On 1/25/2008 at 7:21 PM, in message
[EMAIL PROTECTED], Jesse Becker
[EMAIL PROTECTED] wrote:
On Jan 25, 2008 9:06 PM, Bernard Li [EMAIL PROTECTED] wrote:
Hi Jesse:
On 1/25/08, Jesse Becker [EMAIL PROTECTED] wrote:
Interesting.
How about introducing a new metric: cpu_speed_current.
On Jan 25, 2008 5:09 PM, Bernard Li [EMAIL PROTECTED] wrote:
On 1/25/08, Jesse Becker [EMAIL PROTECTED] wrote:
Arguably, assuming that cpu_speed is constant is also a bug. From the
default gmond.conf:
See this original bug that started it all:
Hi Jesse:
On 1/25/08, Jesse Becker [EMAIL PROTECTED] wrote:
Interesting.
How about introducing a new metric: cpu_speed_current. For systems
without cpuscaling, it is forced to the same value of cpu_speed, or
not sent at all, since it is completely redundant. Otherwise, it
reports the
, The Caribbean and Andean Region
-Original Message-
From: Martin Knoblauch [mailto:[EMAIL PROTECTED]
Sent: Friday, January 25, 2008 9:46 AM
To: Bernard Li; Salamanca, Fabian
Cc: ganglia-general@lists.sourceforge.net
Subject: Re: [Ganglia-general] scaling_max_freq error
Hi,
if I am
On Jan 25, 2008 10:46 AM, Martin Knoblauch [EMAIL PROTECTED] wrote:
if I am not completely wrong this depends on how your kernel is
configured. If you do not have either
CONFIG_CPU_FREQ=y or
CONFIG_CPU_FREQ=m and the cpufreq module loaded
that file will not be existing. So, assuming its
Hi Fabian:
On 1/25/08, [EMAIL PROTECTED] [EMAIL PROTECTED] wrote:
Should I submit a bug? Should I reinstall gmond with another version in the
meantime?
As I mentioned, your problem has nothing to do with the CPU frequency
as gmond works perfectly fine even though it could not find that file
Hi Martin:
On 1/25/08, Martin Knoblauch [EMAIL PROTECTED] wrote:
if I am not completely wrong this depends on how your kernel is
configured. If you do not have either
CONFIG_CPU_FREQ=y or
CONFIG_CPU_FREQ=m and the cpufreq module loaded
We were both using stock kernels from CentOS and that
an email with your comments to my
manager, Gerardo Cesin, [EMAIL PROTECTED]
-Original Message-
From: Bernard Li [mailto:[EMAIL PROTECTED]
Sent: Friday, January 25, 2008 12:56 PM
To: Salamanca, Fabian
Cc: ganglia-general@lists.sourceforge.net
Subject: Re: [Ganglia-general] scaling_max_freq
Hi Jesse:
On 1/25/08, Jesse Becker [EMAIL PROTECTED] wrote:
Arguably, assuming that cpu_speed is constant is also a bug. From the
default gmond.conf:
collection_group {
collect_once = yes
time_threshold = 1200
[...]
metric {
name = cpu_speed
}
[...]
}
See this
On Jan 23, 2008 11:16 PM, [EMAIL PROTECTED] wrote:
I've been trying to run gmond (ganglia 3.0.6) on a Red Hat EL 5 cluster node
using kernel 2.6.18-8 SMP and I got the following error:
/sys/devices/system/cpu/cpu0/cpufreq/scaling_max_freq
That's not really an error--that's a file
Is
no answer from any [HPCC Mexico cluster] datasource
BR,
-Original Message-
From: Jesse Becker [mailto:[EMAIL PROTECTED]
Sent: Thursday, January 24, 2008 7:12 AM
To: Salamanca, Fabian
Cc: ganglia-general@lists.sourceforge.net
Subject: Re: [Ganglia-general] scaling_max_freq
Hi Fabian:
I just checked a server that's running CentOS 5 w/ kernel
2.6.18-8.1.10.el5PAE and indeed the file you specified does not exist.
However, I do not think this is the real reason why Ganglia isn't
working for you, I am guessing you have some sort of setup problems.
Perhaps you can post
Hi!
I've been trying to run gmond (ganglia 3.0.6) on a Red Hat EL 5 cluster
node using kernel 2.6.18-8 SMP and I got the following error:
/sys/devices/system/cpu/cpu0/cpufreq/scaling_max_freq
Is anything I can do to keep it working? Do I need to enable something
in the kernel? Should I use
13 matches
Mail list logo