All of lore.kernel.org
 help / color / mirror / Atom feed
From: Christoph Hellwig <hch@lst.de>
To: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Cc: Dan Williams <dan.j.williams@intel.com>,
	Christoph Hellwig <hch@lst.de>,
	"linux-nvdimm@lists.01.org" <linux-nvdimm@lists.01.org>,
	linux-xfs@vger.kernel.org, Jan Kara <jack@suse.cz>,
	Arnd Bergmann <arnd@arndb.de>,
	"Darrick J. Wong" <darrick.wong@oracle.com>,
	Linux API <linux-api@vger.kernel.org>,
	Dave Chinner <david@fromorbit.com>,
	"J. Bruce Fields" <bfields@fieldses.org>,
	Linux MM <linux-mm@kvack.org>, Jeff Moyer <jmoyer@redhat.com>,
	Al Viro <viro@zeniv.linux.org.uk>,
	Andy Lutomirski <luto@kernel.org>,
	Ross Zwisler <ross.zwisler@linux.intel.com>,
	linux-fsdevel <linux-fsdevel@vger.kernel.org>,
	Jeff Layton <jlayton@poochiereds.net>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Andrew Morton <akpm@linux-foundation.org>
Subject: Re: [PATCH v9 0/6] MAP_DIRECT for DAX userspace flush
Date: Mon, 16 Oct 2017 09:26:44 +0200	[thread overview]
Message-ID: <20171016072644.GB28270@lst.de> (raw)
In-Reply-To: <20171013173145.GA18702@obsidianresearch.com>

On Fri, Oct 13, 2017 at 11:31:45AM -0600, Jason Gunthorpe wrote:
> I don't think that really represents how lots of apps actually use
> RDMA.
> 
> RDMA is often buried down in the software stack (eg in a MPI), and by
> the time a mapping gets used for RDMA transfer the link between the
> FD, mmap and the MR is totally opaque.
> 
> Having a MR specific notification means the low level RDMA libraries
> have a chance to deal with everything for the app.
> 
> Eg consider a HPC app using MPI that uses some DAX aware library to
> get DAX backed mmap's. It then passes memory in those mmaps to the
> MPI library to do transfers. The MPI creates the MR on demand.
> 

I suspect one of the more interesting use cases might be a file server,
for which that's not the case.  But otherwise I agree with the above,
and also thing that notifying the MR handle is the only way to go for
another very important reason:  fencing.  What if the application/library
does not react on the notification?  With a per-MR notification we
can unregister the MR in kernel space and have a rock solid fencing
mechanism.  And that is the most important bit here.

--
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: Christoph Hellwig <hch@lst.de>
To: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Cc: Dan Williams <dan.j.williams@intel.com>,
	Christoph Hellwig <hch@lst.de>,
	"linux-nvdimm@lists.01.org" <linux-nvdimm@lists.01.org>,
	linux-xfs@vger.kernel.org, Jan Kara <jack@suse.cz>,
	Arnd Bergmann <arnd@arndb.de>,
	"Darrick J. Wong" <darrick.wong@oracle.com>,
	Linux API <linux-api@vger.kernel.org>,
	Dave Chinner <david@fromorbit.com>,
	"J. Bruce Fields" <bfields@fieldses.org>,
	Linux MM <linux-mm@kvack.org>, Jeff Moyer <jmoyer@redhat.com>,
	Al Viro <viro@zeniv.linux.org.uk>,
	Andy Lutomirski <luto@kernel.org>,
	Ross Zwisler <ross.zwisler@linux.intel.com>,
	linux-fsdevel <linux-fsdevel@vger.kernel.org>,
	Jeff Layton <jlayton@poochiereds.net>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Andrew Morton <akpm@linux-foundation.org>
Subject: Re: [PATCH v9 0/6] MAP_DIRECT for DAX userspace flush
Date: Mon, 16 Oct 2017 09:26:44 +0200	[thread overview]
Message-ID: <20171016072644.GB28270@lst.de> (raw)
In-Reply-To: <20171013173145.GA18702@obsidianresearch.com>

