Comparing Patches from 2.4.1-pre8,9 and 2.4.0-ac10,9 leads me to the question if the
chances to the MMX und i387 code in this patches could have broken raid5 under SMP?
My boot.log file states that it uses p5_mmx block moves for performance reasons.
In the 2.4.1 series are no changes to raid5 but the corruption issue which expirience are in both
kernel series the same.
Best regards
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
Please read the FAQ at http://www.tux.org/lkml/