DPDK testpmd with E823 link status is down
JackyCT.Chen
JackyCT.Chen at advantech.com.tw
Tue Apr 2 09:05:11 CEST 2024
Hi Zhichao,
Do you have any update /comment ?
Reply and Discussion related to Intel IPS Case (No. 00867743) recently .
Peter
(2024-03-25)
1. i don't think that's fw issue, dpdk modification is more easily path. backend team are working on it.
2. if dpdk will fix this issue, i can't provide schedule since i'm not in dpdk team.
Chen Jacky
(2024-03-25)
Hi Peter ,
1.According to your reply 03/19 " we have to wait for backend team conclusion. " , Currently what's progression of "the fw issue or not" ?
2. "Intel will list the known bug in release note. When the known bug be removed from release note, it means it has been fixed."
Does it mean this known bug will list at new E823 LEK "next release" ? Could you give us detail schedule ? .. .2024/03/E or 2024/06/E or other date.
Thanks a lot!
Peter
(2024-03-20)
Hi, customer,
since dpdk used different way to check link status compare to ice, in kernel ice driver, there is no this issue.
as mao mentioned, we can't confirm that's fw issue. we have to wait for backend team conclusion.
Mao
(2024-03-18)
Q1. It's not confirmed as a FW issue or not.
The FW is in LEK.
Q2. There is conclusion for the issue yet. It's hard to tell when it will be fixed.
Q3 Intel doesn't include any issue fixed information in release note. Intel will list the known bug in release note. When the known bug be removed from release note, it means it has been fixed.
Thanks a lot!
Best Regards,
JackyCT.Chen
x86 Software | Cloud-IoT Group | Advantech Co., Ltd.
02-2792-7818 Ext. 1194
From: JackyCT.Chen
Sent: Friday, March 15, 2024 10:23 AM
To: Zeng, ZhichaoX <zhichaox.zeng at intel.com>; Jason.Hsu <Jason.Hsu at advantech.com.tw>; Chang, Howard C <howard.c.chang at intel.com>
Cc: Amy.Shih <Amy.Shih at advantech.com.tw>; Leo66.Wang <Leo66.Wang at advantech.com.tw>; dev at dpdk.org; Cui, KaixinX <kaixinx.cui at intel.com>
Subject: RE: DPDK testpmd with E823 link status is down
Hi Zhichao,
Do you have any update ?
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Other discussion from Intel IPS Case No. 00867743 ~
[Intel internal sync - between DPDK forum and DPDK IPS case discussion]
Something “the firmware issue “ need you sync with Intel IPS ticket (#00867743) owner – Mao and Howard
It really need your help . thanks a lot!
Mao
Intel Technical Specialist
[mhsieh 03/14/2024 07:37:47]
Dear Customer,
Does Advantech see the similar issue with the kernel driver?
Since I don't get such FW issue, please check with the person who provided the DPDK patch for the following up if v3.36 NVM still see the issue.
He (Mao) said he does NOT hear such FW issue . could you sync this sync that you think with Mao or Howard ?
Hope let it CLOSED this issue more speedily and quickly .
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Meantime, we will arrange to do the same experiment on LEK v3.36 which Howard and Mao 's suggestion recently.
Thanks a lot!
Best Regards,
JackyCT.Chen
x86 Software | Cloud-IoT Group | Advantech Co., Ltd.
02-2792-7818 Ext. 1194
From: Jason.Hsu <Jason.Hsu at advantech.com.tw<mailto:Jason.Hsu at advantech.com.tw>>
Sent: Monday, March 11, 2024 4:26 PM
To: Chang, Howard C <howard.c.chang at intel.com<mailto:howard.c.chang at intel.com>>; Zeng, ZhichaoX <zhichaox.zeng at intel.com<mailto:zhichaox.zeng at intel.com>>; JackyCT.Chen <JackyCT.Chen at advantech.com.tw<mailto:JackyCT.Chen at advantech.com.tw>>
Cc: Amy.Shih <Amy.Shih at advantech.com.tw<mailto:Amy.Shih at advantech.com.tw>>; Leo66.Wang <Leo66.Wang at advantech.com.tw<mailto:Leo66.Wang at advantech.com.tw>>; dev at dpdk.org<mailto:dev at dpdk.org>; Cui, KaixinX <kaixinx.cui at intel.com<mailto:kaixinx.cui at intel.com>>
Subject: RE: DPDK testpmd with E823 link status is down
Hi Howard,
The IPS Case No : 00867743, kindly help to check it and sharing related schedule info for ref., TKS.
Best regards,
Jason Hsu 許文偉
Product Manager | ICVG-ENPD | Advantech Co., Ltd.
