ganglia

ganglia

ganglia安装

需要安装的ganglia包：

yum install ganglia
yum install ganglia-gmond
yum install ganglia-gmond-python

ganglia的配置文件：
/etc/ganglia/gmond.conf

/etc/ganglia/conf.d/是放插件的配置文件的位置
/usr/lib64/ganglia/python_modules/是放python格式的插件脚本的位置

ganglia的启动：

service gmond restart

gmond.conf

gmond分master和slave两个角色。
* master，用于接收各个节点的数据，且提供tcp的对外服务，让其他应用可以从它这里获取到整个集群的监控信息。
* slave，用于采集当前机器的数据，然后通过udp的方式，上报给master。

这两个角色的配置文件，也不大一样。

master

gmond.conf配置文件参见附录一

slave

gmond.conf配置文件参见附录二

插件

可以自行写ganglia插件应用。

插件配置

/etc/ganglia/conf.d目录下放socket_total.pyconf

modules {
  module {
    name = "socket_total"
    language = "python"
  }
}

collection_group {
  collect_every = 30
  time_threshold = 50
  metric {
    name = "socket_total"
    title = "Socket_Total"
    value_threshold = 100
  }
}

插件内容

/usr/lib64/ganglia/python_modules/目录下放socket_total.py

#!/usr/bin/env python
#-*- coding: utf-8 -*-

import subprocess
import time
import logging
import traceback
import os

def socket_handler(name):
    handle = subprocess.Popen("lsof -i -n | wc -l", stdout = subprocess.PIPE, shell = True)
    output = handle.communicate()[0]
    return float(output)

#define metric_init function
def metric_init(params):
    global descriptors

    dict = {
        'name': 'socket_total',
        'call_back': socket_handler,
        'time_max': 30,
        'value_type': 'float',
        'units': 'num',
        'slope': 'both',
        'format': '%f',
        'description': 'Number of sockets connetions',
        'groups': 'network'
        }

    descriptors = [dict]
    return descriptors

#define metric_claunup function
def metric_cleanup():
    '''Clean up the metric module.'''
    #pass

#This code is for debugging and unit testing
if __name__ == '__main__':
    metric_init({})
    for d in descriptors:
        v = d['call_back'](d['name'])
        print 'value for %s is %s' % (d['name'],  v)

ganglia安装后的测试

# telnet gmond_core_ip gmond_server_port
telnet 1.2.3.4 1234

如果获取到一堆xml格式数据，且数据里面能够查到所监控的各节点的ip地址，则安装、运行成功。

附录一

/* 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 = root
  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 = 25 /*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 = "dtdream"
  owner = "dtdream"
  latlong = "dtdream"
  url = "dtdream"
}

/* The host section describes attributes of the host, like the location */
host {
  location = "dtdream"
}

/* Feel free to specify as many udp_send_channels as you like.  Gmond
   used to only support having a single channel */
udp_send_channel {
    host = 192.168.137.82
    port = 61094
    ttl = 1
}

/* You can specify as many udp_recv_channels as you like as well. */
udp_recv_channel {
    port = 61094
}

/* 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 = 61094
  # If you want to gzip XML output
  gzip_output = no
}

/* Channel to receive sFlow datagrams */
#udp_recv_channel {
#  port = 61094
#}

/* Optional sFlow settings */
#sflow {
# udp_port = 61094
# 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")

附录二

/* 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 = root
  debug_level = 0
  max_udp_msg_len = 1472
  mute = no
  deaf = yes
  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 = 25 /*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 = "dtdream"
  owner = "dtdream"
  latlong = "dtdream"
  url = "dtdream"
}

/* The host section describes attributes of the host, like the location */
host {
  location = "dtdream"
}

/* Feel free to specify as many udp_send_channels as you like.  Gmond
   used to only support having a single channel */
udp_send_channel {
    host = 192.168.137.82
    port = 61094
    ttl = 1
}

/* You can specify as many udp_recv_channels as you like as well. */
udp_recv_channel {
    port = 61094
}

/* 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 = 61094
  # If you want to gzip XML output
  gzip_output = no
}

/* Channel to receive sFlow datagrams */
#udp_recv_channel {
#  port = 61094
#}

/* Optional sFlow settings */
#sflow {
# udp_port = 61094
# 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")