Quantcast
Channel: Intel Communities : Discussion List - Wired Ethernet
Viewing all 4405 articles
Browse latest View live

i218-LM code 10 after restart without cable

$
0
0

I have a system using an Intel i218-LM ethernet controller:

  • Fully patched (as of 16th Feb 2015) Windows 8.1 64-bit
  • Intel driver PROWinx64.exe, Version:19.5, Date:28th Oct 2014.  Appears in Windows as driver v12.12.80.19 dated 29th Sept 2014.

 

Under normal operation the LAN works correctly.  I can disconnect and re-connect the LAN cable, and each time the LAN connection is re-established.

 

If I perform a system restart with the LAN cable connected, the LAN is established correctly once Windows boots.

 

However, if I perform a system restart without a LAN cable connected then I get a Code-10 error in Windows under Device-Manager for the i218-LM controller.  When I re-connect the LAN cable obviously the connection isn't re-established due to the Code-10 error.  If within Device-Manager I disable and then re-enable the i218-LM, the Code-10 error goes away, and the connection is correctly established.

 

Any ideas?


Intel 82579LM Gigabit

$
0
0

I have an Intel 82579LM gigabit card but I can´t get it to its default settings, can you help me?

The driver version is 11.15.16.0

I do not have Intel PROset installed

X540-T2 (ixgbe) poor performance over NFS or CIFS (1~2 Gbps)

$
0
0

Hi,

 

Can't reach more than 140 MB/s over NFS or CIFS.

I've tried everything: recompiled the latest driver from Intel (ixgbe-3.23.2.1), tweaked "/etc/sysctl.conf", set a bigger tmpfs on a ram drive. But nothing seems to work.

 

My NFS server is on Debian wheezy 3.2.65-1+deb7u2 x86_64, with 2 X540-T2, Intel(R) Xeon(R) CPU E5-2603 v3 Hexacore, SSD HDD 240 GB (O.S.) and Logic MegaRAID SAS-3 3108 with 4 disk on RAID10.

My 2 NFS clients are Centos 6.6 and Centos 7.1 with X540-T2.

 

What surprises me the most is that I have another scenario with the same version of Debian that works like 400MB/s with less powerful hardware: Server NFS Intel Corei3 and Client NFS Centos 6.6, both with Intel X520 (ixgb driver) interface.

 

Please helpppp!!!!     

 

 

 

Iperf and dd tests:

 

iperf
------------------------------------------------------------
Client connecting to 10.199.50.1, TCP port 5001
TCP window size: 9.54 MByte (default)
------------------------------------------------------------
[  3] local 10.199.50.3 port 27732 connected with 10.199.50.1 port 5001
[ ID] Interval       Transfer     Bandwidth
[  3]  0.0-20.0 sec  22.8 GBytes  9.80 Gbits/sec
[  3]  0.0-20.0 sec  22.7 GBytes  9.74 Gbits/sec
[  3]  0.0-20.0 sec  23.0 GBytes  9.89 Gbits/sec


dd test:
time dd if=/dev/zero of=/media/ISOs/testfile bs=16k count=16384 && rm -f /media/ISOs/testfile
268435456 bytes (268 MB) copied, 2,0134 s, 133 MB/s
268435456 bytes (268 MB) copied, 2,3138 s, 116 MB/s

intel nic drivers 19.3 huge 6000+ dpc latency spike once a few secs

$
0
0

hi, i would like to report that the new intel nic drivers version 19.3 that just released recently has huge 6000+ dpc latency spike once in a few secs.

 

my specs

 

Intel(R) 82579LM Gigabit Network Connection

 

windows 7 SP1 32bit + lastest windows update

 

i downgrade to intel nic drivers previous version 19.1 and the problem is just gone.

Is there any way to get VF's with X710-DA2 on Windows Server 2012 R2?

$
0
0

Hello. We got ourselves new X710-DA2 card recently and put it into Dell's R620 server running Windows Server 2012R2 Datacenter. We want to partition X710 adapter's ports to at least 2 VF's each, one for iSCSI trafic and one for VM's (per port). Is there any way to do it?

