linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Oliver O'Halloran" <oohall@gmail.com>
To: Christoph Hellwig <hch@infradead.org>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>,
	Dan Williams <dan.j.williams@intel.com>,
	Xiao Guangrong <guangrong.xiao@linux.intel.com>,
	Dave Hansen <dave.hansen@intel.com>,
	Paolo Bonzini <pbonzini@redhat.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Michal Hocko <mhocko@suse.com>, Gleb Natapov <gleb@kernel.org>,
	mtosatti@redhat.com, KVM list <kvm@vger.kernel.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	Stefan Hajnoczi <stefanha@redhat.com>,
	Yumei Huang <yuhuang@redhat.com>, Linux MM <linux-mm@kvack.org>,
	"linux-nvdimm@lists.01.org" <linux-nvdimm@ml01.01.org>,
	linux-fsdevel <linux-fsdevel@vger.kernel.org>
Subject: Re: DAX mapping detection (was: Re: [PATCH] Fix region lost in /proc/self/smaps)
Date: Mon, 12 Sep 2016 17:25:15 +1000	[thread overview]
Message-ID: <CAOSf1CHaW=szD+YEjV6vcUG0KKr=aXv8RXomw9xAgknh_9NBFQ@mail.gmail.com> (raw)
In-Reply-To: <20160912052703.GA1897@infradead.org>

On Mon, Sep 12, 2016 at 3:27 PM, Christoph Hellwig <hch@infradead.org> wrote:
> On Thu, Sep 08, 2016 at 04:56:36PM -0600, Ross Zwisler wrote:
>> I think this goes back to our previous discussion about support for the PMEM
>> programming model.  Really I think what NVML needs isn't a way to tell if it
>> is getting a DAX mapping, but whether it is getting a DAX mapping on a
>> filesystem that fully supports the PMEM programming model.  This of course is
>> defined to be a filesystem where it can do all of its flushes from userspace
>> safely and never call fsync/msync, and that allocations that happen in page
>> faults will be synchronized to media before the page fault completes.
>
> That's a an easy way to flag:  you will never get that from a Linux
> filesystem, period.
>
> NVML folks really need to stop taking crack and dreaming this could
> happen.

Well, that's a bummer.

What are the problems here? Is this a matter of existing filesystems
being unable/unwilling to support this or is it just fundamentally
broken? The end goal is to let applications manage the persistence of
their own data without having to involve the kernel in every IOP, but
if we can't do that then what would a 90% solution look like? I think
most people would be OK with having to do an fsync() occasionally, but
not after ever write to pmem.

  reply	other threads:[~2016-09-12  7:25 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-09-08  4:32 DAX mapping detection (was: Re: [PATCH] Fix region lost in /proc/self/smaps) Dan Williams
2016-09-08 22:56 ` Ross Zwisler
2016-09-08 23:04   ` Dan Williams
2016-09-09  8:55     ` Xiao Guangrong
2016-09-09 15:40       ` Dan Williams
2016-09-12  6:00         ` Xiao Guangrong
2016-09-12  3:44       ` Rudoff, Andy
2016-09-12  6:31         ` Xiao Guangrong
2016-09-12  1:40   ` Dave Chinner
2016-09-15  5:55     ` Darrick J. Wong
2016-09-15  6:25       ` Dave Chinner
2016-09-12  5:27   ` Christoph Hellwig
2016-09-12  7:25     ` Oliver O'Halloran [this message]
2016-09-12  7:51       ` Christoph Hellwig
2016-09-12  8:05         ` Nicholas Piggin
2016-09-12 15:01           ` Christoph Hellwig
2016-09-13  1:31             ` Nicholas Piggin
2016-09-13  4:06               ` Dan Williams
2016-09-13  5:40                 ` Nicholas Piggin
2016-09-12 21:34           ` Dave Chinner
2016-09-13  1:53             ` Nicholas Piggin
2016-09-13  7:17               ` Christoph Hellwig
2016-09-13  9:06                 ` Nicholas Piggin
2016-09-14  7:39               ` Dave Chinner
2016-09-14 10:19                 ` Nicholas Piggin
2016-09-15  2:31                   ` Dave Chinner
2016-09-15  3:49                     ` Nicholas Piggin
2016-09-15 10:32                       ` Dave Chinner
2016-09-15 11:42                         ` Nicholas Piggin
2016-09-15 22:33                           ` Dave Chinner
2016-09-16  5:54                             ` Nicholas Piggin
2016-12-19 21:11                               ` Ross Zwisler
2016-12-20  1:09                                 ` Darrick J. Wong
2016-12-20  1:18                                   ` Dan Williams
2016-12-21  0:40                                     ` Darrick J. Wong
2016-12-21 16:53                                       ` Dan Williams
2016-12-21 21:24                                         ` Dave Chinner
2016-12-21 21:33                                           ` Dan Williams

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='CAOSf1CHaW=szD+YEjV6vcUG0KKr=aXv8RXomw9xAgknh_9NBFQ@mail.gmail.com' \
    --to=oohall@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=dan.j.williams@intel.com \
    --cc=dave.hansen@intel.com \
    --cc=gleb@kernel.org \
    --cc=guangrong.xiao@linux.intel.com \
    --cc=hch@infradead.org \
    --cc=kvm@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-nvdimm@ml01.01.org \
    --cc=mhocko@suse.com \
    --cc=mtosatti@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=ross.zwisler@linux.intel.com \
    --cc=stefanha@redhat.com \
    --cc=yuhuang@redhat.com \
    /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;
as well as URLs for NNTP newsgroup(s).