From: Rik van Riel <riel@redhat.com>
To: Dan Williams <dan.j.williams@intel.com>
Cc: Kevin Wolf <kwolf@redhat.com>, Pankaj Gupta <pagupta@redhat.com>,
Jan Kara <jack@suse.cz>,
xiaoguangrong eric <xiaoguangrong.eric@gmail.com>,
kvm-devel <kvm@vger.kernel.org>,
Stefan Hajnoczi <stefanha@gmail.com>,
Ross Zwisler <ross.zwisler@intel.com>,
Qemu Developers <qemu-devel@nongnu.org>,
Stefan Hajnoczi <stefanha@redhat.com>,
"linux-nvdimm@lists.01.org" <linux-nvdimm@ml01.01.org>,
Paolo Bonzini <pbonzini@redhat.com>,
Nitesh Narayan Lal <nilal@redhat.com>
Subject: Re: KVM "fake DAX" flushing interface - discussion
Date: Wed, 26 Jul 2017 19:46:27 -0400 [thread overview]
Message-ID: <1501112787.4073.49.camel@redhat.com> (raw)
In-Reply-To: <CAPcyv4hsqrqBxoipUHPAbSctuzbVWCRnT-gN08i9uhXTWY6iPQ@mail.gmail.com>
On Wed, 2017-07-26 at 14:40 -0700, Dan Williams wrote:
> On Wed, Jul 26, 2017 at 2:27 PM, Rik van Riel <riel@redhat.com>
> wrote:
> > On Wed, 2017-07-26 at 09:47 -0400, Pankaj Gupta wrote:
> > > >
> > >
> > > Just want to summarize here(high level):
> > >
> > > This will require implementing new 'virtio-pmem' device which
> > > presents
> > > a DAX address range(like pmem) to guest with read/write(direct
> > > access)
> > > & device flush functionality. Also, qemu should implement
> > > corresponding
> > > support for flush using virtio.
> > >
> >
> > Alternatively, the existing pmem code, with
> > a flush-only block device on the side, which
> > is somehow associated with the pmem device.
> >
> > I wonder which alternative leads to the least
> > code duplication, and the least maintenance
> > hassle going forward.
>
> I'd much prefer to have another driver. I.e. a driver that refactors
> out some common pmem details into a shared object and can attach to
> ND_DEVICE_NAMESPACE_{IO,PMEM}. A control device on the side seems
> like
> a recipe for confusion.
At that point, would it make sense to expose these special
virtio-pmem areas to the guest in a slightly different way,
so the regions that need virtio flushing are not bound by
the regular driver, and the regular driver can continue to
work for memory regions that are backed by actual pmem in
the host?
> With a $new_driver in hand you can just do:
>
> modprobe $new_driver
> echo $namespace > /sys/bus/nd/drivers/nd_pmem/unbind
> echo $namespace > /sys/bus/nd/drivers/$new_driver/new_id
> echo $namespace > /sys/bus/nd/drivers/$new_driver/bind
>
> ...and the guest can arrange for $new_driver to be the default, so
> you
> don't need to do those steps each boot of the VM, by doing:
>
> echo "blacklist nd_pmem" > /etc/modprobe.d/virt-dax-flush.conf
> echo "alias nd:t4* $new_driver" >> /etc/modprobe.d/virt-dax-
> flush.conf
> echo "alias nd:t5* $new_driver" >> /etc/modprobe.d/virt-dax-
> flush.conf
_______________________________________________
Linux-nvdimm mailing list
Linux-nvdimm@lists.01.org
https://lists.01.org/mailman/listinfo/linux-nvdimm
WARNING: multiple messages have this Message-ID (diff)
From: Rik van Riel <riel@redhat.com>
To: Dan Williams <dan.j.williams@intel.com>
Cc: Pankaj Gupta <pagupta@redhat.com>, Jan Kara <jack@suse.cz>,
Stefan Hajnoczi <stefanha@redhat.com>,
Stefan Hajnoczi <stefanha@gmail.com>,
kvm-devel <kvm@vger.kernel.org>,
Qemu Developers <qemu-devel@nongnu.org>,
"linux-nvdimm@lists.01.org" <linux-nvdimm@ml01.01.org>,
ross zwisler <ross.zwisler@linux.intel.com>,
Paolo Bonzini <pbonzini@redhat.com>,
Kevin Wolf <kwolf@redhat.com>,
Nitesh Narayan Lal <nilal@redhat.com>,
xiaoguangrong eric <xiaoguangrong.eric@gmail.com>,
Haozhong Zhang <haozhong.zhang@intel.com>,
Ross Zwisler <ross.zwisler@intel.com>
Subject: Re: KVM "fake DAX" flushing interface - discussion
Date: Wed, 26 Jul 2017 19:46:27 -0400 [thread overview]
Message-ID: <1501112787.4073.49.camel@redhat.com> (raw)
In-Reply-To: <CAPcyv4hsqrqBxoipUHPAbSctuzbVWCRnT-gN08i9uhXTWY6iPQ@mail.gmail.com>
On Wed, 2017-07-26 at 14:40 -0700, Dan Williams wrote:
> On Wed, Jul 26, 2017 at 2:27 PM, Rik van Riel <riel@redhat.com>
> wrote:
> > On Wed, 2017-07-26 at 09:47 -0400, Pankaj Gupta wrote:
> > > >
> > >
> > > Just want to summarize here(high level):
> > >
> > > This will require implementing new 'virtio-pmem' device which
> > > presents
> > > a DAX address range(like pmem) to guest with read/write(direct
> > > access)
> > > & device flush functionality. Also, qemu should implement
> > > corresponding
> > > support for flush using virtio.
