I have  tested with the “./app/iscsi_tgt/iscsi_tgt   -m 0x101” many times but now I am getting this error on both of my test systems. Something has changed?


tgt_node.c: 700:spdk_iscsi_tgt_node_construct: *ERROR*: Could not construct SCSI device

tgt_node.c: 966:spdk_cf_add_iscsi_tgt_node: *ERROR*: tgt_node1: add_iscsi_target_node error

tgt_node.c: 992:spdk_iscsi_init_tgt_nodes: *ERROR*: spdk_cf_add_iscsi_tgt_node() failed

iscsi_subsystem.c: 984:spdk_iscsi_init: *ERROR*: spdk_iscsi_init_tgt_nodes() failed

subsystem.c: 119:spdk_subsystem_init_next: *ERROR*: Init subsystem iscsi failed



my /usr/local/etc/spdk/iscsi.conf contents:






TransportID "trtype:PCIe traddr:0000:04:00.0" Nvme0

TransportID "trtype:PCIe traddr:0000:05:00.0" Nvme1


  # If 'Yes', iscsi will automatically unbind the kernel NVMe driver from

  # discovered devices and rebind it to the uio driver.

  UnbindFromKernel Yes

  # The following two arguments allow the user to partition NVMe namespaces

  # into multiple LUNs

  NvmeLunsPerNs 2

  LunSizeInMB 1024

  # The number of attempts per I/O when an I/O fails. Do not include

  # this key to get the default behavior.

  RetryCount 4

  # The maximum number of NVMe controllers to claim. Do not include this key to

  # claim all of them.

  #NumControllers 1




#  Comment "Disk 1"

  TargetName disk1

  TargetAlias "Data Disk1"

  Mapping PortalGroup1 InitiatorGroup1

  AuthMethod Auto

  AuthGroup AuthGroup1

  UseDigest Auto

  LUN0 Nvme0

  LUN1 Nvme1

QueueDepth 128



My systems has these devices before I ran scripts/setup.sh

[root@host1]# ls -l /dev/*nv*

crw------- 1 root root 248,   0 Jun 30 11:44 /dev/nvme0

brw-rw---- 1 root disk 259,   0 Jun 30 11:44 /dev/nvme0n1

crw------- 1 root root 248,   1 Jun 30 11:44 /dev/nvme1

brw-rw---- 1 root disk 259,   1 Jun 30 11:44 /dev/nvme1n1

crw------- 1 root root  10, 144 Jun 29 18:31 /dev/nvram