XL710 VF driver can reply to ARP request but cannot reply to ICMP's

$
0
0

We try to write a XL710 VF driver simply,and test it by using  ping command form PF to VF.

Now the VF driver can receive the ARP request and can reply it successfully, and the VF can also receive the ICMP request,and the reply data seems to put into the transmit buffer.

But in the PF, we cannot catch any reply data.

The ARP request can be reply that is to say the VF driver works normally, does it correctly? At least, it shows that the receive part and transmit part are correct.

Things that I want to know is what registers are relative to this issues, or any ideas about this issues?

 

Thanks & regards!

Animy.

Looking for a recommended footprint drawing for the i210 package (64-pin, 9 x 9 QFN package with e-Pad)

$
0
0

Hi,

 

The datasheet for the i210 Ethernet Controller chip has a package drawing (64-pin, 9 x 9 QFN with e-Pad) but not a recommended board footprint nor recommended solder paste stencil pattern.

 

Can anyone help me find recommended footprint and/or solder paste pattern for this package?

 

Thank you,

--- Vaughn

DPC Latency problems with Intel 82579LM based Network Controller on Windows 8

$
0
0

Hi,

 

After weeks of troubleshooting DPC latency problems on my Lenovo Thinkpad T420 laptop which were causing audio dropouts and mouse freezes every few mins I have finally tracked down the source of the issue. It appears that the Intel 82579LM based Network Controller driver may not be correctly optimised for Windows 8. I'm running Windows 8 Pro 64-bit and am using the latest Intel driver for the controller (12.6.45.0). In troubleshooting the issue I tried everything I could think of such as:

 

Update BIOS and all drivers to latest versions

Disable CPU and PCI Power Management in BIOS

Disabled onboard Sound (I use a separate professional audio sound card), Wifi, Bluetooth

Change power management settings to High Performance and Disabled USB selective suspend

Turn on all offloading settings on Ethernet NIC

Ran bcdedit /set disabledynamictick yes

Disabling Network Location Awareness in Windows

 

Nothing made any noticable difference at all. I had also been noticing that my network performance had been pretty poor intermittently on this machine for a while, occasionally experiencing dropouts and low download speeds (yes I know that can be caused by many other factors but please hear me out). Every few mins on the PC I would experience a DPC latency spike of around 95000us to 100000us which would occur right when the audio dropouts, mouse freezes, and probably network pauses would occur. I use the PC for audio production amongst other things so this causes me big issues.

 

I was totally baffled by the problem until I ran an xperf trace in the Windows Performance Toolkit and saw that the spike was being generated from ndis.sys and tcpip.sys. That got me thinking down the lines of a network related problem so I disabled the onboard Intel(R) 82579LM based Network Controller in Device Manager in Windows 8 and what do you know the problem disappeared competely!!  No more DPC latency spikes ever (tested for hours and many times). I can do pretty much whatever I like on the PC and the problem does not reoccur. Not one single audio dropout in my Audio DAW either. The onboard Wifi is still running (Intel Centrino Advanced-N 6205 - v15.8.0.5) providing me with network access and download speeds through the wireless nic are both much faster and more stable surprisingly (should be the other way around if anything). As soon as I re-enable the 82579LM NIC the problem is immediately back within a few mins.

 

I am desperate to get this fixed as I cannot use wireless all of the time. Intel can you please fix the 82579LM driver to make it fully compatible with Windows 8 Pro 64-bit. I'm sure many other people out there are having the same issue and just don't know the cause, or put up with it it as real time applications such as audio are less important to them. I have read about other people having these issues and it only appears to be with Windows 8. I think the drivers are fine for Windows 7, although I haven't confirmed this for sure.

 

Intel please consider patching the 82579LM NIC driver ASAP for full Windows 8 support. I can assist in providing you information if you require as I'm very keen to get this sorted.

