RE: [Lhms-devel] Re: [RFC:PATCH(003/003)] Memory add to onlined node. (ver. 2) (For x86_64)

["Tolentino, Matthew E" <matthew.e.tolentino@intel.com>]

Yasunori Goto <> wrote:
> BTW, I have 2 question about x86_64's memory hot-add.
> 
> Q1)
>>  int add_memory(u64 start, u64 size)
>>  {
>> -	struct pglist_data *pgdat = NODE_DATA(0);
>> -	struct zone *zone = pgdat->node_zones + MAX_NR_ZONES-2;
> 
> Current code adds memory to ZONE_NORMAL like this.
> But, ZONE_DMA32 is available on 2.6.15. So, I'm afraid there are
> 2 types trouble.
> 
>   a) When new memory is added to < 4GB, this should be added to
>      Zone_DMA32.
>      Are there any real machine which allow to add memory under
>      4GB?

The Intel machine that supports this will not hot-add memory in
the physical address space below 4GB, even if you only have 1GB
before hot-adding.  There are too many restrictions and gotchas
involved in the lower 4GB.  Keith has the only other machine that
I'm aware of and I would guess that machine has similar restrictions.
Keith?  

>   b) If machine boots up with under 4GB memory, and new memory
>      is added to over 4GB, then kernel might panic due to Zone
>      Normal's initialization is imcomplete.

I do recall a problem like that a while back where the free lists
weren't initialized properly before hot-adding.  It was fixed
when I submitted the hot-add patches, but I haven't looked in the 
past two weeks or so. 

> Q2)
>   Are there any real machine which can add memory with NUMA feature?
>   Or will be there?
>   In my patch, I assume that DSDT is defined well for NUMA by
>   firmware. (Container device, Memory device...).

I don't currently know of one that is available, but I would 
venture a guess that we would use ACPI to notify the OS, via
the DSDT or perhaps an SSDT.   

matt
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/