Add persisted logstash queues and tag journalbeat

The journalbeat shipper will now have a "journald" tag attached to it
which will then be used by logstash to identify items and add tags to
them based on the systemd slice.

To accomodate this load the logstash config has been updated to better
handle blowback and scale according to the capability of the underlying
hardware.

The logstash grok files have been moved into the files directory which
was done to speed up the time it takes to ship files to a given host.
Originally the task used to copy these files was using the template
module however none of these files have anything templated within them
so there's no need to run them through the template engine.

Change-Id: I4f0e50ac491b595c0d276f6e7292d2c6e61baa22
Signed-off-by: Kevin Carter <kevin.carter@rackspace.com>

elk_metrics_6x/files/02-journald.conf

@@ -0,0 +1,22 @@
+filter {
+  if "journald" in [tags] {
+    if [systemd_slice] {
+      mutate {
+        copy => { "systemd_slice" => "systemd_slice_tag" }
+      }
+      mutate {
+        gsub => [ "systemd_slice_tag", ".slice", "" ]
+      }
+      if [systemd_slice_tag] != "-" {
+        mutate {
+          add_tag => [
+            "%{systemd_slice_tag}"
+          ]
+        }
+      }
+      mutate {
+        remove_field => [ "%{systemd_slice_tag}" ]
+      }
+    }
+  }
+}

elk_metrics_6x/installLogstash.yml

@@ -15,12 +15,14 @@
     - name: Set quarter memory fact
       set_fact:
         q_mem: "{{ (ansible_memtotal_mb | int) // 4 }}"
+        q_storage: "{{ ansible_processor_cores }}"
       tags:
         - always
 
     - name: Set logstash facts
       set_fact:
         elastic_heap_size: "{{ ((q_mem | int) > 30720) | ternary(30720, q_mem) }}"
+        logstash_queue_size: "{{ (((q_storage | int) > 16) | ternary(16, q_storage) | int) * 1024 }}"
       tags:
         - always
 
@@ -79,21 +81,6 @@
       tags:
         - package_install
 
-    - name: Drop Logstash conf for beats input
-      template:
-        src: templates/02-beats-input.conf.j2
-        dest: /etc/logstash/conf.d/02-beats-input.conf
-
-    - name: Drop Logstash conf for beats input
-      template:
-        src: templates/10-syslog-filter.conf.j2
-        dest: /etc/logstash/conf.d/10-syslog-filter.conf
-
-    - name: Drop Logstash conf for elasticsearch output
-      template:
-        src: templates/99-elasticsearch-output.conf.j2
-        dest: /etc/logstash/conf.d/99-elasticsearch-output.conf
-
     - name: Drop elasticsearch conf file
       template:
         src: "{{ item.src }}"
@@ -101,6 +88,14 @@
       with_items:
         - src: templates/jvm.options.j2
           dest: /etc/logstash/jvm.options
+        - src: templates/99-elasticsearch-output.conf.j2
+          dest: /etc/logstash/conf.d/99-elasticsearch-output.conf
+        - src: templates/02-beats-input.conf.j2
+          dest: /etc/logstash/conf.d/02-beats-input.conf
+        - src: templates/logstash.yml.j2
+          dest: /etc/logstash/logstash.yml
+      notify:
+        - Enable and restart logstash
       tags:
         - config
 
@@ -123,16 +118,19 @@
         - extras
       when:
         - logstash_deploy_filters
+      notify:
+        - Enable and restart logstash
       tags:
         - logstash-filters
         - config
 
     - name: Deploy Logstash configuration files
-      template:
+      copy:
-        src: "{{ item }}"
+        src: "files/{{ item }}"
         dest: "/etc/logstash/conf.d/{{ item }}"
       with_items:
         - 02-general.conf
+        - 02-journald.conf
         - 03-nova.conf
         - 04-neutron.conf
         - 05-glance.conf
@@ -141,6 +139,7 @@
         - 08-apache.conf
         - 09-heat.conf
         - 10-mysql.conf
+        - 10-syslog-filter.conf
         - 11-auth.conf
         - 12-logstash.conf
         - 13-swift.conf
@@ -154,6 +153,8 @@
         - 98-traceback.conf
       when:
         - logstash_deploy_filters
+      notify:
+        - Enable and restart logstash
       tags:
         - logstash-filters
         - config
@@ -178,6 +179,8 @@
           template:
             src: "templates/99-kafka-output.conf"
             dest: "/etc/logstash/conf.d/99-kafka-output.conf"
+          notify:
+            - Enable and restart logstash
       when:
         - logstash_kafka_options is defined
 
@@ -187,7 +190,12 @@
         owner: logstash
         group: logstash
         recurse: true
+      register: l_perms
+      until: l_perms is success
+      retries: 3
+      delay: 1
 
