On Tue, 2015-12-01 at 11:59 -0500, Paolo Bonzini wrote:
> > What do you think about virtio-nvme+vhost-nvme?
>
> What would be the advantage over virtio-blk? Multiqueue is not supported
> by QEMU but it's already supported by Linux (commit 6a27b656fc).
I expect performance would be better.
Seems
On Tue, 2015-12-01 at 17:02 +0100, Paolo Bonzini wrote:
>
> On 01/12/2015 00:20, Ming Lin wrote:
> > qemu-nvme: 148MB/s
> > vhost-nvme + google-ext: 230MB/s
> > qemu-nvme + google-ext + eventfd: 294MB/s
> > virtio-scsi: 296MB/s
> > virtio-blk: 344MB/s
> >
On Mon, 2015-11-23 at 15:14 +0100, Paolo Bonzini wrote:
>
> On 23/11/2015 09:17, Ming Lin wrote:
> > On Sat, 2015-11-21 at 14:11 +0100, Paolo Bonzini wrote:
> >>
> >> On 20/11/2015 01:20, Ming Lin wrote:
> >>> One improvment could be to use google&#x
On Wed, 2015-11-25 at 12:27 +0100, Paolo Bonzini wrote:
> Do you still have a blk_set_aio_context somewhere? I'm losing track of
> the changes.
No.
>
> In any case, I think using a separate I/O thread is a bit premature,
> except for benchmarking. In the meanwhile I think the best option is to
On Tue, 2015-11-24 at 11:51 +0100, Paolo Bonzini wrote:
>
> On 24/11/2015 08:27, Ming Lin wrote:
> > handle_notify (qemu/hw/block/dataplane/virtio-blk.c:126)
> > aio_dispatch (qemu/aio-posix.c:329)
> > aio_poll (qemu/aio-posix.c:474)
> > iothread_run (qemu/i
On Mon, 2015-11-23 at 23:27 -0800, Ming Lin wrote:
> On Mon, 2015-11-23 at 15:14 +0100, Paolo Bonzini wrote:
> >
> > On 23/11/2015 09:17, Ming Lin wrote:
> > > On Sat, 2015-11-21 at 14:11 +0100, Paolo Bonzini wrote:
> > >>
> > >> On 20/11/2015 01:
On Mon, 2015-11-23 at 15:14 +0100, Paolo Bonzini wrote:
>
> On 23/11/2015 09:17, Ming Lin wrote:
> > On Sat, 2015-11-21 at 14:11 +0100, Paolo Bonzini wrote:
> >>
> >> On 20/11/2015 01:20, Ming Lin wrote:
> >>> One improvment could be to use google&#x
On Sat, 2015-11-21 at 23:45 -0800, Ming Lin wrote:
> On Sat, 2015-11-21 at 13:56 +0100, Paolo Bonzini wrote:
> >
> > On 21/11/2015 00:05, Ming Lin wrote:
> > > [1.752129] Freeing unused kernel memory: 420K (880001b97000 -
> > > 880001c0)
>
On Sat, 2015-11-21 at 14:11 +0100, Paolo Bonzini wrote:
>
> On 20/11/2015 01:20, Ming Lin wrote:
> > One improvment could be to use google's NVMe vendor extension that
> > I send in another thread, aslo here:
> > https://git.kernel.org/cgit/linux/kernel/git/mlin/lin
On Sat, 2015-11-21 at 13:56 +0100, Paolo Bonzini wrote:
>
> On 21/11/2015 00:05, Ming Lin wrote:
> > [1.752129] Freeing unused kernel memory: 420K (880001b97000 -
> > 880001c0)
> > [1.986573] clocksource: tsc: mask: 0x max_cy
On Fri, 2015-11-20 at 09:58 +0100, Paolo Bonzini wrote:
>
> On 20/11/2015 09:11, Ming Lin wrote:
> > On Thu, 2015-11-19 at 11:37 +0100, Paolo Bonzini wrote:
> >>
> >> On 18/11/2015 06:47, Ming Lin wrote:
> >>> @@ -726,7 +798,11 @@ static void nvme_proce
On Thu, 2015-11-19 at 11:37 +0100, Paolo Bonzini wrote:
>
> On 18/11/2015 06:47, Ming Lin wrote:
> > @@ -726,7 +798,11 @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr,
> > int val)
> > }
> >
> > start_sqs = nvme_cq_full(cq) ? 1 :
n't know why it's lost.
mlin@ssi:~$ history |grep "nab"
1861 git send-email --from "Ming Lin " --to
"linux-n...@lists.infradead.org" --cc "qemu-devel@nongnu.org" --cc
"virtualizat...@lists.linux-foundation.org" --cc "Christoph Hellwig
" --cc "Nicholas A. Bellinger "
--compose ~/patches/*.patch
On Fri, 2015-11-20 at 06:13 +0100, Christoph Hellwig wrote:
> On Thu, Nov 19, 2015 at 04:21:03PM -0800, Ming Lin wrote:
> > #define NVMET_SUBSYS_NAME_LEN 256
> > charsubsys_name[NVMET_SUBSYS_NAME_LEN];
> > +
> > + void
From: Ming Lin
This borrows code from Hannes Reinecke's rts-megasas.
