From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:54179) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1bCOhn-0004sf-93 for qemu-devel@nongnu.org; Mon, 13 Jun 2016 06:02:52 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1bCOhi-0006xm-AQ for qemu-devel@nongnu.org; Mon, 13 Jun 2016 06:02:51 -0400 Received: from mx1.redhat.com ([209.132.183.28]:46172) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1bCOhi-0006xh-4r for qemu-devel@nongnu.org; Mon, 13 Jun 2016 06:02:46 -0400 References: <1465784487-23482-1-git-send-email-chao.p.peng@linux.intel.com> From: Paolo Bonzini Message-ID: <0ad19d18-4ee1-0450-c3fa-b64b34e2cc66@redhat.com> Date: Mon, 13 Jun 2016 12:02:41 +0200 MIME-Version: 1.0 In-Reply-To: <1465784487-23482-1-git-send-email-chao.p.peng@linux.intel.com> Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 7bit Subject: Re: [Qemu-devel] [PATCH] target-i386: kvm: cache KVM_GET_SUPPORTED_CPUID data List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Chao Peng , qemu-devel@nongnu.org Cc: kvm@vger.kernel.org, Eduardo Habkost , Marcelo Tosatti , Richard Henderson On 13/06/2016 04:21, Chao Peng wrote: > KVM_GET_SUPPORTED_CPUID ioctl is called frequently when initializing > CPU. Depends on CPU features and CPU count, the number of calls can be > extremely high which slows down QEMU booting significantly. In our > testing, we saw 5922 calls with switches: > > -cpu SandyBridge -smp 6,sockets=6,cores=1,threads=1 > > This ioctl takes more than 100ms, which is almost half of the total > QEMU startup time. > > While for most cases the data returned from two different invocations > are not changed, that means, we can cache the data to avoid trapping > into kernel for the second time. To make sure the cache safe one > assumption is desirable: the ioctl is stateless. This is not true > however, at least for some CPUID leaves. Which are the CPUID leaves for which KVM_GET_SUPPORTED_CPUID is not stateless? I cannot find any. > The good part is even the ioctl is not fully stateless, we can still > cache the return value if we know the data is unchanged for the leaves > we are interested in. Actually this should be true for most invocations > and looks all the places in current code hold true. > > A non-cached version can be introduced if refresh is required in the > future. [...] > > +static Notifier kvm_exit_notifier; > +static void kvm_arch_destroy(Notifier *n, void *unused) > +{ > + g_free(cpuid_cache); > +} > + > int kvm_arch_init(MachineState *ms, KVMState *s) > { > uint64_t identity_base = 0xfffbc000; > @@ -1165,6 +1176,9 @@ int kvm_arch_init(MachineState *ms, KVMState *s) > smram_machine_done.notify = register_smram_listener; > qemu_add_machine_init_done_notifier(&smram_machine_done); > } > + > + kvm_exit_notifier.notify = kvm_arch_destroy; > + qemu_add_exit_notifier(&kvm_exit_notifier); > return 0; This part is unnecessary; the OS takes care of freeing the heap on exit. Thanks, Paolo