On Mon, Apr 05, 2010 at 05:43:57PM -0400, Jesse Becker wrote:
> I've a need to track CPU speeds...or some semblance of them.
> Currently, the cpu_speed metric is hard-coded as a 'zero' slope metric
> (see gmond/modules/cpu/mod_cpu.c). Can anyone think of a problem with
> this patch? Setting aside
On Wed, May 10, 2006 at 06:04:43PM +0900, Ȳ¿µÃ¶ wrote:
> Hi
>
> I installed ganglia-3.0.3 on AIX 5.2
>
> But It don't disply Pie chart.
>
> I saw Pie chart in ganglia-3.0.2
>
> Why? I used php-4.0.6-5 and apache-1.3.31-1
>
> Do I need to upgraed apache and php?
You need to make sure php
On Thu, May 04, 2006 at 01:00:33PM +0800, [EMAIL PROTECTED] wrote:
>
> G'day all
>
> Newbie type question but I can't seem to find a readily available answer.
>
> I'd like byte counts in and out from my nodes... but on other interfaces (eg.
> eth2 is used for gmond but I'm interested in eth0 and
I've got a FreeBSD script to do this, but it's way overkill for just
doing a backup and restore (it's designed to recover from crashes while
writing and to spend the least amount of time from start to finish since
I run it out of cron). All you need to do is tar or zip or a plain copy.
-- Brooks
On Fri, Jan 27, 2006 at 01:41:28AM -0800, Joel Krauska wrote:
> I've seen similar scaling questions asked, but not a lot of answers.
>
> I hope this query falls on some ears with experience in the brains
> behind them.
>
> I'm looking to deploy ganglia on a largish cluster.
> (1000+ nodes)
>
>
On Wed, Oct 12, 2005 at 04:05:40PM -0400, michael chang wrote:
> On 10/12/05, Woods, Jeff <[EMAIL PROTECTED]> wrote:
> >
> > Is it possible to explicitly specify a value for the static metrics such as
> > cpu_num?
> >
> > We have a number of nodes in our cluster which have hyperthreading enabled,
>
On Wed, Oct 12, 2005 at 03:11:14PM -0400, Woods, Jeff wrote:
> Is it possible to explicitly specify a value for the static metrics such
> as cpu_num?
>
> We have a number of nodes in our cluster which have hyperthreading
> enabled, where each physical CPU appears as two CPUs to the OS. Our
> appl
On Fri, Oct 07, 2005 at 05:42:31PM -0400, Rick Mohr wrote:
>
> On Fri, 7 Oct 2005, michael chang wrote:
>
> > So the key here is that UDP may not be reliable an enough of a
> > solution for your situation, and in that case, a custom TCP may be a
> > better idea.
> >
> > Now, there is one thing to
On Thu, Oct 06, 2005 at 11:42:50AM -0400, Sam Carmichael wrote:
> Hi,
>
> I'm new to ganglia. I'm wondering if anybody use it to do monitoring
> on a per-process basis than per-machine basis. Suppose I have a
> cluster of machines and each machine runs multiple instances of a
> particular process,
On Tue, Sep 13, 2005 at 08:57:23PM -0400, michael chang wrote:
> On 9/13/05, Brooks Davis <[EMAIL PROTECTED]> wrote:
> > On Tue, Sep 13, 2005 at 08:15:56PM -0400, michael chang wrote:
> > > On 9/13/05, Santanu Das <[EMAIL PROTECTED]> wrote:
> > > > michae
On Tue, Sep 13, 2005 at 08:15:56PM -0400, michael chang wrote:
> On 9/13/05, Santanu Das <[EMAIL PROTECTED]> wrote:
> > michael chang wrote:
> >
> > >Oh, I must have misread your statement. These dual-cpu nodes... what
> > >kind of CPUs do they use? How many CPUs does the OS _think_ there
> > >ar
On Tue, Aug 30, 2005 at 08:23:10AM +1000, Ashley Wright wrote:
> Hi,
>
> I have noticed that sometimes my hosts on ganglia are called 'node001'
> and sometimes 'node001.ibm.grid.qut.edu.au'.
>
> How does ganglia determine the name of the node? I was short names in
> all my configurations, and i
On Thu, Aug 18, 2005 at 05:05:58PM -0500, Utsav Agarwal wrote:
> The solution we came up with is to change the code to report only the
> hostname part of the FQDN. That solves our current problem. However, I
> wonder what will happen if the gmond 'collector' cannot resolve hostnames
> (dns down...w
On Tue, Jul 19, 2005 at 02:26:39PM -0700, Vineet Agarwal wrote:
> Guys,
>
> Can ganglia send out alerts, or is anyone aware if some utility can be
> hooked up with ganglia to do the job.
