Re: [OFFTOPIC] Re: K7 SMP

Kurt Garloff (garloff@suse.de)
Sun, 2 May 1999 20:21:15 +0200


--JYK4vJDZwFMowpUq
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: quoted-printable

On Sun, May 02, 1999 at 12:10:46AM +0100, Paul Jakma wrote:
> In unix the kernel runs in process context..=20
>=20
> that i knew. so a process can trap to kernel mode via a syscall on
> cpu1 and hence the kernel runs on that cpu. i grok that.
>=20
> So the kernel ran on both cpus, but two copies of the kernel
> could not run at one (except when doing some trivial things). All
> the int's were processes by cpu0.
> =20
> afaik, the scheduler is called by the timer interrupt, right? so if
> the timer int is only delivered to cpu0, how can a scheduler hand
> over control to a process to run on cpu1, when the scheduler can't
> run on cpu1.
> =20
> i'd be glad if you could fill me in on what i'm missing.

The IPI, see other mail. CPU0 can send IPIs to the other to signal
rescheduling.

--=20
Dipl.Phys. Kurt Garloff <kurt@garloff.de> [Wuppertal, FRG]
Garloff Linux System Development [Linux-ix86,-axp, DUX]
Plasma physics, high perf. computing [Linux SCSI driver: DC390]
PGP key: see mailheader / key servers =20

--JYK4vJDZwFMowpUq
Content-Type: application/pgp-signature

-----BEGIN PGP SIGNATURE-----
Version: 2.6.3in

iQCVAwUBNyyXmxaQN/7O/JIVAQFcvwP/Yl8aKC80H9l4QheAir+lW1ryh+Cv0W+D
oMDk6ouiL0TX2iCn3uNJTcoE01vfA0ns+T3A3uDdEEqccubjU3fN1vbA8s49cJoh
gbR445+8OvSdKv8df+v5rmroTUsvSEOhnLXjm9AUN+GX1smNKPwAagWgbXNUIkQH
+KqSHgm3Dp4=
=Q7/f
-----END PGP SIGNATURE-----

--JYK4vJDZwFMowpUq--

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/