From: Luiz Capitulino <lcapitulino@redhat.com>
To: David Rientjes <rientjes@google.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>,
Andrew Morton <akpm@linux-foundation.org>,
Mel Gorman <mgorman@suse.de>,
Andrea Arcangeli <aarcange@redhat.com>,
Andi Kleen <andi@firstfloor.org>, Rik van Riel <riel@redhat.com>,
davidlohr@hp.com, isimatu.yasuaki@jp.fujitsu.com,
yinghai@kernel.org, linux-kernel@vger.kernel.org,
linux-mm@kvack.org
Subject: Re: [PATCH 4/4] hugetlb: add hugepages_node= command-line option
Date: Thu, 20 Feb 2014 10:06:03 -0500 [thread overview]
Message-ID: <20140220100603.76622b33@redhat.com> (raw)
In-Reply-To: <alpine.DEB.2.02.1402192048240.2568@chino.kir.corp.google.com>
On Wed, 19 Feb 2014 20:51:55 -0800 (PST)
David Rientjes <rientjes@google.com> wrote:
> On Wed, 19 Feb 2014, Luiz Capitulino wrote:
>
> > > Yes, my concrete objection is that the command line interface is
> > > unnecessary if you can dynamically allocate and free 1GB pages at runtime
> > > unless memory will be so fragmented that it cannot be done when userspace
> > > is brought up. That is not your use case, thus this support is not
> >
> > Yes it is. The early boot is the most reliable moment to allocate huge pages
> > and we want to take advantage from that.
> >
>
> Your use case is 8GB of hugepages on a 32GB machine. It shouldn't be
> necessary to do that at boot.
That's shortsighted because it's tied to a particular machine. The same
customer asked for more flexibility, too.
Look, we're also looking forward to allocating 1G huge pages from user-space.
We actually agree here. What we're suggesting is having _both_, the
command-line option (which offers higher reliability and is a low hanging
fruit right now) _and_ later we add support to allocate 1G huge pages from
user-space. No loss here, that's the maximum benefit for all users.
--
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>
WARNING: multiple messages have this Message-ID (diff)
From: Luiz Capitulino <lcapitulino@redhat.com>
To: David Rientjes <rientjes@google.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>,
Andrew Morton <akpm@linux-foundation.org>,
Mel Gorman <mgorman@suse.de>,
Andrea Arcangeli <aarcange@redhat.com>,
Andi Kleen <andi@firstfloor.org>, Rik van Riel <riel@redhat.com>,
davidlohr@hp.com, isimatu.yasuaki@jp.fujitsu.com,
yinghai@kernel.org, linux-kernel@vger.kernel.org,
linux-mm@kvack.org
Subject: Re: [PATCH 4/4] hugetlb: add hugepages_node= command-line option
Date: Thu, 20 Feb 2014 10:06:03 -0500 [thread overview]
Message-ID: <20140220100603.76622b33@redhat.com> (raw)
In-Reply-To: <alpine.DEB.2.02.1402192048240.2568@chino.kir.corp.google.com>
On Wed, 19 Feb 2014 20:51:55 -0800 (PST)
David Rientjes <rientjes@google.com> wrote:
> On Wed, 19 Feb 2014, Luiz Capitulino wrote:
>
> > > Yes, my concrete objection is that the command line interface is
> > > unnecessary if you can dynamically allocate and free 1GB pages at runtime
> > > unless memory will be so fragmented that it cannot be done when userspace
> > > is brought up. That is not your use case, thus this support is not
> >
> > Yes it is. The early boot is the most reliable moment to allocate huge pages
> > and we want to take advantage from that.
> >
>
> Your use case is 8GB of hugepages on a 32GB machine. It shouldn't be
> necessary to do that at boot.
That's shortsighted because it's tied to a particular machine. The same
customer asked for more flexibility, too.
Look, we're also looking forward to allocating 1G huge pages from user-space.
