pzgz
7/8/2014 - 6:37 AM
Ganlia Sample Configuration
Ganlia Sample Configuration
/* 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 {
daemonize = yes
setuid = yes
user = ganglia
debug_level = 0
max_udp_msg_len = 1472
mute = no
deaf = no
allow_extra_data = yes
host_dmax = 86400 /*secs, set this to remove dead host */
cleanup_threshold = 300 /*secs */
gexec = no
send_metadata_interval = 30 /*secs, set this, or sometimes gmond will stuck */
}
/*
* The cluster attributes specified will be used as part of the <CLUSTER>
* tag that will wrap all hosts collected by this instance.
*/
cluster {
name = "cluster_name_to_change"
owner = "Allyes"
latlong = "unspecified"
url = "unspecified"
}
/* The host section describes attributes of the host, like the location */
host {
location = "unspecified"
}
/* Feel free to specify as many udp_send_channels as you like. Gmond
used to only support having a single channel */
udp_send_channel {
#bind_hostname = yes # Highly recommended, soon to be default.
# This option tells gmond to use a source address
# that resolves to the machine's hostname. Without
# this, the metrics may appear to come from any
# interface and the DNS names associated with
# those IPs will be used to create the RRDs.
host = host_name_to_change
port = 8649
ttl = 1
}
/* You can specify as many udp_recv_channels as you like as well. */
udp_recv_channel {
port = 8649
}
/* 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
}
/* Each metrics module that is referenced by gmond must be specified and
loaded. If the module has been statically linked with gmond, it does
not require a load path. However all dynamically loadable modules must
include a load path. */
modules {
module {
name = "core_metrics"
}
module {
name = "cpu_module"
path = "modcpu.so"
}
module {
name = "disk_module"
path = "moddisk.so"
}
module {
name = "load_module"
path = "modload.so"
}
module {
name = "mem_module"
path = "modmem.so"
}
module {
name = "net_module"
path = "modnet.so"
}
module {
name = "proc_module"
path = "modproc.so"
}
module {
name = "sys_module"
path = "modsys.so"
}
}
include ('/etc/ganglia/conf.d/*.conf')
/* The old internal 2.5.x metric array has been replaced by the following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"
title = "CPU Count"
}
metric {
name = "cpu_speed"
title = "CPU Speed"
}
metric {
name = "mem_total"
title = "Memory Total"
}
/* Should this be here? Swap can be added/removed between reboots. */
metric {
name = "swap_total"
title = "Swap Space Total"
}
metric {
name = "boottime"
title = "Last Boot Time"
}
metric {
name = "machine_type"
title = "Machine Type"
}
metric {
name = "os_name"
title = "Operating System"
}
metric {
name = "os_release"
title = "Operating System Release"
}
metric {
name = "location"
title = "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"
title = "Gexec Status"
}
}
/* 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"
title = "CPU User"
}
metric {
name = "cpu_system"
value_threshold = "1.0"
title = "CPU System"
}
metric {
name = "cpu_idle"
value_threshold = "5.0"
title = "CPU Idle"
}
metric {
name = "cpu_nice"
value_threshold = "1.0"
title = "CPU Nice"
}
metric {
name = "cpu_aidle"
value_threshold = "5.0"
title = "CPU aidle"
}
metric {
name = "cpu_wio"
value_threshold = "1.0"
title = "CPU wio"
}
/* 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"
title = "CPU intr"
}
metric {
name = "cpu_sintr"
value_threshold = "1.0"
title = "CPU sintr"
}
*/
}
collection_group {
collect_every = 20
time_threshold = 90
/* Load Averages */
metric {
name = "load_one"
value_threshold = "1.0"
title = "One Minute Load Average"
}
metric {
name = "load_five"
value_threshold = "1.0"
title = "Five Minute Load Average"
}
metric {
name = "load_fifteen"
value_threshold = "1.0"
title = "Fifteen Minute Load Average"
}
}
/* 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"
title = "Total Running Processes"
}
metric {
name = "proc_total"
value_threshold = "1.0"
title = "Total Processes"
}
}
/* 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"
title = "Free Memory"
}
metric {
name = "mem_shared"
value_threshold = "1024.0"
title = "Shared Memory"
}
metric {
name = "mem_buffers"
value_threshold = "1024.0"
title = "Memory Buffers"
}
metric {
name = "mem_cached"
value_threshold = "1024.0"
title = "Cached Memory"
}
metric {
name = "swap_free"
value_threshold = "1024.0"
title = "Free Swap Space"
}
}
collection_group {
collect_every = 40
time_threshold = 300
metric {
name = "bytes_out"
value_threshold = 4096
title = "Bytes Sent"
}
metric {
name = "bytes_in"
value_threshold = 4096
title = "Bytes Received"
}
metric {
name = "pkts_in"
value_threshold = 256
title = "Packets Received"
}
metric {
name = "pkts_out"
value_threshold = 256
title = "Packets Sent"
}
}
/* 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
title = "Total Disk Space"
}
}
collection_group {
collect_every = 40
time_threshold = 180
metric {
name = "disk_free"
value_threshold = 1.0
title = "Disk Space Available"
}
metric {
name = "part_max_used"
value_threshold = 1.0
title = "Maximum Disk Space Used"
