From patchwork Mon Jul 1 18:53:10 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Marcelo Tosatti X-Patchwork-Id: 11026623 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 76E1A746 for ; Mon, 1 Jul 2019 18:57:32 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 6E2162625B for ; Mon, 1 Jul 2019 18:57:32 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 61D2528741; Mon, 1 Jul 2019 18:57:32 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-7.9 required=2.0 tests=BAYES_00,MAILING_LIST_MULTI, RCVD_IN_DNSWL_HI autolearn=unavailable version=3.3.1 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 142062625B for ; Mon, 1 Jul 2019 18:57:31 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1726673AbfGAS5a (ORCPT ); Mon, 1 Jul 2019 14:57:30 -0400 Received: from mx1.redhat.com ([209.132.183.28]:33666 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726576AbfGAS53 (ORCPT ); Mon, 1 Jul 2019 14:57:29 -0400 Received: from smtp.corp.redhat.com (int-mx05.intmail.prod.int.phx2.redhat.com [10.5.11.15]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mx1.redhat.com (Postfix) with ESMTPS id C40178112C; Mon, 1 Jul 2019 18:57:27 +0000 (UTC) Received: from amt.cnet (ovpn-112-3.gru2.redhat.com [10.97.112.3]) by smtp.corp.redhat.com (Postfix) with ESMTP id 717C417108; Mon, 1 Jul 2019 18:57:27 +0000 (UTC) Received: from amt.cnet (localhost [127.0.0.1]) by amt.cnet (Postfix) with ESMTP id A363E105141; Mon, 1 Jul 2019 15:56:49 -0300 (BRT) Received: (from marcelo@localhost) by amt.cnet (8.14.7/8.14.7/Submit) id x61Iuf3Q028547; Mon, 1 Jul 2019 15:56:41 -0300 Message-ID: <20190701185310.540706841@asus.localdomain> User-Agent: quilt/0.66 Date: Mon, 01 Jul 2019 15:53:10 -0300 From: Marcelo Tosatti To: kvm@vger.kernel.org, linux-pm@vger.kernel.org Cc: Paolo Bonzini , Radim Krcmar , Andrea Arcangeli , "Rafael J. Wysocki" , Peter Zijlstra , Wanpeng Li , Konrad Rzeszutek Wilk , Raslan KarimAllah , Boris Ostrovsky , Ankur Arora , Christian Borntraeger Subject: [patch 0/5] cpuidle haltpoll driver and governor (v5) X-Scanned-By: MIMEDefang 2.79 on 10.5.11.15 X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.28]); Mon, 01 Jul 2019 18:57:29 +0000 (UTC) Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP The cpuidle-haltpoll driver with haltpoll governor allows the guest vcpus to poll for a specified amount of time before halting. This provides the following benefits to host side polling: 1) The POLL flag is set while polling is performed, which allows a remote vCPU to avoid sending an IPI (and the associated cost of handling the IPI) when performing a wakeup. 2) The VM-exit cost can be avoided. The downside of guest side polling is that polling is performed even with other runnable tasks in the host. Results comparing halt_poll_ns and server/client application where a small packet is ping-ponged: host --> 31.33 halt_poll_ns=300000 / no guest busy spin --> 33.40 (93.8%) halt_poll_ns=0 / guest_halt_poll_ns=300000 --> 32.73 (95.7%) For the SAP HANA benchmarks (where idle_spin is a parameter of the previous version of the patch, results should be the same): hpns == halt_poll_ns idle_spin=0/ idle_spin=800/ idle_spin=0/ hpns=200000 hpns=0 hpns=800000 DeleteC06T03 (100 thread) 1.76 1.71 (-3%) 1.78 (+1%) InsertC16T02 (100 thread) 2.14 2.07 (-3%) 2.18 (+1.8%) DeleteC00T01 (1 thread) 1.34 1.28 (-4.5%) 1.29 (-3.7%) UpdateC00T03 (1 thread) 4.72 4.18 (-12%) 4.53 (-5%) V2: - Move from x86 to generic code (Paolo/Christian) - Add auto-tuning logic (Paolo) - Add MSR to disable host side polling (Paolo) V3: - Do not be specific about HLT VM-exit in the documentation (Ankur Arora) - Mark tuning parameters static and __read_mostly (Andrea Arcangeli) - Add WARN_ON if host does not support poll control (Joao Martins) - Use sched_clock and cleanup haltpoll_enter_idle (Peter Zijlstra) - Mark certain functions in kvm.c as static (kernel test robot) - Remove tracepoints as they use RCU from extended quiescent state (kernel test robot) V4: - Use a haltpoll governor, use poll_state.c poll code (Rafael J. Wysocki) V5: - Take latency requirement into consideration (Rafael J. Wysocki) - Set target_residency/exit_latency to 1 (Rafael J. Wysocki) - Do not load cpuidle driver if not virtualized (Rafael J. Wysocki)