From mboxrd@z Thu Jan 1 00:00:00 1970 From: Avi Kivity Subject: Re: [PATCH] x86/kvm: Show guest system/user cputime in cpustat Date: Thu, 11 Mar 2010 09:50:54 +0200 Message-ID: <4B98A0DE.1020006@redhat.com> References: <1268292022-31352-1-git-send-email-sheng@linux.intel.com> <4B989D61.70906@redhat.com> <201003111546.44059.sheng@linux.intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: Marcelo Tosatti , Ingo Molnar , linux-kernel@vger.kernel.org, kvm@vger.kernel.org, "Zhang, Yanmin" To: Sheng Yang Return-path: In-Reply-To: <201003111546.44059.sheng@linux.intel.com> Sender: linux-kernel-owner@vger.kernel.org List-Id: kvm.vger.kernel.org On 03/11/2010 09:46 AM, Sheng Yang wrote: > On Thursday 11 March 2010 15:36:01 Avi Kivity wrote: > >> On 03/11/2010 09:20 AM, Sheng Yang wrote: >> >>> Currently we can only get the cpu_stat of whole guest as one. This patch >>> enhanced cpu_stat with more detail, has guest_system and guest_user cpu >>> time statistics with a little overhead. >>> >>> Signed-off-by: Sheng Yang >>> --- >>> >>> This draft patch based on KVM upstream to show the idea. I would split it >>> into more kernel friendly version later. >>> >>> The overhead is, the cost of get_cpl() after each exit from guest. >>> >> This can be very expensive in the nested virtualization case, so I >> wouldn't like this to be in normal paths. I think detailed profiling >> like that can be left to 'perf kvm', which only has overhead if enabled >> at runtime. >> > Yes, that's my concern too(though nested vmcs/vmcb read already too expensive, > they should be optimized...). Any ideas on how to do that? Perhaps use paravirt_ops to covert the vmread into a memory read? We store the vmwrites in the vmcs anyway. > The other concern is, perf alike mechanism would > bring a lot more overhead compared to this. > Ordinarily users won't care if time is spent in guest kernel mode or guest user mode. They want to see which guest is imposing a load on a system. I consider a user profiling a guest from the host an advanced and rarer use case, so it's okay to require tools and additional overhead for this. >> For example you can put the code to note the cpl in a tracepoint which >> is enabled dynamically. >> > Yanmin have already implement "perf kvm" to support this. We are just arguing > if a normal top-alike mechanism is necessary. > > I am also considering to make it a feature that can be disabled. But seems it > make things complicate and result in uncertain cpustat output. > I'm not even sure that guest time was a good idea. -- error compiling committee.c: too many arguments to function