From owner-freebsd-smp Mon Sep 22 19:09:01 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.7/8.8.7) id TAA08026 for smp-outgoing; Mon, 22 Sep 1997 19:09:01 -0700 (PDT) Received: from lamb.sas.com (daemon@lamb.sas.com [192.35.83.8]) by hub.freebsd.org (8.8.7/8.8.7) with SMTP id TAA08019 for ; Mon, 22 Sep 1997 19:08:57 -0700 (PDT) Received: from mozart by lamb.sas.com (5.65c/SAS/Gateway/01-23-95) id AA21234; Mon, 22 Sep 1997 22:08:53 -0400 Received: from iluvatar.unx.sas.com by mozart (5.65c/SAS/Domains/5-6-90) id AA14451; Mon, 22 Sep 1997 22:02:39 -0400 From: "John W. DeBoskey" Received: by iluvatar.unx.sas.com (5.65c/SAS/Generic 9.01/3-26-93) id AA05936; Mon, 22 Sep 1997 22:02:38 -0400 Message-Id: <199709230202.AA05936@iluvatar.unx.sas.com> Subject: Really bad performance with smp vs. up To: freebsd-smp@freebsd.org Date: Mon, 22 Sep 1997 22:02:38 -0400 (EDT) X-Mailer: ELM [version 2.4 PL23] Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, I have 3.0-970911-SNAP installed on 4 UP 180Mhz machines and on 1 200Mhz 4-way (Dell PowerEdge 6100). The application I'm working on is a highly parallel build/make system. The 4 180Mhz machines, running 3 compiles each, takes 1 minute 30 seconds to compile 110 sources. The 4way box, however, takes 1 hour and a few minutes to do the same amount of work. Top reports user cpu at 2%, system cpu at 95%, and the rest is interrupts. This holds very constant. The last SNAP I had installed was 3.0-970815-SNAP, where I didn't see this problem (but was having serious networking/NIC problems). As always, I'm more than happy to try and track this down if someone can point me in the right direction. Thanks, John ps: Yes, this is running with the SMP generic kernel config with only my required changes: options NCPU=4 # Symmetric (APIC) I/O options MFS #Memory Filesystem -- jwd@unx.sas.com (w) John W. De Boskey (919) 677-8000 x6915