From: pbonzini@redhat.com (Paolo Bonzini)
Subject: [RFC PATCH 0/9] vhost-nvme: new qemu nvme backend using nvme target
Date: Tue, 1 Dec 2015 17:02:19 +0100 [thread overview]
Message-ID: <565DC48B.6030903@redhat.com> (raw)
In-Reply-To: <1448925639.27669.7.camel@ssi>
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
>
> "vhost-nvme + google-ext" didn't get good enough performance.
I'd expect it to be on par of qemu-nvme with ioeventfd but the question
is: why should it be better? For vhost-net, the answer is that more
zerocopy can be done if you put the data path in the kernel.
But qemu-nvme is already using io_submit for the data path, perhaps
there's not much to gain from vhost-nvme...
Paolo
> Still tuning.
WARNING: multiple messages have this Message-ID (diff)
From: Paolo Bonzini <pbonzini@redhat.com>
To: Ming Lin <mlin@kernel.org>
Cc: qemu-devel@nongnu.org, Christoph Hellwig <hch@lst.de>,
linux-nvme@lists.infradead.org,
virtualization@lists.linux-foundation.org
Subject: Re: [RFC PATCH 0/9] vhost-nvme: new qemu nvme backend using nvme target
Date: Tue, 1 Dec 2015 17:02:19 +0100 [thread overview]
Message-ID: <565DC48B.6030903@redhat.com> (raw)
In-Reply-To: <1448925639.27669.7.camel@ssi>
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
>
> "vhost-nvme + google-ext" didn't get good enough performance.
I'd expect it to be on par of qemu-nvme with ioeventfd but the question
is: why should it be better? For vhost-net, the answer is that more
zerocopy can be done if you put the data path in the kernel.
But qemu-nvme is already using io_submit for the data path, perhaps
there's not much to gain from vhost-nvme...
Paolo
> Still tuning.
WARNING: multiple messages have this Message-ID (diff)
From: Paolo Bonzini <pbonzini@redhat.com>
To: Ming Lin <mlin@kernel.org>
Cc: qemu-devel@nongnu.org, Christoph Hellwig <hch@lst.de>,
linux-nvme@lists.infradead.org,
virtualization@lists.linux-foundation.org
Subject: Re: [Qemu-devel] [RFC PATCH 0/9] vhost-nvme: new qemu nvme backend using nvme target
Date: Tue, 1 Dec 2015 17:02:19 +0100 [thread overview]
Message-ID: <565DC48B.6030903@redhat.com> (raw)
In-Reply-To: <1448925639.27669.7.camel@ssi>
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
>
> "vhost-nvme + google-ext" didn't get good enough performance.
I'd expect it to be on par of qemu-nvme with ioeventfd but the question
is: why should it be better? For vhost-net, the answer is that more
zerocopy can be done if you put the data path in the kernel.
But qemu-nvme is already using io_submit for the data path, perhaps
there's not much to gain from vhost-nvme...
Paolo
> Still tuning.
next prev parent reply other threads:[~2015-12-01 16:02 UTC|newest]
Thread overview: 90+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-11-20 0:20 [RFC PATCH 0/9] vhost-nvme: new qemu nvme backend using nvme target Ming Lin
2015-11-20 0:20 ` [Qemu-devel] " Ming Lin
2015-11-20 0:20 ` Ming Lin
2015-11-20 0:21 ` [RFC PATCH 1/9] nvme-vhost: add initial commit Ming Lin
2015-11-20 0:21 ` [Qemu-devel] " Ming Lin
2015-11-20 0:21 ` Ming Lin
2015-11-20 0:21 ` [RFC PATCH 2/9] nvme-vhost: add basic ioctl handlers Ming Lin
2015-11-20 0:21 ` [Qemu-devel] " Ming Lin
2015-11-20 0:21 ` Ming Lin
2015-11-20 0:21 ` [RFC PATCH 3/9] nvme-vhost: add basic nvme bar read/write Ming Lin
2015-11-20 0:21 ` [Qemu-devel] " Ming Lin
