auser-poolparty-extensions 0.0.7 → 0.1.1

data/lib/extensions/ganglia/templates/ganglia-web-conf.php.erb

@@ -0,0 +1,191 @@
+<?php
+# $Id: conf.php.in 1831 2008-09-26 12:18:54Z carenas $
+#
+# Gmetad-webfrontend version. Used to check for updates.
+#
+include_once "./version.php";
+
+#
+# The name of the directory in "./templates" which contains the
+# templates that you want to use. Templates are like a skin for the
+# site that can alter its look and feel.
+#
+$template_name = "default";
+
+#
+# If you installed gmetad in a directory other than the default
+# make sure you change it here.
+#
+
+# Where gmetad stores the rrd archives.
+$gmetad_root = "/var/lib/ganglia";
+$rrds = "$gmetad_root/rrds";
+
+# Leave this alone if rrdtool is installed in $gmetad_root,
+# otherwise, change it if it is installed elsewhere (like /usr/bin)
+define("RRDTOOL", "/usr/bin/rrdtool");
+
+# Location for modular-graph files.
+$graphdir='./graph.d';
+
+#
+# If you want to grab data from a different ganglia source specify it here.
+# Although, it would be strange to alter the IP since the Round-Robin
+# databases need to be local to be read. 
+#
+$ganglia_ip = "127.0.0.1";
+$ganglia_port = 8652;
+
+#
+# The maximum number of dynamic graphs to display.  If you set this
+# to 0 (the default) all graphs will be shown.  This option is
+# helpful if you are viewing the web pages from a browser with a 
+# small pipe.
+#
+$max_graphs = 0;
+
+#
+# In the Cluster View this sets the default number of columns used to
+# display the host grid below the summary graphs.
+#
+$hostcols = 4;
+
+#
+# In the Host View this sets the default number of columns used to
+# display the metric grid below the summary graphs.
+#
+$metriccols = 2;
+
+#
+# Turn on and off the Grid Snapshot. Now that we have a
+# hierarchical snapshot (per-cluster instead of per-node) on
+# the meta page this makes more sense. Most people will want this
+# on.
+#
+$show_meta_snapshot = "yes";
+
+# 
+# The default refresh frequency on pages.
+#
+$default_refresh = 300;
+
+#
+# Colors for the CPU report graph
+#
+$cpu_user_color = "3333bb";
+$cpu_nice_color = "ffea00";
+$cpu_system_color = "dd0000";
+$cpu_wio_color = "ff8a60";
+$cpu_idle_color = "e2e2f2";
+
+#
+# Colors for the MEMORY report graph
+#
+$mem_used_color = "5555cc";
+$mem_shared_color = "0000aa";
+$mem_cached_color = "33cc33";
+$mem_buffered_color = "99ff33";
+$mem_free_color = "00ff00";
+$mem_swapped_color = "9900CC";
+
+#
+# Colors for the LOAD report graph
+#
+$load_one_color = "CCCCCC";
+$proc_run_color = "0000FF";
+$cpu_num_color  = "FF0000";
+$num_nodes_color = "00FF00";
+
+# Other colors
+$jobstart_color = "ff3300";
+
+#
+# Colors for the load ranks.
+#
+$load_colors = array(
+   "100+" => "ff634f",
+   "75-100" =>"ffa15e",
+   "50-75" => "ffde5e",
+   "25-50" => "caff98",
+   "0-25" => "e2ecff",
+   "down" => "515151"
+);
+
+#
+# Load scaling
+#
+$load_scale = 1.0;
+
+#
+# Default color for single metric graphs
+#
+$default_metric_color = "555555";
+
+#
+# Default metric 
+#
+$default_metric = "load_one";
+
+#
+# remove the domainname from the FQDN hostnames in graphs
+# (to help with long hostnames in small charts)
+#
+$strip_domainname = false;
+
+#
+# Optional summary graphs
+#
+#$optional_graphs = array('packet');
+
+# 
+# Time ranges
+# Each value is the # of seconds in that range.
+#
+$time_ranges = array(
+   'hour'=>3600,
+   'day'=>86400,
+   'week'=>604800,
+   'month'=>2419200,
+   'year'=>31449600
+);
+
+# this key must exist in $time_ranges
+$default_time_range = 'hour';
+
+#
+# Graph sizes
+#
+$graph_sizes = array(
+   'small'=>array(
+     'height'=>40,
+     'width'=>130,
+     'fudge_0'=>0,
+     'fudge_1'=>0,
+     'fudge_2'=>0
+   ),
+   'medium'=>array(
+     'height'=>75,
+     'width'=>300,
+     'fudge_0'=>0,
+     'fudge_1'=>14,
+     'fudge_2'=>28
+   ),
+   'large'=>array(
+     'height'=>600,
+     'width'=>800,
+     'fudge_0'=>0,
+     'fudge_1'=>0,
+     'fudge_2'=>0
+   ),
+   # this was the default value when no other size was provided.
+   'default'=>array(
+     'height'=>100,
+     'width'=>400,
+     'fudge_0'=>0,
+     'fudge_1'=>0,
+     'fudge_2'=>0
+   )
+);
+$default_graph_size = 'default';
+$graph_sizes_keys = array_keys( $graph_sizes );
+?>

