Re: [patch 05/23] hugetlb: multi hstate proc files

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

On 28.05.2008 [22:07:03 -0700], Nishanth Aravamudan wrote:
> On 26.05.2008 [00:23:22 +1000], npiggin@suse.de wrote:
> > Convert /proc output code over to report multiple hstates
> > 
> > I chose to just report the numbers in a row, in the hope 
> > to minimze breakage of existing software. The "compat" page size
> > is always the first number.
> 
> I'm assuming this is just copied from the old changelog, because as far
> as I can tell, and from my quick testing just now with my sysfs patch,
> hstates[0] is just whichever hugepage size is registered first. So that
> either means by "compat" you meant the default on the current system
> (which is only compatible with boots having the same order of boot-line
> parameters) or we need to fix this patch to put HPAGE_SIZE (which we
> haven't changed, per se) to be in hstates[0]. It might help to have a
> helper macro called default_hstate (or a comment) [which I thought we
> had in the beginnning of the patchset, but I see one of the intervening
> patches removed it] indicating which state is the default when none is
> specified.
> 
> The reason I bring this up is that I have my sysfs patchset in two
> parts. First, I add the sysfs interface and then I remove the
> multi-valued proc files. But for the latter, I rely on hstates[0] to be
> the one we want to be presenting in proc. If that's not the case, how
> should I be determining which hstate is the default? If that is the
> case, shall I make the reverting patch also put the "right" value in
> hstates[0]?

Oh, I think I know what is going on now. It's because I hadn't changed
my test script between the old version of the stack and this one so it
was still putting "hugepagesz=64k hugepagesz=16m hugepagesz=16g" on the
kernel command-line, thus making 64k (the first hugepagesz specified) be
the default for the system. So, actually, using hstates[0] in this way
does work. Running one more test set without specifying any hugepagesz
options on the kernel command-line to see the default layout in proc and
sys is sane.

However, this nuance definitely should be documented in
vm/hugetlbpage.txt / kernel-parameters.txt. Administrators who wish to
preallocate hugepages should be aware that the order in which they
specify the preallocation affects which hugepage size is the default
(presuming my interpretation of my results is correct).

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>