Instead of waiting until the first listen address is added, create a protection domain and a memory map for every RDMA device in the system. This consumes more resources when there are RDMA devices that aren't used by the target, but it will simplify some order of operations issues when listen addresses and poll groups are added and removed at run time. Change-Id: Idfe6f8307decbf19e02765dbf67f03c2510a328f Signed-off-by: Ben Walker <benjamin.walker@intel.com> Reviewed-on: https://review.gerrithub.io/422602 Tested-by: SPDK CI Jenkins <sys_sgci@intel.com> Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com> Reviewed-by: Seth Howell <seth.howell5141@gmail.com> Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com> Reviewed-by: Jim Harris <james.r.harris@intel.com> |
||
---|---|---|
.. | ||
ctrlr_bdev.c | ||
ctrlr_discovery.c | ||
ctrlr.c | ||
Makefile | ||
nvmf_fc.h | ||
nvmf_internal.h | ||
nvmf.c | ||
rdma.c | ||
request.c | ||
subsystem.c | ||
transport.c | ||
transport.h |