Re: [Bug fix PATCH 1/2] acpi, movablemem_map: Exclude memblock.reserved ranges when parsing SRAT.

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On 02/21/2013 08:23 AM, Luck, Tony wrote:
Thanks for your clarify. What's the relationship between memory ranges
and address ranges here?
The ranges in the SRAT table might cover more memory than is present on
the system.  E.g. on some large Itanium systems the SRAT table would say
that 0-1TB was on node0, 1-2TB on node1, etc.

The EFI memory map described the memory actually present (perhaps just
a handful of GB on each node).

X86 systems tend not to have such radically sparse layouts, so this may be less
of a distinction.

What's the relationship between memory/address ranges and /proc/iomem?
I *think* that /proc/iomem just shows what is in e820 (for the memory entries,
it also adds in I/O ranges that come from other ACPI sources).

Funtion detect_memory use int 0x15 to get e820 memory map information, but why the address range is not contigous and seprate to several ranges?


-Tony

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>


[Index of Archives]     [Linux ARM Kernel]     [Linux ARM]     [Linux Omap]     [Fedora ARM]     [IETF Annouce]     [Bugtraq]     [Linux]     [Linux OMAP]     [Linux MIPS]     [ECOS]     [Asterisk Internet PBX]     [Linux API]