[PATCH] 2.4-ac: migration_init improvements

• Next message: Robert Love: "[PATCH] 2.4-ac: separate max RT from max user RT"
• Previous message: Robert Love: "[PATCH] 2.4-ac: more yield abstractions"
• Next in thread: William Lee Irwin III: "Re: [PATCH] 2.4-ac: migration_init improvements"
• Reply: William Lee Irwin III: "Re: [PATCH] 2.4-ac: migration_init improvements"
• Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

Alan,

The attached patch simplifies the migration_init code (an ugly lot) with
a simpler mechanism. This is Erich Focht's version which is now in
2.5. It has proved stable both there and in my testing.

The new method is to bring up the first migration_thread, and then use
it to migrate the remaining threads to their respective CPUs. The
method makes sense and removes a lot of code.

This patch also includes a boot hang fix demonstrated on arches where
logical CPU mapping != physical CPU mapping. The bug was reported and
fixed by James Bottomley in 2.5.

Patch is against 2.4.19-pre7-ac4, please apply.

        Robert Love

• text/x-patch attachment: sched-migration-init-rml-2.4.19-pre7-ac4-1.patch__charset_ISO-8859-1

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

• Next message: Robert Love: "[PATCH] 2.4-ac: separate max RT from max user RT"
• Previous message: Robert Love: "[PATCH] 2.4-ac: more yield abstractions"
• Next in thread: William Lee Irwin III: "Re: [PATCH] 2.4-ac: migration_init improvements"
• Reply: William Lee Irwin III: "Re: [PATCH] 2.4-ac: migration_init improvements"
• Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

This archive was generated by hypermail 2b29 : Tue May 07 2002 - 22:00:30 EST