My Chelsio T420-CR is not establishing a fiber OR dac link with my Brocade ICX7150-C12P.
I've examined the `dmesg` output and pared it down to this:
`ethtool --module-info enp1s0f4d1` shows a module is present AND is receiving laser power from the other side. The "Receiver signal average optical power" changes dramatically when I run "no enable" on the switch side. This indicates no swapped cables AND functioning lasers.
I have another ICX7150-C12P connected to a switch, rather than a computer, and both fiber and DAC connections came right online for it.
There doesn't seem to be any real issues I can find that would prevent this from working.
Any thoughts?
I've examined the `dmesg` output and pared it down to this:
Code:
root@pve:~# dmesg | grep cxgb
[ 0.794594] cxgb4 0000:01:00.0: enabling device (0000 -> 0002)
[ 0.794817] cxgb4 0000:01:00.1: enabling device (0000 -> 0002)
[ 0.794988] cxgb4 0000:01:00.2: enabling device (0000 -> 0002)
[ 0.795099] cxgb4 0000:01:00.3: enabling device (0000 -> 0002)
[ 0.795231] cxgb4 0000:01:00.4: enabling device (0000 -> 0002)
[ 0.810178] cxgb4 0000:01:00.4: Coming up as MASTER: Initializing adapter
[ 1.867522] cxgb4 0000:01:00.4: Direct firmware load for cxgb4/t4-config.txt failed with error -2
[ 2.755444] cxgb4 0000:01:00.4: Successfully configured using Firmware Configuration File "Firmware Default", version 0x0, computed checksum 0x0
[ 2.817266] cxgb4 0000:01:00.4: max_ordird_qp 21 max_ird_adapter 387072
[ 2.829263] cxgb4 0000:01:00.4: Current filter mode/mask 0x32b:0x21
[ 2.854205] cxgb4 0000:01:00.4: 116 MSI-X vectors allocated, nic 32 eoqsets 0 per uld 16 mirrorqsets 2
[ 2.854211] cxgb4 0000:01:00.4: 32.000 Gb/s available PCIe bandwidth (5.0 GT/s PCIe x8 link)
[ 2.863580] cxgb4 0000:01:00.4 eth0: Chelsio T420-CR 1G/10GBASE-SFP
[ 2.863740] cxgb4 0000:01:00.4 eth1: Chelsio T420-CR 1G/10GBASE-SFP
[ 2.863772] cxgb4 0000:01:00.4: Chelsio T420-CR rev 2
[ 2.863773] cxgb4 0000:01:00.4: S/N: PT38120834, P/N: 110112040F0
[ 2.863773] cxgb4 0000:01:00.4: Firmware version: 1.27.5.0
[ 2.863774] cxgb4 0000:01:00.4: Bootstrap version: 255.255.255.255
[ 2.863775] cxgb4 0000:01:00.4: TP Microcode version: 0.1.9.4
[ 2.863776] cxgb4 0000:01:00.4: No Expansion ROM loaded
[ 2.863776] cxgb4 0000:01:00.4: Serial Configuration version: 0x4271203
[ 2.863777] cxgb4 0000:01:00.4: VPD version: 0x1
[ 2.863777] cxgb4 0000:01:00.4: Configuration: RNIC MSI-X, Offload capable
[ 2.878360] cxgb4 0000:01:00.4 enp1s0f4: renamed from eth0
[ 2.891301] cxgb4 0000:01:00.4 enp1s0f4d1: renamed from eth1
[ 7.385773] cxgb4 0000:01:00.4 enp1s0f4: entered promiscuous mode
[ 7.388281] cxgb4 0000:01:00.4 enp1s0f4: port module unplugged
[ 7.770280] cxgb4 0000:01:00.4 enp1s0f4d1: entered promiscuous mode
[ 7.774325] cxgb4 0000:01:00.4 enp1s0f4d1: SR module inserted`ethtool --module-info enp1s0f4d1` shows a module is present AND is receiving laser power from the other side. The "Receiver signal average optical power" changes dramatically when I run "no enable" on the switch side. This indicates no swapped cables AND functioning lasers.
Code:
Laser output power : 0.5483 mW / -2.61 dBm
Receiver signal average optical power : 0.6622 mW / -1.79 dBmI have another ICX7150-C12P connected to a switch, rather than a computer, and both fiber and DAC connections came right online for it.
There doesn't seem to be any real issues I can find that would prevent this from working.
Any thoughts?