From owner-freebsd-arch@freebsd.org  Thu Aug 24 16:41:11 2017
Return-Path: <owner-freebsd-arch@freebsd.org>
Delivered-To: freebsd-arch@mailman.ysv.freebsd.org
Received: from mx1.freebsd.org (mx1.freebsd.org
 [IPv6:2001:1900:2254:206a::19:1])
 by mailman.ysv.freebsd.org (Postfix) with ESMTP id 374DFDE3CED
 for <freebsd-arch@mailman.ysv.freebsd.org>;
 Thu, 24 Aug 2017 16:41:11 +0000 (UTC)
 (envelope-from truckman@FreeBSD.org)
Received: from gw.catspoiler.org (unknown [IPv6:2602:304:b010:ef20::f2])
 (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits))
 (Client CN "gw.catspoiler.org", Issuer "gw.catspoiler.org" (not verified))
 by mx1.freebsd.org (Postfix) with ESMTPS id 17CED83C69;
 Thu, 24 Aug 2017 16:41:11 +0000 (UTC)
 (envelope-from truckman@FreeBSD.org)
Received: from FreeBSD.org (mousie.catspoiler.org [192.168.101.2])
 by gw.catspoiler.org (8.15.2/8.15.2) with ESMTP id v7OGf3pA042851;
 Thu, 24 Aug 2017 09:41:07 -0700 (PDT)
 (envelope-from truckman@FreeBSD.org)
Message-Id: <201708241641.v7OGf3pA042851@gw.catspoiler.org>
Date: Thu, 24 Aug 2017 09:41:03 -0700 (PDT)
From: Don Lewis <truckman@FreeBSD.org>
Subject: Re: ULE steal_idle questions
To: avg@FreeBSD.org
cc: freebsd-arch@FreeBSD.org
In-Reply-To: <d9dae0c1-e718-13fe-b6b5-87160c71784e@FreeBSD.org>
MIME-Version: 1.0
Content-Type: TEXT/plain; charset=us-ascii
X-BeenThere: freebsd-arch@freebsd.org
X-Mailman-Version: 2.1.23
Precedence: list
List-Id: Discussion related to FreeBSD architecture <freebsd-arch.freebsd.org>
List-Unsubscribe: <https://lists.freebsd.org/mailman/options/freebsd-arch>,
 <mailto:freebsd-arch-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-arch/>
List-Post: <mailto:freebsd-arch@freebsd.org>
List-Help: <mailto:freebsd-arch-request@freebsd.org?subject=help>
List-Subscribe: <https://lists.freebsd.org/mailman/listinfo/freebsd-arch>,
 <mailto:freebsd-arch-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Thu, 24 Aug 2017 16:41:11 -0000

Aside from the Ryzen problem, I think the steal_idle code should be
re-written so that it doesn't block interrupts for so long.  In its
current state, interrupt latence increases with the number of cores and
the complexity of the topology.

What I'm thinking is that we should set a flag at the start of the
search for a thread to steal.  If we are preempted by another, higher
priority thread, that thread will clear the flag.  Next we start the
loop to search up the hierarchy.  Once we find a candidate CPU:

                steal = TDQ_CPU(cpu);
                CPU_CLR(cpu, &mask);
                tdq_lock_pair(tdq, steal);
		if (tdq->tdq_load != 0) {
			goto out; /* to exit loop and switch to the new thread */
		}
		if (flag was cleared) {
			tdq_unlock_pair(tdq, steal);
			goto restart; /* restart the search */
		}
		if (steal->tdq_load < thresh || steal->tdq_transferable == 0 ||
		    tdq_move(steal, tdq) == 0) {
			tdq_unlock_pair(tdq, steal);
			continue;
		}
	    out:
	    	TDQ_UNLOCK(steal);
	    	clear flag;
	    	mi_switch(SW_VOL | SWT_IDLE, NULL);
	    	thread_unlock(curthread);
	    	return (0);

And we also have to clear the flag if we did not find a thread to steal.