moira-alert · kotbauk · Oct 22, 2019 · Oct 23, 2019 · Apr 6, 2020 · Apr 6, 2020
diff --git a/api.example.yml b/api.example.yml
@@ -13,17 +13,27 @@ redis:
   dbid: 0
   # Redis client connection pool size
   connection_limit: 512
-graphite:
-  # If true, graphite sender will be enabled.
-  enabled: true
-  # If true, runtime stats will be captured and sent to graphite. Note: It takes to call stoptheworld() with configured "graphite.interval" to capture runtime stats (https://golang.org/src/runtime/mstats.go)
-  runtime_stats: false
-  # Graphite relay URI, format: ip:port
-  uri: "graphite-relay:2003"
-  # Moira metrics prefix. Use 'prefix: {hostname}' to use hostname autoresolver.
-  prefix: DevOps.moira
-  # Metrics sending interval
-  interval: 60s
+  # Allow reading data from slave replicas
+  allow_slave_reads: true
+  # Delete metrics older than this value from Redis
+  metrics_ttl: 3h
+telemetry:
+  # Common port for all telemetry data: Prometheus scraping, pprof, etc.
+  listen: ":8091"
+  pprof:
+    # If true, pprof will be enabled on common telemetry port.
+    enabled: false
+  graphite:
+    # If true, graphite sender will be enabled.
+    enabled: true
+    # If true, runtime stats will be captured and sent to graphite. Note: It takes to call stoptheworld() with configured "graphite.interval" to capture runtime stats (https://golang.org/src/runtime/mstats.go)
+    runtime_stats: false
+    # Graphite relay URI, format: ip:port
+    uri: "graphite-relay:2003"
+    # Moira metrics prefix. Use 'prefix: {hostname}' to use hostname autoresolver.
+    prefix: DevOps.moira
+    # Metrics sending interval
+    interval: 60s
 api:
   # Api local network address. Default is ':8081' so api will be available at http://moira.company.com:8081/api
   listen: ":8081"
@@ -39,6 +49,8 @@ web:
     - type: mail
       label: E-mail
       validation: "^.+@.+\\..+$"
+    - type: msteams
+      label: Microsoft Teams
     - type: pushover
       label: Pushover
       placeholder: "Pushover user key"
@@ -48,8 +60,30 @@ web:
       placeholder: "Slack #channel or @user"
     - type: telegram
       label: Telegram
-      placeholder: "#channel, @username or group"
-      help: "### To make things work you should:\n### In personal chat:\n - start conversation with bot [@YourMoiraBot](https://t.me/YourMoiraBot);\n - execute command `/start`;\n - type your login in above field as `@login`.\n\n### In group chat:\n - invite bot [@YourMoiraBot](https://t.me/YourMoiraBot) into chat;\n - execute command `/start@YourMoiraBot`;\n - bot will send you chat name, you should type it without extra characters in above field.\n\n### In channel:\n - add bot [@YourMoiraBot](https://t.me/YourMoiraBot) into channel;\n - promote bot as channel administrator;\n - type channel name in above field as `#channel`.\n"
+      placeholder: "#public_channel, %private_channel, @username or group"
+      help: |
+        ### To make things work you should:
+        ### In personal chat:
+        - start conversation with bot [@YourMoiraBot](https://t.me/YourMoiraBot);
+        - execute command `/start`;
+        - type your login in above field as `@login`.
+
+        ### In group chat:
+        - invite bot [@YourMoiraBot](https://t.me/YourMoiraBot) into chat;
+        - execute command `/start@YourMoiraBot`;
+        - bot will send you chat name, you should type it without extra characters in above field.
+
+        ### In public channel:
+        - add bot [@YourMoiraBot](https://t.me/YourMoiraBot) into channel;
+        - promote bot as channel administrator;
+        - type channel name in above field as `#channel`.
+
