Created attachment 456633 [details] Output of lspci -vvv Description of problem: Any significant use of either of the builtin NICs soon generates an NMI (with reason 0x21 or 0x31), and the machine locks up or reboots soon after. Note that it doesn't fail with a CentOS 5.5 64-bit Live CD, and the manufacturer's diags and MemTest86 pass. Which is why I think it's specific to the F13 kernel. Version-Release number of selected component (if applicable): tried both these kernels; both fail: 2.6.33.3-85.fc13.x86_64 2.6.34.7-61.fc13.x86_64 How reproducible: Bring up the interface using NM; this will often trigger an immediate NMI; if not, running "cat /dev/zero | ssh other 'cat>/dev/null'" for a few seconds consistently will. Actual results: logged in /var/log/messages: "Uhhuh. NMI received for unknown reason 21 on CPU 0" Expected results: Unicorns farting rainbows etc Additional info: I'm attaching the output of lspci -vvv. Note that the output doesn't change after the NMI. This is a brand new server (and a brand new model of server that Dell have only just started shipping): a Dell PowerEdge R415 with two 6-core Opterons. All relevant firmware is up to date (as specified by Dell support). It's a minimal system with a single drive, no RAID, FC or anything else complex. Apart from using the network, nothing else seems to trigger the NMI (i.e. heavy disk or CPU load don't cause it)
Still get the NMI with kernel 2.6.34.7-66.fc13.x86_64
This message is a reminder that Fedora 13 is nearing its end of life. Approximately 30 (thirty) days from now Fedora will stop maintaining and issuing updates for Fedora 13. It is Fedora's policy to close all bug reports from releases that are no longer maintained. At that time this bug will be closed as WONTFIX if it remains open with a Fedora 'version' of '13'. Package Maintainer: If you wish for this bug to remain open because you plan to fix it in a currently maintained version, simply change the 'version' to a later Fedora version prior to Fedora 13's end of life. Bug Reporter: Thank you for reporting this issue and we are sorry that we may not be able to fix it before Fedora 13 is end of life. If you would still like to see this bug fixed and are able to reproduce it against a later version of Fedora please change the 'version' of this bug to the applicable version. If you are unable to change the version, please add a comment here and someone will do it for you. Although we aim to fix as many bugs as possible during every release's lifetime, sometimes those efforts are overtaken by events. Often a more recent Fedora release includes newer upstream software that fixes bugs or makes them obsolete. The process we are following is described here: http://fedoraproject.org/wiki/BugZappers/HouseKeeping
Just tested it on the F15 x86_64 Live CD, and it still NMI's after a bit of network traffic
Are you still seeing this in 2.6.43/3.3 in F15/F16?
Just tried it with the Fedora 17 x86_64 Live CD. It still NMI'ed after a bit of heavy network traffic. Then the kernel(?) crashed a minute or so later with "NETDEV WATCHDOG: em1 (bnx): transmit queue 6 timed out"
Still seeing this with 3.6.9? It has been a long time since the bug was updated.
Since the machine is unusable with Fedora, it currently runs CentOS. No doubt when F18 comes out I'll briefly test it with a new liveCD and let you know the result.