> > >
> >
> > Alternatively, the existing pmem code, with
> > a flush-only block device on the side, which
> > is somehow associated with the pmem device.
> >
> > I wonder which alternative leads to the least
> > code duplication, and the least maintenance
> > hassle going forward.
>
> I'd much prefer to have another driver. I.e. a driver that refactors
> out some common pmem details into a shared object and can attach to
> ND_DEVICE_NAMESPACE_{IO,PMEM}. A control device on the side seems
> like
> a recipe for confusion.
At that point, would it make sense to expose these special
virtio-pmem areas to the guest in a slightly different way,
so the regions that need virtio flushing are not bound by
the regular driver, and the regular driver can continue to
work for memory regions that are backed by actual pmem in
the host?
> With a $new_driver in hand you can just do:
>
> modprobe $new_driver
> echo $namespace > /sys/bus/nd/drivers/nd_pmem/unbind
> echo $namespace > /sys/bus/nd/drivers/$new_driver/new_id
> echo $namespace > /sys/bus/nd/drivers/$new_driver/bind
>
> ...and the guest can arrange for $new_driver to be the default, so
> you
> don't need to do those steps each boot of the VM, by doing:
>
> echo "blacklist nd_pmem" > /etc/modprobe.d/virt-dax-flush.conf
> echo "alias nd:t4* $new_driver" >> /etc/modprobe.d/virt-dax-
> flush.conf
> echo "alias nd:t5* $new_driver" >> /etc/modprobe.d/virt-dax-
> flush.conf
WARNING: multiple messages have this Message-ID (diff)
From: Rik van Riel <riel@redhat.com>
To: Dan Williams <dan.j.williams@intel.com>
Cc: Pankaj Gupta <pagupta@redhat.com>, Jan Kara <jack@suse.cz>,
Stefan Hajnoczi <stefanha@redhat.com>,
Stefan Hajnoczi <stefanha@gmail.com>,
kvm-devel <kvm@vger.kernel.org>,
Qemu Developers <qemu-devel@nongnu.org>,
"linux-nvdimm@lists.01.org" <linux-nvdimm@ml01.01.org>,
ross zwisler <ross.zwisler@linux.intel.com>,
Paolo Bonzini <pbonzini@redhat.com>,
Kevin Wolf <kwolf@redhat.com>,
Nitesh Narayan Lal <nilal@redhat.com>,
xiaoguangrong eric <xiaoguangrong.eric@gmail.com>,
Haozhong Zhang <haozhong.zhang@intel.com>,
Ross Zwisler <ross.zwisler@intel.com>
Subject: Re: [Qemu-devel] KVM "fake DAX" flushing interface - discussion
Date: Wed, 26 Jul 2017 19:46:27 -0400 [thread overview]
Message-ID: <1501112787.4073.49.camel@redhat.com> (raw)
In-Reply-To: <CAPcyv4hsqrqBxoipUHPAbSctuzbVWCRnT-gN08i9uhXTWY6iPQ@mail.gmail.com>
On Wed, 2017-07-26 at 14:40 -0700, Dan Williams wrote:
> On Wed, Jul 26, 2017 at 2:27 PM, Rik van Riel <riel@redhat.com>
> wrote:
> > On Wed, 2017-07-26 at 09:47 -0400, Pankaj Gupta wrote:
> > > >
> > >
> > > Just want to summarize here(high level):
> > >
> > > This will require implementing new 'virtio-pmem' device which
> > > presents
> > > a DAX address range(like pmem) to guest with read/write(direct
> > > access)
> > > & device flush functionality. Also, qemu should implement
> > > corresponding
> > > support for flush using virtio.
