kernel-ark/arch
Andi Kleen 485761bd6a [PATCH] x86_64: Tell VM about holes in nodes
Some nodes can have large holes on x86-64.

This fixes problems with the VM allowing too many dirty pages because it
overestimates the number of available RAM in a node.  In extreme cases you
can end up with all RAM filled with dirty pages which can lead to deadlocks
and other nasty behaviour.

This patch just tells the VM about the known holes from e820.  Reserved
(like the kernel text or mem_map) is still not taken into account, but that
should be only a few percent error now.

Small detail is that the flat setup uses the NUMA free_area_init_node() now
too because it offers more flexibility.

(akpm: lotsa thanks to Martin for working this problem out)

Cc: Martin Bligh <mbligh@mbligh.org>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-08-26 19:37:12 -07:00
..
alpha [PATCH] alpha spinlock code and bogus constraints 2005-08-23 18:43:44 -07:00
arm [PATCH] qualifiers in return types - easy cases 2005-08-23 18:43:45 -07:00
arm26 It wasn't just x86-64 that had hardcoded VM_FAULT_xxx numbers 2005-08-04 08:33:38 -07:00
cris It wasn't just x86-64 that had hardcoded VM_FAULT_xxx numbers 2005-08-04 08:33:38 -07:00
frv It wasn't just x86-64 that had hardcoded VM_FAULT_xxx numbers 2005-08-04 08:33:38 -07:00
h8300 [PATCH] Don't export machine_restart, machine_halt, or machine_power_off. 2005-07-26 14:35:42 -07:00
i386 [PATCH] i386: fix incorrect FP signal code 2005-08-23 19:52:37 -07:00
ia64 [PATCH] Export pcibios_bus_to_resource 2005-08-24 10:22:44 -07:00
m32r [PATCH] missing exports on m32r 2005-08-23 18:43:46 -07:00
m68k It wasn't just x86-64 that had hardcoded VM_FAULT_xxx numbers 2005-08-04 08:33:38 -07:00
m68knommu [PATCH] Don't export machine_restart, machine_halt, or machine_power_off. 2005-07-26 14:35:42 -07:00
mips [PATCH] mips: remove obsolete GIU driver for vr41xx 2005-07-27 16:25:58 -07:00
parisc It wasn't just x86-64 that had hardcoded VM_FAULT_xxx numbers 2005-08-04 08:33:38 -07:00
ppc [PATCH] ppc32 8xx: fix m8xx_ide_init() #ifdef 2005-08-26 16:31:46 -07:00
ppc64 [PATCH] ppc64: Export machine_power_off for therm_pm72 module 2005-08-24 09:41:35 -07:00
s390 [PATCH] broken inline asm on s390 (misuse of labels) 2005-08-23 18:43:44 -07:00
sh [PATCH] SH: inotify and ioprio syscalls 2005-08-18 12:53:57 -07:00
sh64 [PATCH] SH64: inotify and ioprio syscalls 2005-08-18 12:53:57 -07:00
sparc [SPARC]: Fix weak aliases 2005-08-19 15:56:37 -07:00
sparc64 [PATCH] Export pcibios_bus_to_resource 2005-08-24 10:22:44 -07:00
um [PATCH] uml: fix a crash under screen 2005-08-18 12:53:58 -07:00
v850 [PATCH] v850: Update PCI support 2005-07-27 16:26:03 -07:00
x86_64 [PATCH] x86_64: Tell VM about holes in nodes 2005-08-26 19:37:12 -07:00
xtensa [PATCH] xtensa: use ssleep() instead of schedule_timeout() 2005-07-12 16:01:01 -07:00