Generally I think it is good, but I think it should be set higher, after the "softc->quirks |= DA_Q_NO_6_BYTE;" line.
Tue, Sep 17
Add new line after sentence.
Nope, I'm not sure why this was not closed when it got commited.
Create a iflib_txq_drain_bypass() function called only from
iflib_if_transmit_bypass() which doesn't have the loop,
volatile/devolatile casts, conditional prefetching, txq-cast-to-mbuf,
etc overhead and only locks/unlocks once.
Very useful, and good generalization of shm_open(SHM_ANON) and memfd_create().
Fixed in rP440218
net/ceph is 12.2.7 now. Do we still need have this open?
Do you have a PR to inform the maintainer?
Both remarks seem reasonable to me. I wasn’t going to drop this in the tree without circulating the idea past net@ at a minimum 😀. But I wanted some feedback from a smaller audience first— thank you both.
Is there a PR to inform the maintainer?
Sorry, one last thing to confirm, is firstname.lastname@example.org also your email address?
Uncrappy is nice. But if we've got lock contention, it would be nice to know why.
- Tweaked wording -- memfd_create objects *must* (not can) be adjusted via ftruncate, otherwise they're unusable.