[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20160713150525.8f703dfa5e83a534f8a51106@linux-foundation.org>
Date: Wed, 13 Jul 2016 15:05:25 -0700
From: Andrew Morton <akpm@...ux-foundation.org>
To: Manfred Spraul <manfred@...orfullife.com>
Cc: "H. Peter Anvin" <hpa@...or.com>,
Peter Zijlstra <peterz@...radead.org>,
Davidlohr Bueso <dave@...olabs.net>,
LKML <linux-kernel@...r.kernel.org>,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...e.hu>, 1vier1@....de,
felixh@...ormatik.uni-bremen.de
Subject: Re: [PATCH 0/2] ipc/sem.c: sem_lock fixes
On Wed, 13 Jul 2016 07:06:50 +0200 Manfred Spraul <manfred@...orfullife.com> wrote:
> Hi Andrew, Hi Peter,
>
> next version of the sem_lock() fixes:
> The patches are again vs. tip.
>
> Patch 1 is ready for merging, Patch 2 is for review.
>
> - Patch 1 is the patch as in -next since January
> It fixes the race that was found by Felix.
> - Patch 2 removes the memory barriers that are part of the qspinlock
> code.
> - (The hysteresis patch would be patch 3. The risk of regressions
> can't be ruled out, thus it must wait for benchmarks from real
> workload tests)
I think you're saying that if these two patches cause performance
regressions, we will need ipc-sem-sem_lock-with-hysteresis.patch?
Is that even necessary? If your testing shows that
ipc-sem-sem_lock-with-hysteresis.patch makes things faster then in it
goes, surely?
Powered by blists - more mailing lists