Hi Team,I am using N6001 with Intel OFS (OFS PCIe Attach) . I wanted to test data transfer from Host1 to Host2 as below.Host1 -> N6001(Port0) -> OtherNIC(Port0) -> Host2.Is there any sample application available in OPAE/OFS which performs this transaction? Can you please suggest.In addition to above query, I wants to know how HE-HSSI sends data to QSFP?. The hssi application shows "No eth interface, so not honoring --eth-loopback". ( https://ofs.github.io/ofs-2024.1-1/hw/n6001/user_guides/ug_qs_ofs_n6001/ug_qs_ofs_n6001/ Section 7. Send traffic through the 10G AFU). Does this mean the HE_HSSI will not communicate with E-Tile or QSFPs (FIM) ?Do I need to enable any parameters to pass over QSFPs?Thankyou.

Hi,From the screenshot provided, you enable the loopback on your HSSI testing. You will need to disable to loopback if you are communicating between 2 boards.You may refer to https://ofs.github.io/ofs-2024.2-1/sw/fpga_tools/hssi/hssi/#description on the argument available.Thanks.

Hi @JohnT_Intel ,Thanks for the update.I will test and update the same.In addition to my queries, whether the ice driver will list any interface in Host for N6001? So that interface will list under 'ip a'/'ifconfig'. With this interface, can I create any application to send and receive packets from board to board without HSSI in-built application?. Is it possible to run DPDK application in this FIM?Best regards,Ayshathul Thuhara

Hi,Currently there is no way to run DPDK on this design as it. We do not have application or driver for it to show in the OS level such ipconfig command.

Hi @JohnT_Intel ,I hope you’re doing well. I’ve noticed that there’s an IFPGA driver in DPDK designed for the N6000 & N3000. Would it be feasible to port this driver for the N6001 design with minimal modifications?Thank you for your insights!

Hi,Unfortunately that is not possible. The reason is that the DPDK is communicating to the E810 NIC controller directly through PCIe x4 interface.Thanks.John Tio

OFS : Data Path of QSFP from HE_HSSI

44 Replies

JohnT_Altera
Regular Contributor
11 months ago
Hi,

May I know if you have any other queries?
JohnT_Altera
Regular Contributor
12 months ago
Hi,

I do not have issue on clearing the HSSI STAT from my side.

Below is my logging.

pggae@pggae-PowerEdge-R740:~$ sudo hssistats
Namespace(pcie_address=None, clear=False)
sbdf: 0000:d8:00.0
FPGA dev: {'segment': 0, 'bus': 216, 'dev': 0, 'func': 0, 'path': '/sys/class/fpga_region/region0', 'pcie_address': '0000:d8:00.0'}
args.hssi_grps[('dfl_dev.3', ['/sys/bus/pci/devices/0000:d8:00.0/fpga_region/region0/dfl-fme.0/dfl_dev.3/uio/uio0'], '0000:d8:00.0', 21)]
fpga uio dev:dfl_dev.3

--------HSSI INFO START-------
DFH :0x3000000010002015
HSSI ID :0x15
DFHv :0.5
guidl :0x99a078ad18418b9d
guidh :0x4118a7cbd9db4a9b
HSSI version :1.0
Firmware Version :1
HSSI num ports :2
Port0 :100GCAUI-4
Port4 :100GCAUI-4
--------HSSI INFO END-------