> > >
> >
> > Alternatively, the existing pmem code, with
> > a flush-only block device on the side, which
> > is somehow associated with the pmem device.
> >
> > I wonder which alternative leads to the least
> > code duplication, and the least maintenance
> > hassle going forward.
>
> I'd much prefer to have another driver. I.e. a driver that refactors
> out some common pmem details into a shared object and can attach to
> ND_DEVICE_NAMESPACE_{IO,PMEM}. A control device on the side seems
> like
> a recipe for confusion.
At that point, would it make sense to expose these special
virtio-pmem areas to the guest in a slightly different way,
so the regions that need virtio flushing are not bound by
the regular driver, and the regular driver can continue to
work for memory regions that are backed by actual pmem in
the host?
> With a $new_driver in hand you can just do:
>
> modprobe $new_driver
> echo $namespace > /sys/bus/nd/drivers/nd_pmem/unbind
> echo $namespace > /sys/bus/nd/drivers/$new_driver/new_id
> echo $namespace > /sys/bus/nd/drivers/$new_driver/bind
>
> ...and the guest can arrange for $new_driver to be the default, so
> you
> don't need to do those steps each boot of the VM, by doing:
>
> echo "blacklist nd_pmem" > /etc/modprobe.d/virt-dax-flush.conf
> echo "alias nd:t4* $new_driver" >> /etc/modprobe.d/virt-dax-
> flush.conf
> echo "alias nd:t5* $new_driver" >> /etc/modprobe.d/virt-dax-
> flush.conf
next prev parent reply other threads:[~2017-07-26 23:46 UTC|newest]
Thread overview: 176+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <1455443283.33337333.1500618150787.JavaMail.zimbra@redhat.com>
2017-07-21 6:56 ` KVM "fake DAX" flushing interface - discussion Pankaj Gupta
2017-07-21 6:56 ` [Qemu-devel] " Pankaj Gupta
2017-07-21 6:56 ` Pankaj Gupta
2017-07-21 9:51 ` Haozhong Zhang
2017-07-21 9:51 ` [Qemu-devel] " Haozhong Zhang
2017-07-21 9:51 ` Haozhong Zhang
2017-07-21 10:21 ` Pankaj Gupta
2017-07-21 10:21 ` [Qemu-devel] " Pankaj Gupta
2017-07-21 10:21 ` Pankaj Gupta
2017-07-21 12:12 ` Stefan Hajnoczi
2017-07-21 12:12 ` [Qemu-devel] " Stefan Hajnoczi
2017-07-21 13:29 ` Pankaj Gupta
2017-07-21 13:29 ` [Qemu-devel] " Pankaj Gupta
2017-07-21 13:29 ` Pankaj Gupta
2017-07-21 14:00 ` Rik van Riel
2017-07-21 14:00 ` [Qemu-devel] " Rik van Riel
2017-07-21 14:00 ` Rik van Riel
2017-07-21 15:58 ` Stefan Hajnoczi
2017-07-21 15:58 ` [Qemu-devel] " Stefan Hajnoczi
2017-07-22 19:34 ` Dan Williams
2017-07-22 19:34 ` [Qemu-devel] " Dan Williams
2017-07-22 19:34 ` Dan Williams
2017-07-23 14:04 ` Rik van Riel
2017-07-23 14:04 ` [Qemu-devel] " Rik van Riel
2017-07-23 14:04 ` Rik van Riel
2017-07-23 16:01 ` Dan Williams
2017-07-23 16:01 ` [Qemu-devel] " Dan Williams
2017-07-23 16:01 ` Dan Williams
2017-07-23 18:10 ` Rik van Riel
2017-07-23 18:10 ` [Qemu-devel] " Rik van Riel
2017-07-23 18:10 ` Rik van Riel
2017-07-23 20:10 ` Dan Williams
2017-07-23 20:10 ` [Qemu-devel] " Dan Williams
