ansible deployment for graphite and grafana

* ensure you define [graphite] and [grafana] in your
  hosts file.

* The grafana service is lightweight and can
  live on the same host as the graphite host. However,
  it can also be separated to run on its own server if
  desired.

* Once the graphite-web services are deployed (which also sets
  up the carbon-cache service), and the grafana service is
  deployed, you will need to define the data source for your
  graphite host in the grafana instance.

* The grafana service
  runs on port 3000, and has the default user/pass of admin/admin.

* username / password for graphite is set in install/group_vars/all

* firewalld is disabled on the grafana and graphite hosts
  If firewalls are needed, iptables-service is suggested but
  left us to deployment team.

* Added gen_hostfile.sh updates for the needed hosts entries, with
  comments to the user on what needs to be in 'hosts' file.

graphite db sets up

Change-Id: I27660b6ecbf019699c124b02b4b4fd6185547a54

ansible/README.md

@@ -6,6 +6,8 @@ Playbooks for:
 * Install Browbeat
 * Install collectd
 * Install connmon
+* Install graphite service
+* Install grafana service
 * Install grafana dashboards
 * Install shaker
 * Check overcloud for performance issues
@@ -50,6 +52,17 @@ Install Connmon
 # ansible-playbook -i hosts install/connmon.yml
 ```
 
+Install graphite service
+```
+# ansible-playbook -i hosts install/graphite.yml
+```
+
+Install grafana service
+* Default user is admin/admin and the graphite data source will need to be defined.
+```
+# ansible-playbook -i hosts install/grafana.yml
+```
+
 Install Grafana Dashboards (Requires a Grafana Server)
 * Review install/group_vars/all before deploying the grafana dashboards
 ```

ansible/gen_hostfile.sh

@@ -114,6 +114,19 @@ if [[ ${#ceph_hn} -gt 0 ]]; then
   echo "${ceph}" | tee -a ${ansible_inventory_file}
  done
 fi
+echo "" | tee -a ${ansible_inventory_file}
+echo "[graphite]" | tee -a ${ansible_inventory_file}
+echo "## example host entry." | tee -a ${ansible_inventory_file}
+echo "#host-01" | tee -a ${ansible_inventory_file}
+echo "" | tee -a ${ansible_inventory_file}
+echo "[grafana]" | tee -a ${ansible_inventory_file}
+echo "## example host entry." | tee -a ${ansible_inventory_file}
+echo "#host-02" | tee -a ${ansible_inventory_file}
+
+echo "---------------------------"
+echo "IMPORTANT: If you plan on deploying graphite and grafana, update hosts and make sure"
+echo "           the [graphite] and [grafana] hosts entries are updated with valid hosts."
+echo "           You will need to have passwordless access to root on these hosts."
 echo "---------------------------"
 
 # Before referencing a host in ~/.ssh/config, ensure correct permissions on ssh config file

ansible/install/grafana.yml

@@ -0,0 +1,9 @@
+---
+#
+# Playbook to install grafana
+#
+
+- hosts: grafana
+  remote_user: root
+  roles:
+    - { role: grafana }

ansible/install/graphite.yml

@@ -0,0 +1,9 @@
+---
+#
+# Playbook to install graphite-web
+#
+
+- hosts: graphite
+  remote_user: root
+  roles:
+    - { role: graphite }

ansible/install/group_vars/all

@@ -30,6 +30,10 @@ grafana_api_key: (Your Grafana API Key)
 # Grafana Server IP Address (Can be hosted on the Graphite server)
 grafana_host: 1.1.1.1
 
+# Graphite username and password for login on the dashboard
+graphite_username: root
+graphite_password: calvin
+
 # Dashboards - Batch number of hosts per row for all-{cpu, memory, disk, network} dashboards
 dashboards_batch: 20
 

