Previously -EAGAIN is simply ignored for !s->io_q.plugged case,
and sometimes it is easy to cause -EIO to VM, such as NVME device.
This patch handles -EAGAIN by io queue for !s->io_q.plugged case,
and it will be retried in following aio completion cb.
Suggested-by: Paolo Bonzini
Signed-off-by: M
On Tue, Nov 18, 2014 at 10:06 PM, Paolo Bonzini wrote:
>
>
> On 06/11/2014 16:10, Ming Lei wrote:
>> +/* don't submit until next completion for -EAGAIN of non plug case */
>> +if (unlikely(!s->io_q.plugged)) {
>> +return 0;
>> +}
>> +
>
> Is this an optimization or a fix for so
On 18/11/2014 15:06, Paolo Bonzini wrote:
>> > +/* don't submit until next completion for -EAGAIN of non plug case */
>> > +if (unlikely(!s->io_q.plugged)) {
>> > +return 0;
>> > +}
>> > +
> Is this an optimization or a fix for something?
Ah, if !io_q.plugged we must be in th
On Mon, Nov 24, 2014 at 5:52 PM, Paolo Bonzini wrote:
>
>
> On 18/11/2014 15:06, Paolo Bonzini wrote:
>>> > +/* don't submit until next completion for -EAGAIN of non plug case */
>>> > +if (unlikely(!s->io_q.plugged)) {
>>> > +return 0;
>>> > +}
>>> > +
>> Is this an optimizati
On 24/11/2014 11:11, Ming Lei wrote:
> Yes, the above change need the corresponding comment, but this
> patch needn't since the 1st case won't reach here, :-)
I'm not sure I follow, but you can send v4 with a clearer comment I
guess. :)
Paolo
On 06/11/2014 16:10, Ming Lei wrote:
> +/* don't submit until next completion for -EAGAIN of non plug case */
> +if (unlikely(!s->io_q.plugged)) {
> +return 0;
> +}
> +
Is this an optimization or a fix for something?
> +/*
> + * Switch to queue mode until -EA
