On 02/10/2016 01:15 PM, Daniel P. Berrange wrote:
On Wed, Feb 10, 2016 at 01:53:49PM +0200, Michael S. Tsirkin wrote:
On Wed, Feb 10, 2016 at 10:35:13AM +0100, Didier Pallard wrote:
On 02/09/2016 06:04 PM, Daniel P. Berrange wrote:
On Tue, Feb 09, 2016 at 05:17:16PM +0100, Didier Pallard
nix socket, and processed later.
Add an option boolean flag 'use_mask_notifier' to disable the use
of guest_notifier_mask in virtio pci.
Signed-off-by: Didier Pallard
Signed-off-by: Victor Kaplansky
---
v5 changes:
- rebased to mst tree.
- removed a traling space.
v4 changes:
In
On 02/09/2016 06:04 PM, Daniel P. Berrange wrote:
On Tue, Feb 09, 2016 at 05:17:16PM +0100, Didier Pallard wrote:
On 02/09/2016 01:21 PM, Michael S. Tsirkin wrote:
On Tue, Feb 09, 2016 at 11:48:13AM +, Daniel P. Berrange wrote:
On Thu, Feb 04, 2016 at 04:10:38PM +0200, Michael S. Tsirkin
On 02/09/2016 01:21 PM, Michael S. Tsirkin wrote:
On Tue, Feb 09, 2016 at 11:48:13AM +, Daniel P. Berrange wrote:
On Thu, Feb 04, 2016 at 04:10:38PM +0200, Michael S. Tsirkin wrote:
On Thu, Dec 03, 2015 at 10:53:17AM +0100, Didier Pallard wrote:
unix_send_msgfds is used by vhost-user
On 02/04/2016 02:08 PM, Michael S. Tsirkin wrote:
On Thu, Dec 03, 2015 at 10:53:18AM +0100, Didier Pallard wrote:
Using guest_notifier_mask function in vhost-user case may
break interrupt mask paradigm, because mask/unmask is not
really done when returning from guest_notifier_mask call, instead
On 02/04/2016 03:10 PM, Michael S. Tsirkin wrote:
On Thu, Dec 03, 2015 at 10:53:17AM +0100, Didier Pallard wrote:
unix_send_msgfds is used by vhost-user control socket. qemu_chr_fe_write_all
is used to send a message and retries as long as EAGAIN errno is set,
but write_msgfds buffer is freed
On 01/25/2016 10:22 AM, Victor Kaplansky wrote:
On Thu, Dec 03, 2015 at 10:53:16AM +0100, Didier Pallard wrote:
Hi,
I recently did some stress tests of a vhost-user interface using an UDP
traffic generator. Traffic generator was connected to 2 physical ports
that are in turn connected to 2
On 01/13/2016 04:32 PM, Victor Kaplansky wrote:
On Tue, Jan 12, 2016 at 01:05:52PM +0100, Didier Pallard wrote:
On 01/12/2016 09:26 AM, Victor Kaplansky wrote:
This RFC PATCH tries to solve the problem of lost interrupts
>from a slow back-end. Didier could you test it?
Thanks, Victor
W
andler(&vq->guest_notifier, NULL);
}
else null handler is set in guest_notifier.
And from my understanding, virtio-pci in kvm mode uses irqfd, so when are
we entering the virtio_queue_guest_notifier_read?
did you also change the qemu configuration?
thanks
didier
--
Didier PALLARD
6WIND
Soft
On 12/10/2015 01:56 PM, Victor Kaplansky wrote:
On Wed, Dec 09, 2015 at 06:06:06PM +0100, Didier Pallard wrote:
On 12/09/2015 04:59 PM, Victor Kaplansky wrote:
On Mon, Dec 07, 2015 at 02:31:36PM +0100, Marc-André Lureau wrote:
Hi
On Thu, Dec 3, 2015 at 10:53 AM, Didier Pallard
wrote
On 12/09/2015 04:59 PM, Victor Kaplansky wrote:
On Mon, Dec 07, 2015 at 02:31:36PM +0100, Marc-André Lureau wrote:
Hi
On Thu, Dec 3, 2015 at 10:53 AM, Didier Pallard
wrote:
unix_send_msgfds is used by vhost-user control socket. qemu_chr_fe_write_all
is used to send a message and retries as
On 12/07/2015 02:59 PM, Marc-André Lureau wrote:
Hi
On Mon, Dec 7, 2015 at 2:37 PM, Marc-André Lureau
wrote:
Hi
On Thu, Dec 3, 2015 at 10:53 AM, Didier Pallard
wrote:
Using guest_notifier_mask function in vhost-user case may
break interrupt mask paradigm, because mask/unmask is not
really
On 12/03/2015 10:53 AM, Didier Pallard wrote:
Hi,
I recently did some stress tests of a vhost-user interface using an UDP
traffic generator. Traffic generator was connected to 2 physical ports
that are in turn connected to 2 virtio ports through a linux bridge, VM
(running linux) doing routing
/unmasking interrupts
by taking/giving vring_call fd from/to kernel kvm module).
Patches 2 and 3 of the serie propose an implementation of this second option.
Didier
Didier Pallard (3):
char: fix vhost-user socket full
virtio-pci: add an option to bypass guest_notifier_mask
vhost-net: force
called through qemu_chr_fe_write, it will be
user responsability to resend message as is or to free write_msgfds
using set_msgfds(0)
Signed-off-by: Didier Pallard
Reviewed-by: Thibaut Collet
---
qemu-char.c | 10 ++
1 file changed, 10 insertions(+)
diff --git a/qemu-char.c b/qemu-char.c
guest_notifier_mask
in virtio pci.
Signed-off-by: Didier Pallard
Reviewed-by: Thibaut Collet
---
hw/virtio/virtio-pci.c | 29 +++--
hw/virtio/virtio-pci.h | 6 ++
2 files changed, 29 insertions(+), 6 deletions(-)
diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c
index
Since guest_mask_notifier can not be used in vhost-user
mode due to buffering implied by unix control socket,
force VIRTIO_PCI_FLAG_USE_NOTIFIERMASK on virtio pci
of vhost-user interfaces, and send correct callfd
to the guest at vhost start.
Signed-off-by: Didier Pallard
Reviewed-by: Thibaut
17 matches
Mail list logo
