[Ganglia-general] Running Ganglia, rrdcached on Alma 9 or Rocky 9?

Hi All, Have anyone succeed running Ganglia on a recent Alma or Rocky 9 with system and rrdcached working together? Trying to update our systems monitoring but it is somehow tricky. Any advice much appreciated! Thanks! -- Grigory Shamov Site Lead / HPC Specialist University of Manitoba and

Re: [Ganglia-general] How to check Ganglia Version

On our system: rpm -qa | grep ganglia libganglia-3.7.2-2.el7.grex.x86_64 ganglia-gmond-3.7.2-2.el7.grex.x86_64 ganglia-gmond-modules-python-3.7.2-2.el7.grex.x86_6 So, the current version is 3.7.2 ; which is fairly old, but we still use it and it does the job. -- Grigory Shamov

Re: [Ganglia-general] How to check Ganglia Version

Thanks, that makes a huge difference. Grigory Shamov From: Daniel Rich Sent: Friday, August 28, 2020 1:36:18 PM To: ganglia-general@lists.sourceforge.net; Beyer, Gregory L Subject: Re: [Ganglia-general] How to check Ganglia Version Caution: This message was

Re: [Ganglia-general] How to check Ganglia Version

Ganglia did not update in 10 years or so, so likely you are on the latest version. Grigory Shamov From: Beyer, Gregory L Sent: Thursday, August 27, 2020 2:08:21 PM To: ganglia-general@lists.sourceforge.net Subject: [Ganglia-general] How to check Ganglia

[Ganglia-general] gmond forwarding from one internal network to another?

ute nodes' 192.168.x interface, as telnet shows, but do not pass these further, somehow. I check the metrics as follows: telnet 10.0.0.24 8649 | grep HOST Could you please suggest, what am I doing wrong in this setup? Is gmond supposed to forward like this at all? Thank you very much

Re: [Ganglia-general] rrdcached /gmetad permission problems after update.

Hi Vladimir, Thanks a lot! The TCP method seems to be working for me. -- Grigory Shamov Westgrid/ComputeCanada Site Lead University of Manitoba E2-588 EITC Building, (204) 474-9625 From: Vladimir Vuksan mailto:vli...@veus.hr>> Date: Tuesday, 23 February, 2016 10:27 AM To: Grigory

Re: [Ganglia-general] rrdcached /gmetad permission problems after update.

Dear Adrian, Vladimir, Thank you very much for the answers! Does it depend on rrdtools/rrdcached version? Which one are you using ? -- Grigory Shamov Westgrid/ComputeCanada Site Lead University of Manitoba E2-588 EITC Building, (204) 474-9625 From: Vladimir Vuksan mailto:vli...@veus.hr

[Ganglia-general] rrdcached /gmetad permission problems after update.

Thank you very much in advance! -- Grigory Shamov Westgrid/ComputeCanada Site Lead University of Manitoba E2-588 EITC Building, (204) 474-9625 -- Site24x7 APM Insight: Get Deep Visibility into Application Performanc

[Ganglia-general] binding gmond to an interface?

Hi All, Is there a way to bind gmond not to hostname, but to another interface? For example, if you have hostname on eth0, but want to send your unicast metrics to eth1. -- Grigory Shamov Westgrid/ComputeCanada Site Lead University of Manitoba E2-588 EITC Building, (204) 474-9625

[Ganglia-general] How to use procstat metrics in gmond 3.7.0 ?

amples, that both PID or process name cane be specified? It did not work for me, either with the PID value from server.lock file (commented out now), or with the string value. Thank you very much! -- Grigory Shamov Westgrid/ComputeCanada Site Lead University of Manitoba E2-588 EITC

Re: [Ganglia-general] splitting rrds on different hosts

exactly? Thanks! -- Grigory Shamov Westgrid/ComputeCanada Site Lead University of Manitoba E2-588 EITC Building, (204) 474-9625 On 14-10-11 1:44 PM, "Jesse Becker" wrote: >There isn't a way to do it natively, but there are a few ways to work >around it. > >One

[Ganglia-general] controlling logging level from gmond?

ime, the node's gmod's report connection failures to syslog, creating a bit of traffic (as our compute nodes forward syslog to a log server). Is there an option to suspend the logging or change its level? I couldn't find anything in the example gmond.conf about it.. -- Grigory Shamov

Re: [Ganglia-general] Huge metrics' size being reported to gmetad

Dear Sergio, Somehow on my 300-node cluster Ganglia, with more or less default metrics and RRD configs, collects over 40GB! If there are smarter RRD settings to reduce the size, it would be very interesting to learn them. -- Grigory Shamov HPC Analyst, Tech. Site Lead, Westgrid/Compute Canada

Re: [Ganglia-general] Number of HyperThreaded CPUs

vise please, how to count real cores only? -- Grigory Shamov HPC Analyst, Westgrid/Compute Canada E2-588 EITC Building, University of Manitoba (204) 474-9625 On 14-04-14 9:14 AM, "Grigory Shamov" wrote: >Hi All, > >I am sure this has been resolved already, but googling d

[Ganglia-general] Number of HyperThreaded CPUs

core. This gives utilization of 50% max which is not correct (as we schedule by real cores not HT ones). So, what would be a best way to report only real cores in the new Ganglia? -- Grigory Shamov HPC Analyst, Westgrid/Compute Canada E2-588 EITC Building, University of Manitoba (204) 474