HSSI num ports: 2
HSSI Ports | port:0| port:4|

tx_packets | 102| 0|
rx_packets | 0| 102|
rx_crc_errors | 0| 0|
rx_align_errors | 0| 0|
tx_payload_bytes | 7646| 0|
rx_payload_bytes | 0| 7646|
tx_pause | 0| 0|
rx_pause | 0| 0|
rx_errors | 0| 0|
tx_errors | 0| 0|
rx_unicast | 0| 102|
rx_multicast | 0| 0|
rx_broadcast | 0| 0|
tx_discards | 0| 0|
tx_unicast | 102| 0|
tx_multicast | 0| 0|
tx_broadcast | 0| 0|
ether_drops | 0| 0|
rx_total_bytes | 0| 7826|
rx_total_packets | 0| 102|
rx_undersize | 0| 0|
rx_oversize | 0| 92|
rx_64_bytes | 0| 1|
rx_65_127_bytes | 0| 1|
rx_128_255_bytes | 0| 1|
rx_256_511_bytes | 0| 0|
rx_512_1023_bytes | 0| 3|
rx_1024_1518_bytes | 0| 4|
rx_gte_1519_bytes | 0| 0|
rx_jabbers | 0| 0|
rx_runts | 0| 0|
pggae@pggae-PowerEdge-R740:~$ sudo hssistats clear
usage: hssistats [-h] [--pcie-address PCIE_ADDRESS] [--clear]
hssistats: error: unrecognized arguments: clear
pggae@pggae-PowerEdge-R740:~$ sudo hssistats --clear
Namespace(pcie_address=None, clear=True)
sbdf: 0000:d8:00.0
FPGA dev: {'segment': 0, 'bus': 216, 'dev': 0, 'func': 0, 'path': '/sys/class/fpga_region/region0', 'pcie_address': '0000:d8:00.0'}
args.hssi_grps[('dfl_dev.3', ['/sys/bus/pci/devices/0000:d8:00.0/fpga_region/region0/dfl-fme.0/dfl_dev.3/uio/uio0'], '0000:d8:00.0', 21)]
fpga uio dev:dfl_dev.3

--------HSSI INFO START-------
DFH :0x3000000010002015
HSSI ID :0x15
DFHv :0.5
guidl :0x99a078ad18418b9d
guidh :0x4118a7cbd9db4a9b
HSSI version :1.0
Firmware Version :1
HSSI num ports :2
Port0 :100GCAUI-4
Port4 :100GCAUI-4
--------HSSI INFO END-------

HSSI num ports: 2
HSSI stats clearing ...
HSSI stats cleared
pggae@pggae-PowerEdge-R740:~$ sudo hssistats
Namespace(pcie_address=None, clear=False)
sbdf: 0000:d8:00.0
FPGA dev: {'segment': 0, 'bus': 216, 'dev': 0, 'func': 0, 'path': '/sys/class/fpga_region/region0', 'pcie_address': '0000:d8:00.0'}
args.hssi_grps[('dfl_dev.3', ['/sys/bus/pci/devices/0000:d8:00.0/fpga_region/region0/dfl-fme.0/dfl_dev.3/uio/uio0'], '0000:d8:00.0', 21)]
fpga uio dev:dfl_dev.3

--------HSSI INFO START-------
DFH :0x3000000010002015
HSSI ID :0x15
DFHv :0.5
guidl :0x99a078ad18418b9d
guidh :0x4118a7cbd9db4a9b
HSSI version :1.0
Firmware Version :1
HSSI num ports :2
Port0 :100GCAUI-4
Port4 :100GCAUI-4
--------HSSI INFO END-------

HSSI num ports: 2
HSSI Ports | port:0| port:4|

tx_packets | 0| 0|
rx_packets | 0| 0|
rx_crc_errors | 0| 0|
rx_align_errors | 0| 0|
tx_payload_bytes | 0| 0|
rx_payload_bytes | 0| 0|
tx_pause | 0| 0|
rx_pause | 0| 0|
rx_errors | 0| 0|
tx_errors | 0| 0|
rx_unicast | 0| 0|
rx_multicast | 0| 0|
rx_broadcast | 0| 0|
tx_discards | 0| 0|
tx_unicast | 0| 0|
tx_multicast | 0| 0|
tx_broadcast | 0| 0|
ether_drops | 0| 0|
rx_total_bytes | 0| 0|
rx_total_packets | 0| 0|
rx_undersize | 0| 0|
rx_oversize | 0| 0|
rx_64_bytes | 0| 0|
rx_65_127_bytes | 0| 0|
rx_128_255_bytes | 0| 0|
rx_256_511_bytes | 0| 0|
rx_512_1023_bytes | 0| 0|
rx_1024_1518_bytes | 0| 0|
rx_gte_1519_bytes | 0| 0|
rx_jabbers | 0| 0|
rx_runts | 0| 0|
JohnT_Altera
Regular Contributor
12 months ago
Hi,
Attach is the screenshot
- attdoner
  New Contributor
  12 months ago
  Hi @JohnT_Intel ,
  Can you provide the programming log of 100g. I want to cross verify the method of programming, to check whether I missed out any steps. I was not able to get the above log prints in 100g. Instead it used to get mbox_write
JohnT_Altera
Regular Contributor
12 months ago
Hi,

