From mboxrd@z Thu Jan 1 00:00:00 1970 From: Xiao Guangrong Subject: Re: [PATCH] kvm: add halt_poll_ns module parameter Date: Mon, 09 Feb 2015 18:12:04 +0800 Message-ID: <54D887F4.8000903@linux.intel.com> References: <1423226937-11169-1-git-send-email-pbonzini@redhat.com> <54D86E2D.8010808@linux.intel.com> <54D878AF.5050707@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit Cc: riel@redhat.com, mtosatti@redhat.com, rkrcmar@redhat.com, jan.kiszka@siemens.com, dmatlack@google.com To: Paolo Bonzini , linux-kernel@vger.kernel.org, kvm@vger.kernel.org Return-path: In-Reply-To: <54D878AF.5050707@redhat.com> Sender: linux-kernel-owner@vger.kernel.org List-Id: kvm.vger.kernel.org On 02/09/2015 05:06 PM, Paolo Bonzini wrote: > > > On 09/02/2015 09:22, Xiao Guangrong wrote: >> >> >> On 02/06/2015 08:48 PM, Paolo Bonzini wrote: >> >>> >>> +unsigned int halt_poll_ns = 0; >>> +module_param(halt_poll_ns, uint, S_IRUGO | S_IWUSR); >>> + >> >> Can we make this parameter be changeable? So that we can tune it >> on the fly. > > It is changeable (S_IWUSR). Oh... Yes, sorry for my careless. > >>> finish_wait(&vcpu->wq, &wait); >>> + cur = ktime_get(); >> >> We can move this into the tracepoint to avoid the workload if the >> tracepoint is not enabled. > > You have a point. I didn't do it because I expect that halt_poll_ns > will be always enabled as soon as it auto-tunes, and in that case you'll > always have to do the ktime_get() for autotuning purposes. Great, look forward to your future patches. ;)