From owner-freebsd-hackers@FreeBSD.ORG Mon Apr 16 21:39:13 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 5DF99106564A for ; Mon, 16 Apr 2012 21:39:13 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: from mail-pz0-f44.google.com (mail-pz0-f44.google.com [209.85.210.44]) by mx1.freebsd.org (Postfix) with ESMTP id 2DA5D8FC14 for ; Mon, 16 Apr 2012 21:39:13 +0000 (UTC) Received: by dadz14 with SMTP id z14so25052696dad.17 for ; Mon, 16 Apr 2012 14:39:13 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type :content-transfer-encoding; bh=Oe1Rzw5IV4CqmIbACSJOMKXTOY2z5fT0e+kAqRzGP/A=; b=G/SP3oQIcP4AVNwj0GLd/zXEjI4AMF1cjeW5pdTsoGajGpaR6gMaIhwZteqkAmj/4R RrFKjgNlH1GrHhUD+zSl5iV+fiZIjoJ829fJ+wVnBb8J7EfrDkSSW7633+Bq+O86CQ8g LH1prnlghCZjFYKfeUIPKOOJlFG+8YfS/5zbaZBXo6YpzYrL5CyA0ezNvWxPrvE4ekZe NR3YmhB2WlC7avvLXKrqxDJGXiGGmUUMFQNxfTJLo/B29/l621dmJ7qLetMK314etHjN wwlY1uDqE23fw12sAS0Tw6mo8Cg4UvJHadxNAPF3cAsKfzaC5+SSi3MCRUicTJXuZb4a yapA== MIME-Version: 1.0 Received: by 10.68.212.130 with SMTP id nk2mr28090928pbc.166.1334612352937; Mon, 16 Apr 2012 14:39:12 -0700 (PDT) Sender: adrian.chadd@gmail.com Received: by 10.142.101.9 with HTTP; Mon, 16 Apr 2012 14:39:12 -0700 (PDT) In-Reply-To: <20120411192153.5672b62c@ernst.jennejohn.org> References: <20120403193124.46ad9de9@ernst.jennejohn.org> <20120411192153.5672b62c@ernst.jennejohn.org> Date: Mon, 16 Apr 2012 14:39:12 -0700 X-Google-Sender-Auth: 0c_7IbjDbwKnak4f9NHzYoUPgdA Message-ID: From: Adrian Chadd To: gljennjohn@googlemail.com Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Cc: freebsd-hackers , Jerry Toung Subject: Re: CAM disk I/O starvation 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: Mon, 16 Apr 2012 21:39:13 -0000 On 11 April 2012 10:21, Gary Jennejohn wrote: > Just for the archive my bad disk performance seems to have been fixed in > HEAD by svn commit r234074. =A0Seems that all interrupts were being handl= ed > by a single CPU/core (I have 6), which resulted in abysmal interrupt > handling when mutltiple disks were busy. > > Since this commit my disk preformance is back to normal and long lags > are a thing of the past. Hi, This is kind of worrying. You only have a few disks, a single core SHOULD be able to handle all the interrupts for those disks whilst leaving plenty of cycles to spare to drive the rest of your system. And you have 5 other cores. Would you be willing to help out diagnose exactly why that particular behaviour is causing you so much trouble? It almost sounds like something in the IO path is blocking for far too long, not allowing the rest of the system to move forward. That's very worrying for an interrupt handler. :) Adrian