From: David Rientjes <rientjes@google.com>
To: Luiz Capitulino <lcapitulino@redhat.com>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
akpm@linux-foundation.org, mtosatti@redhat.com, mgorman@suse.de,
aarcange@redhat.com, andi@firstfloor.org, riel@redhat.com,
davidlohr@hp.com, isimatu.yasuaki@jp.fujitsu.com,
yinghai@kernel.org
Subject: Re: [PATCH 4/4] hugetlb: add hugepages_node= command-line option
Date: Fri, 14 Feb 2014 15:14:22 -0800 (PST) [thread overview]
Message-ID: <alpine.DEB.2.02.1402141511200.13935@chino.kir.corp.google.com> (raw)
In-Reply-To: <1392339728-13487-5-git-send-email-lcapitulino@redhat.com>
On Thu, 13 Feb 2014, Luiz Capitulino wrote:
> From: Luiz capitulino <lcapitulino@redhat.com>
>
> The HugeTLB command-line option hugepages= allows a user to specify how
> many huge pages should be allocated at boot. This option is needed because
> it improves reliability when allocating 1G huge pages, which are better
> allocated as early as possible due to fragmentation.
>
> However, hugepages= has a limitation. On NUMA systems, hugepages= will
> automatically distribute memory allocation equally among nodes. For
> example, if you have a 2-node NUMA system and allocate 200 huge pages,
> than hugepages= will try to allocate 100 huge pages from node0 and 100
> from node1.
>
> This is very unflexible, as it doesn't allow you to specify which nodes
> the huge pages should be allocated from. For example, there are use-cases
> where the user wants to specify that a 1GB huge page should be allocated
> from node 2 or that 300 2MB huge pages should be allocated from node 0.
>
> The hugepages_node= command-line option introduced by this commit allows
> just that.
>
> The syntax is:
>
> hugepages_node=nid:nr_pages:size,...
>
Again, I think this syntax is horrendous and doesn't couple well with the
other hugepage-related kernel command line options. We already have
hugepages= and hugepagesz= which you can interleave on the command line to
get 100 2M hugepages and 10 1GB hugepages, for example.
This patchset is simply introducing another variable to the matter: the
node that the hugepages should be allocated on. So just introduce a
hugepagesnode= parameter to couple with the others so you can do
hugepagesz=<size> hugepagesnode=<nid> hugepages=<#>
instead of having completely confusing interfaces where you want to do
hugepages_node=1:1:1G for a 1GB hugepage on page 1 (and try remembering
which "1" means what, yuck) and "hugepagesz=1GB hugepages=1" if you're
indifferent to the node.
--
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>
next prev parent reply other threads:[~2014-02-14 23:14 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-02-14 1:02 [PATCH v2 0/4] " Luiz Capitulino
2014-02-14 1:02 ` [PATCH 1/4] memblock: memblock_virt_alloc_internal(): add __GFP_THISNODE flag support Luiz Capitulino
2014-02-14 1:02 ` [PATCH 2/4] memblock: add memblock_virt_alloc_nid_nopanic() Luiz Capitulino
2014-02-14 1:02 ` [PATCH 3/4] hugetlb: add parse_pagesize_str() Luiz Capitulino
2014-02-14 1:02 ` [PATCH 4/4] hugetlb: add hugepages_node= command-line option Luiz Capitulino
2014-02-14 23:14 ` David Rientjes [this message]
2014-02-15 3:58 ` Luiz Capitulino
2014-02-15 10:06 ` David Rientjes
2014-02-17 13:56 ` Luiz Capitulino
2014-02-17 23:23 ` David Rientjes
2014-02-18 12:30 ` Marcelo Tosatti
2014-02-18 22:16 ` David Rientjes
2014-02-20 2:22 ` Marcelo Tosatti
2014-02-20 3:46 ` David Rientjes
2014-02-20 4:42 ` Luiz Capitulino
2014-02-20 4:51 ` David Rientjes
2014-02-20 15:06 ` Luiz Capitulino
2014-02-20 21:34 ` Marcelo Tosatti
2014-02-20 23:15 ` David Rientjes
2014-02-21 2:28 ` Marcelo Tosatti
2014-02-21 10:07 ` David Rientjes
2014-02-21 19:10 ` Marcelo Tosatti
2014-02-21 22:04 ` David Rientjes
2014-02-21 22:36 ` Andi Kleen
2014-02-21 22:44 ` David Rientjes
2014-02-21 22:55 ` Andi Kleen
2014-02-21 3:35 ` Luiz Capitulino
2014-02-20 21:38 ` Marcelo Tosatti
2014-02-20 23:17 ` David Rientjes
2014-02-18 5:47 ` Davidlohr Bueso
2014-02-21 23:54 ` Andrew Morton
2014-02-22 4:03 ` Andi Kleen
2014-02-22 4:31 ` Davidlohr Bueso
2014-02-22 4:40 ` Andrew Morton
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=alpine.DEB.2.02.1402141511200.13935@chino.kir.corp.google.com \
--to=rientjes@google.com \
--cc=aarcange@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=andi@firstfloor.org \
--cc=davidlohr@hp.com \
--cc=isimatu.yasuaki@jp.fujitsu.com \
--cc=lcapitulino@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
--cc=mtosatti@redhat.com \
--cc=riel@redhat.com \
--cc=yinghai@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox