OpenVZ Forum


Home » Mailing lists » Devel » Re: [ckrm-tech] [RFC][PATCH 5/7] UBC: kernel memory accounting (core)
Re: [ckrm-tech] [RFC][PATCH 5/7] UBC: kernel memory accounting (core) [message #5476 is a reply to message #5429] Mon, 21 August 2006 09:41 Go to previous messageGo to previous message
dev is currently offline  dev
Messages: 1693
Registered: September 2005
Location: Moscow
Senior Member

Alan Cox wrote:
> Ar Gwe, 2006-08-18 am 12:32 -0700, ysgrifennodd Dave Hansen:
>
>>>It ought to be cheap. Given each set of page structs is an array its a
>>>simple subtract and divide (or with care and people try to pack them
>>>nicely for cache lines - shift) to get to the parallel accounting array.
>>
>>I wish page structs were just a simple array. ;)
>
>
> Note I very carefully said "each set of"
>
>
>>It will just be a bit more code, but we'll need this for the two other
>>memory models: sparsemem and discontigmem. For discontig, we'll just
>>need pointers in the pg_data_ts and, for sparsemem, we'll likely need
>>another pointer in the 'struct mem_section'.
>
>
> Actually I don't believe this is true in either case. Change the code
> which allocates the page arrays to allocate (+ sizeof(void *) *
> pages_in_array on the end of each array when using UBC. The rest then
> seems to come out naturally.
I only doubt what gain we will have in this situation.
boot-time selectable vs. CONFIG-selectable?

Kirill
 
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Previous Topic: [PATCH] e1000: e1000_probe resources cleanup
Next Topic: Linux Containers : next steps
Goto Forum:
  


Current Time: Wed Aug 27 17:00:31 GMT 2025

Total time taken to generate the page: 0.12565 seconds