It is also possible to use unicast, though less efficiënt I think.
In case of multiple clusters on different subnets, you just set up your
gmetad to poll a machine from each subnet/cluster, which is just a
normal direct connection to a TCP port.
All this is to be found in Ganglia's documentation also.
Concerning scalability, Ganglia was setup with the usage on large scale
clusters/grids in mind.
We currently have it operational on a 275 node cluster and no problems.
All nodes/machines in Ganglia's setup share their info/XML with each
other, for redundancy. "A lot of overhead" is subjective to a persons
view. I am not sure how much network traffic Ganglia generates exactly
but on a Gigabit or more network it's percentage can be only a fraction
of the total available network.
The only scalability issue I have seen so far is on the the
monitor/gmetad server. When you monitor large amounts of hosts, a lot of
I/O disk access occurs (for RRD storing) which can cause a significant
load on the system. But depending on hardware or certain ramdisk tricks
this varies from situation to situation.
I would suggest you try testing a little to figure out the exact details.
Kind regards,
- Ramon.
Stephen Cartwright wrote:
Thanks... That was helpful... I'm not sure why I got it into my head
that they were alternatives and not complementary.
Also I have some more technical quesitons about Ganglia...
Am I correct in that Ganglia only uses multicast, and so to monitor
two clusters on different subnets you must have a router that supports
multicast.
Also how scalable is Ganglia. I understand that Ganglia caches
information about every other machine on each node... at least when I
telnet to gmond on a machine all the machines information appears.
Would this not generate a lot of overhead in a cluster with thousands
of nodes?
Thank you for your time!
Steve
On 6/14/05, Dan Rich <[EMAIL PROTECTED]> wrote:
Stephen Cartwright wrote:
I am looking at both Ganglia and Nagios... any comments on how they compare?
You're comparing apples and oranges.
Nagios is an active system monitor, it's along the lines of HP Openview
or OpenNMS. It doesn't do any graphing, it is focused on service and
host uptime monitoring.
Ganglia is better used as a data collector and trending tool, along the
lines of cricket, cacti, mrtg, or any other SNMP monitoring tool that
generates graphs based on collected data.
We run both (in fact, three of the above, Nagios, Cricket, and Ganglia);
as they all give you different views into the system. Nagios is what
pages me in the middle of the night. Cricket is where we go for
long-term trending and data collection for non-Linux boxen (routers, air
handlers, etc.). And Ganglia gives us high precision system
statistics. Most SNMP monitors only run every 5 minutes, whereas
Ganglia gives you statistics much more frequently.
--
Dan Rich <[EMAIL PROTECTED]> | http://www.employees.org/~drich/
| "Step up to red alert!" "Are you sure, sir?
| It means changing the bulb in the sign..."
| - Red Dwarf (BBC)
-------------------------------------------------------
SF.Net email is sponsored by: Discover Easy Linux Migration Strategies
from IBM. Find simple to follow Roadmaps, straightforward articles,
informative Webcasts and more! Get everything you need to get up to
speed, fast. http://ads.osdn.com/?ad_idt77&alloc_id492&op=click
_______________________________________________
Ganglia-general mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/ganglia-general
