On Fri, Jul 17, 2015 at 06:17:47AM +0200, Paolo Bonzini wrote:
>
>
> On 16/07/2015 11:56, Paolo Bonzini wrote:
> > @@ -286,13 +283,15 @@ bool aio_poll(AioContext *ctx, bool blocking)
> > npfd = 0;
> > ctx->walking_handlers--;
> >
> > +if (blocking) {
> > +atomic_sub(&ctx->
On 16/07/2015 11:56, Paolo Bonzini wrote:
> @@ -286,13 +283,15 @@ bool aio_poll(AioContext *ctx, bool blocking)
> npfd = 0;
> ctx->walking_handlers--;
>
> +if (blocking) {
> +atomic_sub(&ctx->notify_me, 2);
> +}
> +
I kept this place for subtracting notify_me because
On 17/07/2015 04:25, Fam Zheng wrote:
> What if aio_notify happens after the previous aio_dispatch() but before the
> next necessary atomic_add? The aio_notify would still skip the
> event_notifier_set(), and the next ppoll() will not return. For example:
>
> Thread A
On Thu, 07/16 11:56, Paolo Bonzini wrote:
> diff --git a/aio-posix.c b/aio-posix.c
> index 4abec38..268d14d 100644
> --- a/aio-posix.c
> +++ b/aio-posix.c
> @@ -233,26 +233,23 @@ static void add_pollfd(AioHandler *node)
> bool aio_poll(AioContext *ctx, bool blocking)
> {
> AioHandler *node;
This patch rewrites the ctx->dispatching optimization, which was the cause
of some mysterious hangs that could be reproduced on aarch64 KVM only.
The hangs were indirectly caused by aio_poll() and in particular by
flash memory updates's call to blk_write(), which invokes aio_poll().
Fun stuff: they
