What is a "block CQ"?
There is no such thing... Also, this has no difference
if a block/file/whatever is using the rdma cq.
The naming should really be something like rdma_dim as it accounts
for completions and not bytes/packets.
Sagi,
I think that in the future we could use it in nvme since there is an
option to set the interrupt coalescing in NVMe spec.
This might improve performance for NVMe driver.
That would require changing the spec to make moderation config per-queue
and not controller-wide. This does not apply specifically to block so
naming it with blk does not make sense.
Overall, I think its a great idea to add that to the rdma subsystem
but we cannot make it the default and especially without being able
to turn it off. So this needs to be opt in with a sysctl option.
We can add flag in create_cq command that will
try_coalescing_is_possible instead of module parameter of course.
Storage ULPs can set it to True.
The point is that it can't be universally on.
Also in the internal review Yamin added a table that summarize all the
testing that were done using NVMeoF (I guess it somehow didn't get to
this RFC).
I guess we can do the same for iSER to get more confidence and then set
both to create modifiable cq (if HCA supports, of course).
Agreed ?
Sure.
