[Ganglia-general] How to configure gmetad not to generate rrd files ?

[潇湘居士]

I have 1000+ nodes in my cluster, and it will be a huge size disk to hold the 
rrd files.


so, i just want to use 8651 and 8652 to get the lastest metric infomation, 
don't want to keep the  old data.


how can i achieve it ?--
___
Ganglia-general mailing list
Ganglia-general@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/ganglia-general

[Ganglia-general] abnormal proc_total metric on gmetad 3.6.2

[潇湘居士]

Hi, in my server, the proc_total metric is no correct!
system: rhel5.10
ganglia: 3.6.2

I find the total proc metric is not equal to the real process numbers:
clients:
___
[baadmin@e1060 proc]$ ls /proc/ |wc
353 3531665
[baadmin@e1060 proc]$ top
...
Tasks: 301 total,   1 running, 300 sleeping,   0 stopped,   0 zombie
...
___

gmetad server：
___
[baadmin@ca5 ~]$ echo /cluster 100-109/e1060.blueapple.mobi/proc_total | nc 
localhost 8652 | egrep '(


[baadmin@ca5 ~]$ date +%s
1431347764
___

and this state have hold 1 month.
can any help me ?
--
One dashboard for servers and applications across Physical-Virtual-Cloud 
Widest out-of-the-box monitoring support with 50+ applications
Performance metrics, stats and reports that give you Actionable Insights
Deep dive visibility with transaction tracing using APM Insight.
http://ad.doubleclick.net/ddm/clk/290420510;117567292;y___
Ganglia-general mailing list
Ganglia-general@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/ganglia-general

[Ganglia-general] gmetad(3.6.1) suddenly stoped

[潇湘居士]

Hi,

my gmetad(3.6.1) suddenly stoped, and it has passed much time when I find 
the stop status.
here is the log:


[root@ca5 log]# grep -v RRD_update messages | tail -n 20
Mar 16 15:30:31 ca5 /usr/sbin/gmetad[28087]: poll() timeout from source 0 for 
[hb] data source after 0 bytes read
Mar 16 15:30:46 ca5 /usr/sbin/gmetad[28087]: poll() timeout from source 1 for 
[hb] data source after 0 bytes read
Mar 16 15:31:01 ca5 /usr/sbin/gmetad[28087]: poll() timeout from source 0 for 
[hb] data source after 0 bytes read
Mar 16 15:54:40 ca5 /usr/sbin/gmetad[28087]: poll() timeout from source 1 for 
[hb] data source after 0 bytes read
Mar 16 15:54:48 ca5 /usr/sbin/gmetad[28087]: poll() timeout from source 1 for 
[dp] data source after 0 bytes read
Mar 16 15:54:54 ca5 /usr/sbin/gmetad[28087]: poll() timeout from source 1 for 
[stat] data source after 43261 bytes read
Mar 16 15:54:56 ca5 /usr/sbin/gmetad[28087]: poll() timeout from source 0 for 
[hb] data source after 0 bytes read
Mar 16 15:55:09 ca5 /usr/sbin/gmetad[28087]: poll() timeout from source 0 for 
[test] data source after 5427 bytes read
Mar 16 15:55:10 ca5 /usr/sbin/gmetad[28087]: poll() timeout from source 0 for 
[dp] data source after 11584 bytes read
Mar 16 15:55:27 ca5 /usr/sbin/gmetad[28087]: poll() timeout from source 1 for 
[dp] data source after 0 bytes read
Mar 16 15:55:31 ca5 /usr/sbin/gmetad[28087]: poll() timeout from source 1 for 
[hb] data source after 0 bytes read
Mar 16 18:26:22 ca5 last message repeated 2 times
Mar 16 18:28:23 ca5 kernel: gmetad[28126]: segfault at 3fc22580 rip 
003f1320ba5f rsp 59073790 error 4
Mar 16 19:58:23 ca5 auditd[3025]: Audit daemon rotating log files
Mar 17 00:54:25 ca5 Server Administrator: Storage Service EventID: 2243  The 
Patrol Read has stopped.:  Controller 0 (PERC H700 Integrated)
Mar 17 01:05:29 ca5 auditd[3025]: Audit daemon rotating log files
Mar 17 01:30:04 ca5 auditd[3025]: Audit daemon rotating log files
Mar 17 02:00:10 ca5 /usr/sbin/gmetad[6865]: data_thread() for [db] failed to 
contact node 66.160.159.72
Mar 17 02:06:14 ca5 last message repeated 3 times
Mar 17 03:13:29 ca5 last message repeated 2 times



my system is RHEL 5.5:

[root@ca5 log]# lsb_release -a
LSB Version:
:core-3.1-amd64:core-3.1-ia32:core-3.1-noarch:graphics-3.1-amd64:graphics-3.1-ia32:graphics-3.1-noarch
Distributor ID:RedHatEnterpriseServer
Description:Red Hat Enterprise Linux Server release 5.5 (Tikanga)
Release:5.5
Codename:Tikanga


And I don't know why did gmetad stop, can anyone help me ?
--
Dive into the World of Parallel Programming The Go Parallel Website, sponsored
by Intel and developed in partnership with Slashdot Media, is your hub for all
things parallel software development, from weekly thought leadership blogs to
news, videos, case studies, tutorials and more. Take a look and join the 
conversation now. http://goparallel.sourceforge.net/___
Ganglia-general mailing list
Ganglia-general@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/ganglia-general