[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20180207132619.6595e4a9@gandalf.local.home>
Date: Wed, 7 Feb 2018 13:26:19 -0500
From: Steven Rostedt <rostedt@...dmis.org>
To: Matthew Wilcox <willy@...radead.org>
Cc: Jesper Dangaard Brouer <brouer@...hat.com>,
"Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>,
Kirill Tkhai <ktkhai@...tuozzo.com>, josh@...htriplett.org,
mathieu.desnoyers@...icios.com, jiangshanlai@...il.com,
mingo@...hat.com, cl@...ux.com, penberg@...nel.org,
rientjes@...gle.com, iamjoonsoo.kim@....com,
akpm@...ux-foundation.org, linux-kernel@...r.kernel.org,
linux-mm@...ck.org, rao.shoaib@...cle.com
Subject: Re: [PATCH 0/2] rcu: Transform kfree_rcu() into kvfree_rcu()
On Wed, 7 Feb 2018 10:10:55 -0800
Matthew Wilcox <willy@...radead.org> wrote:
> > For the record, I fully agree with Steve here.
Thanks, but...
> >
> > And being a performance "fanatic" I don't like to have the extra branch
> > (and compares) in the free code path... but it's a MM-decision (and
> > sometimes you should not listen to "fanatics" ;-))
>
> While free_rcu() is not withut its performance requirements, I think it's
> currently dominated by cache misses and not by branches. By the time RCU
> gets to run callbacks, memory is certainly L1/L2 cache-cold and probably
> L3 cache-cold. Also calling the callback functions is utterly impossible
> for the branch predictor.
I agree with Matthew.
This is far from any fast path. A few extra branches isn't going to
hurt anything here as it's mostly just garbage collection. With or
without the Spectre fixes.
-- Steve
Powered by blists - more mailing lists