From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([2001:4830:134:3::10]:59630)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <paolo.bonzini@gmail.com>) id 1Vj4I4-0005RV-G0
	for qemu-devel@nongnu.org; Wed, 20 Nov 2013 04:41:52 -0500
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <paolo.bonzini@gmail.com>) id 1Vj4Hw-0006Of-0w
	for qemu-devel@nongnu.org; Wed, 20 Nov 2013 04:41:44 -0500
Received: from mail-ea0-x236.google.com ([2a00:1450:4013:c01::236]:57566)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <paolo.bonzini@gmail.com>) id 1Vj4Hv-0006NT-PP
	for qemu-devel@nongnu.org; Wed, 20 Nov 2013 04:41:35 -0500
Received: by mail-ea0-f182.google.com with SMTP id o10so4682059eaj.27
	for <qemu-devel@nongnu.org>; Wed, 20 Nov 2013 01:41:34 -0800 (PST)
Sender: Paolo Bonzini <paolo.bonzini@gmail.com>
Message-ID: <528C83C2.2040903@redhat.com>
Date: Wed, 20 Nov 2013 10:41:22 +0100
From: Paolo Bonzini <pbonzini@redhat.com>
MIME-Version: 1.0
References: <CA+hQ2+iknsju27tHW1G=DONGvi0+oRHjGkK56FvcKN=vSdmFWg@mail.gmail.com>
In-Reply-To: <CA+hQ2+iknsju27tHW1G=DONGvi0+oRHjGkK56FvcKN=vSdmFWg@mail.gmail.com>
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
Subject: Re: [Qemu-devel] commit b1bbfe72 causes huge slowdown with no kvm
List-Id: <qemu-devel.nongnu.org>
List-Unsubscribe: <https://lists.nongnu.org/mailman/options/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=unsubscribe>
List-Archive: <http://lists.nongnu.org/archive/html/qemu-devel>
List-Post: <mailto:qemu-devel@nongnu.org>
List-Help: <mailto:qemu-devel-request@nongnu.org?subject=help>
List-Subscribe: <https://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=subscribe>
To: Luigi Rizzo <rizzo@iet.unipi.it>
Cc: qemu-devel <qemu-devel@nongnu.org>, Alex Bligh <alex@alex.org.uk>

Il 20/11/2013 00:00, Luigi Rizzo ha scritto:
> I recently found out that without kvm enabled, and especially
> with -smp 2 or greater, qemu becomes incredibly slow
> (to the point that you can see kernel messages in the
> quest print one character at a time).
> 
> This happens with a Linux host (even with -smp 1)
> and with FreeBSD host (in this case -smp 2 or greater;
> -smp 1 seems to work fine there).


I could not reproduce it; the profile here seems normal, too:

 24,69%  perf-3281.map                       [.] 0x00007f4ab5ac9903
 14,18%  qemu-system-x86_64                  [.] cpu_x86_exec
  2,67%  libglib-2.0.so.0.3800.1             [.] g_source_iter_next
  2,63%  qemu-system-x86_64                  [.] tcg_optimize
  2,47%  qemu-system-x86_64                  [.] helper_pcmpeqb_xmm
  2,28%  qemu-system-x86_64                  [.] phys_page_find
  1,92%  qemu-system-x86_64                  [.] address_space_translate_internal
  1,53%  qemu-system-x86_64                  [.] tcg_liveness_analysis
  1,40%  qemu-system-x86_64                  [.] tcg_reg_alloc_op
  1,17%  qemu-system-x86_64                  [.] helper_psubb_xmm
  0,97%  qemu-system-x86_64                  [.] disas_insn
  0,96%  qemu-system-x86_64                  [.] cpu_x86_handle_mmu_fault
  0,92%  qemu-system-x86_64                  [.] tcg_out_opc
  0,92%  qemu-system-x86_64                  [.] helper_pmovmskb_xmm
  0,91%  qemu-system-x86_64                  [.] tlb_set_page
  0,75%  qemu-system-x86_64                  [.] address_space_translate
  0,74%  qemu-system-x86_64                  [.] ldq_phys
  0,61%  qemu-system-x86_64                  [.] tcg_gen_code
  0,58%  qemu-system-x86_64                  [.] helper_le_ldq_mmu
  0,56%  qemu-system-x86_64                  [.] helper_ctz

This is on Linux, -smp 2, booting a RHEL6.4 guest.

Paolo