 

Thanks,

Brad


X710DA4 SCENARIO

$
0
0

Hi,

It's possible connect directly four server to one server using x710DA4 without fiber switch ?

Intel E10GSFPLR and Cisco SFP-10G-LRM Compatibility

$
0
0

 

Hello,

 

 

I wonder if someone can help me with a seemingly simple but elusive question. I'm looking to

 

make a purchase of several Cisco SFP-10G-LRM modules to support 10Gb communications over our

 

OS2 fibre infrastructure. All runs are less than 300m so this is cost effective compared to

 

using SFP-10G-LR.

 

 

On the other end of the fibre will be some servers using Intel E10GSFPLR optics at 10Gb.

 

 

My question is this - are these optics compatible for the situation I've described? I've done

 

some searching and can't find any definite information either way, despite these being popular

 

choices (I guess).

 

 

Any help is appreciated.

 

Thanks,

 

Andrew

 

XL710 : why 4 receive packets be processed after 4 transmit packets be processed

$
0
0

When i rewrite XL710 VF driver in a polling mode(single process) by porting Linux kernel 3.17.6 i40evf codes, now the VF driver can ping successfully.

And there are problems as following:

1. after transmit be called 4 times that process 4 transmit  packets. (solved. we have fixed it to one transmit,one tx packet processing by delete the WB_STRIDE).

2. processing every 4 rx pakets only after every 4 tx packets processing happened. (not solved)

i don't kown what register makes the 4 receive packets be processed together. and is it relative to hardware only?

I look forward to reply about this issues.

 

Thanks & Best regards!

Animy 

Intel® I350 Quad GBE Controller

$
0
0

Hello every one

                           I am using this Intel® I350 Quad GBE Controller phy which is having a serdes port as well as MDII Interface .with pci as input , I are not using any MDII Interface I am using only serdes interface connected to an SFP module  when an optical based SFP module IT is transmitting and receiving the packets when verified with LAN configration tool but When we use Copper Based SFP the packets are not transmitting and receiving ,the emprom setting we use were provided by intel .we are using I350_2-4port_SerdesFiber_NO-MNG_1_63 eprom settings for fiber which settings to be used for copper ? When diagonised with lAN it is proving LINK failure

 

 

thanks and regards

AGXIN.J

Intel 82579LM Gigabit

$
0
0

I have an Intel 82579LM gigabit card but I can´t get it to its default settings, can you help me?

The driver version is 11.15.16.0

I do not have Intel PROset installed

XL710 VF driver can reply to ARP request but cannot reply to ICMP's

$
0
0

We try to write a XL710 VF driver simply,and test it by using  ping command form PF to VF.

Now the VF driver can receive the ARP request and can reply it successfully, and the VF can also receive the ICMP request,and the reply data seems to put into the transmit buffer.

But in the PF, we cannot catch any reply data.

The ARP request can be reply that is to say the VF driver works normally, does it correctly? At least, it shows that the receive part and transmit part are correct.

Things that I want to know is what registers are relative to this issues, or any ideas about this issues?

 

Thanks & regards!

Animy.

Intel® Ethernet Converged Network Adapter X520-DA2

$
0
0

Hi

what is the corrispondent Adapter with only one port ?

May be X520-DA1 ?


ixgbe 3.21.2 driver for 82599

$
0
0

We are trying to upgrade the NIC ixgbe driver to 3.21.2. I noticed that setting of unicast filtering table (ixgbe_set_uta) to all 1s has been removed. This breaks one of the features on the product. We have a VF that needs to be setup in L2 mode to do L2 switching in software and needs to be in promiscuous mode. It is setup / enabled with AUPE and ROPE bits in VMOLR.  I would like to know the implications if this is conditionally brought back that is set UTA table to 1s when the VF is configured in promiscuous mode (L2 mode) and clear it when VF is disable.  Also would like to understand reasoning behind removal of the setting of uta to all 1s.

