Date: Wed, 28 Nov 2012 18:05:24 +0200 From: Konstantin Belousov <kostikbel@gmail.com> To: Andriy Gapon <avg@freebsd.org> Cc: "freebsd-emulation@freebsd.org" <freebsd-emulation@freebsd.org>, Alexander Motin <mav@freebsd.org> Subject: Re: VirtualBox 4.2.4 on FreeBSD 9.1-PRERELEASE problem: VMs behave very different when pinned to different cores Message-ID: <20121128160524.GT3013@kib.kiev.ua> In-Reply-To: <50B62CB3.70101@FreeBSD.org> References: <CA%2Bkq2xvh3j5CM7UzRVfXCeLhHwpTY%2B_M7dCJx0c27NtV8EVJwg@mail.gmail.com> <CAE-m3X1UPsy%2Bwbqm_02JpXMr-UO3m7N6z_ZwY2HNo4GL0YUi1w@mail.gmail.com> <CA%2Bkq2xva61m_bHdzBZM2TYL5z7XiohvkxsYWtOyoBwQkpyvp0A@mail.gmail.com> <50AFAD05.1050604@FreeBSD.org> <CA%2Bkq2xv%2BU4ZnfK=1js4PRaNpTNdW-y-G50GV4%2BMVP0LugBf1pQ@mail.gmail.com> <50B25C17.20208@FreeBSD.org> <CA%2Bkq2xvjDa1BeuzPUuH99bgriEA-GJH36AZGiqScKSo4QZmHDg@mail.gmail.com> <50B62CB3.70101@FreeBSD.org>
next in thread | previous in thread | raw e-mail | index | archive | help
--jllsgs4PL/sXFNaa Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Wed, Nov 28, 2012 at 05:24:35PM +0200, Andriy Gapon wrote: > on 26/11/2012 09:10 Alex Chistyakov said the following: > > CPU: Intel(R) Core(TM) i7-3930K CPU @ 3.20GHz (3200.18-MHz K8-class CPU) > > Origin =3D "GenuineIntel" Id =3D 0x206d7 Family =3D 0x6 Model =3D = 0x2d > > Stepping =3D 7 > > Features=3D0xbfebfbff<FPU,VME,DE,PSE,TSC,MSR,PAE,MCE,CX8,APIC,SEP,MTRR,= PGE,MCA,CMOV,PAT,PSE36,CLFLUSH,DTS,ACPI,MMX,FXSR,SSE,SSE2,SS,HTT,TM,PBE> > > Features2=3D0x1fbee3bf<SSE3,PCLMULQDQ,DTES64,MON,DS_CPL,VMX,EST,TM2,SSS= E3,CX16,xTPR,PDCM,PCID,DCA,SSE4.1,SSE4.2,x2APIC,POPCNT,TSCDLT,AESNI,XSAVE,O= SXSAVE,AVX> > > AMD Features=3D0x2c100800<SYSCALL,NX,Page1GB,RDTSCP,LM> > > AMD Features2=3D0x1<LAHF> > > TSC: P-state invariant, performance statistics > >=20 >=20 > Is this a multi-socket system? >=20 > It would be very strange that a modern CPU like this would have such a sk= ew > between TSC on different cores. >=20 > On my Core i5-3570 I see that the _observed_ skew is no more than 100 tic= ks (after > many days of uptime). It could be zero, in fact, given the inaccuracy of > inter-core measurements. I believe that Cores have single TSC per package, located in uncore. And Core i7 cannot work in multi-socket systems. --jllsgs4PL/sXFNaa Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.19 (FreeBSD) iEYEARECAAYFAlC2NkQACgkQC3+MBN1Mb4j4HgCcCR/OAp5jigpvyQmFi+QjfCMM Pw0AoLY8s09L4G8yqQpwC4SGkhoUNEjm =IfVF -----END PGP SIGNATURE----- --jllsgs4PL/sXFNaa--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20121128160524.GT3013>