On Tue, Nov 29, 2016 at 09:31:42AM +0530, Jerin Jacob wrote:
> On Mon, Nov 28, 2016 at 09:16:10AM +0000, Bruce Richardson wrote:
> > On Sat, Nov 26, 2016 at 08:24:55AM +0530, Jerin Jacob wrote:
> > > On Fri, Nov 25, 2016 at 11:00:53AM +0000, Bruce Richardson wrote:
> > > > On Fri, Nov 25, 2016 at 05:53:34AM +0530, Jerin Jacob wrote:
> > > > > On Thu, Nov 24, 2016 at 04:35:56PM +0100, Thomas Monjalon wrote:
> > > > > > 2016-11-24 07:29, Jerin Jacob:
> > > > > > > On Wed, Nov 23, 2016 at 07:39:09PM +0100, Thomas Monjalon wrote:
> > > > > > > > 2016-11-18 11:14, Jerin Jacob:
> > > > > > > > > +Eventdev API - EXPERIMENTAL
> > > > > > > > > +M: Jerin Jacob <jerin.jacob at caviumnetworks.com>
> > > > > > > > > +F: lib/librte_eventdev/
> > > > > > > >
> > > > >
> > > > > I don't think there is any portability issue here, I can explain.
> > > > >
> > > > > The application level, we have two more use case to deal with non
> > > > > burst
> > > > > variant
> > > > >
> > > > > - latency critical work
> > > > > - on dequeue, if application wants to deal with only one flow(i.e to
> > > > > avoid processing two different application flows to avoid cache
> > > > > trashing)
> > > > >
> > > > > Selection of the burst variants will be based on
> > > > > rte_event_dev_info_get() and rte_event_dev_configure()(see,
> > > > > max_event_port_dequeue_depth,
> > > > > max_event_port_enqueue_depth, nb_event_port_dequeue_depth,
> > > > > nb_event_port_enqueue_depth )
> > > > > So I don't think their is portability issue here and I don't want to
> > > > > waste my
> > > > > CPU cycles on the for loop if application known to be working with non
> > > > > bursts variant like below
> > > > >
> > > >
> > > > If the application is known to be working on non-burst varients, then
> > > > they always request a burst-size of 1, and skip the loop completely.
> > > > There is no extra performance hit in that case in either the app or the
> > > > driver (since the non-burst driver always returns 1, irrespective of the
> > > > number requested).
> > >
> > > Hmm. I am afraid, There is.
> > > On the app side, the const "1" can not be optimized by the compiler as
> > > on downside it is function pointer based driver interface
> > > On the driver side, the implementation would be for loop based instead
> > > of plain access.
> > > (compiler never can see the const "1" in driver interface)
> > >
> > > We are planning to implement burst mode as kind of emulation mode and
> > > have a different scheme for burst and nonburst. The similar approach we
> > > have
> > > taken in introducing rte_event_schedule() and split the responsibility so
> > > that SW driver can work without additional performance overhead and neat
> > > driver interface.
> > >
> > > If you are concerned about the usability part and regression on the SW
> > > driver, then it's not the case, application will use nonburst variant
> > > only if
> > > dequeue_depth == 1 and/or explicit case where latency matters.
> > >
> > > On the portability side, we support both case and application if written
> > > based
> > > on dequeue_depth it will perform well in both implementations.IMO, There
> > > is
> > > no another shortcut for performance optimized application running on
> > > different
> > > set of model.I think it is not an issue as, in event model as each cores
> > > identical and main loop can be changed based on dequeue_depth
> > > if needs performance(anyway mainloop will be function pointer based).
> > >
> >
> > Ok, I think I see your point now. Here is an alternative suggestion.
> >
> > 1. Keep the single user API.
> > 2. Have both single and burst function pointers in the driver
> > 3. Call appropriately in the eventdev layer based on parameters. For
> > example:
> >
> > rte_event_dequeue_burst(..., int num)
> > {
> > if (num == 1 && single_dequeue_fn != NULL)
> > return single_dequeue_fn(...);
> > return burst_dequeue_fn(...);
> > }
> >
> > This way drivers can optionally special-case the single dequeue case -
> > the function pointer check will definitely be predictable in HW making
> > that a near-zero-cost check - while not forcing all drivers to do so.
> > It also reduces the public API surface, and gives us a single enqueue
> > and dequeue function.
>
> The alternative suggestion looks good to me. Yes, it makes sense to reduces
> the
> public API interface if possible.
>
> Regarding the implementation, I thought to have a bit approach like below
> to reduce the cost of additional AND operation.(with const "1", compiler
> can choose with correct one with out any overhead)
>
> rte_event_dequeue_burst(..., int num)
> {
> if (num == 1)
> return single_dequeue_fn(...);
> return burst_dequeue_fn(...);
> }
>
> "single_dequeue_fn" populated from the driver layer.
> In the absence of populating the "single_dequeue_fn" from the driver layer,
> The common code can create the single_dequeue_fn using driver
> provided "burst_dequeue_fn"
>
> something like
> generic_single_dequeue_fn(dev){
> {
> dev->burst_dequeue_fn(..,1);
> }
>
> Any concerns?
>
No, works ok for me
/Bruce
