[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Qemu-devel] [PATCH v7 RFC] block/vxhs: Initial commit to add Verita
From: |
Ketan Nilangekar |
Subject: |
Re: [Qemu-devel] [PATCH v7 RFC] block/vxhs: Initial commit to add Veritas HyperScale VxHS block device support |
Date: |
Fri, 3 Feb 2017 21:32:11 +0000 |
User-agent: |
Microsoft-MacOutlook/f.1c.1.161117 |
On 2/3/17, 1:45 AM, "Daniel P. Berrange" <address@hidden> wrote:
On Thu, Feb 02, 2017 at 09:22:46PM +0000, Ketan Nilangekar wrote:
>
> On 2/2/17, 12:57 PM, "Ketan Nilangekar" <address@hidden> wrote:
>
> [Ketan]
> Does the QIO interface allow for readv/writev over network for
unsecure sockets?
>
> [Ketan]
> I checked the qio implementation and it seems that there is a pseudo
> implementation of readv/writev which iterates over the individual
> iovecs to make send/recv syscalls. This can’t be too good for performance.
I think you looked at the Win32 code - the qio_channel_socket_writev
and qio_channel_socket_readv methods which are built on non-Win32
platforms use recvmsg/sendmsg to handle iovecs in a single operation.
[Ketan]
Ok I see that.
> Are you suggesting we use the qio interface for secure communication only
> and leave the unsecure communication to libqnio?
If you expect non-QEMU apps to use libqnio, then you could keep support
for plain & TLS sockets in libqnio. Just provide the I/O callbacks facility
as an alternative approach which can be used by QEMU for secure & insecure
I/O handling.
[Ketan]
We do expect non-qemu applications to use libqnio.
However, if this is a "nice to have" from QEMU perspective, I'd like to take
this up later.
Regards,
Daniel
--
|: http://berrange.com -o- http://www.flickr.com/photos/dberrange/
:|
|: http://libvirt.org -o- http://virt-manager.org
:|
|: http://entangle-photo.org -o- http://search.cpan.org/~danberr/
:|
Re: [Qemu-devel] [PATCH v7 RFC] block/vxhs: Initial commit to add Veritas HyperScale VxHS block device support, Ketan Nilangekar, 2017/02/02