At the moment, ganglia only does monitoring, not alarming. At work,
we're looking into writing a nagaios modu
On Wed, Jun 15, 2005 at 04:46:21PM -0600, Stephen Cartwright wrote:
> Is multicast really advantageous? I know for what I am trying to do I
> wron't be just monitoring a few nodes on a subnet... I want to monitor
> them all. Why then multicast with the added compexity and having to
> deal with havi
On Mon, May 09, 2005 at 05:54:48PM +1100, Andrew Sapronov wrote:
> On Thu, 2005-05-05 at 10:59 -0700, Kevin Burton wrote:
> > My Ganglia memory graph is showing 10G of swapped memory the second I
> > disable swap?
> >
> > Whats going on here. Top and all the unix tools report no swap but
> > ga
On Wed, Apr 06, 2005 at 12:30:43AM -0500, Luke A. Kanies wrote:
> Hi all,
>
> Last I checked there was an issue with the libmetrics license -- ganglia
> itself is BSD, but somehow libmetrics is GPL.
>
> Who do I need to talk to to see if I can separate libmetrics out under at
> least a LGPL, if
On Fri, Mar 11, 2005 at 11:18:26AM +0100, Ramon Bastiaans wrote:
> Jason A. Smith wrote:
>
> >Some sort of RAM disk is probably the only thing that will be able to
> >handle the rrd I/O load and allow gmetad to monitor more than a few
> >hundred nodes. If your gmetad node is running Linux then I
On Tue, Feb 15, 2005 at 06:38:09PM -0700, Ian Cunningham wrote:
> Brooks Davis wrote:
>
> >On Tue, Feb 15, 2005 at 05:27:53PM -0500, Robert E. Parrott wrote:
> >
> >
> >>Is there a way to make ganglia hyperthread - aware in v3.0?
> >>
> >>
On Tue, Feb 15, 2005 at 05:27:53PM -0500, Robert E. Parrott wrote:
> Is there a way to make ganglia hyperthread - aware in v3.0?
>
> We have a cluster of dual Xeons with hyperthreading, which ganglia
> reports as 4 processes. This is annoying when using the web frontend,
> since full load appear
On Wed, Feb 02, 2005 at 02:52:41PM -0800, Steve Jones wrote:
> uanme -a: IRIX64 hostname 6.5 07121149 IP35
> file: ganglia-monitor-core-2.5.7.tar.gz
>
> i unpacked and invoked the configure script. when running make, i receive
> the following error message:
>
> hostname 23# make
> make a
On Thu, Sep 02, 2004 at 03:51:52PM -0500, Brian Henerey wrote:
> Hello,
>
> I have a gmond up and running on a 4 PC's, gmetad up on the master, and the
> webfrontend works fine with one exception: I get graphs but no pie charts.
> Strangely I also used to get a little picture of each computer that
On Wed, Jun 23, 2004 at 02:38:33PM +0200, Erwan Velu wrote:
> I've just realised that ganglia is not able to count the number of
> processors of a system.
>
> I've been discussing of that with some other project, it could be good
> to count or show the number of virtual processors.
>
> when gangl
On Mon, May 24, 2004 at 10:18:35AM -0700, Adesanya, Adeyemi wrote:
>
> Hi There.
>
> Our Ganglia monitoring system has been growing in size and popularity
> and we would like to increase it's visibility by serving the frontend
> on a public web server. So far, the frontend has only been accessibl
g else to make this work
> preoperly?
>
> Mark
>
>
> On Mar 7, 2004, at 9:57 PM, Brooks Davis wrote:
>
> >It's not a matter of versions, it's a matter of compile options.
> >Since you're getting no graphs, I don't think that's the real i
9PM -0500, Mark Weinstein wrote:
> My Ganglia web server is running on a Mac OSX 10.3 box with the
> standard installation of Apache and PHP. I could upgrade the PHP
> system if you think it might be necessary.
>
> Mark
>
>
> On Mar 7, 2004, at 3:42 PM, Brooks Davis wrot
0500, Mark Weinstein wrote:
> Yes, I do have rrd installed and configured. As far as GD support, I'm
> not sure, and actually not even sure what it is. :)
> Any way I can check?
>
> Mark
>
>
> On Mar 6, 2004, at 10:35 PM, Brooks Davis wrote:
>
> >On Sat, Mar 06
On Sat, Mar 06, 2004 at 01:34:21PM -0500, Mark Weinstein wrote:
> I have the ganglia core 2.5.6, but was only able to download the 2.5.5
> web frontend, however, none of my graphics are showing up properly.
