v2 2/2] locking/qrwlock: Don't contend with readers when setting _QW_WAITING

[Ingo Molnar <mingo@kernel.org>]

* Waiman Long <waiman.long@hp.com> wrote:

> > Mind posting the microbenchmark?
> 
> I have attached the tool that I used for testing.

Thanks, that's interesting!

Btw., we could also do something like this in user-space, in tools/perf/bench/, we 
have no 'perf bench locking' subcommand yet.

We already build and measure simple x86 kernel methods there such as memset() and 
memcpy():

 triton:~/tip> perf bench mem memcpy -r all
 # Running 'mem/memcpy' benchmark:

 Routine default (Default memcpy() provided by glibc)
 # Copying 1MB Bytes ...

       1.385195 GB/Sec
       4.982462 GB/Sec (with prefault)

 Routine x86-64-unrolled (unrolled memcpy() in arch/x86/lib/memcpy_64.S)
 # Copying 1MB Bytes ...

       1.627604 GB/Sec
       5.336407 GB/Sec (with prefault)

 Routine x86-64-movsq (movsq-based memcpy() in arch/x86/lib/memcpy_64.S)
 # Copying 1MB Bytes ...

       2.132233 GB/Sec
       4.264465 GB/Sec (with prefault)

 Routine x86-64-movsb (movsb-based memcpy() in arch/x86/lib/memcpy_64.S)
 # Copying 1MB Bytes ...

       1.490935 GB/Sec
       7.128193 GB/Sec (with prefault)

Locking primitives would certainly be more complex build in user-space - but we 
could shuffle things around in kernel headers as well to make it easier to test in 
user-space.

That's how we can build lockdep in user-space for example, see tools/lib/lockdep.

Just a thought.

Thanks,

	Ingo