installing ganglia from de repos

files/gmetad.conf

@@ -41,7 +41,9 @@
 # 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 "mambi" 1 10.12.31.9
+data_source "mambi" 60 10.12.31.9:8649 # Ganglia Master node
+data_source "mambi" 60 10.12.31.154 # nodos
+data_source "mambi" 60 10.12.31.155 # nodos
 
 #
 # Round-Robin Archives
@@ -69,7 +71,7 @@ data_source "mambi" 1 10.12.31.9
 # The name of this Grid. All the data sources above will be wrapped in a GRID
 # tag with this name.
 # default: unspecified
-# gridname "MyGrid"
+gridname "UCLV HPC"
 #
 #-------------------------------------------------------------------------------
 # The authority URL for this grid. Used by other gmetads to locate graphs

files/gmond.conf → files/gmond.conf.master

@@ -28,7 +28,7 @@ globals {
  */
 cluster {
   name = "mambi"
-  owner = "uclv"
+  owner = "unspecified"
   latlong = "unspecified"
   url = "unspecified"
 }
@@ -42,7 +42,7 @@ host {
    used to only support having a single channel */
 
 udp_send_channel {
-  host = 10.12.31.9
+  host = localhost
   port = 8649
   ttl = 1
 }
@@ -52,7 +52,7 @@ udp_recv_channel {
   # mcast_join = 239.2.11.71
   port = 8649
   # bind = 239.2.11.71
-  retry_bind = true
+  # retry_bind = true
   # Size of the UDP buffer. If you are handling lots of metrics you really
   # should bump it up to e.g. 10MB or even higher.
   # buffer = 10485760

files/gmond.conf.nodes

+/* 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 = nobody
+  debug_level = 0
+  max_udp_msg_len = 1472
+  mute = no
+  deaf = no
+  allow_extra_data = yes
+  host_dmax = 86400 /*secs. Expires (removes from web interface) hosts in 1 day */
+  host_tmax = 20 /*secs */
+  cleanup_threshold = 300 /*secs */
+  gexec = no
+  # By default gmond will use reverse DNS resolution when displaying your hostname
+  # Uncommeting following value will override that value.
+  # override_hostname = "mywebserver.domain.com"
+  # If you are not using multicast this value should be set to something other than 0.
+  # Otherwise if you restart aggregator gmond you will get empty graphs. 60 seconds is reasonable
+  send_metadata_interval = 0 /*secs */
+
+}
+
+/*
+ * The cluster attributes specified will be used as part of the <CLUSTER>
+ * tag that will wrap all hosts collected by this instance.
+ */
+cluster {
+  name = "mambi"
+  owner = "unspecified"
+  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 {
+  mcast_join = 239.2.11.71
+  host = localhost
+  port = 8649
+  ttl = 1
+}
+
+/* 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
+  retry_bind = true
+  # Size of the UDP buffer. If you are handling lots of metrics you really
+  # should bump it up to e.g. 10MB or even higher.
+  # buffer = 10485760
+}
+
+/* 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
+  # If you want to gzip XML output
+  gzip_output = no
+}
+
+/* Channel to receive sFlow datagrams */
+#udp_recv_channel {
+#  port = 6343
+#}
+
+/* Optional sFlow settings */
+#sflow {
+# udp_port = 6343
+# accept_vm_metrics = yes
+# accept_jvm_metrics = yes
+# multiple_jvm_instances = no
+# accept_http_metrics = yes
+# multiple_http_instances = no
+# accept_memcache_metrics = yes
+# multiple_memcache_instances = no
+#}
+
+/* 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"
+  }
+}
+
+/* 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*/
+collection_group {
+  collect_every = 60
+  time_threshold = 60
+  metric {
+    name = "cpu_num"
+    title = "CPU Count"
+  }
+  metric {
+    name = "cpu_speed"
+    title = "CPU Speed"
+  }
+  metric {
+    name = "mem_total"
+    title = "Memory Total"
+  }
+  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"
+  }
+  metric {
+    name = "cpu_steal"
+    value_threshold = "1.0"
+    title = "CPU steal"
+  }
+  /* 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"
+  }
+}
+
+include ("/etc/ganglia/conf.d/*.conf")

