Re: [driver-core PATCH v6 9/9] libnvdimm: Schedule device registration on node local to the device

From: Bart Van Assche
Date: Tue Nov 27 2018 - 16:22:32 EST

On Tue, 2018-11-27 at 12:50 -0800, Dan Williams wrote:
+AD4 Thanks Bart, so tying this back to Alex's patches, does the ordering
+AD4 problem that Alex's patches solve impact the SCSI case? I'm looking
+AD4 for something like +ACI-SCSI depends on asynchronous probing and without
+AD4 'driver core: Establish clear order of operations for deferred probe
+AD4 and remove' probing is often needlessly serialized+ACI. I.e. does it
+AD4 suffer from the same platform problem that libnvdimm ran into where
+AD4 it's local async probing implementation was hindered by the driver
+AD4 core?


Hi Dan,

Patch 6/9 reduces the time needed to scan SCSI LUNs significantly. The only
way to realize that speedup is by enabling more concurrency. That's why I
think that patch 6/9 is a significant driver core improvement.