Re: [PATCH] vfs: keep inodes with page cache off the inode shrinker LRU

[Arnd Bergmann <arnd@arndb.de>]

On Wed, Feb 26, 2020 at 7:04 PM <santosh.shilimkar@oracle.com> wrote:
>
> On 2/13/20 8:52 AM, Arnd Bergmann wrote:
> > On Wed, Feb 12, 2020 at 9:50 AM Russell King - ARM Linux admin
> > <linux@armlinux.org.uk> wrote:
>
> The Keystone generations of SOCs have been used in different areas and
> they will be used for long unless says otherwise.
>
> Apart from just split of lowmem and highmem, one of the peculiar thing
> with Keystome family of SOCs is the DDR is addressable from two
> addressing ranges. The lowmem address range is actually non-cached
> range and the higher range is the cacheable.

I'm aware of Keystone's special physical memory layout, but for the
discussion here, this is actually irrelevant for the discussion about
highmem here, which is only about the way we map all or part of the
available physical memory into the 4GB of virtual address space.

The far more important question is how much memory any users
(in particular the subset that are going to update their kernels
several years from now) actually have installed. Keystone-II is
one of the rare 32-bit chips with fairly wide memory interfaces,
having two 72-bit (with ECC) channels rather than the usual one
 or two channels of 32-bit DDR3. This means a relatively cheap
4GB configuration using eight 256Mx16 chips is possible, or
even a 8GB using sixteen or eighteen 512Mx8.

Do you have an estimate on how common these 4GB and 8GB
configurations are in practice outside of the TI evaluation
board?

       Arnd