Commit 7d171b61 by Jérome Perrin

Grafana

A quick slapos profile for Grafana, InfluxDB and Telegraf.

/reviewed-on !286
parents 15cf1c3c ebba6fca
......@@ -5,6 +5,7 @@ extends =
../pkgconfig/buildout.cfg
../openssl/buildout.cfg
../zlib/buildout.cfg
../python-2.7/buildout.cfg
parts =
nodejs
......@@ -12,6 +13,24 @@ parts =
[nodejs]
<= nodejs-0.12
[nodejs-8.6.0]
# Server-side Javascript.
recipe = slapos.recipe.cmmi
version = v8.6.0
url = https://nodejs.org/dist/${:version}/node-${:version}.tar.gz
md5sum = 0c95e08220667d8a18b97ecec8218ac6
configure-options =
--shared-openssl
--shared-openssl-includes=${openssl:location}/include
--shared-openssl-libpath=${openssl:location}/lib
environment =
HOME=${buildout:parts-directory}/${:_buildout_section_name_}
PATH=${pkgconfig:location}/bin:${python2.7:location}/bin/:%(PATH)s
PKG_CONFIG_PATH=${openssl:location}/lib/pkgconfig/
CPPFLAGS=-I${zlib:location}/include
LDFLAGS=-Wl,-rpath=${openssl:location}/lib -L${zlib:location}/lib -Wl,-rpath=${zlib:location}/lib
LD_LIBRARY_PATH=${openssl:location}/lib
[nodejs-5]
# Server-side Javascript.
recipe = slapos.recipe.cmmi
......
# grafana / telegraf / influxdb
## Custom telegraf plugins
See https://github.com/influxdata/telegraf to learn about plugins.
Useful plugins in this context are probably
[exec](https://github.com/influxdata/telegraf/tree/1.5.1/plugins/inputs/exec)
or
[httpjson](https://github.com/influxdata/telegraf/tree/1.5.1/plugins/inputs/httpjson).
Telegraf will save in the `telegraf` database from the embedded influxdb server.
## Grafana
You'll have to add yourself the influxdb data source in grafana, using the
parameters published by the slapos instance.
http://docs.grafana.org/features/datasources/influxdb/
When adding datasource, use *proxy* option, otherwise Grafana makes your
browser query influxdb directly, which also uses a self signed certificate.
One workaround is to configure your browser to also accept influxdb certificate
before using grafana, but using proxy seems easier.
## Influxdb
Influxdb backups are not done automatically by this software release.
One important thing to notice is that the backup protocol is enabled on ipv4
provided by slapos, so make sure this ip is not reachable from untrusted
sources.
## TODO
* influxdb and telegraf runs with very low priority, this could become an option
* make one partition for each service and use switch software type
* make it easier to add custom configuration (how ?)
