Re: em0 watchdog timeouts

[Daniel Bond]

Hi Jack,

I'll comment your mail inline:


On Oct 5, 2009, at 6:57 PM, Jack Vogel wrote:

This posting just muddies the issue, first you talk about having a problem that involves Broadcom, ok, so post about that on something other than em :)

I only meant to indicate that the problem might exist outside the intel driver. I'm also indicating that it happens with several drivers (bge, bce and em) on several different machines, on both pci-x and pci-e. I'm sorry if this is confusing to you, but I still think it's relevant to mention.

Then you make some references to hardware that you "might have bought"

can't help you there either :)

but didn't, I'm not about debugging 'possible worlds problems' though so

No. I only made references to hardware I actually used, and had real- world issues with.

Finally you never say what the actual hardware is, other than a person who I do not know told you it was the best performer... so, what exactly is it?

http://people.freebsd.org/~sephe/

Sepherosa is a guy that writes drivers for BSD based operating systems. Including FreeBSD. He has a lot of knowledge in this area. The NIC you are referring to, the one sephe recommended me, is a 82571EB. I didn't mention specific hardware, as I think it's more important to note this is an issue I'm experiencing across different sets of hardware and drivers.

this almost always means something in your environment, a cron job run

suspect given this description is the driver.

You have a problem once every 10 days, and at a specific time no less, amok, a piece of hardware that resets, I dunno, but the last thing I would

but it has happened at random times too.

This is not what I wrote. I wrote I had a problem every 1-10 days, but it would usually happen once every 3-4 days. At worst, every day in periods. It's not at any specific time. If you read my email correctly, I say it *usually* happens arround 11-13:00, This is my point exactly. I don't think it's the Intel-driver, I think the problem is elsewhere. I had a suspicion it had to do with the combination of nic + qlogic fc-controller, but I have no evidence of this.

developer.

You need a good sysadmin for this debugging I would venture, not a driver

I'm sorry to say, but your reply was %0 useful, Jack.

What I need is useful advice/help. I never stated I needed a driver developer. I'd like to be able to run my favorite OS on cool hardware, in the future, for a high-performing NFS-server, without problems like I've experienced the past 6months, on a production system. Please note that I'm managing a server-park almost completely based on FreeBSD, and I'm running many NFS servers on other hardware, for other services, without issues. I've seen several other FreeBSD-users having problems with this too, so I think it's of importance for the project. As I mentioned originally, I'm happy to dispose the hardware to any FreeBSD developer that might want to look further into this. Debugging it further is above my skill-set, I don't even know where to begin looking, especially since I can't produce any panics.

Jack

- Daniel

PGP.sig
Description: This is a digitally signed message part