+  handlers:
     - name: Enable and restart logstash
       systemd:
         name: "logstash"

elk_metrics_6x/templates/journalbeat.yml.j2

@@ -82,7 +82,8 @@ name: journalbeat
 # The tags of the shipper are included in their own field with each
 # transaction published. Tags make it easy to group servers by different
 # logical properties.
-#tags: ["service-X", "web-tier"]
+tags:
+  - journald
 
 # Optional fields that you can specify to add additional information to the
 # output. Fields can be scalar values, arrays, dictionaries, or any nested

elk_metrics_6x/templates/logstash.yml.j2

@@ -0,0 +1,246 @@
+# Settings file in YAML
+#
+# Settings can be specified either in hierarchical form, e.g.:
+#
+#   pipeline:
+#     batch:
+#       size: 125
+#       delay: 5
+#
+# Or as flat keys:
+#
+#   pipeline.batch.size: 125
+#   pipeline.batch.delay: 5
+#
+# ------------  Node identity ------------
+#
+# Use a descriptive name for the node:
+#
+# node.name: test
+#
+# If omitted the node name will default to the machine's host name
+#
+# ------------ Data path ------------------
+#
+# Which directory should be used by logstash and its plugins
+# for any persistent needs. Defaults to LOGSTASH_HOME/data
+#
+path.data: /var/lib/logstash
+#
+# ------------ Pipeline Settings --------------
+#
+# The ID of the pipeline.
+#
+# pipeline.id: main
+#
+# Set the number of workers that will, in parallel, execute the filters+outputs
+# stage of the pipeline.
+#
+# This defaults to the number of the host's CPU cores.
+#
+# pipeline.workers: 2
+#
+# How many events to retrieve from inputs before sending to filters+workers
+#
+# pipeline.batch.size: 125
+#
+# How long to wait in milliseconds while polling for the next event
+# before dispatching an undersized batch to filters+outputs
+#
+# pipeline.batch.delay: 50
+#
+# Force Logstash to exit during shutdown even if there are still inflight
+# events in memory. By default, logstash will refuse to quit until all
+# received events have been pushed to the outputs.
+#
+# WARNING: enabling this can lead to data loss during shutdown
+#
+# pipeline.unsafe_shutdown: false
+#
+# ------------ Pipeline Configuration Settings --------------
+#
+# Where to fetch the pipeline configuration for the main pipeline
+#
+# path.config:
+#
+# Pipeline configuration string for the main pipeline
+#
+# config.string:
+#
+# At startup, test if the configuration is valid and exit (dry run)
+#
+# config.test_and_exit: false
+#
+# Periodically check if the configuration has changed and reload the pipeline
+# This can also be triggered manually through the SIGHUP signal
+#
+# config.reload.automatic: false
+#
+# How often to check if the pipeline configuration has changed (in seconds)
+#
+# config.reload.interval: 3s
+#
+# Show fully compiled configuration as debug log message
+# NOTE: --log.level must be 'debug'
+#
+# config.debug: false
+#
+# When enabled, process escaped characters such as \n and \" in strings in the
+# pipeline configuration files.
+#
+# config.support_escapes: false
+#
+# ------------ Module Settings ---------------
+# Define modules here.  Modules definitions must be defined as an array.
+# The simple way to see this is to prepend each `name` with a `-`, and keep
+# all associated variables under the `name` they are associated with, and
+# above the next, like this:
+#
+# modules:
+#   - name: MODULE_NAME
+#     var.PLUGINTYPE1.PLUGINNAME1.KEY1: VALUE
+#     var.PLUGINTYPE1.PLUGINNAME1.KEY2: VALUE
+#     var.PLUGINTYPE2.PLUGINNAME1.KEY1: VALUE
+#     var.PLUGINTYPE3.PLUGINNAME3.KEY1: VALUE
+#
+# Module variable names must be in the format of
+#
+# var.PLUGIN_TYPE.PLUGIN_NAME.KEY
+#
+# modules:
+#
+# ------------ Cloud Settings ---------------
+# Define Elastic Cloud settings here.
+# Format of cloud.id is a base64 value e.g. dXMtZWFzdC0xLmF3cy5mb3VuZC5pbyRub3RhcmVhbCRpZGVudGlmaWVy
+# and it may have an label prefix e.g. staging:dXMtZ...
+# This will overwrite 'var.elasticsearch.hosts' and 'var.kibana.host'
+# cloud.id: <identifier>
+#
+# Format of cloud.auth is: <user>:<pass>
+# This is optional
+# If supplied this will overwrite 'var.elasticsearch.username' and 'var.elasticsearch.password'
+# If supplied this will overwrite 'var.kibana.username' and 'var.kibana.password'
+# cloud.auth: elastic:<password>
+#
+# ------------ Queuing Settings --------------
+#
+# Internal queuing model, "memory" for legacy in-memory based queuing and
+# "persisted" for disk-based acked queueing. Defaults is memory