# THIS IS NOT A BUILDOUT FILE, despite purposedly using a compatible syntax.
# The only allowed lines here are (regexes):
# - "^#" comments, copied verbatim
# - "^[" section beginings, copied verbatim
# - lines containing an "=" sign which must fit in the following categorie.
# - "^\s*filename\s*=\s*path\s*$" where "path" is relative to this file
# But avoid directories, they are not portable.
# Copied verbatim.
# - "^\s*hashtype\s*=.*" where "hashtype" is one of the values supported
# by the re-generation script.
# Re-generated.
# - other lines are copied verbatim
# Substitution (${...:...}), extension ([buildout] extends = ...) and
# section inheritance (< = ...) are NOT supported (but you should really
# not need these here).
[instance-profile]
filename = instance.cfg.in
md5sum = 7fb6806b139b3a8d0054308397be1dd9
[influxdb-config-file]
filename = influxdb-config-file.cfg.in
md5sum = 7ce85159c0664b251e249eac4b37bea4
[telegraf-config-file]
filename = telegraf-config-file.cfg.in
md5sum = a1a9c22c2a7829c66a49fc2504604d21
[grafana-config-file]
filename = grafana-config-file.cfg.in
md5sum = 8244d430905b968795c7946049bed9e3
reporting-disabled = false
bind-address = "[{{ influxdb['local-host'] }}]:{{ influxdb['rpc-port'] }}"
[meta]
dir = "{{ influxdb['data-dir'] }}/meta"
retention-autocreate = true
logging-enabled = true
[data]
dir = "{{ influxdb['data-dir'] }}/data"
index-version = "inmem"
wal-dir = "{{ influxdb['data-dir'] }}/wal"
wal-fsync-delay = "0s"
query-log-enabled = true
cache-max-memory-size = 1073741824
cache-snapshot-memory-size = 26214400
cache-snapshot-write-cold-duration = "10m0s"
compact-full-write-cold-duration = "4h0m0s"
max-series-per-database = 1000000
max-values-per-tag = 100000
max-concurrent-compactions = 0
trace-logging-enabled = false
[coordinator]
write-timeout = "10s"
max-concurrent-queries = 0
query-timeout = "0s"
log-queries-after = "0s"
max-select-point = 0
max-select-series = 0
max-select-buckets = 0
[retention]
enabled = true
check-interval = "30m0s"
[shard-precreation]
enabled = true
check-interval = "10m0s"
advance-period = "30m0s"
[monitor]
store-enabled = true
store-database = "_internal"
store-interval = "10s"
[subscriber]
enabled = true
http-timeout = "30s"
insecure-skip-verify = false
ca-certs = ""
write-concurrency = 40
write-buffer-size = 1000
[http]
enabled = true
bind-address = "[{{ influxdb['host'] }}]:{{ influxdb['http-port'] }}"
auth-enabled = true
log-enabled = true
write-tracing = false
pprof-enabled = true
https-enabled = true
https-certificate = "{{ influxdb['ssl-cert-file'] }}"
https-private-key = "{{ influxdb['ssl-key-file'] }}"
max-row-limit = 0
max-connection-limit = 0
shared-secret = ""
realm = "InfluxDB"
unix-socket-enabled = true
bind-socket = "{{ influxdb['unix-socket'] }}"
max-body-size = 25000000
[ifql]
enabled = false
log-enabled = true
bind-address = ":8082"
[[graphite]]
enabled = false
bind-address = ":2003"
database = "graphite"
retention-policy = ""
protocol = "tcp"
batch-size = 5000
batch-pending = 10
batch-timeout = "1s"
consistency-level = "one"
separator = "."
udp-read-buffer = 0
[[collectd]]
enabled = false
bind-address = ":25826"
database = "collectd"
retention-policy = ""
batch-size = 5000
batch-pending = 10
batch-timeout = "10s"
read-buffer = 0
typesdb = "/usr/share/collectd/types.db"
security-level = "none"
auth-file = "/etc/collectd/auth_file"
parse-multivalue-plugin = "split"
[[opentsdb]]
enabled = false
bind-address = ":4242"
database = "opentsdb"
retention-policy = ""
consistency-level = "one"
tls-enabled = false
certificate = "/etc/ssl/influxdb.pem"
batch-size = 1000
batch-pending = 5
batch-timeout = "1s"
log-point-errors = true
[[udp]]
enabled = false
bind-address = ":8089"
database = "udp"
retention-policy = ""
batch-size = 5000