We actually agree here. What we're suggesting is having _both_, the
command-line option (which offers higher reliability and is a low hanging
fruit right now) _and_ later we add support to allocate 1G huge pages from
user-space. No loss here, that's the maximum benefit for all users.
next prev parent reply other threads:[~2014-02-20 16:08 UTC|newest]
Thread overview: 68+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-02-14 1:02 [PATCH v2 0/4] hugetlb: add hugepages_node= command-line option Luiz Capitulino
2014-02-14 1:02 ` 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 ` Luiz Capitulino
2014-02-14 1:02 ` [PATCH 2/4] memblock: add memblock_virt_alloc_nid_nopanic() Luiz Capitulino
2014-02-14 1:02 ` Luiz Capitulino
2014-02-14 1:02 ` [PATCH 3/4] hugetlb: add parse_pagesize_str() Luiz Capitulino
2014-02-14 1:02 ` Luiz Capitulino
2014-02-14 1:02 ` [PATCH 4/4] hugetlb: add hugepages_node= command-line option Luiz Capitulino
2014-02-14 1:02 ` Luiz Capitulino
2014-02-14 23:14 ` David Rientjes
2014-02-14 23:14 ` David Rientjes
2014-02-15 3:58 ` Luiz Capitulino
2014-02-15 3:58 ` Luiz Capitulino
2014-02-15 10:06 ` David Rientjes
2014-02-15 10:06 ` David Rientjes
2014-02-17 13:56 ` Luiz Capitulino
2014-02-17 13:56 ` Luiz Capitulino
2014-02-17 23:23 ` David Rientjes
2014-02-17 23:23 ` David Rientjes
2014-02-18 12:30 ` Marcelo Tosatti
2014-02-18 12:30 ` Marcelo Tosatti
2014-02-18 22:16 ` David Rientjes
2014-02-18 22:16 ` David Rientjes
2014-02-20 2:22 ` Marcelo Tosatti
2014-02-20 2:22 ` Marcelo Tosatti
2014-02-20 3:46 ` David Rientjes
2014-02-20 3:46 ` David Rientjes
2014-02-20 4:42 ` Luiz Capitulino
2014-02-20 4:42 ` Luiz Capitulino
2014-02-20 4:51 ` David Rientjes
2014-02-20 4:51 ` David Rientjes
2014-02-20 15:06 ` Luiz Capitulino [this message]
2014-02-20 15:06 ` Luiz Capitulino
2014-02-20 21:34 ` Marcelo Tosatti
2014-02-20 21:34 ` Marcelo Tosatti
2014-02-20 23:15 ` David Rientjes
2014-02-20 23:15 ` David Rientjes
2014-02-21 2:28 ` Marcelo Tosatti
2014-02-21 2:28 ` Marcelo Tosatti
2014-02-21 10:07 ` David Rientjes
2014-02-21 10:07 ` David Rientjes
2014-02-21 19:10 ` Marcelo Tosatti
2014-02-21 19:10 ` Marcelo Tosatti
2014-02-21 22:04 ` David Rientjes
2014-02-21 22:04 ` David Rientjes
2014-02-21 22:36 ` Andi Kleen
2014-02-21 22:36 ` Andi Kleen
2014-02-21 22:44 ` David Rientjes
2014-02-21 22:44 ` David Rientjes
2014-02-21 22:55 ` Andi Kleen
2014-02-21 22:55 ` Andi Kleen
2014-02-21 3:35 ` Luiz Capitulino
2014-02-21 3:35 ` Luiz Capitulino
2014-02-20 21:38 ` Marcelo Tosatti
2014-02-20 21:38 ` Marcelo Tosatti
2014-02-20 23:17 ` David Rientjes
2014-02-20 23:17 ` David Rientjes
2014-02-18 5:47 ` Davidlohr Bueso
2014-02-18 5:47 ` Davidlohr Bueso
2014-02-21 23:54 ` Andrew Morton
2014-02-21 23:54 ` Andrew Morton
2014-02-22 4:03 ` Andi Kleen
2014-02-22 4:03 ` Andi Kleen
2014-02-22 4:31 ` Davidlohr Bueso
2014-02-22 4:31 ` Davidlohr Bueso
2014-02-22 4:40 ` Andrew Morton
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=20140220100603.76622b33@redhat.com \
--to=lcapitulino@redhat.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=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
--cc=mtosatti@redhat.com \
--cc=riel@redhat.com \
--cc=rientjes@google.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.