Tel: +886 2 2792-7818 ext.1602 | Mobile: +886 920-125-625 | Fax: +886 2 2794-7336
www.advantech.com<http://www.advantech.com/> I jason.hsu at advantech.com.tw<mailto:jason.hsu at advantech.com.tw>
[Advantech ENPD]<https://campaign.advantech.online/en/Cloud-IoT/uCPE/>
From: Jason.Hsu
Sent: Thursday, March 7, 2024 5:29 PM
To: Chang, Howard C <howard.c.chang at intel.com<mailto:howard.c.chang at intel.com>>; Zeng, ZhichaoX <zhichaox.zeng at intel.com<mailto:zhichaox.zeng at intel.com>>; JackyCT.Chen <JackyCT.Chen at advantech.com.tw<mailto:JackyCT.Chen at advantech.com.tw>>
Cc: Amy.Shih <Amy.Shih at advantech.com.tw<mailto:Amy.Shih at advantech.com.tw>>; Leo66.Wang <Leo66.Wang at advantech.com.tw<mailto:Leo66.Wang at advantech.com.tw>>; dev at dpdk.org<mailto:dev at dpdk.org>; Cui, KaixinX <kaixinx.cui at intel.com<mailto:kaixinx.cui at intel.com>>
Subject: RE: DPDK testpmd with E823 link status is down
Hi Howard,
As discussed, the issue need to have a IPS ticket for keep following up in next, so we will try to issue it and update the no. soon, TKS.
Best regards,
Jason Hsu 許文偉
Product Manager | ICVG-ENPD | Advantech Co., Ltd.
Tel: +886 2 2792-7818 ext.1602 | Mobile: +886 920-125-625 | Fax: +886 2 2794-7336
www.advantech.com<http://www.advantech.com/> I jason.hsu at advantech.com.tw<mailto:jason.hsu at advantech.com.tw>
[Advantech ENPD]<https://campaign.advantech.online/en/Cloud-IoT/uCPE/>
From: Jason.Hsu
Sent: Tuesday, March 5, 2024 10:07 AM
To: Chang, Howard C <howard.c.chang at intel.com<mailto:howard.c.chang at intel.com>>; Zeng, ZhichaoX <zhichaox.zeng at intel.com<mailto:zhichaox.zeng at intel.com>>; JackyCT.Chen <JackyCT.Chen at advantech.com.tw<mailto:JackyCT.Chen at advantech.com.tw>>
Cc: Amy.Shih <Amy.Shih at advantech.com.tw<mailto:Amy.Shih at advantech.com.tw>>; Leo66.Wang <Leo66.Wang at advantech.com.tw<mailto:Leo66.Wang at advantech.com.tw>>; dev at dpdk.org<mailto:dev at dpdk.org>; Cui, KaixinX <kaixinx.cui at intel.com<mailto:kaixinx.cui at intel.com>>
Subject: RE: DPDK testpmd with E823 link status is down
Hi Howard,
Could you help to check this DPDK testing issue and comments the estimated schedule for next FW ver. release to fix it?
Best regards,
Jason Hsu 許文偉
Product Manager | ICVG-ENPD | Advantech Co., Ltd.
Tel: +886 2 2792-7818 ext.1602 | Mobile: +886 920-125-625 | Fax: +886 2 2794-7336
www.advantech.com<http://www.advantech.com/> I jason.hsu at advantech.com.tw<mailto:jason.hsu at advantech.com.tw>
[Advantech ENPD]<https://campaign.advantech.online/en/Cloud-IoT/uCPE/>
From: JackyCT.Chen <JackyCT.Chen at advantech.com.tw<mailto:JackyCT.Chen at advantech.com.tw>>
Sent: Friday, March 1, 2024 6:25 PM
To: Zeng, ZhichaoX <zhichaox.zeng at intel.com<mailto:zhichaox.zeng at intel.com>>
Cc: Amy.Shih <Amy.Shih at advantech.com.tw<mailto:Amy.Shih at advantech.com.tw>>; Jason.Hsu <Jason.Hsu at advantech.com.tw<mailto:Jason.Hsu at advantech.com.tw>>; Leo66.Wang <Leo66.Wang at advantech.com.tw<mailto:Leo66.Wang at advantech.com.tw>>; dev at dpdk.org<mailto:dev at dpdk.org>; Cui, KaixinX <kaixinx.cui at intel.com<mailto:kaixinx.cui at intel.com>>
Subject: RE: DPDK testpmd with E823 link status is down
Hi Zhichao,
Do you have any update ?
