Large stack usage in fs code (especially for PPC64)

[Josh Boyer]

On Tue, 18 Nov 2008 10:13:16 +1100
Benjamin Herrenschmidt <benh at kernel.crashing.org> wrote:

> 
> > Well, it's not unacceptable on good CPU's with 4kB blocks (just an 8-entry 
> > array), but as you say:
> > 
> > > On PPC64 I'm told that the page size is 64K, which makes the above equal 
> > > to: 64K / 512 = 128  multiply that by 8 byte words, we have 1024 bytes.
> > 
> > Yeah. Not good. I think 64kB pages are insane. In fact, I think 32kB 
> > pages are insane, and 16kB pages are borderline. I've told people so.
> > 
> > The ppc people run databases, and they don't care about sane people 
> > telling them the big pages suck.
> 
> Hehe :-)
> 
> Guess who is pushing for larger page sizes nowadays ? Embedded
> people :-) In fact, we have patches submited on the list to offer the
> option for ... 256K pages on some 44x embedded CPUs :-)

For clarification, that workload is very precise.  Namely embedded 44x
CPUs used in RAID cards.  I'm not entirely convinced bringing 256K
pages into mainline is a good thing yet anyway.

64K pages, while seemingly insane for embedded boards that typically
have less than 512 MiB of DRAM, help for a bit larger set of
workloads.  As a KVM host is the primary winner at the moment.  But
given the small number of TLB entries on these CPUs, it can pay off
elsewhere as well.

josh