Intel i219-LM Had Only Been Running At ~60% Of Maximum Speed Due To Linux Driver Bug

[phoronix]

Phoronix: Intel i219-LM Had Only Been Running At ~60% Of Maximum Speed Due To Linux Driver Bug

If you rely on an Intel I219-LM Gigabit Ethernet adapter, you will want to look forward to upgrading your Linux kernel build soon... A fix was committed today after Intel engineers discovered this particular Ethernet chipset had only been running at around 60% of its maximum speed due to a regression introduced back in 2020...

https://www.phoronix.com/news/Intel-i219-LM-Linux-60p-Fix

[scratchi]

Interesting. I have this board which has one of these NICs:

https://www.asrockrack.com/general/productdetail.asp?Model=C236%20WSI#Specifications

I run TrueNAS Core on it. Wonder if TrueNAS/FreeBSD is impacted by this as well?

[rene]

Now Intel NICs having hardware and driver bugs, ... that is a NEW one: https://www.youtube.com/watch?v=DXNy...UgaW50ZWwgbmlj

[NateHubbard]

Now Intel NICs having hardware and driver bugs, ... that is a NEW one

At a datacenter I used to work at, we struggled for years with broken e1000/e1000e drivers. There was always a new fix... And then there was another.

[rogerx]

Yea ditto. Atypical for Intel Ethernet drivers to have one bug, then another after the previous bug being solved, then subsequently having a regression; usually with a lengthy span of time in between each event.

As they say, be thankful Intel fixes bugs, as most manufacturers never fix any bugs! Other manufacturers just deprecate functioning hardware with a simple software bug, forcing users into buying newer hardware for hopefully fixing the fixable software bug.

[yoshi314]

was this bug around since the hw was introduced to the market, or is the userbase so small nobody noticed?

it's very puzzling to me that something like that would slip unnoticed for so long

[xnor]

was this bug around since the hw was introduced to the market, or is the userbase so small nobody noticed?

it's very puzzling to me that something like that would slip unnoticed for so long

I reported a reproducible bug that crashes an Intel NIC (the driver dumps its registers and then the server is unreachable) a while ago.
I reported this both on the bugtracker and the Intel-specific mailing list (which is low traffic so it could not have been overlooked).

Intel engineers don't care. I didn't even get a response.

I've never had such a bad experience with NICs on Linux as with Intel. Their products are plagued with unfixable hardware bugs and their engineers are busy doing who knows what ... probably designing the next broken product.

[uwgandalf]

I reported a reproducible bug that crashes an Intel NIC (the driver dumps its registers and then the server is unreachable) a while ago.
I reported this both on the bugtracker and the Intel-specific mailing list (which is low traffic so it could not have been overlooked).

Intel engineers don't care. I didn't even get a response.

I've never had such a bad experience with NICs on Linux as with Intel. Their products are plagued with unfixable hardware bugs and their engineers are busy doing who knows what ... probably designing the next broken product.

Feel your pain. The old experiences that intel is vastly superior to say, realtek are long gone. I've hit this above bug sooooo many times in my homelab. Consumer ethernet from intel is a joke.

See official docs for the errata: http://iommu.com/datasheets/e1000-da...pec-update.pdf §1.5.4-5

[uwgandalf]

was this bug around since the hw was introduced to the market, or is the userbase so small nobody noticed?

it's very puzzling to me that something like that would slip unnoticed for so long

Yeah see my previous post, it's officially ack'ed in the docs. I do have to say, with 'normal' usage I hardly ever hit it, but as soon as certain workloads are on a server you hit it as often as every half hour.
My experience was, though totally unscientific, that it definitely happened when using a server as gateway/router.

[Slartifartblast]

Yea ditto. Atypical for Intel Ethernet drivers to have one bug, then another after the previous bug being solved, then subsequently having a regression; usually with a lengthy span of time in between each event.

As they say, be thankful Intel fixes bugs, as most manufacturers never fix any bugs! Other manufacturers just deprecate functioning hardware with a simple software bug, forcing users into buying newer hardware for hopefully fixing the fixable software bug.

Really ?

The I225-V and I226-V 2.5G have been plagued by problems that are not yet fixed......

https://www.techpowerup.com/303854/psa-intel-i226-v-2-5gbe-on-raptor-lake-motherboards-has-a-connection-drop-issue-no-fix-available