Matt Massie wrote:
guys-
i just put what i believe will be the 3.0.1 release at
http://matt-massie.com/ganglia/
i'm not going to release it until we've tested it here longer and you
guys find it works well for you.
3.0.1.
fixes a bug in gmond using unicast only where a network failure to the
listening gmond can cause the sending gmonds to block indefinitely.
fixes a bug in libmetrics for collecting network statistics on 2.6.x
linux kernels.
adds a feature to gmetad that allows you to specify custom round-robin
archives in gmetad.conf.
fixes a bug in ganglia.spec for starting and stopping ganglia services.
I submitted a patch earlier on for the web-frontend, to allow the
specification of a default value for the showing of hosts. Has it been
rejected? I don't see it committed in the cvs.
i also have another question for you guys.
how much do you love/hate java? how would you feel about having
gmetad written in java?
i only ask because i'm playing around with jrobin
(http://www.jrobin.org/) and it has some features that rrdtool does
not which we really need. for example... in-memory rrds (sync to disk
whenever you like).. dynamically altering rrd data sources/archives...
databases are cross-platform.
Sounds great, especially the in-memory rrds.
Any estimates on what is more work; rewriting gmetad in Java from
scratch, or writing similar in-memory rrds functions in c?
Somehow it seems weird to switch programming language just because of a
nice library.
i'm not sold on this idea at all but i wanted to get some early
feedback before i allow my mind to wander any further.
-matt
- Ramon.