ansible/install/roles/grafana/tasks/main.yml

@@ -0,0 +1,35 @@
+---
+#
+# Install/run grafana-server for browbeat
+#
+
+- name: Check for epel
+  shell: rpm -qa | grep -q epel-release
+  ignore_errors: true
+  register: epel_installed
+
+- name: Install epel repo
+  command: rpm -ivh {{ epel_repo }}
+  become: true
+  when: epel_installed.rc != 0
+
+- name: Install grafana rpms
+  yum: name={{ item }} state=present
+  become: true
+  with_items:
+    - https://grafanarel.s3.amazonaws.com/builds/grafana-2.6.0-1.x86_64.rpm
+
+# disable firewalld (might need to create specific firewall rules or leave it to admin to do via iptables)
+
+- name: disable firewalld
+  service: name=firewalld state=stopped enabled=false
+  become: true
+
+#
+# setup the grafana-server service
+#
+
+- name: Setup grafana-server service
+  service: name=grafana-server state=started enabled=true
+  become: true
+

ansible/install/roles/graphite/files/carbon.conf

@@ -0,0 +1,370 @@
+[cache]
+# Configure carbon directories.
+#
+# OS environment variables can be used to tell carbon where graphite is
+# installed, where to read configuration from and where to write data.
+#
+#   GRAPHITE_ROOT        - Root directory of the graphite installation.
+#                          Defaults to ../
+#   GRAPHITE_CONF_DIR    - Configuration directory (where this file lives).
+#                          Defaults to $GRAPHITE_ROOT/conf/
+#   GRAPHITE_STORAGE_DIR - Storage directory for whipser/rrd/log/pid files.
+#                          Defaults to $GRAPHITE_ROOT/storage/
+#
+# To change other directory paths, add settings to this file. The following
+# configuration variables are available with these default values:
+#
+#   STORAGE_DIR    = $GRAPHITE_STORAGE_DIR
+#   LOCAL_DATA_DIR = STORAGE_DIR/whisper/
+#   WHITELISTS_DIR = STORAGE_DIR/lists/
+#   CONF_DIR       = STORAGE_DIR/conf/
+#   LOG_DIR        = STORAGE_DIR/log/
+#   PID_DIR        = STORAGE_DIR/
+#
+# For FHS style directory structures, use:
+#
+#   STORAGE_DIR    = /var/lib/carbon/
+#   CONF_DIR       = /etc/carbon/
+#   LOG_DIR        = /var/log/carbon/
+#   PID_DIR        = /var/run/
+#
+#LOCAL_DATA_DIR = /opt/graphite/storage/whisper/
+
+STORAGE_DIR    = /var/lib/carbon/
+LOCAL_DATA_DIR = /var/lib/carbon/whisper/
+WHITELISTS_DIR = /var/lib/carbon/lists/
+CONF_DIR       = /etc/carbon/
+LOG_DIR        = /var/log/carbon/
+PID_DIR        = /var/run/
+
+# Enable daily log rotation. If disabled, a kill -HUP can be used after a manual rotate
+
+ENABLE_LOGROTATION = True
+
+# Specify the user to drop privileges to
+# If this is blank carbon runs as the user that invokes it
+# This user must have write access to the local data directory
+USER = carbon
+
+#
+# NOTE: The above settings must be set under [relay] and [aggregator]
+#       to take effect for those daemons as well
+
+# Limit the size of the cache to avoid swapping or becoming CPU bound.
+# Sorts and serving cache queries gets more expensive as the cache grows.
+# Use the value "inf" (infinity) for an unlimited cache size.
+MAX_CACHE_SIZE = inf
+
+# Limits the number of whisper update_many() calls per second, which effectively
+# means the number of write requests sent to the disk. This is intended to
+# prevent over-utilizing the disk and thus starving the rest of the system.
+# When the rate of required updates exceeds this, then carbon's caching will
+# take effect and increase the overall throughput accordingly.
+MAX_UPDATES_PER_SECOND = 2000
+
+# If defined, this changes the MAX_UPDATES_PER_SECOND in Carbon when a
+# stop/shutdown is initiated.  This helps when MAX_UPDATES_PER_SECOND is
+# relatively low and carbon has cached a lot of updates; it enables the carbon
+# daemon to shutdown more quickly. 
+# MAX_UPDATES_PER_SECOND_ON_SHUTDOWN = 1000
+
+# Softly limits the number of whisper files that get created each minute.
+# Setting this value low (like at 50) is a good way to ensure your graphite
+# system will not be adversely impacted when a bunch of new metrics are
+# sent to it. The trade off is that it will take much longer for those metrics'
+# database files to all get created and thus longer until the data becomes usable.
+# Setting this value high (like "inf" for infinity) will cause graphite to create
