From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:41578) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1ZxFqm-0000qQ-Mk for qemu-devel@nongnu.org; Fri, 13 Nov 2015 10:01:22 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1ZxFqh-00076i-OM for qemu-devel@nongnu.org; Fri, 13 Nov 2015 10:01:16 -0500 Received: from mx1.redhat.com ([209.132.183.28]:38501) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1ZxFqh-00076e-JV for qemu-devel@nongnu.org; Fri, 13 Nov 2015 10:01:11 -0500 References: <5645F9FD.2050807@proxmox.com> From: Paolo Bonzini Message-ID: <5645FB32.1080108@redhat.com> Date: Fri, 13 Nov 2015 16:01:06 +0100 MIME-Version: 1.0 In-Reply-To: <5645F9FD.2050807@proxmox.com> Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 7bit Subject: Re: [Qemu-devel] Problems with VM after kernel commit b18d5431acc7a2fd22767925f3a6f597aa4bd29e List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Wolfgang Link , guangrong.xiao@linux.intel.com Cc: qemu-devel@nongnu.org On 13/11/2015 15:55, Wolfgang Link wrote: > Hi, > > We have problems with a HP ProLiant DL380 Gen9 and Vm's with large > amount of memory, grater then 30GB. > > The problem is that the vm need about 10 sec to start to boot. > and when it comes to syncing the cpu clock, it takes a long time to > finish this task. > What also occurs is the vcpus need at startup 100% cpu usage and take > over 1 min. This has been fixed already, and the fix is slowly propagating to the stable kernels. The fixes are: - KVM: vmx: obey KVM_QUIRK_CD_NW_CLEARED (fixed already in 4.2) - KVM: x86: obey KVM_X86_QUIRK_CD_NW_CLEARED in kvm_set_cr0() (in 4.4, will be backported) Paolo