Really exciting. But I'm confused how this works with the round robin
nature of RRD. Don't we by default only have (for example) daily data
for past 24 hour period, not 48 hours?
On 05/16/2012 07:54 PM, Vladimir Vuksan wrote:
There is a blog post about a new feature in Ganglia Web called
On 2012-08-02 17:41, Daniel Pocock wrote:
b) we don't have the old branches (at least I can't see them)
This in principle is the least disruptive to fix. The svn repos tag
revisions can be matched with the right commits in the git repo on
github, and then tagged after the fact. Ideally this
Glad it worked out!
On 08/09/2012 08:22 AM, Daniel Pocock wrote:
https://github.com/ganglia/monitor-core/branches
3.1 branch is in git now, just for essential security updates to aid the
legacy packages on Debian and Fedora (and others?)
On 08/22/2012 10:19 AM, Daniel Pocock wrote:
I've started a branch for sending UUID instead of hostname
This necessitates change to the XDR packet format, but it is backwards
compatible
Nonetheless, it is not desirable to change the XDR format regularly, so
it would be good to know if
My understanding is that the 3.5.0 release corresponds to the
release/3.5 branch [1] and there is not a separate tags. It would
increase the warm and fuzzy feeling of people when I advocate for
upgrading if I could point to a tag instead of a particular hash on a
branch.
[1]
Just to tie everything together in a confusing way, this may be
similar/related to https://github.com/ganglia/monitor-core/issues/47
On 04/16/2013 08:30 AM, Chris Burroughs wrote:
This sounds a lot like a problem I have been having once a week or so:
https://github.com/ganglia/monitor-core
There are a few different versions floating around on rpmfind or whatenot.
rpmbuild -tb FILE.tar.gz on the dist tarball should work (and is what we do)
On 06/24/2013 03:33 PM, Valter Silva wrote:
Hi everyone,
I'm trying to install ganglia-gmond at centOS, ganglia-gmond 3.2 (or
bigger)
Would you mind submitting this as a github pull request for review at
https://github.com/ganglia/ganglia-web ?
On 06/25/2013 03:44 PM, Jochen Hein wrote:
We'd like to have the optional graphs in the cluster and host view
bigger. In the past, I just modified cluster_view.php and
I just build it.
On 06/30/2013 07:42 PM, Valter Silva wrote:
Chris, do I have to configure something in .tar.gz before build the rpm ?
Or just download it and build it ?
--
Atenciosamente,
[image: movile logo]http://www.movile.com/ Valter Silva
Analista de Infraestrutura
Tel: +55 19.
I'm not aware of anyone that has tried and published their results.
Does eaccelerator improve both time and memory use, or make time/memory
tradeoffs in favor of the cpu? My largest server side gweb performance
gripe is that I have needed to bump php.ini's memory_limit several
times,
coverity offers free scanning or open source projects. Is there any
interest in adding the ganglia C code there? I think all that's
required is one of the developers clicking 'sign up'.
http://scan.coverity.com/
--
It's somewhat ironic that gmetad does not emit more metrics about it's
operations. I think the 'right' think long term would be for it to
create a unix socket thingy exposing various interesting things, and
then a gmond plugin could read that (or you could wrap it in a http
server or
Could someone with an Official Developer Hat (TM) sign up? I think
Coverity wants the first person to register to be an admin of sorts.
On 07/24/2013 09:58 AM, Nicholas Satterly wrote:
Hi Chris,
I think it's a good idea. There are definitely some memory leaks that it
would be good to track
On 07/29/2013 02:20 PM, Dave Rawks wrote:
. I've never heard anybody have problems with our
serialization, but there is frequent and often confusing troubleshooting
around multicast vs unicast and the various
infrastructural/configuration tweaks to make the most out of those.
My
On 07/30/2013 02:45 AM, Nicholas Satterly wrote:
Could you expand on what you mean by multi-tenancy, please? I'm curious.
There is currently no application or other namespacing. If I have a
bunch of java apps on the same box and they are all emitting
jvm.memory.heap_usage, those metrics will
or http to
expose the metrics of gmetad operations.
Interesting to know that you have done some work regarding this, curious to
know the approach you have followed. Could you please elaborate a little
more on this?
thanks,
Nikhil
On Tue, Jul 30, 2013 at 6:07 PM, Chris Burroughs
I think the more general point here (and has come up in other contexts
such as mobile phones) is that sometimes neither IP nor reverse DNS make
sense and people would like sending something else to be 'smoother' (as
opposed to hacky/spoofy).
