I think we have a better feeling for the behaviour of SPARSE under
ia64. From
the lmbench results it looks like we're seeing an overall performance
improvement...
Dave, please apply the attached patch.
P.
--- linux-2.6.17.ia64/configs/kernel-2.6.17-ia64.config.orig 2006-07-25 12:41:59.000000000 -0400
+++ linux-2.6.17.ia64/configs/kernel-2.6.17-ia64.config 2006-07-25 15:18:10.000000000 -0400
@@ -136,12 +135,14 @@ CONFIG_SCHED_SMT=y
# CONFIG_PREEMPT is not set
CONFIG_SELECT_MEMORY_MODEL=y
# CONFIG_FLATMEM_MANUAL is not set
-CONFIG_DISCONTIGMEM_MANUAL=y
-# CONFIG_SPARSEMEM_MANUAL is not set
-CONFIG_DISCONTIGMEM=y
-CONFIG_FLAT_NODE_MEM_MAP=y
+# CONFIG_DISCONTIGMEM_MANUAL is not set
+CONFIG_SPARSEMEM_MANUAL=y
+CONFIG_SPARSEMEM=y
CONFIG_NEED_MULTIPLE_NODES=y
+CONFIG_HAVE_MEMORY_PRESENT=y
# CONFIG_SPARSEMEM_STATIC is not set
+CONFIG_SPARSEMEM_EXTREME=y
+# CONFIG_MEMORY_HOTPLUG is not set
CONFIG_SPLIT_PTLOCK_CPUS=4
CONFIG_MIGRATION=y
CONFIG_RESOURCES_64BIT=y
@@ -152,8 +153,6 @@ CONFIG_ARCH_SPARSEMEM_ENABLE=y
CONFIG_ARCH_DISCONTIGMEM_DEFAULT=y
CONFIG_NUMA=y
CONFIG_NODES_SHIFT=8
-CONFIG_VIRTUAL_MEM_MAP=y
-CONFIG_HOLES_IN_ZONE=y
CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID=y
CONFIG_HAVE_ARCH_NODEDATA_EXTENSION=y
# CONFIG_IA32_SUPPORT is not set
--
fedora-devel-list mailing list
fedora-devel-list@xxxxxxxxxx
https://www.redhat.com/mailman/listinfo/fedora-devel-list
