On 04/05/2017 12:23, Stefan Hajnoczi wrote:
> The main loop uses aio_disable_external()/aio_enable_external() to
> temporarily disable processing of external AioContext clients like
> device emulation.
>
> This allows monitor commands to quiesce I/O and prevent the guest from
> submitting new requests while a monitor command is in progress.
>
> The aio_enable_external() API is currently broken when an IOThread is in
> aio_poll() waiting for fd activity when the main loop re-enables
> external clients. Incrementing ctx->external_disable_cnt does not wake
> the IOThread from ppoll(2) so fd processing remains suspended and leads
> to unresponsive emulated devices.
>
> This patch adds an aio_notify() call to aio_enable_external() so the
> IOThread is kicked out of ppoll(2) and will re-arm the file descriptors.
>
> The bug can be reproduced as follows:
>
> $ qemu -M accel=kvm -m 1024 \
> -object iothread,id=iothread0 \
> -device virtio-scsi-pci,iothread=iothread0,id=virtio-scsi-pci0 \
> -drive
> if=none,id=drive0,aio=native,cache=none,format=raw,file=test.img \
> -device scsi-hd,id=scsi-hd0,drive=drive0 \
> -qmp tcp::5555,server,nowait
>
> $ scripts/qmp/qmp-shell localhost:5555
> (qemu) blockdev-snapshot-sync device=drive0 snapshot-file=sn1.qcow2
> mode=absolute-paths format=qcow2
>
> After blockdev-snapshot-sync completes the SCSI disk will be
> unresponsive. This leads to request timeouts inside the guest.
I agree this is the minimal fix and is the right thing to do. The
bdrv_drained_begin/end device callbacks would also make it possible to
remove disable/enable external altogether, but that's more invasive.
Reviewed-by: Paolo Bonzini <pbonz...@redhat.com>
Cc: qemu-sta...@nongnu.org
> Reported-by: Qianqian Zhu <qi...@redhat.com>
> Suggested-by: Fam Zheng <f...@redhat.com>
> Signed-off-by: Stefan Hajnoczi <stefa...@redhat.com>
> ---
> include/block/aio.h | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/include/block/aio.h b/include/block/aio.h
> index 406e323..5294b04 100644
> --- a/include/block/aio.h
> +++ b/include/block/aio.h
> @@ -456,6 +456,7 @@ static inline void aio_enable_external(AioContext *ctx)
> {
> assert(ctx->external_disable_cnt > 0);
> atomic_dec(&ctx->external_disable_cnt);
> + aio_notify(ctx);
> }
>
> /**
>
