Don't like ads? PRO users don't see any ads ;-)
Guest

Untitled

By: a guest on Jun 19th, 2011  |  syntax: None  |  size: 8.09 KB  |  hits: 56  |  expires: Never
download  |  raw  |  embed  |  report abuse  |  print
Text below is selected. Please press Ctrl+C to copy to your clipboard. (⌘+C on Mac)
  1. /* This configuration is as close to 2.5.x default behavior as possible
  2.    The values closely match ./gmond/metric.h definitions in 2.5.x */
  3. globals {                    
  4.   daemonize = yes              
  5.   setuid = yes            
  6.   user = ganglia              
  7.   debug_level = 0              
  8.   max_udp_msg_len = 1472        
  9.   mute = no            
  10.   deaf = no            
  11.   host_dmax = 0 /*secs */
  12.   cleanup_threshold = 300 /*secs */
  13.   gexec = no            
  14.   send_metadata_interval = 0    
  15. }
  16.  
  17. /* If a cluster attribute is specified, then all gmond hosts are wrapped inside
  18.  * of a <CLUSTER> tag.  If you do not specify a cluster tag, then all <HOSTS> will
  19.  * NOT be wrapped inside of a <CLUSTER> tag. */
  20. cluster {
  21.   name = "Mu Sigma IRD"
  22.   owner = "unspecified"
  23.   latlong = "unspecified"
  24.   url = "unspecified"
  25. }
  26.  
  27. /* The host section describes attributes of the host, like the location */
  28. host {
  29.   location = "unspecified"
  30. }
  31.  
  32. /* Feel free to specify as many udp_send_channels as you like.  Gmond
  33.    used to only support having a single channel */
  34. udp_send_channel {
  35.   mcast_join = 239.2.11.71
  36.   port = 8649
  37.   ttl = 1
  38. }
  39.  
  40. /* You can specify as many udp_recv_channels as you like as well. */
  41. udp_recv_channel {
  42.   mcast_join = 239.2.11.71
  43.   port = 8649
  44.   bind = 239.2.11.71
  45. }
  46.  
  47. /* You can specify as many tcp_accept_channels as you like to share
  48.    an xml description of the state of the cluster */
  49. tcp_accept_channel {
  50.   port = 8649
  51. }
  52.  
  53. /* Each metrics module that is referenced by gmond must be specified and
  54.    loaded. If the module has been statically linked with gmond, it does not
  55.    require a load path. However all dynamically loadable modules must include
  56.    a load path. */
  57. modules {
  58.   module {
  59.     name = "core_metrics"
  60.   }
  61.   module {
  62.     name = "cpu_module"
  63.     path = "/usr/lib/ganglia/modcpu.so"
  64.   }
  65.   module {
  66.     name = "disk_module"
  67.     path = "/usr/lib/ganglia/moddisk.so"
  68.   }
  69.   module {
  70.     name = "load_module"
  71.     path = "/usr/lib/ganglia/modload.so"
  72.   }
  73.   module {
  74.     name = "mem_module"
  75.     path = "/usr/lib/ganglia/modmem.so"
  76.   }
  77.   module {
  78.     name = "net_module"
  79.     path = "/usr/lib/ganglia/modnet.so"
  80.   }
  81.   module {
  82.     name = "proc_module"
  83.     path = "/usr/lib/ganglia/modproc.so"
  84.   }
  85.   module {
  86.     name = "sys_module"
  87.     path = "/usr/lib/ganglia/modsys.so"
  88.   }
  89. }
  90.  
  91. include ('/etc/ganglia/conf.d/*.conf')
  92.  
  93.  
  94. /* The old internal 2.5.x metric array has been replaced by the following
  95.    collection_group directives.  What follows is the default behavior for
  96.    collecting and sending metrics that is as close to 2.5.x behavior as
  97.    possible. */
  98.  
  99. /* This collection group will cause a heartbeat (or beacon) to be sent every
  100.    20 seconds.  In the heartbeat is the GMOND_STARTED data which expresses
  101.    the age of the running gmond. */
  102. collection_group {
  103.   collect_once = yes
  104.   time_threshold = 20
  105.   metric {
  106.     name = "heartbeat"
  107.   }
  108. }
  109.  
  110. /* This collection group will send general info about this host every 1200 secs.
  111.    This information doesn't change between reboots and is only collected once. */
  112. collection_group {
  113.   collect_once = yes
  114.   time_threshold = 1200
  115.   metric {
  116.     name = "cpu_num"
  117.     title = "CPU Count"
  118.   }
  119.   metric {
  120.     name = "cpu_speed"
  121.     title = "CPU Speed"
  122.   }
  123.   metric {
  124.     name = "mem_total"
  125.     title = "Memory Total"
  126.   }
  127.   /* Should this be here? Swap can be added/removed between reboots. */
  128.   metric {
  129.     name = "swap_total"
  130.     title = "Swap Space Total"
  131.   }
  132.   metric {
  133.     name = "boottime"
  134.     title = "Last Boot Time"
  135.   }
  136.   metric {
  137.     name = "machine_type"
  138.     title = "Machine Type"
  139.   }
  140.   metric {
  141.     name = "os_name"
  142.     title = "Operating System"
  143.   }
  144.   metric {
  145.     name = "os_release"
  146.     title = "Operating System Release"
  147.   }
  148.   metric {
  149.     name = "location"
  150.     title = "Location"
  151.   }
  152. }
  153.  
