Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756660Ab1BCTnu (ORCPT ); Thu, 3 Feb 2011 14:43:50 -0500 Received: from mvp.visionpro.com ([63.91.95.19]:39415 "EHLO extern.visionpro.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1756491Ab1BCTnt (ORCPT ); Thu, 3 Feb 2011 14:43:49 -0500 User-Agent: Microsoft-Entourage/12.28.0.101117 Date: Thu, 03 Feb 2011 11:43:46 -0800 Subject: Memset very slow From: "Brian D. McGrew" To: Message-ID: Thread-Topic: Memset very slow Thread-Index: AcvD2qui0ZuNMyexxECaW+q0w1/TUQ== Mime-version: 1.0 Content-type: text/plain; charset="US-ASCII" Content-transfer-encoding: 7bit X-OriginalArrivalTime: 03 Feb 2011 19:43:46.0147 (UTC) FILETIME=[ABB87330:01CBC3DA] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1659 Lines: 37 Hello All! We're using Dell T5500 workstations and a kernel-2.6.18.194 in CentOS 5.5_x86-64. When we get these Dells, we have to flash the BIOS back to rev A02 or else everything is so slow its unusable. Now, the "new" T5500's are here and we don't have the option to flash the BIOS back to A02 since it's a faster processor and memory and a new motherboard. We do memset in lots of places in our code, and in a couple places, the memset is as large as 3GB. Using the old machines with old BIOS, we were fine but with a newer (current) BIOS on the new machines or the old machines, memset is so slow it renders the system unusable. But also after using memset and that taking too long, everything else is slow, especially system() calls. On a properly configured "old" machine with the "old" BIOS, I can memset 3GBx2 in about .45 seconds and system calls return in under .25 seconds. However, sing the new BIOS on either machine, that same memset takes about 20 seconds and system calls 6 to 7 seconds. I grabbed the bleeding edge 2.6.37 from Elrepo and everything works fine, new or old boxes and/or BIOS. So, my question is, can someone explain to me what is going on here? I am not convinced this is a kernel problem just because a new kernel fixed it; but, if there were changes related to this in the kernel, then what is the oldest version I should be looking at to fix my issues? Thanks! -brian -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/