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=-15.9 required=3.0 tests=BAYES_00,DKIMWL_WL_HIGH, DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_CR_TRAILER,INCLUDES_PATCH,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS autolearn=unavailable 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 56724C48BE8 for ; Fri, 18 Jun 2021 07:02:19 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 3A61B613BA for ; Fri, 18 Jun 2021 07:02:17 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S232214AbhFRHEX (ORCPT ); Fri, 18 Jun 2021 03:04:23 -0400 Received: from mail.kernel.org ([198.145.29.99]:44268 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S232059AbhFRHEV (ORCPT ); Fri, 18 Jun 2021 03:04:21 -0400 Received: by mail.kernel.org (Postfix) with ESMTPSA id CCE746100A; Fri, 18 Jun 2021 07:02:11 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=linuxfoundation.org; s=korg; t=1623999732; bh=lPwhwKYjLCuBb8iHU8Fh4mII4hR3kacqcXifOpUboVE=; h=Date:From:To:Cc:Subject:References:In-Reply-To:From; b=pd4DtYq3djICAHUOSGQlUqCHGrPLaz23j7yHmMvA9IlMEFXXRx5TcHYpUNnHS+cZZ e7k1Q3mzozRQaz8RD5qRcWMEBdzePEi3+EUkbh7Nd/z6fcmVdiDgihCW3nyPzogDR0 2b10gOywi6w5pc+tS/hdE6hw/4+bnU2P58rz9in0= Date: Fri, 18 Jun 2021 09:02:10 +0200 From: Greg KH To: Jing Zhang Cc: KVM , KVMARM , LinuxMIPS , KVMPPC , LinuxS390 , Linuxkselftest , Paolo Bonzini , Marc Zyngier , James Morse , Julien Thierry , Suzuki K Poulose , Will Deacon , Huacai Chen , Aleksandar Markovic , Thomas Bogendoerfer , Paul Mackerras , Christian Borntraeger , Janosch Frank , David Hildenbrand , Cornelia Huck , Claudio Imbrenda , Sean Christopherson , Vitaly Kuznetsov , Jim Mattson , Peter Shier , Oliver Upton , David Rientjes , Emanuele Giuseppe Esposito , David Matlack , Ricardo Koller , Krish Sadhukhan , Fuad Tabba Subject: Re: [PATCH v11 5/7] KVM: stats: Add documentation for binary statistics interface Message-ID: References: <20210618044819.3690166-1-jingzhangos@google.com> <20210618044819.3690166-6-jingzhangos@google.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20210618044819.3690166-6-jingzhangos@google.com> Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org On Fri, Jun 18, 2021 at 04:48:17AM +0000, Jing Zhang wrote: > This new API provides a file descriptor for every VM and VCPU to read > KVM statistics data in binary format. > It is meant to provide a lightweight, flexible, scalable and efficient > lock-free solution for user space telemetry applications to pull the > statistics data periodically for large scale systems. The pulling > frequency could be as high as a few times per second. > The statistics descriptors are defined by KVM in kernel and can be > by userspace to discover VM/VCPU statistics during the one-time setup > stage. > The statistics data itself could be read out by userspace telemetry > periodically without any extra parsing or setup effort. > There are a few existed interface protocols and definitions, but no > one can fulfil all the requirements this interface implemented as > below: > 1. During high frequency periodic stats reading, there should be no > extra efforts except the stats data read itself. > 2. Support stats annotation, like type (cumulative, instantaneous, > peak, histogram, etc) and unit (counter, time, size, cycles, etc). > 3. The stats data reading should be free of lock/synchronization. We > don't care about the consistency between all the stats data. All > stats data can not be read out at exactly the same time. We really > care about the change or trend of the stats data. The lock-free > solution is not just for efficiency and scalability, also for the > stats data accuracy and usability. For example, in the situation > that all the stats data readings are protected by a global lock, > if one VCPU died somehow with that lock held, then all stats data > reading would be blocked, then we have no way from stats data that > which VCPU has died. > 4. The stats data reading workload can be handed over to other > unprivileged process. > > Reviewed-by: David Matlack > Reviewed-by: Ricardo Koller > Reviewed-by: Krish Sadhukhan > Reviewed-by: Fuad Tabba > Signed-off-by: Jing Zhang > --- > Documentation/virt/kvm/api.rst | 176 ++++++++++++++++++++++++++++++++- > 