From: Waiman Long <waiman.long@hp.com>
To: paulmck@linux.vnet.ibm.com
Cc: Romanov Arya <romanov.arya@gmail.com>,
Pranith Kumar <bobby.prani@gmail.com>,
Josh Triplett <josh@joshtriplett.org>,
LKML <linux-kernel@vger.kernel.org>,
Peter Zijlstra <peterz@infradead.org>,
torvalds@linux-foundation.org
Subject: Re: [RFC PATCH 1/1] kernel/rcu/tree.c: simplify force_quiescent_state()
Date: Tue, 17 Jun 2014 16:06:43 -0400 [thread overview]
Message-ID: <53A09FD3.1050709@hp.com> (raw)
In-Reply-To: <20140617173717.GA28198@linux.vnet.ibm.com>
On 06/17/2014 01:37 PM, Paul E. McKenney wrote:
>
> Oh, and to answer the implicit question... A properly configured 4096-CPU
> system will have two funnel levels, with 64 nodes at the leaf level
> and a single node at the root level. If the system is not properly
> configured, it will have three funnel levels. The maximum number of
> funnel levels is four, which would handle more than four million CPUs
> (sixteen million if properly configured), so we should be good. ;-)
>
> The larger numbers of levels are intended strictly for testing. I set
> CONFIG_RCU_FANOUT_LEAF=2 and CONFIG_RCU_FANOUT=2 on a 16-CPU system just
> to make sure that I am testing something uglier than what will be running
> in production. A large system should have both of these set to 64,
> though this requires also booting with skew_tick=1 as well.
>
> Thanx, Paul
Thank for the clarification as I haven't looked deep into the code to
see how many levels there are. I totally understand the impact cacheline
contention can have on system performance. After all, this is what many
of my patches are trying to address.
-Longman
next prev parent reply other threads:[~2014-06-17 20:06 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-06-17 2:55 [RFC PATCH 1/1] kernel/rcu/tree.c: simplify force_quiescent_state() Pranith Kumar
2014-06-17 14:54 ` Paul E. McKenney
2014-06-17 16:01 ` Romanov Arya
2014-06-17 16:56 ` Waiman Long
2014-06-17 17:11 ` Paul E. McKenney
2014-06-17 17:37 ` Paul E. McKenney
2014-06-17 20:06 ` Waiman Long [this message]
2014-06-23 10:28 ` Peter Zijlstra
2014-06-23 15:57 ` Paul E. McKenney
2014-06-23 17:33 ` Paul E. McKenney
2014-06-23 18:57 ` Peter Zijlstra
2014-06-23 19:05 ` Paul E. McKenney
2014-06-17 17:10 ` Paul E. McKenney
2014-06-17 18:22 ` Pranith Kumar
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=53A09FD3.1050709@hp.com \
--to=waiman.long@hp.com \
--cc=bobby.prani@gmail.com \
--cc=josh@joshtriplett.org \
--cc=linux-kernel@vger.kernel.org \
--cc=paulmck@linux.vnet.ibm.com \
--cc=peterz@infradead.org \
--cc=romanov.arya@gmail.com \
--cc=torvalds@linux-foundation.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.