On Fri, Oct 13, 2017 at 11:31:45AM -0600, Jason Gunthorpe wrote:
> I don't think that really represents how lots of apps actually use
> RDMA.
> 
> RDMA is often buried down in the software stack (eg in a MPI), and by
> the time a mapping gets used for RDMA transfer the link between the
> FD, mmap and the MR is totally opaque.
> 
> Having a MR specific notification means the low level RDMA libraries
> have a chance to deal with everything for the app.
> 
> Eg consider a HPC app using MPI that uses some DAX aware library to
> get DAX backed mmap's. It then passes memory in those mmaps to the
> MPI library to do transfers. The MPI creates the MR on demand.
> 

I suspect one of the more interesting use cases might be a file server,
for which that's not the case.  But otherwise I agree with the above,
and also thing that notifying the MR handle is the only way to go for
another very important reason:  fencing.  What if the application/library
does not react on the notification?  With a per-MR notification we
can unregister the MR in kernel space and have a rock solid fencing
mechanism.  And that is the most important bit here.

WARNING: multiple messages have this Message-ID (diff)
From: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
To: Jason Gunthorpe
	<jgunthorpe-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
Cc: Dan Williams
	<dan.j.williams-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>,
	Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>,
	"linux-nvdimm-hn68Rpc1hR1g9hUCZPvPmw@public.gmane.org"
	<linux-nvdimm-hn68Rpc1hR1g9hUCZPvPmw@public.gmane.org>,
	linux-xfs-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
	Jan Kara <jack-AlSwsSmVLrQ@public.gmane.org>,
	Arnd Bergmann <arnd-r2nGTMty4D4@public.gmane.org>,
	"Darrick J. Wong"
	<darrick.wong-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>,
	Linux API <linux-api-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
	Dave Chinner <david-FqsqvQoI3Ljby3iVrkZq2A@public.gmane.org>,
	"J. Bruce Fields"
	<bfields-uC3wQj2KruNg9hUCZPvPmw@public.gmane.org>,
	Linux MM <linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org>,
	Jeff Moyer <jmoyer-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>,
	Al Viro <viro-RmSDqhL/yNMiFSDQTTA3OLVCufUGDwFn@public.gmane.org>,
	Andy Lutomirski <luto-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>,
	Ross Zwisler
	<ross.zwisler-VuQAYsv1563Yd54FQh9/CA@public.gmane.org>,
	linux-fsdevel
	<linux-fsdevel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
	Jeff Layton <jlayton-vpEMnDpepFuMZCB2o+C8xQ@public.gmane.org>,
	Linus Torvalds
	<torvalds-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>,
	Andrew Morton
	<akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>
Subject: Re: [PATCH v9 0/6] MAP_DIRECT for DAX userspace flush
Date: Mon, 16 Oct 2017 09:26:44 +0200	[thread overview]
Message-ID: <20171016072644.GB28270@lst.de> (raw)
In-Reply-To: <20171013173145.GA18702-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>

On Fri, Oct 13, 2017 at 11:31:45AM -0600, Jason Gunthorpe wrote:
> I don't think that really represents how lots of apps actually use
> RDMA.
> 
> RDMA is often buried down in the software stack (eg in a MPI), and by
> the time a mapping gets used for RDMA transfer the link between the
> FD, mmap and the MR is totally opaque.
> 
> Having a MR specific notification means the low level RDMA libraries
> have a chance to deal with everything for the app.
> 
> Eg consider a HPC app using MPI that uses some DAX aware library to
> get DAX backed mmap's. It then passes memory in those mmaps to the
> MPI library to do transfers. The MPI creates the MR on demand.
> 

I suspect one of the more interesting use cases might be a file server,
for which that's not the case.  But otherwise I agree with the above,
and also thing that notifying the MR handle is the only way to go for
another very important reason:  fencing.  What if the application/library
does not react on the notification?  With a per-MR notification we
can unregister the MR in kernel space and have a rock solid fencing
mechanism.  And that is the most important bit here.

