Hi,
igb driver, Linux platform
Suppose dma to tx ring is successful and There are a lot of link
flaps happens in short period of time. So
1) NIC will queue these packets and try to transmit when link becomes up again ?
2) Suppose a lot of dma happens , where the new packets will store ?
3) H
Hi,
I am using e1000 driver. I happened to see multiple watdog messages
in a small interval of time. But all those messages are " Link is up
1000mbps full duplex " . But there is no "Link Down" messages. How
Link can go up multiple times without going down ?
-Ratheesh
--
Hello,
we have upgraded from 2.6.27.4 to 3.6.8 kernel.
We have to operate a link at 100MBit/FD, no auto-neg.
It worked with the 2.6.27.4 kernel, but does no longer
work with 3.6.8:
# ethtool -s eth2 speed 100 duplex full autoneg off
Cannot set new settings: Invalid argument
not setting speed
Runtime power management is enabled in the kernel with the CONFIG_PM_RUNTIME
parameter.
According to the link, the issue is already fixed in a more recent kernel.
AFAICR, it was
not fixed in the driver, it was fixed elsewhere in the kernel.
> -Original Message-
> From: Roger Cruz [mailt
It probably does. How do I determine where this is configured in my kernel?
I found this link and if I set the power management from auto to on as
mentioned there, I am able to shutdown correctly. What is the proper way to
fix this then?
https://bugzilla.kernel.org/show_bug.cgi?id=36132#c9
_
Sounds to me like a possible issue with runtime power management. Is
that feature enabled in your kernel and for the LAN interface?
> -Original Message-
> From: Roger Cruz [mailto:roger.c...@citrix.com]
> Sent: Thursday, November 29, 2012 11:51 AM
> To: e1000-devel@lists.sourceforge.net
I have determined that if the LAN cable is removed prior to a shutdown of a
Toshiba Portege Z930, the system will hang. With the cable plugged in, the
system shuts down fine. If I unload the e1000e ethernet driver prior to the
shutdown request, the platform will shut down successfully. I am
Hi,
We are measuring packet latency on 10G port pair using
bi-directional UDP 64 byte packets.
Test machine is connected with load generator using direct 10G ports.
Test machine configuration:
CPU:2 - 6 core Intel(R) Xeon(R) CPU E5645 @
2.40GHz(T
Someone else pointed this out to me locally. If you have a non-client BIOS, you
should be able to set the MaxPayloadSize using setpci. You have to make sure
that you're being consistent throughout all the associated links.
Todd Fujinaka
Technical Marketing Engineer
LAN Access Division (LAD)
Inte
Hello,
Fujinaka, Todd wrote:
> Those are completely different parts with completely different architectures
> (and completely different problems).
> All the fixes I know for your onboard part
> (the 82579LM if I'm reading things correctly) are from the
> motherboard group so you should check to
10 matches
Mail list logo