>
> Any ideas on what I can do to fix this? I am only getting broken links
> instead of
On Wed, Mar 03, 2004 at 01:14:19AM +, karthik wrote:
> I have configured Ganglia network monitor over a bunch
> of Sun cpu's running solaris 8. Ganglia works fine
> except that I dont get the network traffic graph and
> the pie chart. But all other graphs and monitoring run
> fine.
>
> Any spe
On Thu, Feb 05, 2004 at 11:15:45AM -0600, Fabián Salamanca wrote:
> Hi!
>
> I installed ganglia on a 2 node FreeBSD cluster but Im able to see
> only one node at a time, I declared both nodes in the data_source line
> in the gmetad.conf and i can telnet both nodes on port 8649,
>
> How should I con
On Wed, Feb 04, 2004 at 12:54:26PM -, [EMAIL PROTECTED] wrote:
> Over the past year I have deployed Ganglia on 12 clusters - including
> Linux on IA32, IA64, Opteron and Alpha (Tru64). The installation and
> configuration of gmond and gmetad has always been straightforward -
> either as the RPM
On Wed, Jan 28, 2004 at 03:14:25PM -0800, Adesanya, Adeyemi wrote:
>
> Hi Jason.
>
> I know that multicasting is a very convenient way of sending data to
> multiple recipients but I'd like some tighter control. Less network
> traffic is always preferred and thought of all those nodes (maybe
> > 1
On Thu, Jan 22, 2004 at 01:31:48PM -0500, Jason A. Smith wrote:
> I think the difference you are refering to is with the middle section of
> colored computer icons, right? That comes from an older version of the
> webfrontend. The current version of the webfrontend combines the
> colored icons an
On Thu, Jan 22, 2004 at 05:21:26PM +0100, [EMAIL PROTECTED] wrote:
>
> Hi all,
>
> I would like my ganglia web to look as:
>
> http://xm1.millennium.berkeley.edu/ganglia/?c=IBM%20Cluster
>
> so I see a graphical representation of my cluster nodes... Does anybody
> know how to do that? What sh
On Fri, Dec 19, 2003 at 03:54:16PM -0700, dio wrote:
> Anyone running on this OS?
There's no BSDi port in the tree, but it should be straight forward to
use the FreeBSD port as a basis for one. The basic functionality is
likely to work since much of it uses 4.4BSD interfaces. The full stuff
like
On Tue, Nov 25, 2003 at 01:43:19PM -0800, steven wagner wrote:
> I'm sorry to report that you should be getting metric data back on
> Tru64. Sadly, I can't offer any developmental support here now because
> all our Alpha are belong to dumpster (although for the record, I am the
> one to blame f
On Thu, Nov 06, 2003 at 10:02:07PM -0500, Krishna Kumar wrote:
> Hi,
> I installed ganglia on my solaris (with gmetad).. when I try to start the
> daemon, it gives me this error..
>
> $ /gmond start
> /etc/rc.d/init.d/functions not found
>
> I've copied the gmond.init to /usr/sbin.. Is there som
On Mon, Oct 20, 2003 at 12:09:59PM -0700, Adesanya, Adeyemi wrote:
>
> I'm making progress with the ganglia 2.5.4 web frontend but I'm
> having trouble getting the various pull down menus to function
> correctly. Eventually I realized that the generated URLs do not
> contain 'index.php':
>
> For
On Wed, Oct 08, 2003 at 03:50:48PM -0700, Bernard Li wrote:
>
> What would be involved in changing the hostname of a host currently
> being reported in ganglia? I am talking about the data being stored by
> rrdtools in /var/lib/ganglia/rrdtools.
>
> An example is right now we have a box that i
On Tue, Jun 24, 2003 at 05:08:26PM +0200, Yohann DESQUERRE (DSI NOISIEL) wrote:
> Hi all,
>
> I've got a terminology problem:
>
> What is a cluster for ganglia is a group of computer which have scalable
> or failover properties or just computer with similar activities???
It's a group of comput
I'm wondering how much disk I/O gmetad is expected to perform. I've got
a cluster with around 150 nodes running FreeBSD and gmetad was running
something like 200-300 transactions per second with 3.5MBytes/sec disk
bandwidth. The disk was an adaptec 2100 with three disks in a RAID5
configuration.
On Tue, Jun 10, 2003 at 01:22:56PM -0700, matt massie wrote:
> -BEGIN PGP SIGNED MESSAGE-
> Hash: SHA1
>
> ganglia gets it's host names from gethostbyaddr(). when gmond gets a
> message from a remote gmond it reads the message header to get the IP
> address of the sender. it then plugs
42 matches
Mail list logo