2017-07-23 20:10 ` Dan Williams
2017-07-24 10:23 ` Jan Kara
2017-07-24 10:23 ` [Qemu-devel] " Jan Kara
2017-07-24 10:23 ` Jan Kara
2017-07-24 12:06 ` Pankaj Gupta
2017-07-24 12:06 ` [Qemu-devel] " Pankaj Gupta
2017-07-24 12:06 ` Pankaj Gupta
2017-07-24 12:37 ` Jan Kara
2017-07-24 12:37 ` [Qemu-devel] " Jan Kara
2017-07-24 12:37 ` Jan Kara
2017-07-24 15:10 ` Dan Williams
2017-07-24 15:10 ` [Qemu-devel] " Dan Williams
2017-07-24 15:10 ` Dan Williams
2017-07-24 15:48 ` Jan Kara
2017-07-24 15:48 ` [Qemu-devel] " Jan Kara
2017-07-24 15:48 ` Jan Kara
2017-07-24 16:19 ` Dan Williams
2017-07-24 16:19 ` [Qemu-devel] " Dan Williams
2017-07-24 16:19 ` Dan Williams
2017-07-25 14:27 ` Pankaj Gupta
2017-07-25 14:27 ` [Qemu-devel] " Pankaj Gupta
2017-07-25 14:27 ` Pankaj Gupta
2017-07-25 14:46 ` Dan Williams
2017-07-25 14:46 ` [Qemu-devel] " Dan Williams
2017-07-25 14:46 ` Dan Williams
2017-07-25 20:59 ` Rik van Riel
2017-07-25 20:59 ` [Qemu-devel] " Rik van Riel
2017-07-26 13:47 ` Pankaj Gupta
2017-07-26 13:47 ` [Qemu-devel] " Pankaj Gupta
2017-07-26 13:47 ` Pankaj Gupta
2017-07-26 21:27 ` Rik van Riel
2017-07-26 21:27 ` [Qemu-devel] " Rik van Riel
2017-07-26 21:40 ` Dan Williams
2017-07-26 21:40 ` [Qemu-devel] " Dan Williams
2017-07-26 21:40 ` Dan Williams
2017-07-26 23:46 ` Rik van Riel [this message]
2017-07-26 23:46 ` [Qemu-devel] " Rik van Riel
2017-07-26 23:46 ` Rik van Riel
2017-07-27 0:54 ` Dan Williams
2017-07-27 0:54 ` [Qemu-devel] " Dan Williams
2017-07-27 0:54 ` Dan Williams
2017-10-31 7:13 ` Xiao Guangrong
2017-10-31 7:13 ` [Qemu-devel] " Xiao Guangrong
2017-10-31 7:13 ` Xiao Guangrong
2017-10-31 14:20 ` Dan Williams
2017-10-31 14:20 ` [Qemu-devel] " Dan Williams
2017-10-31 14:20 ` Dan Williams
2017-11-01 3:43 ` Xiao Guangrong
2017-11-01 3:43 ` [Qemu-devel] " Xiao Guangrong
2017-11-01 3:43 ` Xiao Guangrong
2017-11-01 4:25 ` Dan Williams
2017-11-01 4:25 ` [Qemu-devel] " Dan Williams
2017-11-01 4:25 ` Dan Williams
2017-11-01 6:46 ` Xiao Guangrong
2017-11-01 6:46 ` [Qemu-devel] " Xiao Guangrong
2017-11-01 6:46 ` Xiao Guangrong
2017-11-01 15:20 ` Dan Williams
2017-11-01 15:20 ` [Qemu-devel] " Dan Williams
2017-11-01 15:20 ` Dan Williams
2017-11-02 8:50 ` Xiao Guangrong
2017-11-02 8:50 ` [Qemu-devel] " Xiao Guangrong
2017-11-02 8:50 ` Xiao Guangrong
2017-11-02 16:30 ` Dan Williams
2017-11-02 16:30 ` [Qemu-devel] " Dan Williams
2017-11-02 16:30 ` Dan Williams
2017-11-03 6:21 ` Xiao Guangrong
2017-11-03 6:21 ` [Qemu-devel] " Xiao Guangrong
2017-11-03 6:21 ` Xiao Guangrong
2017-11-21 18:19 ` Rik van Riel
2017-11-21 18:19 ` [Qemu-devel] " Rik van Riel
2017-11-21 18:26 ` Dan Williams
2017-11-21 18:26 ` [Qemu-devel] " Dan Williams
2017-11-21 18:26 ` Dan Williams
2017-11-21 18:35 ` Rik van Riel
2017-11-21 18:35 ` [Qemu-devel] " Rik van Riel
2017-11-23 4:05 ` Xiao Guangrong
2017-11-23 4:05 ` [Qemu-devel] " Xiao Guangrong
2017-11-23 4:05 ` Xiao Guangrong
2017-11-23 16:14 ` Dan Williams
2017-11-23 16:14 ` [Qemu-devel] " Dan Williams
