Bump to v2.0.8: Bootstrap VMWatch Process if vmWatchSettings present

.github/workflows/go.yml → .github/workflows/merge_validation_v2.yml

@@ -1,4 +1,4 @@
-name: Go
+name: Merge Validation (Ext V2)
 
 on:
   workflow_dispatch:
@@ -10,6 +10,7 @@ on:
 jobs:
   build:
     strategy:
+      fail-fast: false
       matrix:
         os: [ubuntu-latest, ubuntu-20.04]
 
@@ -91,5 +92,13 @@ jobs:
       working-directory: ${{ env.repo_root }}
 
     - name: Run Integration Tests
-      run: sudo bats integration-test/test
+      continue-on-error: true
+      run: |
+        mkdir -p integration-test/test/.bats/run-logs/
+        sudo bats integration-test/test
+      working-directory: ${{ env.repo_root }}
+
+    - name: Retry Failing Integration Tests
+      run: |
+        sudo bats integration-test/test --filter-status failed
       working-directory: ${{ env.repo_root }}

.gitignore

@@ -12,6 +12,7 @@ applicationhealth-extension-linux
 _obj
 _test
 testbin
+integration-test/test/.bats
 
 # Architecture specific extensions/prefixes
 *.[568vq]

README.md

@@ -1,7 +1,7 @@
 # Azure ApplicationHealth Extension for Linux (1.0.0)
 [![Build Status](https://travis-ci.org/Azure/applicationhealth-extension-linux.svg?branch=master)](https://travis-ci.org/Azure/applicationhealth-extension-linux)
 
-[![GitHub Build Status](https://github.com/Azure/applicationhealth-extension-linux/actions/workflows/go.yml/badge.svg)](https://github.com/Azure/applicationhealth-extension-linux/actions/workflows/go.yml)
+[![GitHub Build Status](https://github.com/Azure/applicationhealth-extension-linux/actions/workflows/merge_validation_v2.yml/badge.svg)](https://github.com/Azure/applicationhealth-extension-linux/actions/workflows/merge_validation_v2.yml)
 
 The application health extension periodically probes for application health within a Linux VM when configured.
 The result of the health checks guide automatic actions that can take place on VMs such as stopping rolling upgrades

integration-test/env/Extension/HandlerEnvironment.json

@@ -4,7 +4,7 @@
     "seqNo": "0",
     "version": 1,
     "handlerEnvironment": {
-      "logFolder": "/var/log/azure/Extension/VE.RS.ION",
+      "logFolder": "/var/log/azure/Extension",
       "configFolder": "/var/lib/waagent/Extension/config",
       "statusFolder": "/var/lib/waagent/Extension/status",
       "heartbeatFile": "/var/lib/waagent/Extension/heartbeat.log"

