On Fri, Apr 29, 2011 at 1:02 PM, Cyrill Gorcunov <gorcunov@xxxxxxxxx> wrote:
> So, if I understand all the things correct -- making virtio devices to
> belong separated irqs
> issued some race conditions on read\write operations between host and
> guest and adding
> thread pool revealed it, right? (because previously we were doing all
> the work inside i/o
> path on guest site).
So does reverting commit a37089da817ce7aad9789aeb9fc09b68e088ad9a
("kvm tools: Use threadpool for virtio-net") fix things? I think the
problem here is that now RX path relies on VIRTIO_PCI_QUEUE_NOTIFY to
happen in order for it to trigger KVM_IRQ_LINE which is wrong. Using
shared IRQs obviously masks the problem which is why reverting
Cyrill's commit makes the problem go away.
Pekka
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