data/lib/extensions/ganglia/templates/gmetad.conf.erb

@@ -0,0 +1,116 @@
+# This is an example of a Ganglia Meta Daemon configuration file
+#                http://ganglia.sourceforge.net/
+#
+# $Id: gmetad.conf.in 1639 2008-08-09 23:30:32Z carenas $
+#
+#-------------------------------------------------------------------------------
+# 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 "my cluster" localhost
+#
+#
+<%= @node[:poolparty][:ganglia_gmetad_data_sources] %>
+
+#
+# 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 "<%= @node[:poolparty][:ganglia_pool_name] %>"
+#
+#-------------------------------------------------------------------------------
+# 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 "nobody")
+# default: "nobody"
+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"

data/lib/extensions/ganglia/templates/gmond.conf.erb

@@ -0,0 +1,426 @@
+/* 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 */
+/* some comments borrowed from http://www-user.tu-chemnitz.de/~aas/wiki/lib/exe/fetch.php?id=projekte%3Aganglia&cache=cache&media=gmond.conf.template */
+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 = 0 /*secs */
+  cleanup_threshold = 300 /*secs */
+  gexec = no
+  send_metadata_interval = 10 
+}
+
+/*
+ * The cluster attributes specified will be used as part of the <CLUSTER>
+ * tag that will wrap all hosts collected by this instance.
+ */
+cluster {
+  name = "<%= @node[:poolparty][:ganglia_cloud_name] %>"
+  owner = "unspecified"
+  latlong = "unspecified"
+  url = "unspecified"
+}
+
+/* The host section describes attributes of the host, like the location */
+host {
+  location = "unspecified"
+}
+
+/*
+	UDP send channels
+
+	Gmond will use UDP send channel(s) for sending monitoring
+	data it collects from _the local node_ to other nodes.
+
+	There are two different kinds of UDP send channels:
+	- unicast channel:
+	  specifies a single host that is supposed to receive monitoring
+	  data from other client nodes
+
+	- multicast channel:
+	  specifies a multicast domain that will be used to spread monitoring data
+
+	Note:
+	- the type of channel that should be used depends on the kind of monitoring 
+	  architecture you want to implement
+	- make sure to set 'mute = no' in the global configuration section!
+	- multiple UDP send channels can be configured
+	- gmond will send its data through all channels simultaneously
+	
+	See "Monitoringsoftware Ganglia - Installation, Konfiguration und Bewertung",
+	section "Architektur der Monitoringsoftware Ganglia" for further details!
+
+	Unicast UDP send channels:
+	- the target host has to be a node running gmond
+	- the gmond running on the target host has to be configured to
+	  accept data from other gmonds
+*/
+
+/* 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 = <%= @node[:poolparty][:ganglia_masters_ip] %> */
+  /* host = <%= @node[:poolparty][:ganglia_masters_ip] %> */
+  host = <%= @node[:poolparty][:ganglia_first_node_in_clusters_ip] %>
+  port = 8649
+  ttl = 1
+}
+
+/*
+	UDP receive channels
+
+	Gmond will 'listen' on all UDP receive channels for incoming
+	monitoring data. Incoming data from other gmonds will be added
+	to the cluster state maintained by the local node.
+
+	There are two different kinds of UDP receive channels:
+	- unicast channel:
+	  specifies a single UDP port that will accept incoming data
+
+	- multicast channel:
+	  tells gmond to join a multicast domain and accept incoming
+	  data sent by other members of the same domain
+
+	Note:
+	- the type of channel that should be used depends on the kind of monitoring 
+	  architecture you want to implement
+	- make sure to set 'deaf = no' in the global configuration section!
+	- multiple UDP receive channels can be configured
+	- gmond will accept data on all channels simultaneously
+
+	See "Monitoringsoftware Ganglia - Installation, Konfiguration und Bewertung",
+	section "Architektur der Monitoringsoftware Ganglia" for further details!
+
+    You can specify as many udp_recv_channels as you like. */
+udp_recv_channel {
+  /* mcast_join = <%= @node[:poolparty][:ganglia_this_nodes_private_ip] %> */
+  port = 8649
+  bind = <%= @node[:poolparty][:ganglia_this_nodes_private_ip] %>  
+  /* bind = 0.0.0.0 */
+  family = inet4
+
+  acl {
+    default = "allow"
+  }
+}
+<%# if @node[:poolparty][:ganglia_gmond_is_master] %>
+<%# end %>
+/*
+	TCP accept channels
+
+	Gmond will listen on all TCP accept channels for incoming connections
+	from nodes running gmetad. When a gmetad connects, gmond will transmit
+	_all monitoring data_ it has collected so far (i.e. the state of the
+	_whole cluster_ as far as gmond knows about it).
+
+	Note:
+	- make sure to set 'mute = no' in the global configuration section
+	- multiple TCP accept channels can be configured
+	- gmond will accept requests on all channels simultaneously
+
+   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
+  bind = <%= @node[:poolparty][:ganglia_this_nodes_private_ip] %>
+  acl {
+    default = "allow"
+  }
+}
+
+/* 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"
+  }
+}
+
+
+/* vim: ft=javascript */