+# the files quickly but at the risk of slowing I/O down considerably for a while.
+MAX_CREATES_PER_MINUTE = 200
+
+LINE_RECEIVER_INTERFACE = 0.0.0.0
+LINE_RECEIVER_PORT = 2003
+
+# Set this to True to enable the UDP listener. By default this is off
+# because it is very common to run multiple carbon daemons and managing
+# another (rarely used) port for every carbon instance is not fun.
+ENABLE_UDP_LISTENER = False
+UDP_RECEIVER_INTERFACE = 0.0.0.0
+UDP_RECEIVER_PORT = 2003
+
+PICKLE_RECEIVER_INTERFACE = 0.0.0.0
+PICKLE_RECEIVER_PORT = 2004
+
+# Set to false to disable logging of successful connections
+LOG_LISTENER_CONNECTIONS = True
+
+# Per security concerns outlined in Bug #817247 the pickle receiver
+# will use a more secure and slightly less efficient unpickler.
+# Set this to True to revert to the old-fashioned insecure unpickler.
+USE_INSECURE_UNPICKLER = False
+
+CACHE_QUERY_INTERFACE = 0.0.0.0
+CACHE_QUERY_PORT = 7002
+
+# Set this to False to drop datapoints received after the cache
+# reaches MAX_CACHE_SIZE. If this is True (the default) then sockets
+# over which metrics are received will temporarily stop accepting
+# data until the cache size falls below 95% MAX_CACHE_SIZE.
+USE_FLOW_CONTROL = True
+
+# By default, carbon-cache will log every whisper update and cache hit. This can be excessive and
+# degrade performance if logging on the same volume as the whisper data is stored.
+LOG_UPDATES = False
+LOG_CACHE_HITS = False
+LOG_CACHE_QUEUE_SORTS = True
+
+# The thread that writes metrics to disk can use on of the following strategies
+# determining the order in which metrics are removed from cache and flushed to
+# disk. The default option preserves the same behavior as has been historically
+# available in version 0.9.10.
+#
+# sorted - All metrics in the cache will be counted and an ordered list of
+# them will be sorted according to the number of datapoints in the cache at the
+# moment of the list's creation. Metrics will then be flushed from the cache to
+# disk in that order.
+#
+# max - The writer thread will always pop and flush the metric from cache
+# that has the most datapoints. This will give a strong flush preference to
+# frequently updated metrics and will also reduce random file-io. Infrequently
+# updated metrics may only ever be persisted to disk at daemon shutdown if
+# there are a large number of metrics which receive very frequent updates OR if
+# disk i/o is very slow.
+#
+# naive - Metrics will be flushed from the cache to disk in an unordered
+# fashion. This strategy may be desirable in situations where the storage for
+# whisper files is solid state, CPU resources are very limited or deference to
+# the OS's i/o scheduler is expected to compensate for the random write
+# pattern.
+#
+CACHE_WRITE_STRATEGY = sorted
+
+# On some systems it is desirable for whisper to write synchronously.
+# Set this option to True if you'd like to try this. Basically it will
+# shift the onus of buffering writes from the kernel into carbon's cache.
+WHISPER_AUTOFLUSH = False
+
+# By default new Whisper files are created pre-allocated with the data region
+# filled with zeros to prevent fragmentation and speed up contiguous reads and
+# writes (which are common). Enabling this option will cause Whisper to create
+# the file sparsely instead. Enabling this option may allow a large increase of
+# MAX_CREATES_PER_MINUTE but may have longer term performance implications
+# depending on the underlying storage configuration.
+# WHISPER_SPARSE_CREATE = False
+
+# Only beneficial on linux filesystems that support the fallocate system call.
+# It maintains the benefits of contiguous reads/writes, but with a potentially
+# much faster creation speed, by allowing the kernel to handle the block
+# allocation and zero-ing. Enabling this option may allow a large increase of
+# MAX_CREATES_PER_MINUTE. If enabled on an OS or filesystem that is unsupported
+# this option will gracefully fallback to standard POSIX file access methods.
+WHISPER_FALLOCATE_CREATE = True
+
+# Enabling this option will cause Whisper to lock each Whisper file it writes
+# to with an exclusive lock (LOCK_EX, see: man 2 flock). This is useful when
+# multiple carbon-cache daemons are writing to the same files
