Intel 82574L Gigabit network card - issues and resolution
I am posting this so that if anyone has the same problem they will know what to do.
NIC: Intel 82574L Gigabit mobo network card
Issue: after the server has been up for a random amount of time, the network connection is lost. attaching a console and looking at ifconfig I see a large number of dropped packets and collisions.
In this case: Intel 82574L, e1000e
Look in var/log/messages to get the version of the driver, in this case 1.0.2
Download .gz file with source code, follow instructions to install newest driver (e1000e.ko), in my case version 1.2.10
This resolved the issue.
Nice find. Thanks for the detailed info and resolution!
I'm also seeing corruption with the 82574L, but I am also seeing strange entries in /proc/interrupts
33: 0 0 0 4834 0 0 165903 0 PCI-MSI-edge ahci
34: 0 0 0 0 177981 568 0 0 PCI-MSI-edge (random chars, looks like memory space of another process or data sent over the nic)
35: 0 0 0 0 0 5 0 0 PCI-MSI-edge eth0
36: 0 0 0 0 0 7294274 376401 0 PCI-MSI-edge (random chars, looks like memory space of another process or data sent over the nic)
37: 0 0 0 0 2960 0 104 0 PCI-MSI-edge eth1
Are you seeing this same type of corruption? I see it even with the 1.2.10 driver (although I haven't yet noticed drops/corruption with this driver). Not sure if it's cosmetic or something to worry about.
more info here
actually this was caused by ASPM and MSI-X interrupts, you can find more info here: Resolved Intel e1000e driver bug on 82574L Ethernet controller causing network blipping
Just for guys who may arrive here after searching:
1.there's kernel bug in intel 82574L e1000e driver on centos 6(MSI/MSI-X interrupts issue), we can resolve this by install kmod-e1000e package from ELrepo.org and later add pcie_aspm=off e1000e.IntMode=1,1 e1000e.InterruptThrottleRate=10000,10000 acpi=off to kernel parameters. You can read more info Intel e1000e driver bug on 82574L Ethernet controller causing network blipping.
2.For the high Tx traffic, this was caused by port 53 dns flooding attack. I've resolved this by writing some iptable rules. More info here: port 53 dns flooding attack
|All times are GMT -5. The time now is 10:35 AM.|