+        ### In private channel:
+        - add bot [@YourMoiraBot](https://t.me/YourMoiraBot) into the channel;
+        - promote bot as channel administrator;
+        - open your private channel on the [web](https://web.telegram.org/#/im);
+        - get channel id from URL (e.g., `https://web.telegram.org/#/im?p=c1494975744_17340166617136722341`) between `c` and `_`;
+        - type channel id in the above field as `%1494975744`.
     - type: twilio sms
       label: Twilio SMS
       validation: "^\\+79\\d{9}$"
@@ -92,5 +126,7 @@ remote:
   # Min period to perform triggers re-check. 
   # Note: Reducing of this value leads to increasing of CPU and memory usage values and extra load on Graphite HTTP API
   check_interval: 60s
+  # Don't fetch metrics older than this value from remote storage
+  metrics_ttl: 168h
   # Maximum timeout for HTTP-request made to Graphite HTTP API
-  timeout: 60s
+  timeout: 60s
diff --git a/checker.example.yml b/checker.example.yml
@@ -13,17 +13,27 @@ redis:
   dbid: 0
   # Redis client connection pool size
   connection_limit: 512
-graphite:
-  # If true, graphite sender will be enabled.
-  enabled: true
-  # If true, runtime stats will be captured and sent to graphite. Note: It takes to call stoptheworld() with configured "graphite.interval" to capture runtime stats (https://golang.org/src/runtime/mstats.go)
-  runtime_stats: false
-  # Graphite relay URI, format: ip:port
-  uri: "graphite-relay:2003"
-  # Moira metrics prefix. Use 'prefix: {hostname}' to use hostname autoresolver.
-  prefix: DevOps.moira
-  # Metrics sending interval
-  interval: 60s
+  # Allow reading data from slave replicas
+  allow_slave_reads: true
+  # Delete metrics older than this value from Redis
+  metrics_ttl: 3h
+telemetry:
+  # Common port for all telemetry data: Prometheus scraping, pprof, etc.
+  listen: ":8091"
+  pprof:
+    # If true, pprof will be enabled on common telemetry port.
+    enabled: false
+  graphite:
+    # If true, graphite sender will be enabled.
+    enabled: true
+    # If true, runtime stats will be captured and sent to graphite. Note: It takes to call stoptheworld() with configured "graphite.interval" to capture runtime stats (https://golang.org/src/runtime/mstats.go)
+    runtime_stats: false
+    # Graphite relay URI, format: ip:port
+    uri: "graphite-relay:2003"
+    # Moira metrics prefix. Use 'prefix: {hostname}' to use hostname autoresolver.
+    prefix: DevOps.moira
+    # Metrics sending interval
+    interval: 60s
 checker:
   # Period for every trigger to perform forced check on
   nodata_check_interval: 60s
@@ -34,8 +44,6 @@ checker:
   # You can change this behaviour using option below. This can reduce CPU usage on your server.
   # Lazy triggers checker works if lazy_triggers_check_interval > check_interval. We recommend setting it to 10m.
   lazy_triggers_check_interval: 10m
-  # Time interval to store metrics. Note: Increasing of this value leads to increasing of Redis memory consumption value
-  metrics_ttl: 3h
   # Period for every trigger to cancel forced check (greater than 'NoDataCheckInterval') if no metrics were received
   stop_checking_interval: 30s
   # Equals to the number of processor cores found on Moira host by default or when variable is defined as 0.
@@ -57,6 +65,8 @@ remote:
   # Min period to perform triggers re-check. 
   # Note: Reducing of this value leads to increasing of CPU and memory usage values and extra load on Graphite HTTP API
   check_interval: 60s
+  # Don't fetch metrics older than this value from remote storage
+  metrics_ttl: 168h
   # Maximum timeout for HTTP-request made to Graphite HTTP API
   timeout: 60s
 log:

