CM MC7 correctable error message spamming log / console

[ninesguard]

I am getting the following message in the console / log and I'm not exactly sure what it is.
I have tried to replace my RAM and CPU and that hasn't seemed to change anything.

The only thing I've seen was that it seems to be related to the cxgb driver? I'd really like to get some insight on what this is before I try replacing my network cards, since it appears to otherwise be working normally. I'd either like to get rid of the message or find out what exactly is causing the issue.

Code:

Jun 20 15:46:26 hostname kernel: CM MC7 correctable error at addr 0x1000000, data 0x0 0x0 0x4
Jun 20 15:46:26 hostname kernel: CM MC7 correctable error at addr 0x1000000, data 0x0 0x0 0x4
Jun 20 15:46:26 hostname kernel: CM MC7 correctable error at addr 0x1000000, data 0x0 0x0 0x4
Jun 20 15:46:26 hostname kernel: CM MC7 correctable error at addr 0x1000000, data 0x0 0x0 0x4
Jun 20 15:46:26 hostname kernel: CM MC7 correctable error at addr 0x1000000, data 0x0 0x0 0x4
Jun 20 15:46:26 hostname kernel: CM MC7 correctable error at addr 0x1000000, data 0x0 0x0 0x4
Jun 20 15:46:26 hostname kernel: CM MC7 correctable error at addr 0x1000000, data 0x0 0x0 0x4
Jun 20 15:46:26 hostname kernel: CM MC7 correctable error at addr 0x1000000, data 0x0 0x0 0x4
...
Jun 20 15:46:29 hostname kernel: CM MC7 correctable error at addr 0x1000000, data 0x0 0x0 0x4
Jun 20 15:46:29 hostname kernel: CM MC7 correctable error at addr 0x1000000, data 0x0 0x0 0x4
Jun 20 15:46:30 hostname kernel: CM MC7 correctable error at addr 0x1000000, data 0x0 0x0 0x4
Jun 20 15:46:30 hostname kernel: CM MC7 correctable error at addr 0x1000000, data 0x0 0x0 0x4
Jun 20 15:46:30 hostname kernel: CM MC7 correctable error at addr 0x1000000, data 0x0 0x0 0x4
Jun 20 15:46:30 hostname kernel: CM MC7 correctable error at addr 0x1000000, data 0x0 0x0 0x4
Jun 20 15:46:30 hostname kernel: CM MC7 correctable error at addr 0x1000000, data 0x0 0x0 0x4
Jun 20 15:46:30 hostname kernel: CM MC7 correctable error at addr 0x1000000, data 0x0 0x0 0x4
Jun 20 15:46:30 hostname kernel: CM MC7 correctable error at addr 0x1000000, data 0x0 0x0 0x4

Thanks in advance

Dell R510
2x Intel Xeon L5609
32GB
12x WD WDC WD30EZRZ-00Z 3TB
LSI 9211-8i in IT Mode
2x Chelsio 10GB 110-1088-30 \ T320

 

[Samuel Tai]

Yes, this is related to the cxgb driver. I suspect MC7 is the specific PCI-E interrupt line used for offload. Your NIC is starting to go bad.

 

[ninesguard]

Yes, this is related to the cxgb driver. I suspect MC7 is the specific PCI-E interrupt line used for offload. Your NIC is starting to go bad.

Yeah, after downing both interfaces on one of the NICS, I can see that the message stopped. Looks like I'll be needing to replace that NIC for sure. Thank you.