My experience with vendor data hasn't given me warm
Thank you Devon and Vladimir for starting this thread. We (AddThis)
have been struggling with gmetad performance and stability for a while
and I'm personally excited to see the focus here. I'll explain briefly
how we are using ganglia for context and then have inline comments.
We have two
On 12/07/2013 03:00 PM, Vladimir Vuksan wrote:
Were these failures totally random or grouped in some way? (Same
cluster, type, etc).
We run multiple dozens of clusters and some of the larger clusters ie.
clusters that had 2-3x machines that other clusters would exhibit either
gaps, slower
On 12/07/2013 03:22 PM, Devon H. O'Dell wrote:
We were polling every 10 seconds, and it was taking over 2 minutes to
finish parsing the XML (which includes writing the RRDs). With my
changes, the 10 second poll is feasible.
Parse, or fetch parse? We have a simple python script we use to
On 12/08/2013 04:43 PM, Devon H. O'Dell wrote:
This is a simple `perf top -p $PID` on one of of our gmetad nodes
Samples: 1M of event 'cycles', Event count (approx.): 64115959770
6.59% libexpat.so.1.5.2 [.] 0x00011b8d
4.77% libganglia-3.6.0.so.0.0.0 [.] hashval
On 02/03/2014 08:05 AM, Daniel Pocock wrote:
Bernard, if both you and I are interested, then we probably need at
least one more person willing to mentor and then we can make an application.
I'm more of a ganglia power-user than developer, but if there is a way I
can help with GSoC I'm
I thought the distro anti-bundling stance was paired with a we already
have X so you should just depend on it. I'm not sure how this works
with javascript. Is there some debian jquery package that could be
depended on?
On 01/31/2014 04:23 AM, Daniel Pocock wrote:
Debian is proposing to
On 03/02/2014 09:05 PM, Vladimir Vuksan wrote:
I like the fact that Github Wiki's are just another Git repo.
Perhaps we ought to figure out if we can use github pages to serve
Wiki's directly e.g. something like
wiki.ganglia.info
Anyone know ?
I like the idea of docs.ganglia.info or
On 10/24/2014 06:14 PM, Daniel Pocock wrote:
- doesn't appear to be available at all in any Fedora version yet,
so it can't even start going through to EPEL6 or EPEL7
- if releasing Ganglia 3.7.x before the Concurrency Kit packages are
available,
then it means the
aren't generally platform agnostic
since platform specific stuff sometimes causes problems with downstream
linux distro adoption/packaging. I.E. the official python modules
should be expected to work on the full set of platforms that gmond works on.
-Dave
On 02/05/2015 11:21 AM, Chris
I think this mostly works out:
* https://github.com/ganglia/monitor-core/pull/183
* https://github.com/ganglia/gmond_python_modules/pull/184
On 02/06/2015 09:35 AM, Chris Burroughs wrote:
That makes sense. For me in the import short term the thing is not
manually trying to keep dupe code
tasks if the custom ones had a different location
or easy to identify based on filename.
regards,
chris hunter
yale hpc group
On 02/05/2015 11:21 AM, Chris Burroughs wrote:
Currently python modules are bundled in monitor-core, some are in
gmond_python_modules (or os specific repos
it. Here
are some popular sets:
https://www.gnu.org/software/indent/manual/indent.html#SEC4
On Feb 26, 2015, at 4:14 PM, Chris Burroughs chris.burrou...@gmail.com
wrote:
Is there a C style file or emacs/vi config for the ganglia C source code
floating around anywhere? I admit I'm a bit spoiled
FWIW I've also been running approximately this build in production since
February.
On 03/23/2015 12:09 PM, Vladimir Vuksan wrote:
Hello all,
Since we had issues with 3.7.0 and inability to get concurrency toolkit
stuff built we will be skipping releasing it. This was changed with this
Is there a C style file or emacs/vi config for the ganglia C source code
floating around anywhere? I admit I'm a bit spoiled by Python and the
One True Style and a bit befuddled by the mix of {1,2,3(!),4} space
indents and variable brace placement.
It would be nice if for GSoC the code was a
31 matches
Mail list logo