manifests/common.pp

@@ -5,67 +5,7 @@
 # @example
 #   include ganglia::common
 class ganglia::common inherits ganglia::params {
-  package { $common_repos_pack:
+  package { 'ganglia-gmond':
     ensure  => installed,
-    #notify => File['/root/ganglia/libconfuse-2.7-7.el7.x86_64.rpm'],
-  }
-
-  file {'/root/ganglia/libconfuse-2.7-7.el7.x86_64.rpm':
-    ensure => present,
-    source => 'puppet:///modules/ganglia/libconfuse-2.7-7.el7.x86_64.rpm',
-    # notify => File['/root/ganglia/libconfuse-devel-2.7-7.el7.x86_64.rpm'],
-  }
-  file {'/root/ganglia/libconfuse-devel-2.7-7.el7.x86_64.rpm':
-    ensure => present,
-    source => 'puppet:///modules/ganglia/libconfuse-devel-2.7-7.el7.x86_64.rpm',
-  }
-
-  package { 'libconfuse':
-    ensure   => '2.7-7.el7',
-    provider => rpm,
-    source   => '/root/ganglia/libconfuse-2.7-7.el7.x86_64.rpm',
-    require  => File['/root/ganglia/libconfuse-2.7-7.el7.x86_64.rpm'],
-  }
-  package { 'libconfuse-devel':
-    ensure  => '2.7-7.el7',
-    provider => rpm,
-    source  => '/root/ganglia/libconfuse-devel-2.7-7.el7.x86_64.rpm',
-    require => File['/root/ganglia/libconfuse-devel-2.7-7.el7.x86_64.rpm'],
-  }
-
-  file {'/root/ganglia':
-    ensure  => directory,
-    #require => Package['libconfuse-devel-2.7-7.el7.x86_64.rpm'],
-  }
-  file {'/root/ganglia/ganglia-3.7.2.tar.gz':
-    ensure => present,
-    source => 'puppet:///modules/ganglia/ganglia-3.7.2.tar.gz',
-    require => File['/root/ganglia'],
-  }
-
-
-  exec { 'rpmbuild -tb ganglia-3.7.2.tar.gz':
-    cwd         => '/root/ganglia',
-    #path        => '/usr/bin:/usr/sbin:/bin:/usr/local/bin',
-    path        => ['/usr/bin', '/usr/sbin',],
-    subscribe   => File['/root/ganglia/ganglia-3.7.2.tar.gz'],
-    refreshonly => true,
-  }
-  exec { 'yum install *ganglia*.rpm -y':
-    cwd         => '/rpmbuild/RPMS/x86_64/',
-    path        => ['/usr/bin', '/usr/sbin',],
-    #path        => '/usr/bin:/usr/sbin:/bin:/usr/local/bin',
-    subscribe   => Exec['rpmbuild -tb ganglia-3.7.2.tar.gz'],
-    refreshonly => true,
-  }
-  file {'/etc/ganglia':
-    ensure => directory,
-  }
-  file { '/etc/ganglia/gmond.conf':
-    ensure  => file,
-    mode    => '0644',
-    source  => 'puppet:///modules/ganglia/gmond.conf',
-    require => File['/etc/ganglia'],
-    notify  => Service['gmond'],
   }
 }

manifests/init.pp

@@ -5,8 +5,7 @@
 # @example
 #   include ganglia
 class ganglia (
-  String $version = $ganglia::params::version,
-  Boolean $with_server = $ganglia::params::with_server,
+    Boolean $with_server = $ganglia::params::with_server,
 ) inherits ganglia::params
 {
   include ganglia::common

manifests/nodes.pp

@@ -6,6 +6,11 @@
 #   include ganglia::nodes
 class ganglia::nodes {
   include ganglia::common
+  file { '/etc/ganglia/gmond.conf':
+    ensure => file,
+    mode => '0644',
+    source => 'puppet:///modules/ganglia/gmond.conf.nodes',
+  }
   service { 'gmond':
     ensure => running,
     enable => true,

manifests/params.pp

@@ -5,27 +5,12 @@
 # @example
 #   include ganglia::params
 class ganglia::params {
-  $version = '3.7.2'
   $with_server = false
-  $common_repos_pack = [
-    'freetype-devel',
-    'rpm-build',
-    'libpng-devel',
-    'libart_lgpl-devel',
-    'python-devel',
-    'pcre-devel',
-    'autoconf',
-    'automake',
-    'libtool',
-    'expat-devel',
-    'apr-devel',
-    'gcc-c++',
-    'make',
-    'pkgconfig'
-  ]
   $server_pack = [
-    'php',
-    'httpd',
-    'php-gd',
+    'ganglia',
+    'rrdtool',
+    'ganglia-gmetad',
+    'ganglia-gmond',
+    'ganglia-web'
   ]
 }

manifests/server.pp

@@ -14,26 +14,11 @@ class ganglia::server inherits ganglia::params {
     source => 'puppet:///modules/ganglia/gmetad.conf',
     notify => Service['gmetad'],
   }
-  file { '/root/ganglia/ganglia-web-3.1.1-1.noarch.rpm':
-    ensure => file,
-    mode => '0644',
-    source => 'puppet:///modules/ganglia/ganglia-web-3.1.1-1.noarch.rpm',
-  }
-  package { 'ganglia-web':
-    ensure   => '3.1.1-1',
-    provider => rpm,
-    source   => '/root/ganglia/ganglia-web-3.1.1-1.noarch.rpm',
-    require  => File['/root/ganglia/ganglia-web-3.1.1-1.noarch.rpm'],
-    notify   => Service['httpd'],
-  }
-
   service { 'gmond':
     ensure => running,
     enable => true,
     hasrestart => true,
     hasstatus  => true,
-    subscribe   => File['/etc/ganglia/gmetad.conf'],
-    # pattern => 'gmond',
   }
   service { 'gmetad':
     ensure => running,
@@ -47,7 +32,5 @@ class ganglia::server inherits ganglia::params {
     enable => true,
     hasrestart => true,
     hasstatus  => true,
-    # pattern => 'httpd',
   }
-
 }