Q: As you said “We are tracking this issue, it is a firmware issue that has been reported to the hardware team and the fix will take some time.“
Could you descript more detail ?
2-1 The “firmware issue” that mean the LEK firmware-version: 3.26 0x8001b733 1.3429.0 of the Intel NIC - E823 has some question or not ?
2-2 When it will release new E823 LEK that fix link status/speed issue ?
2-3 Where we could get the new E823 LEK that fix link status/speed issue ?.. Content ID # of Intel RDC .
We look forward to receiving your reply . 😊
Thanks your help !
Best Regards,
JackyCT.Chen
x86 Software | Cloud-IoT Group | Advantech Co., Ltd.
02-2792-7818 Ext. 1194
From: JackyCT.Chen
Sent: Friday, February 16, 2024 4:26 PM
To: Zeng, ZhichaoX <zhichaox.zeng at intel.com<mailto:zhichaox.zeng at intel.com>>
Cc: Amy.Shih <Amy.Shih at advantech.com.tw<mailto:Amy.Shih at advantech.com.tw>>; Jason.Hsu <Jason.Hsu at advantech.com.tw<mailto:Jason.Hsu at advantech.com.tw>>; Leo66.Wang <Leo66.Wang at advantech.com.tw<mailto:Leo66.Wang at advantech.com.tw>>; dev at dpdk.org<mailto:dev at dpdk.org>; Cui, KaixinX <kaixinx.cui at intel.com<mailto:kaixinx.cui at intel.com>>
Subject: RE: DPDK testpmd with E823 link status is down
Hi Zhichao,
1. This workaround in ICE_PMD which change the “no wait” to “wait_to_complete” ==> it seemed workable .
When we run testpmd on E823 port0/1 , it got “link status : up and link speed : 10 Gbps” as below (Detail see attached file)
testpmd> show port summary all
Number of available ports: 2
Port MAC Address Name Driver Status Link
0 00:00:00:00:01:00 89:00.0 net_ice up 10 Gbps
1 00:00:00:00:01:01 89:00.1 net_ice up 10 Gbps
1. As you said “We are tracking this issue, it is a firmware issue that has been reported to the hardware team and the fix will take some time.“
Could you descript more detail ?
2-1 The “firmware issue” that mean the LEK firmware-version: 3.26 0x8001b733 1.3429.0 of the Intel NIC - E823 has some question or not ?
2-2 When it will release new E823 LEK that fix link status/speed issue ?
2-3 Where we could get the new E823 LEK that fix link status/speed issue ?.. Content ID # of Intel RDC .
We look forward to receiving your reply . 😊
Thanks your help !
Best Regards,
JackyCT.Chen
x86 Software | Cloud-IoT Group | Advantech Co., Ltd.
02-2792-7818 Ext. 1194
From: Zeng, ZhichaoX <zhichaox.zeng at intel.com<mailto:zhichaox.zeng at intel.com>>
Sent: Tuesday, February 6, 2024 11:24 AM
To: JackyCT.Chen <JackyCT.Chen at advantech.com.tw<mailto:JackyCT.Chen at advantech.com.tw>>
Cc: Amy.Shih <Amy.Shih at advantech.com.tw<mailto:Amy.Shih at advantech.com.tw>>; Jason.Hsu <Jason.Hsu at advantech.com.tw<mailto:Jason.Hsu at advantech.com.tw>>; Leo66.Wang <Leo66.Wang at advantech.com.tw<mailto:Leo66.Wang at advantech.com.tw>>; dev at dpdk.org<mailto:dev at dpdk.org>; Cui, KaixinX <kaixinx.cui at intel.com<mailto:kaixinx.cui at intel.com>>
Subject: RE: DPDK testpmd with E823 link status is down
Hi JackyCT.Chen:
We are tracking this issue, it is a firmware issue that has been reported to the hardware team and the fix will take some time.