diff --git a/filter.example.yml b/filter.example.yml
@@ -13,17 +13,27 @@ redis:
   dbid: 0
   # Redis client connection pool size
   connection_limit: 512
-graphite:
-  # If true, graphite sender will be enabled.
-  enabled: true
-  # If true, runtime stats will be captured and sent to graphite. Note: It takes to call stoptheworld() with configured "graphite.interval" to capture runtime stats (https://golang.org/src/runtime/mstats.go)
-  runtime_stats: false
-  # Graphite relay URI, format: ip:port
-  uri: "graphite-relay:2003"
-  # Moira metrics prefix. Use 'prefix: {hostname}' to use hostname autoresolver.
-  prefix: DevOps.moira
-  # Metrics sending interval
-  interval: 60s
+  # Allow reading data from slave replicas
+  allow_slave_reads: true
+  # Delete metrics older than this value from Redis
+  metrics_ttl: 3h
+telemetry:
+  # Common port for all telemetry data: Prometheus scraping, pprof, etc.
+  listen: ":8091"
+  pprof:
+    # If true, pprof will be enabled on common telemetry port.
+    enabled: false
+  graphite:
+    # If true, graphite sender will be enabled.
+    enabled: true
+    # If true, runtime stats will be captured and sent to graphite. Note: It takes to call stoptheworld() with configured "graphite.interval" to capture runtime stats (https://golang.org/src/runtime/mstats.go)
+    runtime_stats: false
+    # Graphite relay URI, format: ip:port
+    uri: "graphite-relay:2003"
+    # Moira metrics prefix. Use 'prefix: {hostname}' to use hostname autoresolver.
+    prefix: DevOps.moira
+    # Metrics sending interval
+    interval: 60s
 filter:
   # Metrics listener uri
   listen: ":2003"
@@ -37,6 +47,8 @@ filter:
   # Defines number of threads to match incoming graphite-metrics.
   # Equals to the number of processor cores found on Moira host by default or when variable is defined as 0.
   max_parallel_matches: 0
+  # Period in which patterns will be reloaded from Redis
+  patterns_update_period: 1s
 log:
   log_file: stdout
   log_level: info
diff --git a/notifier.example.yml b/notifier.example.yml
@@ -13,17 +13,34 @@ redis:
   dbid: 0
   # Redis client connection pool size
   connection_limit: 512
-graphite:
-  # If true, graphite sender will be enabled.
-  enabled: true
-  # If true, runtime stats will be captured and sent to graphite. Note: It takes to call stoptheworld() with configured "graphite.interval" to capture runtime stats (https://golang.org/src/runtime/mstats.go)
-  runtime_stats: false
-  # Graphite relay URI, format: ip:port
-  uri: "graphite-relay:2003"
-  # Moira metrics prefix. Use 'prefix: {hostname}' to use hostname autoresolver.
-  prefix: DevOps.moira
-  # Metrics sending interval
-  interval: 60s
+  # Allow reading data from slave replicas
+  allow_slave_reads: true
+  # Delete metrics older than this value from Redis
+  metrics_ttl: 3h
+telemetry:
+  # Common port for all telemetry data: Prometheus scraping, pprof, etc.
+  listen: ":8091"
+  pprof:
+    # If true, pprof will be enabled on common telemetry port.
+    enabled: false
+  graphite:
+    # If true, graphite sender will be enabled.
+    enabled: true
+    # If true, runtime stats will be captured and sent to graphite. Note: It takes to call stoptheworld() with configured "graphite.interval" to capture runtime stats (https://golang.org/src/runtime/mstats.go)
+    runtime_stats: false
+    # Graphite relay URI, format: ip:port
+    uri: "graphite-relay:2003"
+    # Moira metrics prefix. Use 'prefix: {hostname}' to use hostname autoresolver.
+    prefix: DevOps.moira
+    # Metrics sending interval
+    interval: 60s
+image_store:
+  # AWS S3 bucket to store images
+  s3:
+    access_key_id: "myaccesskeyid"
+    access_key: "myaccesskey"
+    region: "eu-central-1"
+    bucket: "moira"
 notifier:
   # Soft timeout to start retrying to send notification after single failed attempt
   sender_timeout: 10s
@@ -38,6 +55,9 @@ notifier:
   # List of senders, every element has "type" field (one of ["pushover", "slack", "mail", "telegram", "twilio sms", "twilio voice", "script"])
   # Every type of sender has additional config fields
   senders:
+    - type: msteams
+      #the max amount of events you want to be sent to your channel, -1 for unlimited, any other positive value to limit events
+      max_events: -1
     - type: pushover
       # Api token for your pushover channel, for more info see https://pushover.net/api#registration
       api_token: ...
@@ -90,6 +110,8 @@ notifier:
       user: ...
       password: ...
     - type: pagerduty
+      # Configured image storage to store plots images
+      image_store: "s3"
     - type: opsgenie
       api_key: ...
     - type: victorops
@@ -134,5 +156,7 @@ remote:
   # Min period to perform triggers re-check. 
   # Note: Reducing of this value leads to increasing of CPU and memory usage values and extra load on Graphite HTTP API
   check_interval: 60s
+  # Don't fetch metrics older than this value from remote storage
+  metrics_ttl: 168h
   # Maximum timeout for HTTP-request made to Graphite HTTP API
-  timeout: 60s
+  timeout: 60s
diff --git a/requirements.txt b/requirements.txt
@@ -1,5 +1,5 @@
 Pillow
-Sphinx<=1.6.7
+Sphinx==1.8.5
 sphinx-rtd-theme
 sphinxcontrib-httpdomain
 sphinxcontrib-images

diff --git a/source/_static/web-ui-example.png b/source/_static/web-ui-example.png
diff --git a/source/conf.py b/source/conf.py
@@ -74,9 +74,9 @@
 # built documents.
 #
 # The short X.Y version.
-version = '2.5'
+version = '2.6'
 # The full version, including alpha/beta/rc tags.
-release = '2.5.1'
+release = '2.6.0'
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.

diff --git a/source/installation/configuration.rst b/source/installation/configuration.rst
@@ -125,7 +125,7 @@ Web contact fields:
 
 .. image:: ../_static/web-ui-example.png
    :alt: WEB UI example
-   :width: 596
+   :width: 575
 
 Remote API
 ----------