From owner-freebsd-current@FreeBSD.ORG Mon Mar 18 21:48:40 2013 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by hub.freebsd.org (Postfix) with ESMTP id AFCF971 for ; Mon, 18 Mar 2013 21:48:40 +0000 (UTC) (envelope-from m.e.sanliturk@gmail.com) Received: from mail-vb0-x235.google.com (mail-vb0-x235.google.com [IPv6:2607:f8b0:400c:c02::235]) by mx1.freebsd.org (Postfix) with ESMTP id 6C7C1E48 for ; Mon, 18 Mar 2013 21:48:40 +0000 (UTC) Received: by mail-vb0-f53.google.com with SMTP id fj18so3677075vbb.40 for ; Mon, 18 Mar 2013 14:48:40 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:x-received:in-reply-to:references:date:message-id :subject:from:to:cc:content-type; bh=Y286Acf8rMUJ2wnnVIPHio16Fh7Ul5wyhlXLD3Fsulo=; b=HcD8RB0E0n+mK9sykte8Ln/xTwC9XgBNyIb/xwLZ46KjUv9nYDKKFSKIA0phi0csoo 5yKw3xINmxJd7uGeF5WeLngYPa4mI4Rfl7BNZjqm+6xmk1YDl58WACzwoVIqNVPf/oBt vp3ehN2efHSPzWR2qVdJTrzy0yDa5JRb+xloVWx2qM61/eln5ItzPzYvuJHE3iTmB/pZ hH7CDC/OKnnnjaorKmoiMEMaTSfd/Fr182ZlNCv9q7SbhWfsTam0jpysim+kl6wsA7Mn EDyzFXRdog4S4F4jGQjzUWKTxLeGc6TWUeupzkRzlLAiYmtKdWMpfNR/Ata5AMfOmHAa c4VA== MIME-Version: 1.0 X-Received: by 10.58.252.72 with SMTP id zq8mr22634744vec.20.1363643319973; Mon, 18 Mar 2013 14:48:39 -0700 (PDT) Received: by 10.58.132.203 with HTTP; Mon, 18 Mar 2013 14:48:39 -0700 (PDT) In-Reply-To: <51478703.7030907@gmx.de> References: <35878.1363607691@critter.freebsd.dk> <514715F9.2080506@freebsd.org> <43BD412145BF4C7A9E2EFF91CF2ED379@multiplay.co.uk> <51478703.7030907@gmx.de> Date: Mon, 18 Mar 2013 14:48:39 -0700 Message-ID: Subject: Re: FreeBSD is very slow when Memory chip sizes are imbalanced in slots From: Mehmet Erol Sanliturk To: olli hauer Content-Type: text/plain; charset=UTF-8 X-Content-Filtered-By: Mailman/MimeDel 2.1.14 Cc: freebsd-current@freebsd.org X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 18 Mar 2013 21:48:40 -0000 On Mon, Mar 18, 2013 at 2:28 PM, olli hauer wrote: > On 2013-03-18 21:43, Mehmet Erol Sanliturk wrote: > > On Mon, Mar 18, 2013 at 9:48 AM, Scot Hetzel wrote: > > > >> On Mon, Mar 18, 2013 at 11:06 AM, Mehmet Erol Sanliturk > >> wrote: > >>> Computer A : Memory Chip Sizes : ( 2 GB , 1 GB , 2 GB , 1 GB ) : > Working > >>> SLOW . FreeBSD A > >>> Computer B : Memory Chip Sizes : ( 2 GB , 2 GB , 2 GB , 2 GB ) : > Working > >>> FAST . FreeBSD B > >>> > >>> Interchange memory chips : > >>> > >>> Computer A : Memory Chip Sizes : ( 2 GB , 2 GB , 2 GB , 2 GB ) : > Working > >>> FAST . FreeBSD A > >>> Computer B : Memory Chip Sizes : ( 2 GB , 1 GB , 2 GB , 1 GB ) : > Working > >>> SLOW . FreeBSD B > >>> > >>> > >> > >> What happens if you configure the memory as ( 2 GB , 2 GB , 1 GB , 1 GB > )? > >> > >> -- > >> DISCLAIMER: > >> > >> No electrons were maimed while sending this message. Only slightly > bruised. > >> > > > > > > This can NOT be done , because > > > > Channel A : Slot 1 : > > Slot 2 : > > > > Channel B : Slot 1 : > > Slot 2 : > > > > ( Slot 1 , Slot 1 ) should be equivalent when chips inserted to both . > > ( Slot 2 , Slot 2 ) should be equivalent when chips inserted to both . > > > > Thank you ver much . > > > > I suspect the BIOS does not detect the optimal timing for the "SLOW" RAM or > a RAM Module is running on a slower timing. > > What happen if you test with only the 2GB or the 1GB modules (to identify > possible CHIP issues). > How is the memory detected in the BIOS (timings ...) some newer BIOS can > run manual tests to detect timing issues. > > > > These are worked : http://lists.freebsd.org/pipermail/freebsd-current/2012-February/031836.html http://lists.freebsd.org/pipermail/freebsd-current/2012-February/031912.html http://lists.freebsd.org/pipermail/freebsd-current/2012-February/031928.html http://lists.freebsd.org/pipermail/freebsd-current/2012-February/032012.html It seems that memory chip sizes are not checked one by one or used per chip in slots , but a COMMON value is used : Size of chip in first slot . When size of chip in second slot is smaller than size of chip in first slot , problem appears . Thank you very much . Mehmet Erol Sanliturk