There is a workaround in ICE PMD, change the “no wait” to “wait_to_complete” mode when ice_interrupt_handler() updates the link status in drivers/net/ice/ice_ethdev.c:
#ifdef ICE_LSE_SPT
if (int_fw_ctl & PFINT_FW_CTL_INTEVENT_M) {
PMD_DRV_LOG(INFO, "FW_CTL: link state change event");
ice_handle_aq_msg(dev);
}
#else
if (oicr & PFINT_OICR_LINK_STAT_CHANGE_M) {
PMD_DRV_LOG(INFO, "OICR: link state change event");
- ret = ice_link_update(dev, 0);
+ ret = ice_link_update(dev, 1);
if (!ret)
rte_eth_dev_callback_process
(dev, RTE_ETH_EVENT_INTR_LSC, NULL);
}
#endif
Best Regards
Zhichao
From: JackyCT.Chen <JackyCT.Chen at advantech.com.tw<mailto:JackyCT.Chen at advantech.com.tw>>
Sent: Wednesday, January 31, 2024 6:53 PM
To: Yang, Qiming <qiming.yang at intel.com<mailto:qiming.yang at intel.com>>; dev at dpdk.org<mailto:dev at dpdk.org>
Cc: Shih, Amy <amy.shih at advantech.com.tw<mailto:amy.shih at advantech.com.tw>>; Hsu, Jason <jason.hsu at advantech.com.tw<mailto:jason.hsu at advantech.com.tw>>; Wang, Leo <leo66.wang at advantech.com.tw<mailto:leo66.wang at advantech.com.tw>>
Subject: RE: DPDK testpmd with E823 link status is down
Hi Qiming & dpdk dev team:
This is JackyCT.Chen from Advantech, we have a question about E823 DPDK loopback testpmd ,
Could you please give us some advice?
We bind the E823 and X710 devices with vfio-pci driver and execute the DPDK testpmd . (detail see attached files please)
However, both E823 “link status : down and link speed : None” , we expected that “link status : up and link speed : 10 Gbps” .
Do you have any suggestions?
Testing procedure & result:
Platform : Moro City Reference Planform ICX-D ~ CRB
l On-Board : E823
l Ext-PCIE CARD : PCIE-2230NP-00A1E ( Intel X710 )
OS/Kernel : Debian 12 / kernel 6.1.0-16-amd64 x86_64
DPDK : DPDK 24.03.0-rc0 (from trunk build)
NIC_BDF_INFO :
CRB EXT-PCIE CARD : X710
Port : 10G * 4
firmware-version: 7.10 0x80007b33 255.65535.255
CRB On-BOARD : E823
Port Option : 4x10-4x2.5
firmware-version: 3.26 0x8001b733 1.3429.0
BDF = 91:00.0
---
BDF = 89:00.0
BDF = 91:00.1
---
BDF = 89:00.1
Prepare and config :
root at 5-efi:~# modprobe uio
root at 5-efi:~# modprobe vfio-pci
root at 5-efi:~# echo 2048 > /sys/devices/system/node/node0/hugepages/hugepages-2048kB/nr_hugepages
root at 5-efi:~# mkdir -p /mnt/huge
root at 5-efi:~# mount -t hugetlbfs nodev /mnt/huge
root at 5-efi:~# dpdk-devbind.py -b vfio-pci 91:00.0
root at 5-efi:~# dpdk-devbind.py -b vfio-pci 91:00.1
root at 5-efi:~# dpdk-devbind.py -b vfio-pci 89:00.0
root at 5-efi:~# dpdk-devbind.py -b vfio-pci 89:00.1
LOG :
root at 5-efi:~# dpdk-testpmd -c 0xff -n 4 -a 89:00.0 -a 89:00.1 --socket-mem=256 -- -i --mbcache=512 --socket-num=0 --coremask=0xc --nb-cores=2 --rxq=1 --txq=1 --portmask=0xf --rxd=4096 --rxfreet=128 --rxpt=128 --rxht=8 --rxwt=0 --txd=4096 --txfreet=128 --txpt=128 --txht=0 --txwt=0 --burst=64 --txrst=64 --rss-ip -a
EAL: Detected CPU lcores: 24
EAL: Detected NUMA nodes: 1
EAL: Detected static linkage of DPDK
EAL: Multi-process socket /var/run/dpdk/rte/mp_socket
EAL: Selected IOVA mode 'VA'
EAL: VFIO support initialized
EAL: Using IOMMU type 1 (Type 1)
EAL: Ignore mapping IO port bar(1)
EAL: Ignore mapping IO port bar(4)
EAL: Probe PCI driver: net_ice (8086:188a) device: 0000:89:00.0 (socket 0)
ice_dev_init(): Failed to read device serial number
ice_load_pkg_type(): Active package is: 1.3.35.0, ICE OS Default Package (double VLAN mode)
EAL: Ignore mapping IO port bar(1)
EAL: Ignore mapping IO port bar(4)
EAL: Probe PCI driver: net_ice (8086:188a) device: 0000:89:00.1 (socket 0)
ice_dev_init(): Failed to read device serial number
ice_load_pkg_type(): Active package is: 1.3.35.0, ICE OS Default Package (double VLAN mode)
TMTY: TELEMETRY: No legacy callbacks, legacy socket not created
Interactive-mode selected
previous number of forwarding cores 1 - changed to number of configured cores 2
Auto-start selected
testpmd: create a new mbuf pool <mb_pool_0>: n=262144, size=2176, socket=0
testpmd: preferred mempool ops selected: ring_mp_mc
Configuring Port 0 (socket 0)
ice_set_rx_function(): Using AVX2 Vector Rx (port 0).