batch-pending = 10
read-buffer = 0
batch-timeout = "1s"
precision = ""
[continuous_queries]
log-enabled = true
enabled = true
query-stats-enabled = false
run-interval = "1s"
{
"$schema": "http://json-schema.org/draft-04/schema#",
"description": "Parameters to instantiate Grafana",
"additionalProperties": false,
"properties": {
"smtp-server": {
"description": "SMTP server used by grafana to send emails (in host:port format). Leaving this empty will disable email sending.",
"type": "string"
},
"smtp-username": {
"description": "Username to connect to SMTP server",
"type": "string"
},
"smtp-password": {
"description": "Password to connect to SMTP server",
"type": "string"
},
"smtp-verify-ssl": {
"description": "Verify SSL certificate of SMTP server",
"type": "boolean",
"default": true
},
"email-from-address": {
"description": "Email address used in From: header of emails",
"type": "string"
},
"email-from-name": {
"description": "Name used in From: header of emails",
"default": "Grafana",
"type": "string"
}
}
}
{
"$schema": "http://json-schema.org/draft-04/schema#",
"description": "Values returned by Grafana instantiation",
"additionalProperties": false,
"properties": {
"url": {
"description": "Shared frontend for this Grafana instance",
"pattern": "^https://",
"type": "string"
},
"grafana-username": {
"description": "Admin user for grafana",
"type": "string"
},
"grafana-password": {
"description": "Password for grafana's admin user",
"type": "string"
},
"grafana-url": {
"description": "IPv6 URL to access grafana",
"pattern": "^https://",
"type": "string"
},
"influxdb-url": {
"description": "IPv6 URL of influxdb HTTP endpoint",
"pattern": "^https://",
"type": "string"
},
"influxdb-database": {
"description": "database created in influxdb",
"type": "string"
},
"influxdb-username": {
"description": "username for influxdb",
"type": "string"
},
"influxdb-password": {
"description": "password for influxdb user",
"type": "string"
},
"telegraf-extra-config-dir": {
"description": "Directory in telegraf partition where extra configuration file will be loaded. These files must match *.conf pattern",
"type": "string"
}
},
"type": "object"
}
[buildout]
parts =
promises
publish-connection-parameter
eggs-directory = {{ buildout['eggs-directory'] }}
develop-eggs-directory = {{ buildout['develop-eggs-directory'] }}
offline = true
[instance-parameter]
recipe = slapos.cookbook:slapconfiguration
computer = ${slap-connection:computer-id}
partition = ${slap-connection:partition-id}
url = ${slap-connection:server-url}
key = ${slap-connection:key-file}
cert = ${slap-connection:cert-file}
[slap-configuration]
# apache-frontend reads from from a part named [slap-configuration]
recipe = slapos.cookbook:slapconfiguration.serialised
computer = ${slap-connection:computer-id}
partition = ${slap-connection:partition-id}
url = ${slap-connection:server-url}
key = ${slap-connection:key-file}
cert = ${slap-connection:cert-file}
[directory]
recipe = slapos.cookbook:mkdirectory
home = ${buildout:directory}
etc = ${:home}/etc
var = ${:home}/var
srv = ${:home}/srv
service = ${:etc}/service
promise = ${:etc}/promise
influxdb-data-dir = ${:srv}/influxdb
grafana-dir = ${:srv}/grafana
grafana-data-dir = ${:grafana-dir}/data
grafana-logs-dir = ${:var}/log
grafana-plugins-dir = ${:grafana-dir}/plugins
grafana-provisioning-config-dir = ${:grafana-dir}/provisioning-config
grafana-provisioning-datasources = ${:grafana-provisioning-config-dir}/datasources
grafana-provisioning-dashboards = ${:grafana-provisioning-config-dir}/dashboards
telegraf-dir = ${:srv}/telegraf
telegraf-extra-config-dir = ${:telegraf-dir}/extra-config
# macros
[generate-certificate]
recipe = plone.recipe.command
command =
if [ ! -e ${:key-file} ]
then
{{ openssl_bin }} req -x509 -nodes -days 3650 \
