A 16:20 27/03/2006 -0800, Bernard Li a écrit :
Hey Jerome:
Okay, so it appears that you should at least have 2 hosts in your Ganglia
page http://localhost/ganglia.
However, I wonder why the other nodes aren't showing up properly...
- Did you make any modifications/configurations to your Ganglia setup from
the default?
No
- Check /etc/gmond.conf for all the other nodes (node2, node3, node4) and
see if the network interfaces configured are correct?
See below content of editr_gmond.conf. With diff command, I compare
node[1-4]_gmond.conf with editr_gmond.conf and they are same.
Actually, what does your Ganglia page look like? How many nodes does it
say you have?
Yes, two hosts : Editr (Master) and Node 1, this latter is down .
???
Thanks for your support
/* This configuration is as close to 2.5.x default behavior as possible
The values closely match ./gmond/metric.h definitions in 2.5.x */
globals {
setuid = yes
user = nobody
cleanup_threshold = 300 /*secs */
}
/* If a cluster attribute is specified, then all gmond hosts are wrapped
inside
* of a <CLUSTER> tag. If you do not specify a cluster tag, then all
<HOSTS> will
* NOT be wrapped inside of a <CLUSTER> tag. */
cluster {
name = "EDITR Cluster"
owner = "IRD"
}
/* Feel free to specify as many udp_send_channels as you like. Gmond
used to only support having a single channel */
udp_send_channel {
mcast_join = 239.2.11.71
port = 8649
}
/* You can specify as many udp_recv_channels as you like as well. */
udp_recv_channel {
mcast_join = 239.2.11.71
port = 8649
bind = 239.2.11.71
}
/* You can specify as many tcp_accept_channels as you like to share
an xml description of the state of the cluster */
tcp_accept_channel {
port = 8649
}
/* The old internal 2.5.x metric array has been replaced by the following
collection_group directives. What follows is the default behavior for
collecting and sending metrics that is as close to 2.5.x behavior as
possible. */
/* This collection group will cause a heartbeat (or beacon) to be sent every
20 seconds. In the heartbeat is the GMOND_STARTED data which expresses
the age of the running gmond. */
collection_group {
collect_once = yes
time_threshold = 20
metric {
name = "heartbeat"
}
}
/* This collection group will send general info about this host every 1200
secs.
This information doesn't change between reboots and is only collected
once. */
collection_group {
collect_once = yes
time_threshold = 1200
metric {
name = "cpu_num"
}
metric {
name = "cpu_speed"
}
metric {
name = "mem_total"
}
/* Should this be here? Swap can be added/removed between reboots. */
metric {
name = "swap_total"
}
metric {
name = "boottime"
}
metric {
name = "machine_type"
}
metric {
name = "os_name"
}
metric {
name = "os_release"
}
metric {
name = "location"
}
}
/* This collection group will send the status of gexecd for this host every
300 secs */
/* Unlike 2.5.x the default behavior is to report gexecd OFF. */
collection_group {
collect_once = yes
time_threshold = 300
metric {
name = "gexec"
}
}
/* This collection group will collect the CPU status info every 20 secs.
The time threshold is set to 90 seconds. In honesty, this
time_threshold could be
set significantly higher to reduce unneccessary network chatter. */
collection_group {
collect_every = 20
time_threshold = 90
/* CPU status */
metric {
name = "cpu_user"
value_threshold = "1.0"
}
metric {
name = "cpu_system"
value_threshold = "1.0"
}
metric {
name = "cpu_idle"
value_threshold = "5.0"
}
metric {
name = "cpu_nice"
value_threshold = "1.0"
}
metric {
name = "cpu_aidle"
value_threshold = "5.0"
}
metric {
name = "cpu_wio"
value_threshold = "1.0"
}
/* The next two metrics are optional if you want more detail...
... since they are accounted for in cpu_system.
metric {
name = "cpu_intr"
value_threshold = "1.0"
}
metric {
name = "cpu_sintr"
value_threshold = "1.0"
}
*/
}
collection_group {
collect_every = 20
time_threshold = 90
/* Load Averages */
metric {
name = "load_one"
value_threshold = "1.0"
}
metric {
name = "load_five"
value_threshold = "1.0"
}
metric {
name = "load_fifteen"
value_threshold = "1.0"
}
}
/* This group collects the number of running and total processes */
collection_group {
collect_every = 80
time_threshold = 950
metric {
name = "proc_run"
value_threshold = "1.0"
}
metric {
name = "proc_total"
value_threshold = "1.0"
}
}
/* This collection group grabs the volatile memory metrics every 40 secs and
sends them at least every 180 secs. This time_threshold can be increased
significantly to reduce unneeded network traffic. */
collection_group {
collect_every = 40
time_threshold = 180
metric {
name = "mem_free"
value_threshold = "1024.0"
}
metric {
name = "mem_shared"
value_threshold = "1024.0"
}
metric {
name = "mem_buffers"
value_threshold = "1024.0"
}
metric {
name = "mem_cached"
value_threshold = "1024.0"
}
metric {
name = "swap_free"
value_threshold = "1024.0"
}
}
collection_group {
collect_every = 40
time_threshold = 300
metric {
name = "bytes_out"
value_threshold = 4096
}
metric {
name = "bytes_in"
value_threshold = 4096
}
metric {
name = "pkts_in"
value_threshold = 256
}
metric {
name = "pkts_out"
value_threshold = 256
}
}
/* Different than 2.5.x default since the old config made no sense */
collection_group {
collect_every = 1800
time_threshold = 3600
metric {
name = "disk_total"
value_threshold = 1.0
}
}
collection_group {
collect_every = 40
time_threshold = 180
metric {
name = "disk_free"
value_threshold = 1.0
}
metric {
name = "part_max_used"
value_threshold = 1.0
}
}
-------------------------------------------------------
This SF.Net email is sponsored by xPML, a groundbreaking scripting language
that extends applications into web and mobile media. Attend the live webcast
and join the prime developer group breaking into this new coding territory!
http://sel.as-us.falkag.net/sel?cmd=lnk&kid0944&bid$1720&dat1642
_______________________________________________
Oscar-users mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/oscar-users
