nodegpu01 gmond.conf

nodegpu gmond.conf


/* 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
  host_dmax = 0 /*secs */
  cleanup_threshold = 300 /*secs */
  gexec = no
  send_metadata_interval = 0
}

/* 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 = "GPU cluster"
  owner = "Propietat de FBM"
  latlong = "unspecified"
  url = "unspecified"
}

/* The host section describes attributes of the host, like the location */
host {
  location = "suport.informatica@example.org"
}

/* 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 = 239.2.11.72
  port = 8649
  ttl = 1
}

/* You can specify as many udp_recv_channels as you like as well. */
udp_recv_channel {
  mcast_join = 239.2.11.72
  port = 8649
  bind = 239.2.11.72
}

/* 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 = "/usr/lib/ganglia/modcpu.so"
  }
  module {
    name = "disk_module"
    path = "/usr/lib/ganglia/moddisk.so"
  }
  module {
    name = "load_module"
    path = "/usr/lib/ganglia/modload.so"
  }
  module {
    name = "mem_module"
    path = "/usr/lib/ganglia/modmem.so"
  }
  module {
    name = "net_module"
    path = "/usr/lib/ganglia/modnet.so"
  }
  module {
    name = "proc_module"
    path = "/usr/lib/ganglia/modproc.so"
  }
  module {
    name = "sys_module"
    path = "/usr/lib/ganglia/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/* The old internal 2.5.x metric array has been replaced by the following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"
  }
}