}
}
# This is an example of a Ganglia Meta Daemon configuration file
# http://ganglia.sourceforge.net/
#
# $Id: gmetad.conf 667 2006-07-20 08:49:41Z knobi1 $
#
#-------------------------------------------------------------------------------
# Setting the debug_level to 1 will keep daemon in the forground and
# show only error messages. Setting this value higher than 1 will make
# gmetad output debugging information and stay in the foreground.
# default: 0
# debug_level 10
#
#-------------------------------------------------------------------------------
# What to monitor. The most important section of this file.
#
# The data_source tag specifies either a cluster or a grid to
# monitor. If we detect the source is a cluster, we will maintain a complete
# set of RRD databases for it, which can be used to create historical
# graphs of the metrics. If the source is a grid (it comes from another gmetad),
# we will only maintain summary RRDs for it.
#
# Format:
# data_source "my cluster" [polling interval] address1:port addreses2:port ...
#
# The keyword 'data_source' must immediately be followed by a unique
# string which identifies the source, then an optional polling interval in
# seconds. The source will be polled at this interval on average.
# If the polling interval is omitted, 15sec is asssumed.
#
# A list of machines which service the data source follows, in the
# format ip:port, or name:port. If a port is not specified then 8649
# (the default gmond port) is assumed.
# default: There is no default value
#
# data_source "my cluster" 10 localhost my.machine.edu:8649 1.2.3.5:8655
# data_source "my grid" 50 1.3.4.7:8655 grid.org:8651 grid-backup.org:8651
# data_source "another source" 1.3.4.7:8655 1.3.4.8
data_source "Hadoop" dspprod-m:8649
data_source "Console" dspprod-c:8649
data_source "App" dspprod-a1:8649
gridname "Allyes Dsp Hangzhou"
# 15 seconds for 1 month, 6 minutes for 1 year
RRAs "RRA:AVERAGE:0.5:1:178560" "RRA:AVERAGE:0.5:24:88800"
rrd_rootdir "/data/ganglia/rrds"
#
# Round-Robin Archives
# You can specify custom Round-Robin archives here (defaults are listed below)
#
# RRAs "RRA:AVERAGE:0.5:1:244" "RRA:AVERAGE:0.5:24:244" "RRA:AVERAGE:0.5:168:244" "RRA:AVERAGE:0.5:672:244" \
# "RRA:AVERAGE:0.5:5760:374"
#
#
#-------------------------------------------------------------------------------
# Scalability mode. If on, we summarize over downstream grids, and respect
# authority tags. If off, we take on 2.5.0-era behavior: we do not wrap our output
# in <GRID></GRID> tags, we ignore all <GRID> tags we see, and always assume
# we are the "authority" on data source feeds. This approach does not scale to
# large groups of clusters, but is provided for backwards compatibility.
# default: on
# scalable off
#
#-------------------------------------------------------------------------------
# The name of this Grid. All the data sources above will be wrapped in a GRID
# tag with this name.
# default: Unspecified
# gridname "MyGrid"
#
#-------------------------------------------------------------------------------
# The authority URL for this grid. Used by other gmetads to locate graphs
# for our data sources. Generally points to a ganglia/
# website on this machine.
# default: "http://hostname/ganglia/",
# where hostname is the name of this machine, as defined by gethostname().
# authority "http://mycluster.org/newprefix/"
#
#-------------------------------------------------------------------------------
# List of machines this gmetad will share XML with. Localhost
# is always trusted.
# default: There is no default value
# trusted_hosts 127.0.0.1 169.229.50.165 my.gmetad.org
#
#-------------------------------------------------------------------------------
# If you want any host which connects to the gmetad XML to receive
# data, then set this value to "on"
# default: off
# all_trusted on
#
#-------------------------------------------------------------------------------
# If you don't want gmetad to setuid then set this to off
# default: on
# setuid off
#
#-------------------------------------------------------------------------------
# User gmetad will setuid to (defaults to "ganglia")
# default: "ganglia"
# setuid_username "ganglia"
#
#-------------------------------------------------------------------------------
# The port gmetad will answer requests for XML
# default: 8651
# xml_port 8651
#
#-------------------------------------------------------------------------------
# The port gmetad will answer queries for XML. This facility allows
# simple subtree and summation views of the XML tree.
# default: 8652
# interactive_port 8652
#
#-------------------------------------------------------------------------------
# The number of threads answering XML requests
# default: 4
# server_threads 10
#
#-------------------------------------------------------------------------------
# Where gmetad stores its round-robin databases
# default: "/var/lib/ganglia/rrds"
# rrd_rootdir "/some/other/place"