[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20181002090652.GC116695@gmail.com>
Date: Tue, 2 Oct 2018 11:06:52 +0200
From: Ingo Molnar <mingo@...nel.org>
To: Waiman Long <longman@...hat.com>
Cc: Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...hat.com>,
Will Deacon <will.deacon@....com>,
linux-kernel@...r.kernel.org, Thomas Gleixner <tglx@...utronix.de>
Subject: Re: [PATCH 0/5] locking/lockdep: Improve lockdep performance
* Waiman Long <longman@...hat.com> wrote:
> Enabling CONFIG_LOCKDEP and other related debug options will greatly
> reduce system performance. This patchset aims to reduce the performance
> slowdown caused by the lockdep code.
>
> Patch 1 just removes an inline function that wasn't used.
>
> Patches 2 and 3 are minor twists to optimize the code.
>
> Patch 4 makes class->ops a per-cpu counter.
>
> Patch 5 moves the lock_release() call outside of a lock critical section.
>
> Parallel kernel compilation tests (make -j <#cpu>) were performed on
> 2 different systems:
>
> 1) an 1-socket 22-core 44-thread Skylake system
> 2) a 4-socket 72-core 144-thread Broadwell system
>
> The build times with pre-patch and post-patch debug kernels were:
>
> System Pre-patch Post-patch %Change
> ------ --------- ---------- -------
> 1-socket 8m53.9s 8m41.2s -2.4%
> 4-socket 7m27.0s 5m31.0s -26%
>
> I think it is the last 2 patches that yield most of the performance
> improvement.
Impressive speedup!
Mind including the non-lockdep numbers as well, for reference?
Thanks,
Ingo
Powered by blists - more mailing lists