2015-11-20 0:21 ` Ming Lin
2015-11-20 0:21 ` [RFC PATCH 4/9] nvmet: add a controller "start" hook Ming Lin
2015-11-20 0:21 ` [Qemu-devel] " Ming Lin
2015-11-20 0:21 ` Ming Lin
2015-11-20 5:13 ` Christoph Hellwig
2015-11-20 5:13 ` Christoph Hellwig
2015-11-20 5:13 ` [Qemu-devel] " Christoph Hellwig
2015-11-20 5:31 ` Ming Lin
2015-11-20 5:31 ` [Qemu-devel] " Ming Lin
2015-11-20 5:31 ` Ming Lin
2015-11-20 0:21 ` [RFC PATCH 5/9] nvme-vhost: add controller "start" callback Ming Lin
2015-11-20 0:21 ` [Qemu-devel] " Ming Lin
2015-11-20 0:21 ` Ming Lin
2015-11-20 0:21 ` [RFC PATCH 6/9] nvmet: add a "parse_extra_admin_cmd" hook Ming Lin
2015-11-20 0:21 ` [Qemu-devel] " Ming Lin
2015-11-20 0:21 ` Ming Lin
2015-11-20 0:21 ` [RFC PATCH 7/9] nvme-vhost: add "parse_extra_admin_cmd" callback Ming Lin
2015-11-20 0:21 ` [Qemu-devel] " Ming Lin
2015-11-20 0:21 ` Ming Lin
2015-11-20 0:21 ` [RFC PATCH 8/9] nvme-vhost: add vhost memory helpers Ming Lin
2015-11-20 0:21 ` [Qemu-devel] " Ming Lin
2015-11-20 0:21 ` Ming Lin
2015-11-20 0:21 ` [RFC PATCH 9/9] nvme-vhost: add nvme queue handlers Ming Lin
2015-11-20 0:21 ` [Qemu-devel] " Ming Lin
2015-11-20 0:21 ` Ming Lin
2015-11-20 5:16 ` [RFC PATCH 0/9] vhost-nvme: new qemu nvme backend using nvme target Christoph Hellwig
2015-11-20 5:16 ` Christoph Hellwig
2015-11-20 5:16 ` [Qemu-devel] " Christoph Hellwig
2015-11-20 5:33 ` Ming Lin
2015-11-20 5:33 ` [Qemu-devel] " Ming Lin
2015-11-20 5:33 ` Ming Lin
2015-11-21 13:11 ` Paolo Bonzini
2015-11-21 13:11 ` [Qemu-devel] " Paolo Bonzini
2015-11-23 8:17 ` Ming Lin
2015-11-23 8:17 ` [Qemu-devel] " Ming Lin
2015-11-23 8:17 ` Ming Lin
2015-11-23 14:14 ` Paolo Bonzini
2015-11-23 14:14 ` [Qemu-devel] " Paolo Bonzini
2015-11-23 14:14 ` Paolo Bonzini
2015-11-24 7:27 ` Ming Lin
2015-11-24 7:27 ` [Qemu-devel] " Ming Lin
2015-11-24 7:27 ` Ming Lin
2015-11-24 8:23 ` Ming Lin
2015-11-24 8:23 ` [Qemu-devel] " Ming Lin
2015-11-24 8:23 ` Ming Lin
2015-11-24 10:51 ` Paolo Bonzini
2015-11-24 10:51 ` [Qemu-devel] " Paolo Bonzini
2015-11-24 10:51 ` Paolo Bonzini
2015-11-24 19:25 ` Ming Lin
2015-11-24 19:25 ` [Qemu-devel] " Ming Lin
2015-11-24 19:25 ` Ming Lin
2015-11-25 11:27 ` Paolo Bonzini
2015-11-25 11:27 ` [Qemu-devel] " Paolo Bonzini
2015-11-25 11:27 ` Paolo Bonzini
2015-11-25 18:51 ` Ming Lin
2015-11-25 18:51 ` [Qemu-devel] " Ming Lin
2015-11-25 18:51 ` Ming Lin
2015-11-25 19:32 ` Paolo Bonzini
2015-11-25 19:32 ` [Qemu-devel] " Paolo Bonzini
2015-11-25 19:32 ` Paolo Bonzini
2015-11-30 23:20 ` Ming Lin
2015-11-30 23:20 ` [Qemu-devel] " Ming Lin
2015-11-30 23:20 ` Ming Lin
2015-12-01 16:02 ` Paolo Bonzini [this message]
2015-12-01 16:02 ` [Qemu-devel] " Paolo Bonzini
2015-12-01 16:02 ` Paolo Bonzini
2015-12-01 16:26 ` Ming Lin
2015-12-01 16:26 ` [Qemu-devel] " Ming Lin
2015-12-01 16:26 ` Ming Lin
2015-12-01 16:59 ` Paolo Bonzini
2015-12-01 16:59 ` [Qemu-devel] " Paolo Bonzini
2015-12-01 16:59 ` Paolo Bonzini
2015-12-02 5:13 ` Ming Lin
2015-12-02 5:13 ` [Qemu-devel] " Ming Lin
2015-12-02 5:13 ` Ming Lin
2015-12-02 10:07 ` Paolo Bonzini
2015-12-02 10:07 ` [Qemu-devel] " Paolo Bonzini
2015-12-02 10:07 ` Paolo Bonzini
2015-11-21 13:11 ` Paolo Bonzini
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=565DC48B.6030903@redhat.com \
--to=pbonzini@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 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.