that often. You can just send it once an hour, and gmetad will
end up writing the same value every 15 secs for an hour.
-- Rick
--
Rick Mohr
Systems Developer
Ohio Supercomputer Center
--
Rick Mohr
Systems Developer
Ohio Supercomputer Center
in a subversion
repository instead of cvs. I have made the switch at work in the last 6
months, and I see no need to go back to cvs ever again :-)
-- Rick
--
Rick Mohr
Systems Developer
Ohio Supercomputer Center
For example, lets say that for the first 3 weeks of the month your
cluster was idle and over the last week it was 100% busy. In this
example, the numbers on the web frontend would probably say 100%, but in
actuality, your cluster utilization was only around 25%. The patch I
made uses the data
to keep
the current behaviour would be fine.
-- Rick
--
Rick Mohr
Systems Developer
Ohio Supercomputer Center
On Thu, 15 Dec 2005, Jason A. Smith wrote:
I was thinking that if some people would prefer the current behavior, it
could either be made into an admin config
and the one previously mentioned
would be to look in /proc/partitions to find out what devices are actually
local and compare that to what is in /proc/mounts.
--Rick
--
Rick Mohr
Systems Developer
Ohio Supercomputer Center
the risk involved
with this depends on many factors like who has access to the machines you
are monitoring, who has access to the network on which ganglia metrics get
transmitted, etc.
--Rick
--
Rick Mohr
Systems Developer
Ohio Supercomputer Center
On Mon, 6 Jun 2005, Prahlad Bhakt wrote:
1) How could I get the CPU model info like pentium 4, AMD, pentium 3
etc. using ganglia
You can use the gmetric command to send your own custom metrics. Perhaps
something like this:
gmetric -n cpu_model -v Pentium 4 -t string
2) What are the
I subscribe, and yes, I can verify that. It was really a nice
coincidence. I just started using ganglia, and poof! There's the
article. Pretty handy.
--Rick
On Tue, 12 Aug 2003, matt massie wrote:
is anyone in the group a subscriber of linux magazine? i just got a
voicemail from a
Thanks for the fix. I wasn't sure if/when I would get around to it. And
it was more general than the one I had in mind :-)
--Rick
On Mon, 11 Aug 2003, Periklis Charchalakis wrote:
Attached is a quick replacement for remote_mount() that compares the
mounted filesystems with the fs types
I noticed on our cluster that all nodes had the same Most Full Disk
Partition percentage listed. Turns out that ganglia isn't discerning
remote NFS filesystems quite right. The remote_mount function in
gmond/machines/linux.c looks for a : to determine if a partition is NFS
mounted. This of
.)
I also added a new metric and XML tag so that I could tell when a computer
had hypertherading processors and report that via the web frontend.
By the way, this was for Ganglia 2.5.3 running on RedHat 9 with kernel
2.4.20-8.
Rick Mohr
-BEGIN PATCH-
diff -Naur ganglia-monitor-core
12 matches
Mail list logo