From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S936587AbdGTT5N (ORCPT <rfc822;w@1wt.eu>);
        Thu, 20 Jul 2017 15:57:13 -0400
Received: from shards.monkeyblade.net ([184.105.139.130]:35146 "EHLO
        shards.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S934707AbdGTT5M (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Thu, 20 Jul 2017 15:57:12 -0400
Date: Thu, 20 Jul 2017 12:57:10 -0700 (PDT)
Message-Id: <20170720.125710.1645099626446989744.davem@davemloft.net>
To: vijay.ac.kumar@oracle.com
Cc: sparclinux@vger.kernel.org, rob.gardner@oracle.com,
        anthony.yznaga@oracle.com, linux-kernel@vger.kernel.org
Subject: Re: [PATCH 0/2] sparc64: Use low latency path to resume idle cpu
From: David Miller <davem@davemloft.net>
In-Reply-To: <1499545424-415240-1-git-send-email-vijay.ac.kumar@oracle.com>
References: <1499545424-415240-1-git-send-email-vijay.ac.kumar@oracle.com>
X-Mailer: Mew version 6.7 on Emacs 25.2 / Mule 6.0 (HANACHIRUSATO)
Mime-Version: 1.0
Content-Type: Text/Plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Greylist: Sender succeeded SMTP AUTH, not delayed by milter-greylist-4.5.12 (shards.monkeyblade.net [149.20.54.216]); Thu, 20 Jul 2017 12:57:11 -0700 (PDT)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

From: Vijay Kumar <vijay.ac.kumar@oracle.com>
Date: Sat,  8 Jul 2017 14:23:42 -0600

> cpu_poke is a low latency path to resume the target cpu if suspended
> using cpu_yield. Use cpu poke to resume cpu if supported by hypervisor.
> 
> 	     hackbench results (lower is better):
> Number of		
> Process:		w/o fix		with fix
> 1  			0.012		 0.010
> 10			0.021		 0.019
> 100			0.151		 0.148

So this only works for a cpu which has yielded.

The kernel sends reschedule events to both idle and non-idle cpus.
That's why you have to have that fallback code to still send the
mondo IPI right?

For the case where POKE works, it seems like completely unnecessary
overhead to set the PIL interrupt.  Just disable local cpu interrupts
and call schedule_ipi() directly.

I bet that improves your benchmark even more.