Re: [RFC][PATCH 2/2] hugetlb: remove multi-valued proc files.

[Nishanth Aravamudan <nacc@us.ibm.com>]

On 30.05.2008 [05:51:23 +0200], Nick Piggin wrote:
> On Wed, May 28, 2008 at 11:42:42PM -0700, Nishanth Aravamudan wrote:
> > Now that we present the same information in a cleaner way in sysfs, we
> > can remove the duplicate information and interfaces from procfs (and
> > consider them to be the legacy interface). The proc interface only
> > controls the default hugepage size, which is either
> > 
> > a) the first one specified via hugepagesz= on the kernel command-line, if any
> > b) the legacy huge page size, otherwise
> > 
> > All other hugepage size pool manipulations can occur through sysfs.
> > 
> > Signed-off-by: Nishanth Aravamudan <nacc@us.ibm.com>
> > 
> > ---
> > Note, this does end up making the manipulation and validation of
> > multiple hstates impossible without sysfs enabled and mounted. As such,
> 
> I don't think that's such a problem. The overlap between users with
> no sysfs and those that use multiple hugepages won't be large. And
> if any exist, they can specify at boot or come up with their own
> customer solution.

Yeah, like I said, I imagine the only ones that might care are sh folks
and even there, I don't know their MMU well enough to know how big of a
deal it is.

> > I'm not sure if this is the right approach and perhaps we should be
> > leaving the multi-valued proc files in place (but not as the preferred
> > interface). Or we could present the values in procfs only if SYSFS is
> > not enabled in the kernel? I imagine (but am not 100% sure) that the
> > only current architecture where this might be important is SUPERH?
> 
> I wouldn't worry too much. I think /proc/sys/vm/nr_hugepages etc
> is better as one (the compat) value after we now have the sysfs
> stuff. However /proc/meminfo is a little more tricky. Of course
> the information does exist in sysfs too, but meminfo is also for
> user reporting, so maybe it will be better to leave it multi
> column?

Yeah, I suppose it could be either way. I definitely agree the writable
interfaces are cleaner single-valued.

Thanks,
Nish

-- 
Nishanth Aravamudan <nacc@us.ibm.com>
IBM Linux Technology Center

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>