-subj "/C=AA/ST=X/L=X/O=Dis/CN=${:common-name}" \
-newkey rsa:1024 -keyout ${:key-file} \
-out ${:cert-file}
fi
update-command = ${:command}
key-file = ${directory:etc}/${:_buildout_section_name_}.key
cert-file = ${directory:etc}/${:_buildout_section_name_}.crt
common-name = ${:_buildout_section_name_}
[config-file]
recipe = slapos.recipe.template:jinja2
template = {{ buildout['parts-directory'] }}/${:_buildout_section_name_}/${:_buildout_section_name_}.cfg.in
rendered = ${directory:etc}/${:_buildout_section_name_}.cfg
mode = 0644
extensions = jinja2.ext.do
[check-port-listening-promise]
recipe = slapos.cookbook:check_port_listening
path = ${directory:promise}/${:_buildout_section_name_}
[influxdb]
ipv6 = ${instance-parameter:ipv6-random}
ipv4 = ${instance-parameter:ipv4-random}
host = ${:ipv6}
local-host = ${:ipv4}
rpc-port = 8088
http-port = 8086
url = https://[${:host}]:${:http-port}
data-dir = ${directory:influxdb-data-dir}
auth-username = ${influxdb-password:username}
auth-password = ${influxdb-password:passwd}
unix-socket = ${directory:var}/influxdb.socket
ssl-cert-file = ${influxdb-certificate:cert-file}
ssl-key-file = ${influxdb-certificate:key-file}
database = telegraf
recipe = slapos.cookbook:wrapper
command-line =
nice -19 chrt --idle 0 ionice -c3 {{ influxd_bin }} -config ${influxdb-config-file:rendered}
wrapper-path = ${directory:service}/influxdb
[influxdb-config-file]
<= config-file
context =
section influxdb influxdb
[influxdb-password]
recipe = slapos.cookbook:generate.password
username = influxdb
[influxdb-certificate]
<= generate-certificate
[influxdb-listen-promise]
<= check-port-listening-promise
hostname = ${influxdb:ipv6}
port = ${influxdb:http-port}
[influxdb-password-promise]
recipe = slapos.cookbook:wrapper
command-line =
{{ influx_bin }} -username ${influxdb:auth-username} -password ${influxdb:auth-password} -socket ${influxdb:unix-socket} -execute "CREATE USER ${influxdb:auth-username} WITH PASSWORD '${influxdb:auth-password}' WITH ALL PRIVILEGES"
wrapper-path = ${directory:promise}/${:_buildout_section_name_}
[grafana]
ipv6 = ${instance-parameter:ipv6-random}
port = 8080
url = https://[${:ipv6}]:${:port}
data-dir = ${directory:grafana-data-dir}
logs-dir = ${directory:grafana-logs-dir}
plugins-dir = ${directory:grafana-plugins-dir}
provisioning-config-dir = ${directory:grafana-provisioning-config-dir}
admin-user = ${grafana-password:username}
admin-password = ${grafana-password:passwd}
secret-key = ${grafana-secret-key:passwd}
ssl-key-file = ${grafana-certificate:key-file}
ssl-cert-file = ${grafana-certificate:cert-file}
recipe = slapos.cookbook:wrapper
command-line =
{{ grafana_bin }} -config ${grafana-config-file:rendered} -homepath {{ grafana_homepath }}
wrapper-path = ${directory:service}/grafana
[grafana-certificate]
<= generate-certificate
[grafana-password]
recipe = slapos.cookbook:generate.password
username = admin
[grafana-secret-key]
recipe = slapos.cookbook:generate.password
[grafana-config-file]
<= config-file
context =
section grafana grafana
section apache_frontend apache-frontend
key slapparameter_dict slap-configuration:configuration
[grafana-listen-promise]
<= check-port-listening-promise
hostname= ${grafana:ipv6}
port = ${grafana:port}
[telegraf]
recipe = slapos.cookbook:wrapper
extra-config-dir = ${directory:telegraf-extra-config-dir}
# telegraf needs influxdb to be already listening before starting
command-line =
bash -c '${influxdb-listen-promise:path} && nice -19 chrt --idle 0 ionice -c3 {{ telegraf_bin }} --config ${telegraf-config-file:rendered} --config-directory ${:extra-config-dir}'
wrapper-path = ${directory:service}/telegraf
[telegraf-config-file]
<= config-file
context =
section influxdb influxdb
section telegraf telegraf
[apache-frontend]