2017-11-23 16:14 ` Dan Williams
2017-11-23 16:28 ` Paolo Bonzini
2017-11-23 16:28 ` [Qemu-devel] " Paolo Bonzini
2017-11-23 16:28 ` Paolo Bonzini
2017-11-24 12:40 ` Pankaj Gupta
2017-11-24 12:40 ` [Qemu-devel] " Pankaj Gupta
2017-11-24 12:40 ` Pankaj Gupta
2017-11-24 12:44 ` Paolo Bonzini
2017-11-24 12:44 ` [Qemu-devel] " Paolo Bonzini
2017-11-24 12:44 ` Paolo Bonzini
2017-11-24 13:02 ` [Qemu-devel] " Pankaj Gupta
2017-11-24 13:02 ` Pankaj Gupta
2017-11-24 13:20 ` Paolo Bonzini
2017-11-24 13:20 ` Paolo Bonzini
2017-11-28 18:03 ` Dan Williams
2017-11-28 18:03 ` [Qemu-devel] " Dan Williams
2017-11-28 18:03 ` Dan Williams
2018-01-13 6:23 ` Pankaj Gupta
2018-01-13 6:23 ` [Qemu-devel] " Pankaj Gupta
2018-01-13 6:23 ` Pankaj Gupta
2018-01-17 16:17 ` Dan Williams
2018-01-17 16:17 ` [Qemu-devel] " Dan Williams
2018-01-17 16:17 ` Dan Williams
2018-01-17 17:31 ` Pankaj Gupta
2018-01-17 17:31 ` [Qemu-devel] " Pankaj Gupta
2018-01-17 17:31 ` Pankaj Gupta
2018-01-18 16:53 ` David Hildenbrand
2018-01-18 16:53 ` [Qemu-devel] " David Hildenbrand
2018-01-18 16:53 ` David Hildenbrand
2018-01-18 17:38 ` Dan Williams
2018-01-18 17:38 ` [Qemu-devel] " Dan Williams
2018-01-18 17:38 ` Dan Williams
2018-01-18 17:48 ` David Hildenbrand
2018-01-18 17:48 ` [Qemu-devel] " David Hildenbrand
2018-01-18 17:48 ` David Hildenbrand
2018-01-18 18:45 ` Dan Williams
2018-01-18 18:45 ` [Qemu-devel] " Dan Williams
2018-01-18 18:45 ` Dan Williams
2018-01-18 18:54 ` Pankaj Gupta
2018-01-18 18:54 ` [Qemu-devel] " Pankaj Gupta
2018-01-18 18:54 ` Pankaj Gupta
2018-01-18 18:59 ` Dan Williams
2018-01-18 18:59 ` [Qemu-devel] " Dan Williams
2018-01-18 18:59 ` Dan Williams
2018-01-18 19:36 ` Pankaj Gupta
2018-01-18 19:36 ` [Qemu-devel] " Pankaj Gupta
2018-01-18 19:36 ` Pankaj Gupta
2018-01-18 19:48 ` Dan Williams
2018-01-18 19:48 ` [Qemu-devel] " Dan Williams
2018-01-18 19:48 ` Dan Williams
2018-01-18 19:51 ` David Hildenbrand
2018-01-18 19:51 ` [Qemu-devel] " David Hildenbrand
2018-01-18 19:51 ` David Hildenbrand
2018-01-18 20:11 ` Dan Williams
2018-01-18 20:11 ` [Qemu-devel] " Dan Williams
2018-01-18 20:11 ` Dan Williams
2017-11-06 7:57 ` [Qemu-devel] " Pankaj Gupta
2017-11-06 7:57 ` Pankaj Gupta
2017-11-06 16:57 ` Dan Williams
2017-11-06 16:57 ` Dan Williams
2017-11-07 11:21 ` Pankaj Gupta
2017-11-07 11:21 ` Pankaj Gupta
2017-11-07 11:21 ` Pankaj Gupta
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=1501112787.4073.49.camel@redhat.com \
--to=riel@redhat.com \
--cc=dan.j.williams@intel.com \
--cc=jack@suse.cz \
--cc=kvm@vger.kernel.org \
--cc=kwolf@redhat.com \
--cc=linux-nvdimm@ml01.01.org \
--cc=nilal@redhat.com \
--cc=pagupta@redhat.com \
--cc=pbonzini@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=ross.zwisler@intel.com \
--cc=stefanha@gmail.com \
--cc=stefanha@redhat.com \
--cc=xiaoguangrong.eric@gmail.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 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.