integration-test/env/Extension/bin/VMWatch/vmwatch.conf

@@ -0,0 +1,154 @@
+# Telegraf Configuration
+#
+# Telegraf is entirely plugin driven. All metrics are gathered from the
+# declared inputs, and sent to the declared outputs.
+#
+# Plugins must be declared in here to be active.
+# To deactivate a plugin, comment out the name and any variables.
+#
+# Use 'telegraf -config telegraf.conf -test' to see what metrics a config
+# file would generate.
+#
+# Environment variables can be used anywhere in this config file, simply surround
+# them with ${}. For strings the variable must be within quotes (ie, "${STR_VAR}"),
+# for numbers and booleans they should be plain (ie, ${INT_VAR}, ${BOOL_VAR})
+
+# Configuration for telegraf agent
+[agent]
+  ## Default data collection interval for all inputs
+  interval = "10s"
+  ## Rounds collection interval to 'interval'
+  ## ie, if interval="10s" then always collect on :00, :10, :20, etc.
+  round_interval = true
+
+  ## Telegraf will send metrics to outputs in batches of at most
+  ## metric_batch_size metrics.
+  ## This controls the size of writes that Telegraf sends to output plugins.
+  metric_batch_size = 1000
+
+  ## Maximum number of unwritten metrics per output.  Increasing this value
+  ## allows for longer periods of output downtime without dropping metrics at the
+  ## cost of higher maximum memory usage.
+  metric_buffer_limit = 10000
+
+  ## Collection jitter is used to jitter the collection by a random amount.
+  ## Each plugin will sleep for a random time within jitter before collecting.
+  ## This can be used to avoid many plugins querying things like sysfs at the
+  ## same time, which can have a measurable effect on the system.
+  collection_jitter = "0s"
+
+  ## Collection offset is used to shift the collection by the given amount.
+  ## This can be be used to avoid many plugins querying constraint devices
+  ## at the same time by manually scheduling them in time.
+  # collection_offset = "0s"
+
+  ## Default flushing interval for all outputs. 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"
+
+  ## Collected metrics are rounded to the precision specified. Precision is
+  ## specified as an interval with an integer + unit (e.g. 0s, 10ms, 2us, 4s).
+  ## Valid time units are "ns", "us" (or "µs"), "ms", "s".
+  ##
+  ## By default or when set to "0s", precision will be set to the same
+  ## timestamp order as the collection interval, with the maximum being 1s:
+  ##   ie, when interval = "10s", precision will be "1s"
+  ##       when interval = "250ms", precision will be "1ms"
+  ##
+  ## Precision will NOT be used for service inputs. It is up to each individual
+  ## service input to set the timestamp at the appropriate precision.
+  precision = "0s"
+
+  ## Log at debug level.
+  # debug = false
+  ## Log only error level messages.
+  # quiet = false
+
+  ## Log target controls the destination for logs and can be one of "file",
+  ## "stderr" or, on Windows, "eventlog".  When set to "file", the output file
+  ## is determined by the "logfile" setting.
+  # logtarget = "file"
+
+  ## Name of the file to be logged to when using the "file" logtarget.  If set to
+  ## the empty string then logs are written to stderr.
+  # logfile = ""
+
+  ## The logfile will be rotated after the time interval specified.  When set
+  ## to 0 no time based rotation is performed.  Logs are rotated only when
+  ## written to, if there is no log activity rotation may be delayed.
+  # logfile_rotation_interval = "0h"
+
+  ## The logfile will be rotated when it becomes larger than the specified
+  ## size.  When set to 0 no size based rotation is performed.
+  # logfile_rotation_max_size = "0MB"
+
+  ## Maximum number of rotated archives to keep, any older logs are deleted.
+  ## If set to -1, no archives are removed.
+  # logfile_rotation_max_archives = 5
+
+  ## Pick a timezone to use when logging or type 'local' for local time.
+  ## Example: America/Chicago
+  # log_with_timezone = ""
+
+  ## Override default hostname, if empty use os.Hostname()
+  hostname = ""
+  ## If set to true, do no set the "host" tag in the telegraf agent.
+  omit_hostname = true
+
+  ## Method of translating SNMP objects. Can be "netsnmp" (deprecated) which
+  ## translates by calling external programs snmptranslate and snmptable,
+  ## or "gosmi" which translates using the built-in gosmi library.
+  # snmp_translator = "netsnmp"
+
+  ## Name of the file to load the state of plugins from and store the state to.
+  ## If uncommented and not empty, this file will be used to save the state of
+  ## stateful plugins on termination of Telegraf. If the file exists on start,
+  ## the state in the file will be restored for the plugins.
+  # statefile = ""
+
+[[inputs.outbound_connectivity]]
+  urls = []
+  timeout_in_seconds = 30
+
+[[inputs.disk_io]]
+  drives = []
+
+[[inputs.simple]]
+  ok = true
+  interval = "10s"
+
+# Send telegraf metrics to file(s)
+[[outputs.file]]
+  flush_interval = "30s"
+  ## Files to write to, "stdout" is a specially handled file.
+  #folder = "/Users/mizhe/tmporary"
+  #folder = "stdout"
+  folder = "/var/log/azure/Microsoft.ManagedServices.ApplicationHealthLinux/events"
+
+  ## Use batch serialization format instead of line based delimiting.  The
+  ## batch format allows for the production of non line based output formats and
+  ## may more efficiently encode and write metrics.
+  use_batch_format = true
+
+  ## The file will be rotated after the time interval specified.  When set
+  ## to 0 no time based rotation is performed.
+  rotation_interval = "10s"
+
+  ## The logfile will be rotated when it becomes larger than the specified
+  ## size.  When set to 0 no size based rotation is performed.
+  # rotation_max_size = "0MB"
+
+  ## Data format to output.
+  ## Each data format has its own unique set of configuration options, read
+  ## more about them here:
+  ## https://github.com/influxdata/telegraf/blob/master/docs/DATA_FORMATS_OUTPUT.md
+  data_format = "json"
+  json_timestamp_format = "2006-01-02T15:04:05Z07:00"
+  json_transformation = '''
+    metrics.$merge([{"Timestamp": timestamp, "Message": $string(fields)}, tags])
+  '''
+

integration-test/env/README.md

@@ -5,12 +5,15 @@ integration testing Docker image.
 
 ```
 .
-├── {THUMBPRINT}.crt            <-- tests generate and push this certificate
-├── {THUMBPRINT}.prv            <-- tests generate and push this private key
-└── Extension/                  
-    ├── HandlerManifest.json    <-- docker image build pushes it here
-    ├── HandlerEnvironment.json <-- the extension reads this
-    ├── bin/                    <-- docker image build pushes the extension binary here
-    ├── config/                 <-- tests push 0.settings file here
-    └── status/                 <-- extension should write here
+├── {THUMBPRINT}.crt                <-- tests generate and push this certificate
+├── {THUMBPRINT}.prv                <-- tests generate and push this private key
+├── Extension/                  
+├   ├── HandlerManifest.json        <-- docker image build pushes it here
+├   ├── HandlerEnvironment.json     <-- the extension reads this
+├   ├── bin/                        <-- docker image build pushes the extension binary here
+├   ├   └── VMWatch/
+├   ├       ├── vmwatch_linux_amd64 <-- VMWatch AMD64 binary
+├   ├       └── vmwatch.conf        <-- VMWatch configuration file
+├───├── config/                     <-- tests push 0.settings file here
+└───└── status/                     <-- extension should write here
 ```

integration-test/test/2_handler-commands.bats

@@ -11,7 +11,7 @@ teardown(){
 }
 
 @test "handler command: install - creates the data dir" {
-    mk_container sh -c "fake-waagent install && sleep 2"
+    mk_container sh -c "fake-waagent install"
     push_settings '' ''
 
     run start_container