<= slap-connection
recipe = slapos.cookbook:requestoptional
name = Grafana Frontend
# XXX We have hardcoded SR URL here.
software-url = http://git.erp5.org/gitweb/slapos.git/blob_plain/HEAD:/software/apache-frontend/software.cfg
slave = true
config-url = ${grafana:url}
config-https-only = true
return = domain secure_access
[promises]
recipe =
instance-promises =
${influxdb-listen-promise:path}
${influxdb-password-promise:wrapper-path}
${grafana-listen-promise:path}
[publish-connection-parameter]
recipe = slapos.cookbook:publish
influxdb-url = ${influxdb:url}
influxdb-database = ${influxdb:database}
influxdb-username = ${influxdb:auth-username}
influxdb-password = ${influxdb:auth-password}
telegraf-extra-config-dir = ${telegraf:extra-config-dir}
grafana-url = ${grafana:url}
grafana-username = ${grafana:admin-user}
grafana-password = ${grafana:admin-password}
url = ${apache-frontend:connection-secure_access}
[buildout]
extends =
../../stack/slapos.cfg
../../stack/nodejs.cfg
../../component/make/buildout.cfg
../../component/golang/buildout.cfg
../../component/openssl/buildout.cfg
buildout.hash.cfg
gowork.cfg
versions = versions
parts =
slapos-cookbook
instance-profile
gowork
influxdb-config-file
telegraf-config-file
grafana-config-file
[nodejs]
<= nodejs-8.6.0
[yarn]
# this could become a component, but it needs to be invoked from nodejs explicitly,
# otherwise it uses system's nodejs
recipe = slapos.recipe.build:download-unpacked
url = https://github.com/yarnpkg/yarn/releases/download/v1.3.2/yarn-v1.3.2.tar.gz
md5sum = db82fa09c996e9318f2f1d2ab99228f9
[gowork]
# All the softwares installed in the go work have "non standard" installation
# methods, so we install them in specific parts with custom commands.
# They will be installed because they are dependencies of ${gowork.goinstall}
install =
telegraf-bin = ${:bin}/telegraf
influx-bin = ${:bin}/influx
influxd-bin = ${:bin}/influxd
grafana-bin = ${:bin}/grafana-server
grafana-homepath = ${go_github.com_grafana_grafana:location}
[gowork.goinstall]
command = :
depends =
${influxdb-install:recipe}
${telegraf-install:recipe}
${grafana-install:recipe}
[influxdb-install]
<= gowork.goinstall
command = bash -c ". ${gowork:env.sh} && \
cd ${gowork:directory}/src/github.com/influxdata/influxdb && \
go install ./cmd/..."
update-command =
[telegraf-install]
<= gowork.goinstall
command = bash -c ". ${gowork:env.sh} && \
cd ${gowork:directory}/src/github.com/influxdata/telegraf && \
${make:location}/bin/make &&
cp telegraf ${gowork:bin}"
update-command =
[grafana-install]
<= gowork.goinstall
# yarn and go run build.go needs our nodejs in $PATH
command = bash -c "export PATH=${nodejs:location}/bin/:$PATH && \
. ${gowork:env.sh} && \
cd ${gowork:directory}/src/github.com/grafana/grafana && \
${gowork:golang}/bin/go run build.go setup && \
${gowork:golang}/bin/go run build.go build && \
${yarn:location}/bin/yarn install --pure-lockfile && \
${nodejs:location}/bin/npm run build"
update-command =
[download-file-base]
recipe = slapos.recipe.build:download
url = ${:_profile_base_location_}/${:filename}
download-only = true
mode = 0644
[influxdb-config-file]
<= download-file-base
[telegraf-config-file]
<= download-file-base
[grafana-config-file]
<= download-file-base
[instance-profile]
recipe = slapos.recipe.template:jinja2
template = ${:_profile_base_location_}/${:filename}
rendered = ${buildout:directory}/instance.cfg
mode = 0644
extensions = jinja2.ext.do
context =
section buildout buildout
key openssl_bin openssl-output:openssl
key telegraf_bin gowork:telegraf-bin
key influxd_bin gowork:influxd-bin
key influx_bin gowork:influx-bin
key grafana_bin gowork:grafana-bin
key grafana_homepath gowork:grafana-homepath
[versions]
