From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-0.8 required=3.0 tests=HEADER_FROM_DIFFERENT_DOMAINS, MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,URIBL_BLOCKED autolearn=no autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 3D668C433DF for ; Fri, 15 May 2020 17:41:59 +0000 (UTC) Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id 11EBB20657 for ; Fri, 15 May 2020 17:41:59 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 11EBB20657 Authentication-Results: mail.kernel.org; dmarc=none (p=none dis=none) header.from=bugs.launchpad.net Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=qemu-devel-bounces+qemu-devel=archiver.kernel.org@nongnu.org Received: from localhost ([::1]:58850 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1jZeLO-0001JA-Ag for qemu-devel@archiver.kernel.org; Fri, 15 May 2020 13:41:58 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:47052) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1jZeKV-0000on-GX for qemu-devel@nongnu.org; Fri, 15 May 2020 13:41:03 -0400 Received: from indium.canonical.com ([91.189.90.7]:50968) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1jZeKU-0004GX-Cp for qemu-devel@nongnu.org; Fri, 15 May 2020 13:41:03 -0400 Received: from loganberry.canonical.com ([91.189.90.37]) by indium.canonical.com with esmtp (Exim 4.86_2 #2 (Debian)) id 1jZeKS-0004Op-La for ; Fri, 15 May 2020 17:41:00 +0000 Received: from loganberry.canonical.com (localhost [127.0.0.1]) by loganberry.canonical.com (Postfix) with ESMTP id 991892E8109 for ; Fri, 15 May 2020 17:41:00 +0000 (UTC) MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Date: Fri, 15 May 2020 17:34:31 -0000 From: Babu Moger <1856335@bugs.launchpad.net> To: qemu-devel@nongnu.org X-Launchpad-Notification-Type: bug X-Launchpad-Bug: product=qemu; status=New; importance=Undecided; assignee=None; X-Launchpad-Bug-Information-Type: Public X-Launchpad-Bug-Private: no X-Launchpad-Bug-Security-Vulnerability: no X-Launchpad-Bug-Commenters: babumoger djdatte h-sieger janklos X-Launchpad-Bug-Reporter: Damir (djdatte) X-Launchpad-Bug-Modifier: Babu Moger (babumoger) References: <157625616239.22064.10423897892496347105.malonedeb@gac.canonical.com> Message-Id: <158956407118.23006.16594252430116823246.malone@gac.canonical.com> Subject: [Bug 1856335] Re: Cache Layout wrong on many Zen Arch CPUs X-Launchpad-Message-Rationale: Subscriber (QEMU) @qemu-devel-ml X-Launchpad-Message-For: qemu-devel-ml Precedence: bulk X-Generated-By: Launchpad (canonical.com); Revision="0385b538081bc4718df6fb844a3afc89729c94ce"; Instance="production-secrets-lazr.conf" X-Launchpad-Hash: 304020681fe1e86333dcb0ef62c707058023cd98 Received-SPF: none client-ip=91.189.90.7; envelope-from=bounces@canonical.com; helo=indium.canonical.com X-detected-operating-system: by eggs.gnu.org: First seen = 2020/05/15 13:41:01 X-ACL-Warn: Detected OS = Linux 3.11 and newer X-Spam_score_int: -65 X-Spam_score: -6.6 X-Spam_bar: ------ X-Spam_report: (-6.6 / 5.0 requ) BAYES_00=-1.9, HEADER_FROM_DIFFERENT_DOMAINS=0.249, RCVD_IN_DNSWL_HI=-5, RCVD_IN_MSPIKE_H3=0.001, RCVD_IN_MSPIKE_WL=0.001, URIBL_BLOCKED=0.001 autolearn=_AUTOLEARN X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.23 List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Reply-To: Bug 1856335 <1856335@bugs.launchpad.net> Errors-To: qemu-devel-bounces+qemu-devel=archiver.kernel.org@nongnu.org Sender: "Qemu-devel" Latest qemu has removed all the hard coded configurations for AMD. It is leaving everything to customize. One way is to configure is using numa nodes. This will make sure cpus under one numa node share same L3. Then pin the correct host cpus to guest cpus using vcpupin. I would change this -numa node,nodeid=3D0,cpus=3D0-2,cpus=3D12-14,mem=3D12288 to -numa node,nodeid=3D0,cpus=3D0-2,cpus=3D3-5,mem=3D12288. Then have vcpupin map the correct host cpu to guest cpu. Check if this works for you. Can you please post lscpu output from host for everybody's understanding? -- = You received this bug notification because you are a member of qemu- devel-ml, which is subscribed to QEMU. https://bugs.launchpad.net/bugs/1856335 Title: Cache Layout wrong on many Zen Arch CPUs Status in QEMU: New Bug description: AMD CPUs have L3 cache per 2, 3 or 4 cores. Currently, TOPOEXT seems to always map Cache ass if it was an 4-Core per CCX CPU, which is incorrect, and costs upwards 30% performance (more realistically 10%) in L3 Cache Layout aware applications. Example on a 4-CCX CPU (1950X /w 8 Cores and no SMT): =C2=A0=C2=A0 =C2=A0=C2=A0=C2=A0=C2=A0EPYC-IBPB =C2=A0=C2=A0=C2=A0=C2=A0AMD =C2=A0=C2=A0=C2=A0=C2=A0 In windows, coreinfo reports correctly: ****---- Unified Cache 1, Level 3, 8 MB, Assoc 16, LineSize 64 ----**** Unified Cache 6, Level 3, 8 MB, Assoc 16, LineSize 64 On a 3-CCX CPU (3960X /w 6 cores and no SMT): =C2=A0 =C2=A0=C2=A0=C2=A0=C2=A0EPYC-IBPB =C2=A0=C2=A0=C2=A0=C2=A0AMD =C2=A0=C2=A0=C2=A0=C2=A0 in windows, coreinfo reports incorrectly: ****-- Unified Cache 1, Level 3, 8 MB, Assoc 16, LineSize 64 ----** Unified Cache 6, Level 3, 8 MB, Assoc 16, LineSize 64 Validated against 3.0, 3.1, 4.1 and 4.2 versions of qemu-kvm. With newer Qemu there is a fix (that does behave correctly) in using the = dies parameter: =C2=A0 The problem is that the dies are exposed differently than how AMD does it natively, they are exposed to Windows as sockets, which means, that if you are nto a business user, you can't ever have a machine with more than two CCX (6 cores) as consumer versions of Windows only supports two sockets. (Should this be reported as a separate bug?) To manage notifications about this bug go to: https://bugs.launchpad.net/qemu/+bug/1856335/+subscriptions