Below is what I observed.
- attdoner
  New Contributor
  12 months ago
  Hi @JohnT_Intel ,
  Can you please reshare the image.
  The image is not able to view.
JohnT_Altera
Regular Contributor
12 months ago
Hi,

I have try the bin file that you provided and I do not observed the mbox error that you mention.
- attdoner
  New Contributor
  12 months ago
  Hi @JohnT_Intel ,
  Can you please share the output of 100g using below command
  sudo hssi hssi_100g
omprasad
New Contributor
12 months ago
Subscribing for the same
JohnT_Altera
Regular Contributor
12 months ago
Hi,

I observed that you are sharing .pof file. Can you share .bin file that I can directly load into the board?
- attdoner
  New Contributor
  12 months ago
  Hi @JohnT_Intel ,
  The .bin files : https://drive.google.com/file/d/1PdiDg2SX70VpYdDg1G5l46wRGfkmc9a5/view?usp=sharing
JohnT_Altera
Regular Contributor
12 months ago
Hi,

Can you share with me your bitstream?
- attdoner
  New Contributor
  12 months ago
  Hi @JohnT_Intel ,
  I had attahced the bitstream generated using this command "./ofs-common/scripts/common/syn/build_top.sh --ofss tools/ofss_config/hssi/hssi_2x100.ofss n6001 work_n6001"
  https://drive.google.com/file/d/1Vz35lGX3VPandzAgsU8NGwGR-9Z6ItOw/view?usp=sharing
  Please let us know any update on this
JohnT_Altera
Regular Contributor
12 months ago
Hi,

It will be limited due to traffic generator. When you have too much packet to sent, it is impacting the traffic generator to generate the packet needed.
- attdoner
  New Contributor
  12 months ago
  Hi @JohnT_Intel ,
  
  With your previous reply "
  Unfortunately we do not have the design for the 100G. You will need to build the FIM with this command "./ofs-common/scripts/common/syn/build_top.sh --ofss tools/ofss_config/hssi/hssi_2x100.ofss n6001 work_n6001"
  "
  I had tried this command , and I face the below issue.
  sudo hssi hssi_100g
  100G loopback test
  port: 0
  eth_loopback: on
  num_packets: 1
  gap: none
  src_address: 11:22:33:44:55:66
  (bits): 0x112233445566
  dest_address: 77:88:99:aa:bb:cc
  (bits): 0x778899aabbcc
  pattern: random
  start size: 40
  end size: 2580
  end select: pkt_num
  eth:
  continuous mode: off
  monitor duration: 0 sec
  No eth interface, so not honoring --eth-loopback. Try using the hssiloopback command instead.
  mbox_write timed out [a]
JohnT_Altera
Regular Contributor
12 months ago
Hi,

Unfortunately we do not have the design for the 100G. You will need to build the FIM with this command "./ofs-common/scripts/common/syn/build_top.sh --ofss tools/ofss_config/hssi/hssi_2x100.ofss n6001 work_n6001"

Thanks.
- attdoner
  New Contributor
  12 months ago
  Hi @JohnT_Intel ,
  Thanks for the update, I will compile and get back to you.
  
  Meanwhile, with 10g_hssi tests, I could see throughput difference.
  
  TX Packet Count (N6001) TX Throughput(N6001) GB/s
  1 25.7812
  50 16.0559
  500 15.5692
  5000 15.5638
  50000 15.5708
  500000 15.5693
  5000000 15.5692
  9586980 15.5652
  9586981 6.96E-07
  10000000 0.643037
  1000000000 0.177615
  As packet count increases, the throughput decreases. In above table,
  For Packet Count 1: The TX throughput = 25Gbps
  For Packet Count 50: The TX throughput = 16.05Gbps
  Can I know why the "throughput" values are lesser for higher packet counts?

Forum Discussion

OFS : Data Path of QSFP from HE_HSSI

44 Replies

Recent Discussions

This is a test post

Agilex 7 M series Open FPGA Stack support

Deprecation Notice for FPGA Support Package for oneAPI DPC++/C++. What is the alternative?

Agilex 7 I-Series "aocl diagnose acl0" error following OFS

OneAPI Support for Agilex 5 and 7 Development Kits

TX Packet Count (N6001)	TX Throughput(N6001) GB/s
1	25.7812
50	16.0559
500	15.5692
5000	15.5638
50000	15.5708
500000	15.5693
5000000	15.5692
9586980	15.5652
9586981	6.96E-07
10000000	0.643037
1000000000	0.177615