Re: [PATCH 2.6.16.29 1/1] memory: enhance Linux swap subsystem

["yunfeng zhang" <zyf.zeroos@gmail.com>]

No, a new idea to re-write swap subsystem at all. In fact, it's an
impossible task to me, so I provide a compromising solution -- pps
(pure private page system).

2006/12/30, Zhou Yingchao <yingchao.zhou@gmail.com>:
> 2006/12/27, yunfeng zhang <zyf.zeroos@gmail.com>:
> > To multiple address space, multiple memory inode architecture, we can introduce
> > a new core object -- section which has several features
> Do you mean "in-memory inode"  or "memory node(pglist_data)" by "memory inode" ?
> > The idea issued by me is whether swap subsystem should be deployed on layer 2 or
> > layer 3 which is described in Documentation/vm_pps.txt of my patch. To multiple
> > memory inode architecture, the special memory model should be encapsulated on
> > layer 3 (architecture-dependent), I think.
> I guess that you are  wanting to do something to remove arch-dependent
> code in swap subsystem.  Just like the pud introduced in the
> page-table related codes. Is it right?
> However, you should verify that your changes will not deteriorate
> system performance. Also, you need to maintain it for a long time with
> the evolution of mainline kernel before it is accepted.
>
> Best regards
> --
> Yingchao Zhou
> ***********************************************
>  Institute Of Computing Technology
>  Chinese Academy of Sciences
> ***********************************************
>