Re: [PATCH 4/4] scsi: core: don't limit per-LUN queue depth for SSD

[Sumanesh Samanta <sumanesh.samanta@broadcom.com>]

>Ordinarily I'd prefer a host template attribute as Sumanesh proposed,
>but I dislike wrapping the examination of that and the queue flag in
>a macro that makes it not obvious how the behavior is affected.

I think we can have a host template attribute and discard this check
altogether, that is not check device_busy for both SDD and HDDs.

As both you and Hannes mentioned, this change affects high end controllers
most, and most of them have some storage IO size limit. Also, for HDD
sequential IO is almost always large and
touch the controller max IO size limit. Thus, I am not sure merge matters
for these kind of controllers. Database use REDO log and small sequential
IO, but those are targeted to SSDs, where latency and IOPs are far more
important than IO merging.
If this patch is opt-in for drivers, so any LLD that cannot take advantage
of the flag need not set it, and would work as-is


Thanks,
Sumanesh