On 12/27/18 6:55 AM, Christoph Hellwig wrote:
>> diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h
>> index 8387e0af0f76..a6829bae9ada 100644
>> --- a/include/uapi/linux/aio_abi.h
>> +++ b/include/uapi/linux/aio_abi.h
>> @@ -52,9 +52,11 @@ enum {
>> * is valid.
>> * IOCB_FLAG_IOPRIO - Set if the "aio_reqprio" member of the "struct iocb"
>> * is valid.
>> + * IOCB_FLAG_HIPRI - Use IO completion polling
>> */
>> #define IOCB_FLAG_RESFD (1 << 0)
>> #define IOCB_FLAG_IOPRIO (1 << 1)
>> +#define IOCB_FLAG_HIPRI (1 << 2)
>
> NAK for this hunk. We already have a hipri-flag on the command,
> which we have to force on, and we have another one on the context.
So what do you prefer? The polling tied to the ioctx, and not have
userspace set it? As I said previously, I don't really care, but I
obviously lean towards having this be explicit in the app. If you
feel strongly about it, I'm fine with dropping IOCB_FLAG_HIPRI and
the polling being implied by the io context it's submitted against.
--
Jens Axboe
