pcp
[Top] [All Lists]

Re: [pcp] pernode metrics still wrong on 1 CPU systems

To: Ken McDonell <kenj@xxxxxxxxxxxxxxxx>, PCP <pcp@xxxxxxxxxxx>
Subject: Re: [pcp] pernode metrics still wrong on 1 CPU systems
From: Mark Goodwin <goodwinos@xxxxxxxxx>
Date: Thu, 22 Jan 2015 09:13:08 +1100
Delivered-to: pcp@xxxxxxxxxxx
In-reply-to: <54C00816.10808@xxxxxxxxxxxxxxxx>
References: <54C00816.10808@xxxxxxxxxxxxxxxx>
User-agent: Mozilla/5.0 (X11; Linux x86_64; rv:31.0) Gecko/20100101 Thunderbird/31.3.0
On 01/22/2015 07:12 AM, Ken McDonell wrote:
I'm seeing a handful of qa/873 failures.

I've modified 873 to save the pmprobe output, which looks like this on vm04
kernel.pernode.cpu.user 0
kernel.all.cpu.user 1 7800

looks like it found one cpu but no numa nodes.

I blew away all the linux PMDA's indom cache files and restarted pmcd but this
made no difference.

Mark, what additional info would help diagnose/fix this?

what is vm04 (kernel non-smp? uname -a, which distro)?

ls -l /sys/devices/system/node
ls -l /sys/devices/system/node/node0/cpu*

As previously noted, I'm merging and partly re-writing proc_cpuinfo.[ch]
and proc_stat.[ch], including the pernode metrics. I wont get time to work
on this at all until Saturday. A shorter term fix might be possible with
the above requested info ..

Regards


<Prev in Thread] Current Thread [Next in Thread>