From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([140.186.70.92]:43799) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1QuuAh-0001Y4-LW for qemu-devel@nongnu.org; Sat, 20 Aug 2011 18:37:44 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1QuuAg-0006Lf-8z for qemu-devel@nongnu.org; Sat, 20 Aug 2011 18:37:43 -0400 Received: from fmmailgate01.web.de ([217.72.192.221]:53645) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1QuuAf-0006LZ-SC for qemu-devel@nongnu.org; Sat, 20 Aug 2011 18:37:42 -0400 Message-ID: <4E503715.7080103@web.de> Date: Sat, 20 Aug 2011 15:37:09 -0700 From: Jan Kiszka MIME-Version: 1.0 References: <20110820205122.GA29545@zapo> In-Reply-To: <20110820205122.GA29545@zapo> Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="------------enig5357C18086E843E5ECCCA006" Sender: jan.kiszka@web.de Subject: Re: [Qemu-devel] TCG slowdown List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: "Edgar E. Iglesias" Cc: qemu-devel@nongnu.org This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enig5357C18086E843E5ECCCA006 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable On 2011-08-20 13:51, Edgar E. Iglesias wrote: > Lately, my TCG emulated machines have been running terribly slow. > Like a factor 3 or 4 slower, hardly usable. >=20 > I bisected it to this: >=20 > commit d5ab9713d2d4037fd56b0adddd26c8d4dc11cf09 > Author: Jan Kiszka > Date: Tue Aug 2 16:10:21 2011 +0200 >=20 > Avoid allocating TCG resources in non-TCG mode > =20 > Do not allocate TCG-only resources like the translation buffer when= > running over KVM or XEN. Saves a "few" bytes in the qemu address sp= ace > and is also conceptually cleaner. > =20 > Signed-off-by: Jan Kiszka > Signed-off-by: Anthony Liguori >=20 >=20 > It turns out that the init of the tb cache is now moved to before ram_s= ize > gets it's default value. And because the default tb cache size, if no > -tb-size option is given, is based on the ram_size it is now zero.. Yes, already stumbled over that regression myself. See http://thread.gmane.org/gmane.comp.emulators.qemu/113547 Jan --------------enig5357C18086E843E5ECCCA006 Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.16 (GNU/Linux) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/ iEYEARECAAYFAk5QNxUACgkQitSsb3rl5xQ7cgCfQYrbRfr9o98PZIwXCVYqvgS8 psUAoOXmWbVhYPxW51uHkDPfYd1qHKiQ =13MZ -----END PGP SIGNATURE----- --------------enig5357C18086E843E5ECCCA006--