1 file changed, 175 insertions(+), 1 deletion(-) > > diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst > index e328caa35d6c..7ca1c8d190c0 100644 > --- a/Documentation/virt/kvm/api.rst > +++ b/Documentation/virt/kvm/api.rst > @@ -5034,7 +5034,6 @@ see KVM_XEN_VCPU_SET_ATTR above. > The KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST type may not be used > with the KVM_XEN_VCPU_GET_ATTR ioctl. > > - > 4.131 KVM_GET_SREGS2 > ------------------ > > @@ -5081,6 +5080,173 @@ Writes special registers into the vcpu. > See KVM_GET_SREGS2 for the data structures. > This ioctl (when supported) replaces the KVM_SET_SREGS. > > +4.133 KVM_GET_STATS_FD > +---------------------- > + > +:Capability: KVM_CAP_STATS_BINARY_FD > +:Architectures: all > +:Type: vm ioctl, vcpu ioctl > +:Parameters: none > +:Returns: statistics file descriptor on success, < 0 on error > + > +Errors: > + > + ====== ====================================================== > + ENOMEM if the fd could not be created due to lack of memory > + EMFILE if the number of opened files exceeds the limit > + ====== ====================================================== > + > +The file descriptor can be used to read VM/vCPU statistics data in binary > +format. The file data is organized into three blocks as below: > ++-------------+ > +| Header | > ++-------------+ > +| Descriptors | > ++-------------+ > +| Stats Data | > ++-------------+ > + > +The Header block is always at the start of the file. It is only needed to be > +read one time for the lifetime of the file descriptor. > +It is in the form of ``struct kvm_stats_header`` as below:: > + > + #define KVM_STATS_ID_MAXLEN 64 > + > + struct kvm_stats_header { > + __u32 name_size; > + __u32 count; > + __u32 desc_offset; > + __u32 data_offset; > + char id[]; > + }; > + > +The ``id`` field is a '\0' terminated string which identifies the corresponding > +KVM statistics. For VM statistics, it is in the form of "kvm-{kvm pid}", like > +"kvm-12345". For VCPU statistics, it is in the form of > +"kvm-{kvm pid}/vcpu-{vcpu id}", like "kvm-12345/vcpu-12". > + > +The ``name_size`` field is the size (in byte) of the statistics name string > +(including trailing '\0') appended to the end of every statistics descriptor. > + > +The ``count`` field is the number of statistics. > + > +The ``desc_offset`` field is the offset of the Descriptors block from the start > +of the file indicated by the file descriptor. > + > +The ``data_offset`` field is the offset of the Stats Data block from the start > +of the file indicated by the file descriptor. > + > +The Descriptors block is only needed to be read once for the lifetime of the > +file descriptor. It is an array of ``struct kvm_stats_desc`` as shown in > +below code block:: > + > + #define KVM_STATS_TYPE_SHIFT 0 > + #define KVM_STATS_TYPE_MASK (0xF << KVM_STATS_TYPE_SHIFT) > + #define KVM_STATS_TYPE_CUMULATIVE (0x0 << KVM_STATS_TYPE_SHIFT) > + #define KVM_STATS_TYPE_INSTANT (0x1 << KVM_STATS_TYPE_SHIFT) > + #define KVM_STATS_TYPE_MAX KVM_STATS_TYPE_INSTANT > + > + #define KVM_STATS_UNIT_SHIFT 4 > + #define KVM_STATS_UNIT_MASK (0xF << KVM_STATS_UNIT_SHIFT) > + #define KVM_STATS_UNIT_NONE (0x0 << KVM_STATS_UNIT_SHIFT) > + #define KVM_STATS_UNIT_BYTES (0x1 << KVM_STATS_UNIT_SHIFT) > + #define KVM_STATS_UNIT_SECONDS (0x2 << KVM_STATS_UNIT_SHIFT) > + #define KVM_STATS_UNIT_CYCLES (0x3 << KVM_STATS_UNIT_SHIFT) > + #define KVM_STATS_UNIT_MAX KVM_STATS_UNIT_CYCLES > + > + #define KVM_STATS_BASE_SHIFT 8 > + #define KVM_STATS_BASE_MASK (0xF << KVM_STATS_BASE_SHIFT) > + #define KVM_STATS_BASE_POW10 (0x0 << KVM_STATS_BASE_SHIFT) > + #define KVM_STATS_BASE_POW2 (0x1 << KVM_STATS_BASE_SHIFT) > + #define KVM_STATS_BASE_MAX KVM_STATS_BASE_POW2 > + > + struct kvm_stats_desc { > + __u32 flags; > + __s16 exponent; > + __u16 size; > + __u32 offset; > + __u32 unused; > + char name[]; > + }; As I mention in another patch, this should be sucked in directly from the .h file in kerneldoc format, so that everything stays in sync. I bet almost this whole file can be put into the .h file, look at how drm and v4l2 does this in a way that you only have to write the above one time, not try to keep it in sync in two different places. thanks, greg k-h