Re: [RFC][PATCH 1/2] hugetlb: present information in sysfs

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

On 29.05.2008 [19:58:46 -0700], Greg KH wrote:
> On Wed, May 28, 2008 at 11:39:15PM -0700, Nishanth Aravamudan wrote:
> > While the procfs presentation of the hstate counters has tried to be as
> > backwards compatible as possible, I do not believe trying to maintain
> > all of the information in the same files is a good long-term plan. This
> > particularly matters for architectures that can support many hugepage
> > sizes (sparc64 might be one). Even with the three potential pagesizes on
> > power (64k, 16m and 16g), I found the proc interface to be a little
> > awkward.
> > 
> > Instead, migrate the information to sysfs in a new directory,
> > /sys/kernel/hugepages. Underneath that directory there will be a
> > directory per-supported hugepage size, e.g.:
> > 
> > /sys/kernel/hugepages/hugepages-64
> > /sys/kernel/hugepages/hugepages-16384
> > /sys/kernel/hugepages/hugepages-16777216
> > 
> > corresponding to 64k, 16m and 16g respectively. Within each
> > hugepages-size directory there are a number of files, corresponding to
> > the tracked counters in the hstate, e.g.:
> > 
> > /sys/kernel/hugepages/hugepages-64/nr_hugepages
> > /sys/kernel/hugepages/hugepages-64/nr_overcommit_hugepages
> > /sys/kernel/hugepages/hugepages-64/free_hugepages
> > /sys/kernel/hugepages/hugepages-64/resv_hugepages
> > /sys/kernel/hugepages/hugepages-64/surplus_hugepages
> > 
> > Of these files, the first two are read-write and the latter three are
> > read-only. The size of the hugepage being manipulated is trivially
> > deducible from the enclosing directory and is always expressed in kB (to
> > match meminfo).
> > 
> > Signed-off-by: Nishanth Aravamudan <nacc@us.ibm.com>
> > 
> > ---
> > Nick, I tested this patch and the following one at this point the
> > series, that is between patches 7 and 8. This does require a few compile
> > fixes/patch modifications in the later parts of the series. If we decide
> > that 2/2 is undesirable, there will be fewer of those and 1/2 could also
> > apply at the end, with less work. I can send you that diff, if you'd
> > prefer.
> > 
> > Greg, I didn't hear back from you on the last posting of this patch. Not
> > intended as a complaint, just an indication of why I didn't make any
> > changes relative to that version. Does this seem like a reasonable
> > patch as far as using the sysfs API? I realize a follow-on patch will be
> > needed to updated Documentation/ABI.
> 
> I'm sorry, it got lost in the bowels of my inbox, my appologies.

No need to apologize, you get a lot more e-mail than I ever will :) I
appreciate all your help with this stuff as well as the excellent
examples in samples and the Documentation.

> This looks fine to me, nice job.  And yes, i do want to see the ABI
> addition as well :)
> 
> If you add that, feel free to add an:
> 	Acked-by: Greg Kroah-Hartman <gregkh@suse.de>
> to the patch.

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>