Port 0: 00:00:00:00:01:00
Configuring Port 1 (socket 0)
ice_set_rx_function(): Using AVX2 Vector Rx (port 1).
Port 1: 00:00:00:00:01:01
Checking link statuses...
Done
Start automatic packet forwarding
io packet forwarding - ports=2 - cores=2 - streams=2 - NUMA support enabled, MP allocation mode: native
Logical Core 2 (socket 0) forwards packets on 1 streams:
RX P=0/Q=0 (socket 0) -> TX P=1/Q=0 (socket 0) peer=02:00:00:00:00:01
Logical Core 3 (socket 0) forwards packets on 1 streams:
RX P=1/Q=0 (socket 0) -> TX P=0/Q=0 (socket 0) peer=02:00:00:00:00:00
io packet forwarding packets/burst=64
nb forwarding cores=2 - nb forwarding ports=2
port 0: RX queue number: 1 Tx queue number: 1
Rx offloads=0x0 Tx offloads=0x10000
RX queue: 0
RX desc=4096 - RX free threshold=128
RX threshold registers: pthresh=0 hthresh=0 wthresh=0
RX Offloads=0x0
TX queue: 0
TX desc=4096 - TX free threshold=128
TX threshold registers: pthresh=128 hthresh=0 wthresh=0
TX offloads=0x10000 - TX RS bit threshold=64
port 1: RX queue number: 1 Tx queue number: 1
Rx offloads=0x0 Tx offloads=0x10000
RX queue: 0
RX desc=4096 - RX free threshold=128
RX threshold registers: pthresh=0 hthresh=0 wthresh=0
RX Offloads=0x0
TX queue: 0
TX desc=4096 - TX free threshold=128
TX threshold registers: pthresh=128 hthresh=0 wthresh=0
TX offloads=0x10000 - TX RS bit threshold=64
testpmd>
testpmd> show port stats all
######################## NIC statistics for port 0 ########################
RX-packets: 442827099 RX-missed: 0 RX-bytes: 26569625172
RX-errors: 0
RX-nombuf: 0
TX-packets: 443292288 TX-errors: 0 TX-bytes: 26597536896
Throughput (since last show)
Rx-pps: 14390795 Rx-bps: 6907582048
Tx-pps: 14405470 Tx-bps: 6914626456
############################################################################
######################## NIC statistics for port 1 ########################
RX-packets: 443293641 RX-missed: 0 RX-bytes: 26597617500
RX-errors: 0
RX-nombuf: 0
TX-packets: 442827661 TX-errors: 0 TX-bytes: 26569658892
Throughput (since last show)
Rx-pps: 14405477 Rx-bps: 6914629232
Tx-pps: 14390795 Tx-bps: 6907581696
############################################################################
testpmd> show port summary all
Number of available ports: 2
Port MAC Address Name Driver Status Link
0 00:00:00:00:01:00 89:00.0 net_ice down None
1 00:00:00:00:01:01 89:00.1 net_ice down None
testpmd> show port stats all
######################## NIC statistics for port 0 ########################
RX-packets: 2267795378 RX-missed: 0 RX-bytes: 136067721784
RX-errors: 0
RX-nombuf: 0
TX-packets: 2270213831 TX-errors: 0 TX-bytes: 136212829092
Throughput (since last show)
Rx-pps: 14385293 Rx-bps: 6904940896
Tx-pps: 14400690 Tx-bps: 6912331240
############################################################################
######################## NIC statistics for port 1 ########################
RX-packets: 2270215290 RX-missed: 0 RX-bytes: 136212916568
RX-errors: 0
RX-nombuf: 0
TX-packets: 2267796060 TX-errors: 0 TX-bytes: 136067762768
Throughput (since last show)
Rx-pps: 14400690 Rx-bps: 6912331344
Tx-pps: 14385293 Tx-bps: 6904941024
############################################################################
Thanks!
Best Regards,
JackyCT.Chen
x86 Software | Cloud-IoT Group | Advantech Co., Ltd.
02-2792-7818 Ext. 1194
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mails.dpdk.org/archives/dev/attachments/20240402/a30a311d/attachment-0001.htm>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image001.jpg
Type: image/jpeg
Size: 103480 bytes
Desc: image001.jpg
URL: <http://mails.dpdk.org/archives/dev/attachments/20240402/a30a311d/attachment-0001.jpg>
More information about the dev
mailing list