[CentOS] APIC error on Intel Atom CPU, CentOS 5.x

Timo Schoeler timo.schoeler at riscworks.net
Tue Mar 16 09:53:32 UTC 2010

Hash: SHA1

thus Martin Jungowski spake:
> If it helps I'm experiencing a *very* similar problem with all Atom N270 
> based company netbooks (Lenovo S10e) with openSUSE 11.2 and Kernel 2.6.31, 
> as well as openSUSE 11.1 and Kernel 2.6.27. Putting load on the NIC works 
> fine until I start rsync. Literally everything else allows me to put load 
> on it - ftp, scp, downloading large files via HTTP, copying via NFS or 
> SMB, etc. But as soon as I start rsync it locks up. 

For me it dies on any kind of traffic, not just rsync. I even saw this
fetching ISOs using FTP. The machine just died (network-wise; I don't
have console on this machine in the data centre, but I do have a machine
of this type here in the office, so I could build a test setup with KVM).

On the machine that runs stable for weeks now

# uptime
09:51:33 up 47 days, 47 min,  1 user,  load average: 0.14, 0.11, 0.09

I've got TOR running, which uses a sustained bandwidth of about three
MBit (which is not that much, it had about ten MBit for quite a while
with an additional FreeNet daemon running).

> It doesn't even start 
> to transfer anything - the NIC instantly dies and more often than not 
> takes the entire system down with it. Every now and then instead of a full 
> lockup I only get a dead NIC. Killing the rsync process hard (-9) and 
> restarting the network often helps.
> I realize that this is a very different software environment but I was 
> about to try CentOS on that baby next. I'll try the noapic option when I 
> get back to my office but it's interesting how so different environments 
> seem to produce similar errors. I guess what I'm trying to say is that 
> it's probably not a CentOS-specific issue we're dealing with here.
> Martin


Version: GnuPG v1.4.5 (GNU/Linux)


More information about the CentOS mailing list