slapos.recipe.template = 4.2
inotifyx = 0.2.2
{
"name": "Grafana",
"description": "Grafana, Telegraf and Influxdb",
"serialisation": "json-in-xml",
"software-type": {
"default": {
"title": "Default",
"description": "Grafana, Telegraf and Influxdb in same partition",
"request": "instance-input-schema.json",
"response": "instance-output-schema.json",
"index": 0
}
}
}
# Telegraf configuration
# Telegraf is entirely plugin driven. All metrics are gathered from the
# declared plugins.
# Even if a plugin has no configuration, it must be declared in here
# to be active. Declaring a plugin means just specifying the name
# as a section with no variables. To deactivate a plugin, comment
# out the name and any variables.
# Use 'telegraf -config telegraf.toml -test' to see what metrics a config
# file would generate.
# One rule that plugins conform to is wherever a connection string
# can be passed, the values '' and 'localhost' are treated specially.
# They indicate to the plugin to use their own builtin configuration to
# connect to the local system.
# NOTE: The configuration has a few required parameters. They are marked
# with 'required'. Be sure to edit those to make this configuration work.
# Tags can also be specified via a normal map, but only one form at a time:
[tags]
# dc = "us-east-1"
# Configuration for telegraf agent
[agent]
# Default data collection interval for all plugins
interval = "10s"
# Rounds collection interval to 'interval'
# ie, if interval="10s" then always collect on :00, :10, :20, etc.
round_interval = true
# Default data flushing interval for all outputs. You should not set this below
# interval. Maximum flush_interval will be flush_interval + flush_jitter
flush_interval = "10s"
# Jitter the flush interval by a random amount. This is primarily to avoid
# large write spikes for users running a large number of telegraf instances.
# ie, a jitter of 5s and interval 10s means flushes will happen every 10-15s
flush_jitter = "0s"
# Run telegraf in debug mode
debug = false
# Override default hostname, if empty use os.Hostname()
hostname = ""
###############################################################################
# OUTPUTS #
###############################################################################
[outputs]
# Configuration for influxdb server to send metrics to
[outputs.influxdb]
# The full HTTP or UDP endpoint URL for your InfluxDB instance
# Multiple urls can be specified for InfluxDB cluster support.
# urls = ["udp://localhost:8089"] # UDP endpoint example
# XXX XXX XXX
#urls = ["http://localhost:8086"] # required
urls = ["{{ influxdb['url'] }}"]
insecure_skip_verify = true # because we are using a self signed certificate
# The target database for metrics (telegraf will create it if not exists)
database = "{{ influxdb['database'] }}" # required
# Precision of writes, valid values are n, u, ms, s, m, and h
# note: using second precision greatly helps InfluxDB compression
precision = "s"
# Connection timeout (for the connection with InfluxDB), formatted as a string.
# If not provided, will default to 0 (no timeout)
# timeout = "5s"
username = "{{ influxdb['auth-username'] }}"
password = "{{ influxdb['auth-password'] }}"
# Set the user agent for HTTP POSTs (can be useful for log differentiation)
# user_agent = "telegraf"
# Set UDP payload size, defaults to InfluxDB UDP Client default (512 bytes)
# udp_payload = 512
###############################################################################
# PLUGINS #
###############################################################################
# Read metrics about cpu usage
[cpu]
# Whether to report per-cpu stats or not
percpu = true
# Whether to report total system cpu stats or not
totalcpu = true
# Comment this line if you want the raw CPU time metrics
drop = ["cpu_time"]
# Read metrics about memory usage
[mem]
# no configuration
[disk]
[io]
[system]
###############################################################################
# ERP5 - PLUGINS #
###############################################################################
#
# Left here as example, don't edit this file directly, but place your config
# files in {{ telegraf['extra-config-dir'] }}
#
#[mysql]
# servers = ["root@unix(/srv/slapgrid/slappart12/srv/runner/instance/slappart1/var/run/mariadb.sock)/erp5"]
#[memcached]
# # XXX kumofs does not support memcached's stat command
# servers = ["10.0.248.233:2013", "10.0.248.233:2003"]
#[haproxy]