+#
+queue.type: persisted
+#
+# If using queue.type: persisted, the directory path where the data files will be stored.
+# Default is path.data/queue
+#
+# path.queue:
+#
+# If using queue.type: persisted, the page data files size. The queue data consists of
+# append-only data files separated into pages. Default is 64mb
+#
+# queue.page_capacity: 64mb
+#
+# If using queue.type: persisted, the maximum number of unread events in the queue.
+# Default is 0 (unlimited)
+#
+# queue.max_events: 0
+#
+# If using queue.type: persisted, the total capacity of the queue in number of bytes.
+# If you would like more unacked events to be buffered in Logstash, you can increase the
+# capacity using this setting. Please make sure your disk drive has capacity greater than
+# the size specified here. If both max_bytes and max_events are specified, Logstash will pick
+# whichever criteria is reached first
+# Default is 1024mb or 1gb
+#
+queue.max_bytes: {{ logstash_queue_size }}mb
+#
+# If using queue.type: persisted, the maximum number of acked events before forcing a checkpoint
+# Default is 1024, 0 for unlimited
+#
+# queue.checkpoint.acks: 1024
+#
+# If using queue.type: persisted, the maximum number of written events before forcing a checkpoint
+# Default is 1024, 0 for unlimited
+#
+# queue.checkpoint.writes: 1024
+#
+# If using queue.type: persisted, the interval in milliseconds when a checkpoint is forced on the head page
+# Default is 1000, 0 for no periodic checkpoint.
+#
+# queue.checkpoint.interval: 1000
+#
+# ------------ Dead-Letter Queue Settings --------------
+# Flag to turn on dead-letter queue.
+#
+# dead_letter_queue.enable: false
+
+# If using dead_letter_queue.enable: true, the maximum size of each dead letter queue. Entries
+# will be dropped if they would increase the size of the dead letter queue beyond this setting.
+# Default is 1024mb
+# dead_letter_queue.max_bytes: 1024mb
+
+# If using dead_letter_queue.enable: true, the directory path where the data files will be stored.
+# Default is path.data/dead_letter_queue
+#
+# path.dead_letter_queue:
+#
+# ------------ Metrics Settings --------------
+#
+# Bind address for the metrics REST endpoint
+#
+# http.host: "127.0.0.1"
+#
+# Bind port for the metrics REST endpoint, this option also accept a range
+# (9600-9700) and logstash will pick up the first available ports.
+#
+# http.port: 9600-9700
+#
+# ------------ Debugging Settings --------------
+#
+# Options for log.level:
+#   * fatal
+#   * error
+#   * warn
+#   * info (default)
+#   * debug
+#   * trace
+#
+# log.level: info
+path.logs: /var/log/logstash
+#
+# ------------ Other Settings --------------
+#
+# Where to find custom plugins
+# path.plugins: []
+#
+# ------------ X-Pack Settings (not applicable for OSS build)--------------
+#
+# X-Pack Monitoring
+# https://www.elastic.co/guide/en/logstash/current/monitoring-logstash.html
+#xpack.monitoring.enabled: false
+#xpack.monitoring.elasticsearch.username: logstash_system
+#xpack.monitoring.elasticsearch.password: password
+#xpack.monitoring.elasticsearch.url: ["https://es1:9200", "https://es2:9200"]
+#xpack.monitoring.elasticsearch.ssl.ca: [ "/path/to/ca.crt" ]
+#xpack.monitoring.elasticsearch.ssl.truststore.path: path/to/file
+#xpack.monitoring.elasticsearch.ssl.truststore.password: password
+#xpack.monitoring.elasticsearch.ssl.keystore.path: /path/to/file
+#xpack.monitoring.elasticsearch.ssl.keystore.password: password
+#xpack.monitoring.elasticsearch.ssl.verification_mode: certificate
+#xpack.monitoring.elasticsearch.sniffing: false
+#xpack.monitoring.collection.interval: 10s
+#xpack.monitoring.collection.pipeline.details.enabled: true
+#
+# X-Pack Management
+# https://www.elastic.co/guide/en/logstash/current/logstash-centralized-pipeline-management.html
+#xpack.management.enabled: false
+#xpack.management.pipeline.id: ["main", "apache_logs"]
+#xpack.management.elasticsearch.username: logstash_admin_user
+#xpack.management.elasticsearch.password: password
+#xpack.management.elasticsearch.url: ["https://es1:9200", "https://es2:9200"]
+#xpack.management.elasticsearch.ssl.ca: [ "/path/to/ca.crt" ]
+#xpack.management.elasticsearch.ssl.truststore.path: /path/to/file
+#xpack.management.elasticsearch.ssl.truststore.password: password
+#xpack.management.elasticsearch.ssl.keystore.path: /path/to/file
+#xpack.management.elasticsearch.ssl.keystore.password: password
+#xpack.management.elasticsearch.sniffing: false
+#xpack.management.logstash.poll_interval: 5s