On Mon, 2019-08-05 at 11:27 -0700, Sagi Grimberg wrote: > > > Ping ? I had another look today and I don't feel like mucking > > > around > > > with all the AQ size logic, AEN magic tag etc... just for that > > > sake of > > > that Apple gunk. I'm happy to have it give up IO tags, it doesn't > > > seem > > > to make much of a difference in practice anyway. > > > > > > But if you feel strongly about it, then I'll implement the > > > "proper" way > > > sometimes this week, adding a way to shrink the AQ down to > > > something > > > like 3 (one admin request, one async event (AEN), and the empty > > > slot) > > > by making a bunch of the constants involved variables instead. > > > > I don't feel too strongly about it. I think your patch is fine, so > > > > Acked-by: Keith Busch <keith.bu...@intel.com> > > Should we pick this up for 5.3-rc?
Well, if you are talking about just this patch, it's not needed unless you also merge the rest of the Apple T2 support patches, which some people I'm sure would like but I think Christoph is a bit cold feet about (I don't care either way). If you are talking about the whole series, give me a day or two to respin with the added check that Keith requested (I believe his ack is for a respin with the check so setting the IO queue too small doesn't kill the driver). Cheers, Ben.