+# WHISPER_LOCK_WRITES = False
+
+# Set this to True to enable whitelisting and blacklisting of metrics in
+# CONF_DIR/whitelist and CONF_DIR/blacklist. If the whitelist is missing or
+# empty, all metrics will pass through
+# USE_WHITELIST = False
+
+# By default, carbon itself will log statistics (such as a count,
+# metricsReceived) with the top level prefix of 'carbon' at an interval of 60
+# seconds. Set CARBON_METRIC_INTERVAL to 0 to disable instrumentation
+# CARBON_METRIC_PREFIX = carbon
+# CARBON_METRIC_INTERVAL = 60
+
+# Enable AMQP if you want to receve metrics using an amqp broker
+# ENABLE_AMQP = False
+
+# Verbose means a line will be logged for every metric received
+# useful for testing
+# AMQP_VERBOSE = False
+
+# AMQP_HOST = localhost
+# AMQP_PORT = 5672
+# AMQP_VHOST = /
+# AMQP_USER = guest
+# AMQP_PASSWORD = guest
+# AMQP_EXCHANGE = graphite
+# AMQP_METRIC_NAME_IN_BODY = False
+
+# The manhole interface allows you to SSH into the carbon daemon
+# and get a python interpreter. BE CAREFUL WITH THIS! If you do
+# something like time.sleep() in the interpreter, the whole process
+# will sleep! This is *extremely* helpful in debugging, assuming
+# you are familiar with the code. If you are not, please don't
+# mess with this, you are asking for trouble :)
+#
+# ENABLE_MANHOLE = False
+# MANHOLE_INTERFACE = 127.0.0.1
+# MANHOLE_PORT = 7222
+# MANHOLE_USER = admin
+# MANHOLE_PUBLIC_KEY = ssh-rsa AAAAB3NzaC1yc2EAAAABiwAaAIEAoxN0sv/e4eZCPpi3N3KYvyzRaBaMeS2RsOQ/cDuKv11dlNzVeiyc3RFmCv5Rjwn/lQ79y0zyHxw67qLyhQ/kDzINc4cY41ivuQXm2tPmgvexdrBv5nsfEpjs3gLZfJnyvlcVyWK/lId8WUvEWSWHTzsbtmXAF2raJMdgLTbQ8wE=
+
+# Patterns for all of the metrics this machine will store. Read more at
+# http://en.wikipedia.org/wiki/Advanced_Message_Queuing_Protocol#Bindings
+#
+# Example: store all sales, linux servers, and utilization metrics
+# BIND_PATTERNS = sales.#, servers.linux.#, #.utilization
+#
+# Example: store everything
+# BIND_PATTERNS = #
+
+# To configure special settings for the carbon-cache instance 'b', uncomment this:
+#[cache:b]
+#LINE_RECEIVER_PORT = 2103
+#PICKLE_RECEIVER_PORT = 2104
+#CACHE_QUERY_PORT = 7102
+# and any other settings you want to customize, defaults are inherited
+# from [carbon] section.
+# You can then specify the --instance=b option to manage this instance
+
+
+
+[relay]
+USER = carbon
+LINE_RECEIVER_INTERFACE = 0.0.0.0
+LINE_RECEIVER_PORT = 2013
+PICKLE_RECEIVER_INTERFACE = 0.0.0.0
+PICKLE_RECEIVER_PORT = 2014
+
+# Set to false to disable logging of successful connections
+LOG_LISTENER_CONNECTIONS = True
+
+# Carbon-relay has several options for metric routing controlled by RELAY_METHOD
+#
+# Use relay-rules.conf to route metrics to destinations based on pattern rules
+#RELAY_METHOD = rules
+#
+# Use consistent-hashing for even distribution of metrics between destinations
+#RELAY_METHOD = consistent-hashing
+#
+# Use consistent-hashing but take into account an aggregation-rules.conf shared
+# by downstream carbon-aggregator daemons. This will ensure that all metrics
+# that map to a given aggregation rule are sent to the same carbon-aggregator
+# instance.
+# Enable this for carbon-relays that send to a group of carbon-aggregators
+#RELAY_METHOD = aggregated-consistent-hashing
+RELAY_METHOD = rules
+
+# If you use consistent-hashing you can add redundancy by replicating every
+# datapoint to more than one machine.
+REPLICATION_FACTOR = 1
+
+# This is a list of carbon daemons we will send any relayed or
+# generated metrics to. The default provided would send to a single
+# carbon-cache instance on the default port. However if you
+# use multiple carbon-cache instances then it would look like this:
+#
+# DESTINATIONS = 127.0.0.1:2004:a, 127.0.0.1:2104:b
+#
+# The general form is IP:PORT:INSTANCE where the :INSTANCE part is
+# optional and refers to the "None" instance if omitted.
+#
+# Note that if the destinations are all carbon-caches then this should
+# exactly match the webapp's CARBONLINK_HOSTS setting in terms of
+# instances listed (order matters!).
+#
+# If using RELAY_METHOD = rules, all destinations used in relay-rules.conf
+# must be defined in this list
+DESTINATIONS = 127.0.0.1:2004
+
+# This defines the maximum "message size" between carbon daemons.