  parent reply	other threads:[~2017-10-16  7:26 UTC|newest]

Thread overview: 116+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-10-12  0:47 [PATCH v9 0/6] MAP_DIRECT for DAX userspace flush Dan Williams
2017-10-12  0:47 ` Dan Williams
2017-10-12  0:47 ` Dan Williams
2017-10-12  0:47 ` [PATCH v9 1/6] mm: introduce MAP_SHARED_VALIDATE, a mechanism to safely define new mmap flags Dan Williams
2017-10-12  0:47   ` Dan Williams
2017-10-12  0:47   ` Dan Williams
2017-10-12  0:47   ` Dan Williams
2017-10-12 13:51   ` Jan Kara
2017-10-12 13:51     ` Jan Kara
2017-10-12 13:51     ` Jan Kara
2017-10-12 13:51     ` Jan Kara
2017-10-12 16:32     ` Linus Torvalds
2017-10-12 16:32       ` Linus Torvalds
2017-10-12 16:32       ` Linus Torvalds
2017-10-16  7:38       ` Christoph Hellwig
2017-10-16  7:38         ` Christoph Hellwig
2017-10-16  7:38         ` Christoph Hellwig
2017-10-16  7:56       ` Jan Kara
2017-10-16  7:56         ` Jan Kara
2017-10-16  7:56         ` Jan Kara
2017-10-12  0:47 ` [PATCH v9 2/6] fs, mm: pass fd to ->mmap_validate() Dan Williams
2017-10-12  0:47   ` Dan Williams
2017-10-12  0:47   ` Dan Williams
2017-10-12  1:21   ` Al Viro
2017-10-12  1:21     ` Al Viro
2017-10-12  1:21     ` Al Viro
2017-10-12  1:21     ` Al Viro
2017-10-12  1:28     ` Dan Williams
2017-10-12  1:28       ` Dan Williams
2017-10-12  1:28       ` Dan Williams
2017-10-12  1:28       ` Dan Williams
2017-10-12  2:17       ` Dan Williams
2017-10-12  2:17         ` Dan Williams
2017-10-12  2:17         ` Dan Williams
2017-10-12  2:17         ` Dan Williams
2017-10-12  3:44         ` Dan Williams
2017-10-12  3:44           ` Dan Williams
2017-10-12  3:44           ` Dan Williams
2017-10-12  3:44           ` Dan Williams
2017-10-12  0:47 ` [PATCH v9 3/6] fs: MAP_DIRECT core Dan Williams
2017-10-12  0:47   ` Dan Williams
2017-10-12  0:47   ` Dan Williams
2017-10-12  0:47   ` Dan Williams
2017-10-12  0:47 ` [PATCH v9 4/6] xfs: prepare xfs_break_layouts() for reuse with MAP_DIRECT Dan Williams
2017-10-12  0:47   ` Dan Williams
2017-10-12  0:47   ` Dan Williams
2017-10-12  0:47   ` Dan Williams
2017-10-12  0:47 ` [PATCH v9 5/6] fs, xfs, iomap: introduce break_layout_nowait() Dan Williams
2017-10-12  0:47   ` Dan Williams
2017-10-12  0:47   ` Dan Williams
2017-10-12  0:47   ` Dan Williams
2017-10-12  0:47 ` [PATCH v9 6/6] xfs: wire up MAP_DIRECT Dan Williams
2017-10-12  0:47   ` Dan Williams
2017-10-12  0:47   ` Dan Williams
2017-10-12  0:47   ` Dan Williams
2017-10-12 14:23 ` [PATCH v9 0/6] MAP_DIRECT for DAX userspace flush Christoph Hellwig
2017-10-12 14:23   ` Christoph Hellwig
2017-10-12 14:23   ` Christoph Hellwig
2017-10-12 17:41   ` Dan Williams
2017-10-12 17:41     ` Dan Williams
2017-10-12 17:41     ` Dan Williams
2017-10-13  6:57     ` Christoph Hellwig
2017-10-13  6:57       ` Christoph Hellwig
2017-10-13  6:57       ` Christoph Hellwig
2017-10-13 15:14       ` Dan Williams
2017-10-13 15:14         ` Dan Williams
2017-10-13 15:14         ` Dan Williams
2017-10-13 16:38         ` Jason Gunthorpe
2017-10-13 16:38           ` Jason Gunthorpe
2017-10-13 16:38           ` Jason Gunthorpe
