From owner-freebsd-hackers@FreeBSD.ORG Wed May 2 21:28:47 2012 Return-Path: Delivered-To: freebsd-hackers@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 180671065677; Wed, 2 May 2012 21:28:47 +0000 (UTC) (envelope-from rysto32@gmail.com) Received: from mail-we0-f182.google.com (mail-we0-f182.google.com [74.125.82.182]) by mx1.freebsd.org (Postfix) with ESMTP id 71F6B8FC15; Wed, 2 May 2012 21:28:46 +0000 (UTC) Received: by weyt57 with SMTP id t57so950402wey.13 for ; Wed, 02 May 2012 14:28:45 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:content-transfer-encoding; bh=5FRLmdMMiShLjy2oCI3Tr94d+fX+nEJm0k97i0zF3to=; b=QqH3hW3u2W4ifyJIRf11ho7OiVhqh1lol5O38MthavVvHAsKcuP8Kf7DpZeKExzgCn JPr0w+3BWB/QZIIa9Z93E4T4LseMQM7DWCVktCzlJi5RhHitTN4GT8yxJcvMsdCJzRQi ZzusZIll5J2O84E9X/DeDPU5589MPyHeeeM9XGXbvHuJKEdxBw1tuWMfFAYUOFkeT1Sf s4s5TPwQzZG9n2zj2+rCTl4ZFMnasVclwKcTAW96xHNqHHbsc8OmQKze2EJzIRvQIT4M MdMaDhvXEpxaQh8KKdd9/dyf6lB/8qDonWEUfOEsqNhkNzzalJ//X+tnEeLsTL99hrgL PtXA== MIME-Version: 1.0 Received: by 10.180.86.197 with SMTP id r5mr14011879wiz.21.1335994125418; Wed, 02 May 2012 14:28:45 -0700 (PDT) Received: by 10.180.94.97 with HTTP; Wed, 2 May 2012 14:28:45 -0700 (PDT) In-Reply-To: <4FA1A421.6020601@FreeBSD.org> References: <4FA1A421.6020601@FreeBSD.org> Date: Wed, 2 May 2012 17:28:45 -0400 Message-ID: From: Ryan Stone To: Navdeep Parhar Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Cc: freebsd-hackers@freebsd.org Subject: Re: CPU selection for ithreads on 8.3 X-BeenThere: freebsd-hackers@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Technical Discussions relating to FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 02 May 2012 21:28:47 -0000 On Wed, May 2, 2012 at 5:16 PM, Navdeep Parhar wrote: > There seems to be a regression in 8.3 in the way the kernel selects CPUs > for interrupts. =A0For example, cxgb(4) on 8.3 ends up with all > its ithreads on the same CPU (CPU7 in this case). > > 12 root =A0 =A0 -68 =A0 =A0- =A0 =A0 0K =A0 816K WAIT =A0 =A07 =A0 0:55 = =A00.00% intr{irq279: > cxgbc0} > 12 root =A0 =A0 -68 =A0 =A0- =A0 =A0 0K =A0 816K WAIT =A0 =A07 =A0 0:52 = =A00.00% intr{irq275: > cxgbc0} > 12 root =A0 =A0 -68 =A0 =A0- =A0 =A0 0K =A0 816K WAIT =A0 =A07 =A0 0:47 = =A00.00% intr{irq278: > cxgbc0} > 12 root =A0 =A0 -68 =A0 =A0- =A0 =A0 0K =A0 816K WAIT =A0 =A07 =A0 0:43 = =A00.00% intr{irq277: > cxgbc0} > 12 root =A0 =A0 -68 =A0 =A0- =A0 =A0 0K =A0 816K WAIT =A0 =A07 =A0 0:43 = =A00.00% intr{irq282: > cxgbc0} > 12 root =A0 =A0 -68 =A0 =A0- =A0 =A0 0K =A0 816K WAIT =A0 =A07 =A0 0:41 = =A00.00% intr{irq281: > cxgbc0} > 12 root =A0 =A0 -68 =A0 =A0- =A0 =A0 0K =A0 816K WAIT =A0 =A07 =A0 0:32 = =A00.00% intr{irq276: > cxgbc0} > 12 root =A0 =A0 -68 =A0 =A0- =A0 =A0 0K =A0 816K WAIT =A0 =A07 =A0 0:31 = =A00.00% intr{irq280: > cxgbc0} > > Back in the day there used to be code in cxgb to bind different > interrupts to different CPUs but it was removed because the kernel > distributed them across CPUs anyway. =A0So what changed? =A0This appears = 8.3 > specific. =A0I don't see it on head and I don't have a 9 system readily > available right now. Does r232757 fix this? That just missed 8.3-RELEASE.