Cc: Hannes Reinecke
Signed-off-by: Ming Lin
---
drivers/nvme/target/vhost.c | 108
1 file changed, 108 insertions(+)
diff --git a/drivers/nvme/target/vhost.c b/drivers
From: Ming Lin
This is used to execute controller specific cmd parse code
Signed-off-by: Ming Lin
---
drivers/nvme/target/admin-cmd.c | 7 +++
drivers/nvme/target/nvmet.h | 3 +++
2 files changed, 10 insertions(+)
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target
From: Ming Lin
This adds nvme submission/completion queue handlers,
which are ported from qemu-nvme.
And hooks into nvme-target to do the real job.
Cc: Keith Busch
Signed-off-by: Ming Lin
---
drivers/nvme/target/vhost.c | 420 +++-
1 file changed, 416
From: Ming Lin
Signed-off-by: Ming Lin
---
drivers/nvme/target/vhost.c | 102
include/uapi/linux/vhost.h | 17 ++--
2 files changed, 116 insertions(+), 3 deletions(-)
diff --git a/drivers/nvme/target/vhost.c b/drivers/nvme/target/vhost.c
From: Ming Lin
This is used to execute controller specific start code
Signed-off-by: Ming Lin
---
drivers/nvme/target/core.c | 3 +++
drivers/nvme/target/nvmet.h | 3 +++
2 files changed, 6 insertions(+)
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 1bfef66
From: Ming Lin
Signed-off-by: Ming Lin
---
drivers/nvme/target/vhost.c | 153
1 file changed, 153 insertions(+)
diff --git a/drivers/nvme/target/vhost.c b/drivers/nvme/target/vhost.c
index 4a147d6..04ed0bc 100644
--- a/drivers/nvme/target/vhost.c
From: Ming Lin
Signed-off-by: Ming Lin
---
drivers/nvme/target/vhost.c | 106
1 file changed, 106 insertions(+)
diff --git a/drivers/nvme/target/vhost.c b/drivers/nvme/target/vhost.c
index 01c44b8..4a147d6 100644
--- a/drivers/nvme/target/vhost.c
Hi,
This is the first attempt to add a new qemu nvme backend using
in-kernel nvme target.
Most code are ported from qemu-nvme and also borrow code from
Hannes Reinecke's rts-megasas.
It's similar as vhost-scsi, but doesn't use virtio.
The advantage is guest can run unmodified NVMe driver.
So gue
From: Ming Lin
Signed-off-by: Ming Lin
---
drivers/nvme/target/core.c | 1 +
drivers/nvme/target/vhost.c | 264 +++-
include/uapi/linux/vhost.h | 15 +++
3 files changed, 279 insertions(+), 1 deletion(-)
diff --git a/drivers/nvme/target/core.c b
From: Ming Lin
Signed-off-by: Ming Lin
---
drivers/nvme/target/Kconfig | 11 +++
drivers/nvme/target/Makefile | 2 ++
drivers/nvme/target/vhost.c | 16
3 files changed, 29 insertions(+)
create mode 100644 drivers/nvme/target/vhost.c
diff --git a/drivers/nvme
Hi Rob & Mihai,
I wrote vhost-nvme patches on top of Christoph's NVMe target.
vhost-nvme still uses mmio. So the guest OS can run unmodified NVMe
driver. But the tests I have done didn't show competitive performance
compared to virtio-blk/virtio-scsi. The bottleneck is in mmio. Your nvme
vendor ex
=1 --verify=0 --verify_fatal=0 --numjobs=4
--rw=randread --blocksize=4k --randrepeat=false
Signed-off-by: Rob Nelson
[mlin: port for upstream]
Signed-off-by: Ming Lin
---
drivers/nvme/host/Kconfig | 7 +++
drivers/nvme/host/core.c | 1 +
drivers/nvme/host/pci.c | 147
-by: Keith Busch
[mlin: port for upstream]
Signed-off-by: Ming Lin
---
hw/block/nvme.c | 92 ++---
hw/block/nvme.h | 18 +++
2 files changed, 106 insertions(+), 4 deletions(-)
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index 169e4f
27 matches
Mail list logo