+# You shouldn't need to tune this unless you really know what you're doing.
+MAX_DATAPOINTS_PER_MESSAGE = 2000
+MAX_QUEUE_SIZE = 400000
+
+# Set this to False to drop datapoints when any send queue (sending datapoints
+# to a downstream carbon daemon) hits MAX_QUEUE_SIZE. If this is True (the
+# default) then sockets over which metrics are received will temporarily stop accepting
+# data until the send queues fall below 80% MAX_QUEUE_SIZE.
+USE_FLOW_CONTROL = True
+
+# Set this to True to enable whitelisting and blacklisting of metrics in
+# CONF_DIR/whitelist and CONF_DIR/blacklist. If the whitelist is missing or
+# empty, all metrics will pass through
+# USE_WHITELIST = False
+
+# By default, carbon itself will log statistics (such as a count,
+# metricsReceived) with the top level prefix of 'carbon' at an interval of 60
+# seconds. Set CARBON_METRIC_INTERVAL to 0 to disable instrumentation
+# CARBON_METRIC_PREFIX = carbon
+# CARBON_METRIC_INTERVAL = 60
+
+
+[aggregator]
+USER = carbon
+LINE_RECEIVER_INTERFACE = 0.0.0.0
+LINE_RECEIVER_PORT = 2023
+
+PICKLE_RECEIVER_INTERFACE = 0.0.0.0
+PICKLE_RECEIVER_PORT = 2024
+
+# Set to false to disable logging of successful connections
+LOG_LISTENER_CONNECTIONS = True
+
+# If set true, metric received will be forwarded to DESTINATIONS in addition to
+# the output of the aggregation rules. If set false the carbon-aggregator will
+# only ever send the output of aggregation.
+FORWARD_ALL = True
+
+# This is a list of carbon daemons we will send any relayed or
+# generated metrics to. The default provided would send to a single
+# carbon-cache instance on the default port. However if you
+# use multiple carbon-cache instances then it would look like this:
+#
+# DESTINATIONS = 127.0.0.1:2004:a, 127.0.0.1:2104:b
+# 
+# The format is comma-delimited IP:PORT:INSTANCE where the :INSTANCE part is
+# optional and refers to the "None" instance if omitted.
+#
+# Note that if the destinations are all carbon-caches then this should
+# exactly match the webapp's CARBONLINK_HOSTS setting in terms of
+# instances listed (order matters!).
+DESTINATIONS = 127.0.0.1:2004
+
+# If you want to add redundancy to your data by replicating every
+# datapoint to more than one machine, increase this.
+REPLICATION_FACTOR = 1
+
+# This is the maximum number of datapoints that can be queued up
+# for a single destination. Once this limit is hit, we will
+# stop accepting new data if USE_FLOW_CONTROL is True, otherwise
+# we will drop any subsequently received datapoints.
+MAX_QUEUE_SIZE = 10000
+
+# Set this to False to drop datapoints when any send queue (sending datapoints
+# to a downstream carbon daemon) hits MAX_QUEUE_SIZE. If this is True (the
+# default) then sockets over which metrics are received will temporarily stop accepting
+# data until the send queues fall below 80% MAX_QUEUE_SIZE.
+USE_FLOW_CONTROL = True
+
+# This defines the maximum "message size" between carbon daemons.
+# You shouldn't need to tune this unless you really know what you're doing.
+MAX_DATAPOINTS_PER_MESSAGE = 500
+
+# This defines how many datapoints the aggregator remembers for
+# each metric. Aggregation only happens for datapoints that fall in
+# the past MAX_AGGREGATION_INTERVALS * intervalSize seconds.
+MAX_AGGREGATION_INTERVALS = 5
+
+# By default (WRITE_BACK_FREQUENCY = 0), carbon-aggregator will write back
+# aggregated data points once every rule.frequency seconds, on a per-rule basis.
+# Set this (WRITE_BACK_FREQUENCY = N) to write back all aggregated data points
+# every N seconds, independent of rule frequency. This is useful, for example,
+# to be able to query partially aggregated metrics from carbon-cache without
+# having to first wait rule.frequency seconds.
+# WRITE_BACK_FREQUENCY = 0
+
+# Set this to True to enable whitelisting and blacklisting of metrics in
+# CONF_DIR/whitelist and CONF_DIR/blacklist. If the whitelist is missing or
+# empty, all metrics will pass through
+# USE_WHITELIST = False
+
+# By default, carbon itself will log statistics (such as a count,
+# metricsReceived) with the top level prefix of 'carbon' at an interval of 60
+# seconds. Set CARBON_METRIC_INTERVAL to 0 to disable instrumentation
+# CARBON_METRIC_PREFIX = carbon
+# CARBON_METRIC_INTERVAL = 60

