Re: [PATCH v5 1/6] libnvdimm: nd_region flush callback support

[Jeff Moyer]

Dan Williams <dan.j.williams@xxxxxxxxx> writes:

> On Fri, Apr 12, 2019 at 6:12 AM Jeff Moyer <jmoyer@xxxxxxxxxx> wrote:
>>
>> Jan Kara <jack@xxxxxxx> writes:
>>
>> > On Thu 11-04-19 07:51:48, Dan Williams wrote:
>> >> On Tue, Apr 9, 2019 at 9:09 PM Pankaj Gupta <pagupta@xxxxxxxxxx> wrote:
>> >> > +       } else {
>> >> > +               if (nd_region->flush(nd_region))
>> >> > +                       rc = -EIO;
>> >>
>> >> Given the common case wants to be fast and synchronous I think we
>> >> should try to avoid retpoline overhead by default. So something like
>> >> this:
>> >>
>> >> if (nd_region->flush == generic_nvdimm_flush)
>> >>     rc = generic_nvdimm_flush(...);
>> >
>> > I'd either add a comment about avoiding retpoline overhead here or just
>> > make ->flush == NULL mean generic_nvdimm_flush(). Just so that people don't
>> > get confused by the code.
>>
>> Isn't this premature optimization?  I really don't like adding things
>> like this without some numbers to show it's worth it.
>
> I don't think it's premature given this optimization technique is
> already being deployed elsewhere, see:
>
> https://lwn.net/Articles/774347/

The technique is fine, but that doesn't mean it should be applied
everywhere.  Is *this* code path really going to benefit from the
optimization?

-Jeff