2017-10-13 16:38           ` Jason Gunthorpe
2017-10-13 17:01           ` Dan Williams
2017-10-13 17:01             ` Dan Williams
2017-10-13 17:01             ` Dan Williams
2017-10-13 17:01             ` Dan Williams
2017-10-13 17:31             ` Jason Gunthorpe
2017-10-13 17:31               ` Jason Gunthorpe
2017-10-13 17:31               ` Jason Gunthorpe
2017-10-13 17:31               ` Jason Gunthorpe
2017-10-13 18:22               ` Dan Williams
2017-10-13 18:22                 ` Dan Williams
2017-10-13 18:22                 ` Dan Williams
2017-10-13 18:22                 ` Dan Williams
2017-10-14  1:57                 ` Jason Gunthorpe
2017-10-14  1:57                   ` Jason Gunthorpe
2017-10-14  1:57                   ` Jason Gunthorpe
2017-10-14  1:57                   ` Jason Gunthorpe
2017-10-16 12:02                   ` Sagi Grimberg
2017-10-16 12:02                     ` Sagi Grimberg
2017-10-19  6:02                     ` Jason Gunthorpe
2017-10-19  6:02                       ` Jason Gunthorpe
2017-10-19  6:02                       ` Jason Gunthorpe
2017-10-19  6:02                       ` Jason Gunthorpe
2017-10-16  7:30                 ` Christoph Hellwig
2017-10-16  7:30                   ` Christoph Hellwig
2017-10-16  7:30                   ` Christoph Hellwig
2017-10-16  7:26               ` Christoph Hellwig [this message]
2017-10-16  7:26                 ` Christoph Hellwig
2017-10-16  7:26                 ` Christoph Hellwig
2017-10-16 12:07                 ` Sagi Grimberg
2017-10-16 12:07                   ` Sagi Grimberg
2017-10-16 12:07                   ` Sagi Grimberg
2017-10-16 17:43                 ` Dan Williams
2017-10-16 17:43                   ` Dan Williams
2017-10-16 17:43                   ` Dan Williams
2017-10-16 19:44                   ` Dan Williams
2017-10-16 19:44                     ` Dan Williams
2017-10-16 19:44                     ` Dan Williams
2017-10-17  6:46                     ` Christoph Hellwig
2017-10-17  6:46                       ` Christoph Hellwig
2017-10-17  6:46                       ` Christoph Hellwig
2017-10-17  6:46                       ` Christoph Hellwig
2017-10-16  7:22           ` Christoph Hellwig
2017-10-16  7:22             ` Christoph Hellwig
2017-10-16  7:22             ` Christoph Hellwig
2017-10-16  7:22             ` Christoph Hellwig

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=20171016072644.GB28270@lst.de \
    --to=hch@lst.de \
    --cc=akpm@linux-foundation.org \
    --cc=arnd@arndb.de \
    --cc=bfields@fieldses.org \
    --cc=dan.j.williams@intel.com \
    --cc=darrick.wong@oracle.com \
    --cc=david@fromorbit.com \
    --cc=jack@suse.cz \
    --cc=jgunthorpe@obsidianresearch.com \
    --cc=jlayton@poochiereds.net \
    --cc=jmoyer@redhat.com \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-nvdimm@lists.01.org \
    --cc=linux-xfs@vger.kernel.org \
    --cc=luto@kernel.org \
    --cc=ross.zwisler@linux.intel.com \
    --cc=torvalds@linux-foundation.org \
    --cc=viro@zeniv.linux.org.uk \
    /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.