public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
* NUMA-Q breakage 7/7 preempt vs. printk bootstrap ordering
@ 2002-07-12 22:40 William Lee Irwin III
  0 siblings, 0 replies; only message in thread
From: William Lee Irwin III @ 2002-07-12 22:40 UTC (permalink / raw)
  To: linux-kernel; +Cc: rml

CONFIG_PREEMPT creates a bootstrap ordering issue as some implicit
scheduling done in printk.c raises exceptions prior to the secondary
cpus being prepared to handle them (seen as no vm86_info: BAD).

The workaround, enclosed below is not to use preempt on NUMA-Q.


Cheers,
Bill


===== arch/i386/config.in 1.40 vs edited =====
--- 1.40/arch/i386/config.in	Mon Jun 17 07:03:16 2002
+++ edited/arch/i386/config.in	Fri Jul 12 01:12:25 2002
@@ -165,7 +165,9 @@
       define_bool CONFIG_X86_IO_APIC y
    fi
 else
-   bool 'Multiquad NUMA system' CONFIG_MULTIQUAD
+   if [ "$CONFIG_PREEMPT" != "y" ]; then
+      bool 'Multiquad NUMA system' CONFIG_MULTIQUAD
+   fi
 fi
 
 bool 'Machine Check Exception' CONFIG_X86_MCE

^ permalink raw reply	[flat|nested] only message in thread

only message in thread, other threads:[~2002-07-12 22:39 UTC | newest]

Thread overview: (only message) (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2002-07-12 22:40 NUMA-Q breakage 7/7 preempt vs. printk bootstrap ordering William Lee Irwin III

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox