Re: [RFC PATCH RT] rwsem: The return of multi-reader PI rwsems

From: Steven Rostedt <rostedt@goodmis.org>
To: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: LKML <linux-kernel@vger.kernel.org>,
	linux-rt-users <linux-rt-users@vger.kernel.org>,
	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
	Paul Gortmaker <paul.gortmaker@windriver.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
	Clark Williams <williams@redhat.com>,
	Frederic Weisbecker <fweisbec@gmail.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@kernel.org>
Subject: Re: [RFC PATCH RT] rwsem: The return of multi-reader PI rwsems
Date: Thu, 10 Apr 2014 10:32:55 -0400	[thread overview]
Message-ID: <20140410103255.2eba08c6@gandalf.local.home> (raw)
In-Reply-To: <1397140123.5137.99.camel@marge.simpson.net>

On Thu, 10 Apr 2014 16:28:43 +0200
Mike Galbraith <umgwanakikbuti@gmail.com> wrote:

> On Thu, 2014-04-10 at 16:18 +0200, Mike Galbraith wrote: 
> > On Wed, 2014-04-09 at 15:19 -0400, Steven Rostedt wrote:
> > 
> > > If you have any benchmark on large machines I would be very happy if
> > > you could test this patch against the unpatched version of -rt.
> > 
> > Too bad I don't have (and know how to use) specjbb.
> > 
> > I dug up old vmark, thinking I'd be able to get some halfway useful
> > relative numbers from it, but that was a waste of a day.  The thing
> > performs so badly on 40 core box that rt _beats_ nopreempt, and after 2
> > nodes, you're going backward.  40 Westmere EX cores does a whopping ~2.5
> > * dinky old Q6600 box throughput.
> 
> P.S.  What I didn't see was any sign of a delta patched/unpatched..
> which may mean nothing at all :-/

Actually that at least means it didn't cause any regressions for you.

-- Steve