Thanks in advance.

i40e sr-iov packets latency

$
0
0

Hi all,

Currently, I'm using XL710 SR-IOV in VM. We are using DPDK 1.8 PMD driver. The VM can communicate with other equipment, but the packets have long latency. you can refer below picture.

I don't know reason, it seemed rte_eth_rx_burst didn't return the packets it received in time.

Does anyone meet this problem before? or I just need to modify some macro in the code?

BTW: I have tried modify RTE_LIBRTE_I40E_ITR_INTERVAL and RTE_LIBRTE_I40E_QUEUE_NUM_PER_VF, and no effect.

Any answer will be appreciated!

i40evf.png

XL710 do not work after NVM update

$
0
0

Have the following hardware configuration:

Server 2xIntel Xeon E5-2680 v3 @ 2.50GHz

Six XL-710 adapters (Intel Corporation Ethernet Controller X710 for 10GbE SFP+)

CentOS 7 Linux, kernel 3.10.0-123.el7.x86_64

Driver version i40e-1.2.38.

 

Firmware of all six adapters has been updated to the latest version available from (https://downloadcenter.intel.com/download/24769)

Tool used for firmware update

After successful flashing (as reported by NVM update tool) one of the adapters stopped working.

EEPROM Image Version: 4.42 MAP2.66 (after update)

The failed card is visible under lspci, but i40e driver reports errors during device initialization:

[ 2682.320170] i40e 0000:03:00.0: Initial pf_reset failed: -15

[ 2682.320173] i40e 0000:03:00.0: HW reset failed or FW unresponsive, module loaded in debug mode

[ 2684.523590] i40e 0000:03:00.1: Initial pf_reset failed: -15

[ 2684.523593] i40e 0000:03:00.1: HW reset failed or FW unresponsive, module loaded in debug mode

[ 2686.727010] i40e 0000:03:00.2: Initial pf_reset failed: -15

[ 2686.727013] i40e 0000:03:00.2: HW reset failed or FW unresponsive, module loaded in debug mode

[ 2688.930435] i40e 0000:03:00.3: Initial pf_reset failed: -15

[ 2688.930437] i40e 0000:03:00.3: HW reset failed or FW unresponsive, module loaded in debug mode

 

Update utility refuses to re-update firmware for that device, reporting ‘access error’.


Updating NVM using `eeupdate64e` tool also failed.

For failed XL-710:

$> ./eeupdate64e /NIC=5 /EEPROMVER

...

Unable to initialize adapter 5 code c86a0a00

Admin Queue initialization failed

 

For normal XL-710:

$> ./eeupdate64e /NIC=5 /EEPROMVER

...

1: EEPROM Image Version: 4.42 MAP2.66


Thank you in advance.

i218-LM code 10 after restart without cable

$
0
0

I have a system using an Intel i218-LM ethernet controller:

  • Fully patched (as of 16th Feb 2015) Windows 8.1 64-bit
  • Intel driver PROWinx64.exe, Version:19.5, Date:28th Oct 2014.  Appears in Windows as driver v12.12.80.19 dated 29th Sept 2014.

 

Under normal operation the LAN works correctly.  I can disconnect and re-connect the LAN cable, and each time the LAN connection is re-established.

 

If I perform a system restart with the LAN cable connected, the LAN is established correctly once Windows boots.

 

However, if I perform a system restart without a LAN cable connected then I get a Code-10 error in Windows under Device-Manager for the i218-LM controller.  When I re-connect the LAN cable obviously the connection isn't re-established due to the Code-10 error.  If within Device-Manager I disable and then re-enable the i218-LM, the Code-10 error goes away, and the connection is correctly established.

 

Any ideas?

configuring external SFP through I2C

$
0
0

Hai every one ,

                          I am using inter I350chip and connecting to copper SFP modules how to enter the values of the registors of PHY inside the SFP through I2C is there any software available with intel foe this

thanks and regards

AGXIN.J

Viewing all 4405 articles
Browse latest View live


Latest Images

<script src="https://jsc.adskeeper.com/r/s/rssing.com.1596347.js" async> </script>