ansible/install/roles/graphite/files/graphite-web.conf

@@ -0,0 +1,39 @@
+# Graphite Web Basic mod_wsgi vhost
+
+<VirtualHost *:80>
+    DocumentRoot "/usr/share/graphite/webapp"
+    ErrorLog /var/log/httpd/graphite-web-error.log
+    CustomLog /var/log/httpd/graphite-web-access.log common
+
+    # Header set Access-Control-Allow-Origin "*"
+    # Header set Access-Control-Allow-Methods "GET, OPTIONS"
+    # Header set Access-Control-Allow-Headers "origin, authorization, accept"
+    # Header set Access-Control-Allow-Credentials true
+   
+    WSGIScriptAlias / /usr/share/graphite/graphite-web.wsgi
+    WSGIImportScript /usr/share/graphite/graphite-web.wsgi process-group=%{GLOBAL} application-group=%{GLOBAL}
+
+    <Location "/content/">
+        SetHandler None
+    </Location>
+
+    Alias /media/ "/usr/lib/python2.7/site-packages/django/contrib/admin/media/"
+    <Location "/media/">
+        SetHandler None
+    </Location>
+
+   <Directory "/usr/share/graphite/">
+       <IfModule mod_authz_core.c>
+           # Apache 2.4
+           Require all granted
+           Require local
+       </IfModule>
+       <IfModule !mod_authz_core.c>
+           # Apache 2.2
+           Order Deny,Allow
+           Deny from all
+           Allow from 127.0.0.1
+           Allow from ::1
+       </IfModule>
+   </Directory>
+</VirtualHost>

ansible/install/roles/graphite/files/setup-graphite-db.exp

@@ -0,0 +1,32 @@
+#!/usr/bin/expect
+#
+# non-interactive setup of the initial graphite.db sqlite3 database
+#
+# if run manually, the following is the expected output.
+# Would you like to create one now? (yes/no): yes
+# Username (leave blank to use 'root'): 
+# Email address:
+# Password:
+# Password (again):
+# Superuser created successfully.
+# Installing custom SQL ...
+# Installing indexes ...
+# Installed 0 object(s) from 0 fixture(s)
+
+set timeout 20
+set superuser [lindex $argv 0]
+set password [lindex $argv 1]
+spawn /usr/lib/python2.7/site-packages/graphite/manage.py syncdb
+expect "Would you like to create one now? (yes/no):"
+send "yes\r";
+expect "Username (leave blank to use 'root'):"
+send "$superuser\r";
+expect "Email address:"
+send "\r";
+expect "Password:"
+send "$password\r";
+expect "Password (again):"
+send "$password\r";
+
+interact
+