  154. /* This collection group will send the status of gexecd for this host every 300 secs */
  155. /* Unlike 2.5.x the default behavior is to report gexecd OFF.  */
  156. collection_group {
  157.   collect_once = yes
  158.   time_threshold = 300
  159.   metric {
  160.     name = "gexec"
  161.     title = "Gexec Status"
  162.   }
  163. }
  164.  
  165. /* This collection group will collect the CPU status info every 20 secs.
  166.    The time threshold is set to 90 seconds.  In honesty, this time_threshold could be
  167.    set significantly higher to reduce unneccessary network chatter. */
  168. collection_group {
  169.   collect_every = 20
  170.   time_threshold = 90
  171.   /* CPU status */
  172.   metric {
  173.     name = "cpu_user"  
  174.     value_threshold = "1.0"
  175.     title = "CPU User"
  176.   }
  177.   metric {
  178.     name = "cpu_system"  
  179.     value_threshold = "1.0"
  180.     title = "CPU System"
  181.   }
  182.   metric {
  183.     name = "cpu_idle"  
  184.     value_threshold = "5.0"
  185.     title = "CPU Idle"
  186.   }
  187.   metric {
  188.     name = "cpu_nice"  
  189.     value_threshold = "1.0"
  190.     title = "CPU Nice"
  191.   }
  192.   metric {
  193.     name = "cpu_aidle"
  194.     value_threshold = "5.0"
  195.     title = "CPU aidle"
  196.   }
  197.   metric {
  198.     name = "cpu_wio"
  199.     value_threshold = "1.0"
  200.     title = "CPU wio"
  201.   }
  202.   /* The next two metrics are optional if you want more detail...
  203.      ... since they are accounted for in cpu_system.  
  204.   metric {
  205.     name = "cpu_intr"
  206.     value_threshold = "1.0"
  207.     title = "CPU intr"
  208.   }
  209.   metric {
  210.     name = "cpu_sintr"
  211.     value_threshold = "1.0"
  212.     title = "CPU sintr"
  213.   }
  214.   */
  215. }
  216.  
  217. collection_group {
  218.   collect_every = 20
  219.   time_threshold = 90
  220.   /* Load Averages */
  221.   metric {
  222.     name = "load_one"
  223.     value_threshold = "1.0"
  224.     title = "One Minute Load Average"
  225.   }
  226.   metric {
  227.     name = "load_five"
  228.     value_threshold = "1.0"
  229.     title = "Five Minute Load Average"
  230.   }
  231.   metric {
  232.     name = "load_fifteen"
  233.     value_threshold = "1.0"
  234.     title = "Fifteen Minute Load Average"
  235.   }
  236. }
  237.  
  238. /* This group collects the number of running and total processes */
  239. collection_group {
  240.   collect_every = 80
  241.   time_threshold = 950
  242.   metric {
  243.     name = "proc_run"
  244.     value_threshold = "1.0"
  245.     title = "Total Running Processes"
  246.   }
  247.   metric {
  248.     name = "proc_total"
  249.     value_threshold = "1.0"
  250.     title = "Total Processes"
  251.   }
  252. }
  253.  
  254. /* This collection group grabs the volatile memory metrics every 40 secs and
  255.    sends them at least every 180 secs.  This time_threshold can be increased
  256.    significantly to reduce unneeded network traffic. */
  257. collection_group {
  258.   collect_every = 40
  259.   time_threshold = 180
  260.   metric {
  261.     name = "mem_free"
  262.     value_threshold = "1024.0"
  263.     title = "Free Memory"
  264.   }
  265.   metric {
  266.     name = "mem_shared"
  267.     value_threshold = "1024.0"
  268.     title = "Shared Memory"
  269.   }
  270.   metric {
  271.     name = "mem_buffers"
  272.     value_threshold = "1024.0"
  273.     title = "Memory Buffers"
  274.   }
  275.   metric {
  276.     name = "mem_cached"
  277.     value_threshold = "1024.0"
  278.     title = "Cached Memory"
  279.   }
  280.   metric {
  281.     name = "swap_free"
  282.     value_threshold = "1024.0"
  283.     title = "Free Swap Space"
  284.   }
  285. }
  286.  
  287. collection_group {
  288.   collect_every = 40
  289.   time_threshold = 300
  290.   metric {
  291.     name = "bytes_out"
  292.     value_threshold = 4096
  293.     title = "Bytes Sent"
  294.   }
  295.   metric {
  296.     name = "bytes_in"
  297.     value_threshold = 4096
  298.     title = "Bytes Received"
  299.   }
  300.   metric {
  301.     name = "pkts_in"
  302.     value_threshold = 256
  303.     title = "Packets Received"
  304.   }
  305.   metric {
  306.     name = "pkts_out"
  307.     value_threshold = 256
  308.     title = "Packets Sent"
  309.   }
  310. }
  311.  
  312. /* Different than 2.5.x default since the old config made no sense */
  313. collection_group {
  314.   collect_every = 1800
  315.   time_threshold = 3600
  316.   metric {
  317.     name = "disk_total"
  318.     value_threshold = 1.0
  319.     title = "Total Disk Space"
  320.   }
  321. }
  322.  
  323. collection_group {
  324.   collect_every = 40
  325.   time_threshold = 180
  326.   metric {
  327.     name = "disk_free"
  328.     value_threshold = 1.0
  329.     title = "Disk Space Available"
  330.   }
  331.   metric {
  332.     name = "part_max_used"
  333.     value_threshold = 1.0
  334.     title = "Maximum Disk Space Used"
  335.   }
  336. }