Well, I personally think you should continue your development on the
next major version. 2.5.x is pretty stable. If someone wants to
maintain it, I would think Matt would be glad to let someone support
2.5.
I feel that if you spend alot of time maintaining 2.5, or bouncing back
between 2.5
On Darwin:
hc652a119:~/Desktop/libmetrics-200409211005 jdurham$ gcc --version
gcc (GCC) 3.3 20030304 (Apple Computer, Inc. build 1640)
Copyright (C) 2002 Free Software Foundation, Inc.
This is free software; see the source for copying conditions. There is
NO
warranty; not even for MERCHANTABILIT
This is an issue with rrdtool. I think I had to change all the
time_value references inside of RRD to rrdtool_time_value.
- Josh
On Aug 18, 2004, at 11:35 AM, Eric Wages wrote:
Hi all.
Trying to get Ganglia working for our new mac cluster, but having
significant difficulties. Wonder if any
I don't have access to a system right now, but he probably wants:
telnet 127.0.0.1 8749 and
telnet 8749
I think I remember trying these, and it failing, but I wouldn't bet
money on it.
- Josh
Josh Durham [EMAIL PROTECTED]
Computer System
I think I mentioned this probably on OS X before. No response then. :)
I removed all IPV6 addresses from all interfaces, especially the
localhost one, and it seemed to work.
Not sure what exactly is happening.
- Josh
On Jun 8, 2004, at 9:22 AM, Martin Knoblauch wrote:
Hi Matt, [please for
Even
doing a 'telnet 127.0.0.1 8649' returns 0.0.0.0 as the source address.
I just deleted the IPv6 addresses on all the interfaces, and it began
working in the normal behavior.
Has anyone tried the new ganglia on another system with IPv6 enabled?
- Josh
On Apr 12, 2004, at 4:53 PM, Jo
don't know how
this is impacting things.
- Josh
Josh Durham [EMAIL PROTECTED]
Computer Systems Engineer P: 540.231.2361
Terascale Computing Facility
Virginia Tech
Two patches. The first can be easily applied, the second should be
tested on another platform. First one allows Ganglia to be compiled if
GEXEC_SUPPORTED == 0, and the second fixes a libtool problem with
multiple memory_pool symbols declared. Now, I have to figure out why
all hosts are comin
.lo) definition of _memory_pool
in section (__DATA,__common)
../libhttpd/.libs/libhttpd.al(httpd_protocol.lo) definition of
_memory_pool in section (__DATA,__common)
make[2]: *** [libganglia.la] Error 1
make[1]: *** [all-recursive] Error 1
make: *** [all] Error 2
Hel
explicitly
set.
excuse me while i go hang my head in shame and quickly alter the code.
-matt
On Thu, 2004-02-26 at 20:42, Josh Durham wrote:
if it's a unicast channel, gmond configures itself a little
differently.
gmond will send messages on the unicast channel (which will write to
a
single h
if it's a unicast channel, gmond configures itself a little
differently.
gmond will send messages on the unicast channel (which will write to a
single host) but it will NOT listen to unicast messages unless
"msg_port" is explicitly set.
I may be missing something here, but how do you configure
Ah ha! You hit the problem on the head.
gmetad is assigning a negative value to tn, which is a uint32. This
messes up the comparison.
So. We can abs() tn when it gets assigned, in process_xml.
Or you can make tn and tmax regular int32s.
Though another solution is to make sure TN is never ne
Thanks for your quick response.
So, I've been playing around a bit with the TN thing. Here is
something interesting.. Here is a larger sample of the output from
gmetad:
telnet localhost 8651:
...
http://blahblah/ganglia/";
LOCALTIME="1072822698">
...
TN="0" TMAX="20" DMAX="0" LOCATION="uns
I have another problem.
I have 1100 nodes, with 4GB of RAM each.
1100 nodes * 4,194,304 kilobytes of RAM = 4,613,734,400
uint32 max value = 2^32 = 4,294,967,296
I have a feeling, from what I've looked at, that moving all the memory
stuff to uint64 is going to be painful. Not t
Greetings from Virginia Tech.
I'm working on getting Ganglia on our 1100 node G5 cluster, and have
had some pretty good success.
I do have an issue, and I wonder if it's related to scaling, or the
Darwin platform. First, let me describe how I've set everything up so
far.
All 1100 nodes ar
15 matches
Mail list logo