ansible/install/roles/graphite/files/storage-schemas.conf

@@ -0,0 +1,17 @@
+# Schema definitions for Whisper files. Entries are scanned in order,
+# and first match wins. This file is scanned for changes every 60 seconds.
+#
+#  [name]
+#  pattern = regex
+#  retentions = timePerPoint:timeToStore, timePerPoint:timeToStore, ...
+#
+# Carbon's internal metrics. This entry should match what is specified in
+# CARBON_METRIC_PREFIX and CARBON_METRIC_INTERVAL settings
+[carbon]
+pattern = ^carbon\.
+retentions = 60:90d
+
+[default]
+pattern = .*
+retentions = 10s:7d,60s:90d,1h:180d
+

ansible/install/roles/graphite/tasks/main.yml

@@ -0,0 +1,122 @@
+---
+#
+# Install/run graphite-web for browbeat
+#
+
+- name: Check for epel
+  shell: rpm -qa | grep -q epel-release
+  ignore_errors: true
+  register: epel_installed
+
+- name: Install epel repo
+  command: rpm -ivh {{ epel_repo }}
+  become: true
+  when: epel_installed.rc != 0
+
+- name: Install graphite rpms
+  yum: name={{ item }} state=present
+  become: true
+  with_items:
+    - graphite-web
+    - python-carbon
+    - expect
+
+# moved to grafana specific playbook
+#    - https://grafanarel.s3.amazonaws.com/builds/grafana-2.6.0-1.x86_64.rpm
+
+- name: Check for graphite.db sqlite
+  shell: ls /var/lib/graphite-web/graphite.db
+  ignore_errors: true
+  register: graphite_db_installed
+
+- name: Copy setup-graphite-db.exp
+  copy:
+    src=setup-graphite-db.exp
+    dest=/root/setup-graphite-db.exp
+    owner=root
+    group=root
+    mode=0755
+  become: true
+
+- name: Create initial graphite db
+  shell: /root/setup-graphite-db.exp {{ graphite_username }} {{ graphite_password }} && chown apache:apache /var/lib/graphite-web/graphite.db
+  become: true
+  when: graphite_db_installed.rc != 0
+  register: apache_needs_restart
+
+- name: copy httpd graphite-web config
+  copy:
+    src=graphite-web.conf
+    dest=/etc/httpd/conf.d/graphite-web.conf
+    owner=root
+    group=root
+    mode=0644
+  become: true
+  register: apache_needs_restart
+
+
+# Start graphite-web service
+
+- name: Setup httpd service
+  service: name=httpd state=started enabled=true
+  become: true
+
+# disable firewalld (might need to create specific firewall rules or leave it to admin to do via iptables)
+
+- name: disable firewalld
+  service: name=firewalld state=stopped enabled=false
+  become: true
+
+# remove silly welcome from apache (if it exists)
+- name: Remove httpd welcome config
+  become: true
+  file: path=/etc/httpd/conf.d/welcome.conf state=absent
+  register: apache_needs_restart
+
+- name: Bounce Apache
+  service: name=httpd state=restarted enabled=true
+  become: true
+  when: apache_needs_restart.changed
+
+#
+# setup the python-carbon service
+#
+
+- name: Setup carbon-cache service
+  service: name=carbon-cache state=started enabled=true
+  become: true
+
+- name: copy carbon storage schema config
+  copy:
+    src=storage-schemas.conf
+    dest=/etc/carbon/storage-schemas.conf
+    owner=root
+    group=root
+    mode=0644
+  become: true
+  register: carbon_cache_needs_restart
+
+- name: copy carbon storage aggregation config
+  copy:
+    src=storage-aggregation.conf
+    dest=/etc/carbon/storage-aggregation.conf
+    owner=root
+    group=root
+    mode=0644
+  become: true
+  register: carbon_cache_needs_restart
+
+- name: copy carbon config
+  copy:
+    src=carbon.conf
+    dest=/etc/carbon/carbon.conf
+    owner=root
+    group=root
+    mode=0644
+  become: true
+  register: carbon_cache_needs_restart
+
+- name: bounce carbon cache
+  service: name=carbon-cache state=restarted enabled=true
+  become: true
+  when: carbon_cache_needs_restart.changed