On 02-06-17 15:58, Bart Van Assche wrote:
On Fri, 2017-06-02 at 14:10 +0200, Pascal de Bruijn wrote:I'd appreciate any pointers you could give me as to the nature of the above kernel messages, and whether they warrant further investigation.Hello Pascal, Please provide the output sent to the system log by the following command after having reproduced the lockup: echo w > /proc/sysrq-trigger
Thanks for your response. I'll try. I did get some data out of the last lockup though.Collectd was somehow still logging stats over the network, even though the machine didn't do much else anymore.
I can see system load going up to ~18 around 00:30u. And I can see CPU4/CPU7/CPU-12 going nuts on Wait-IO on the graphs and CPU-15 seems affected too but much less so. I've attached one of the graphs, which is rather peculiar.
Regards, Pascal de Bruijn
Attachment:
collectd_cpu_lockup.png
Description: PNG image
