From mboxrd@z Thu Jan 1 00:00:00 1970 From: Nate Lawson Subject: Re: Bad power savings with high network traffic Date: Tue, 20 Jan 2004 11:57:05 -0800 (PST) Sender: acpi-devel-admin-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org Message-ID: <20040120115507.N96919@root.org> References: Mime-Version: 1.0 Content-Type: TEXT/PLAIN; charset=ISO-8859-15 Content-Transfer-Encoding: QUOTED-PRINTABLE Return-path: In-Reply-To: Errors-To: acpi-devel-admin-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , List-Archive: To: Markus Gaugusch Cc: acpi-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org List-Id: linux-acpi@vger.kernel.org On Sun, 18 Jan 2004, Markus Gaugusch wrote: > [I'm not subscribed, please CC: me on answers! Thanks!] > I had my laptop connected to a network with lots of multicast/broadcast > traffic (40kb broadcast + 80kb multicast/sec). The multicast traffic was > only visible on the network meter, when promiscous mode was enabled. > > Usually my CPU temperature is around 50=B0C when being idle, but it raise= d > up to 54=B0C! I found out, that although CPU usage was minimal (1-2%), th= e > C1 state was used very frequently. After unplugging the network cable, th= e > temperature went down again. > > My kernel is 2.4.24 with software suspend patch and realtek 8139 ethernet > card. I suppose, that kernel internal code doesn't honor C-states or > something like that? 8139 is a piece of junk. It probably doesn't have hw multicast filter, hence does a lot of DMA to memory or interrupts and you lose > C1 sleep states. -Nate ------------------------------------------------------- The SF.Net email is sponsored by EclipseCon 2004 Premiere Conference on Open Tools Development and Integration See the breadth of Eclipse activity. February 3-5 in Anaheim, CA. http://www.eclipsecon.org/osdn