AppHealthLinux's VMWatch binary update to 1.2.0, AppHealthLinux manifest version bump to 2.0.13

VMWatch/version.txt

@@ -0,0 +1 @@
+1.2.02798.0-official-2d923cdf

VMWatch/vmwatch.conf

@@ -0,0 +1,287 @@
+# 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 = false
+
+  ## 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 = "20s"
+
+  ## 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 = "${VERBOSE_LOG_FILE_FULL_PATH:-}"
+
+  ## 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 = "60s"
+
+  ## 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 = "4MB"
+
+  ## 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]]
+  interval = "${OUTBOUND_CONNECTIVITY_INTERVAL:-60s}"
+  name_suffix = "${OUTBOUND_CONNECTIVITY_NAME_SUFFIX:-}"
+  urls = "${OUTBOUND_CONNECTIVITY_URLS:-http://www.msftconnecttest.com/connecttest.txt}"
+  timeout_in_milliseconds = ${OUTBOUND_CONNECTIVITY_TIMEOUT_IN_MILLISECONDS:-5000}
+  total_attempts = ${OUTBOUND_CONNECTIVITY_TOTAL_ATTEMPTS:-3}
+  retry_interval_in_seconds = ${OUTBOUND_CONNECTIVITY_RETRY_INTERVAL_IN_SECONDS:-10}
+
+[[inputs.disk_io]]
+  interval = "${DISK_IO_INTERVAL:-180s}"
+  name_suffix = "${DISK_IO_NAME_SUFFIX:-}"
+  mount_points = "${DISK_IO_MOUNT_POINTS:-}"
+  ignore_file_system_list = "${DISK_IO_IGNORE_FS_LIST:-tmpfs,devtmpfs,devfs,iso9660,overlay,aufs,squashfs,autofs}"
+  file_name = "${DISK_IO_FILENAME:-}"
+
+[[inputs.simple]]
+  interval = "${SIMPLE_INTERVAL:-10s}"
+  name_suffix = "${SIMPLE_NAME_SUFFIX:-}"
+  ok = ${SIMPLE_OK:-false}
+
+[[inputs.az_storage_blob]]
+    interval = "${AZ_STORAGE_BLOB_INTERVAL:-180s}"
+    name_suffix = "${AZ_STORAGE_BLOB_NAME_SUFFIX:-}"
+    storage_account_name = "${AZ_STORAGE_ACCOUNT_NAME:-}"
+    container_name = "${AZ_STORAGE_CONTAINER_NAME:-}"
+    blob_name = "${AZ_STORAGE_BLOB_NAME:-}"
+    blob_domain_name = "${AZ_STORAGE_BLOB_DOMAIN_NAME:-blob.core.windows.net}"
+    sas_token_base64 = "${AZ_STORAGE_SAS_TOKEN_BASE64:-}"
+    use_managed_identity = ${AZ_STORAGE_USE_MANAGED_IDENTITY:-false}
+    managed_identity_client_id = "${AZ_STORAGE_MANAGED_IDENTITY_CLIENT_ID:-}"
+
+[[inputs.clockskew]]
+    interval = "${CLOCK_SKEW_INTERVAL:-180s}"
+    name_suffix = "${CLOCK_SKEW_NAME_SUFFIX:-}"
+    ntp_server = "${CLOCK_SKEW_NTP_SERVER:-time.windows.com}"
+    time_skew_threshold_in_seconds = ${CLOCK_SKEW_TIME_SKEW_THRESHOLD_IN_SECONDS:-5.0}
+
+[[inputs.process]]
+    interval = "${PROCESS_INTERVAL:-180s}"
+    name_suffix = "${PROCESS_NAME_SUFFIX:-}"
+    timeout = "${PROCESS_TIMEOUT:-10s}"
+
+[[inputs.process_monitor]]
+    interval = "${PROCESS_MONITOR_INTERVAL:-180s}"
+    name_suffix = "${PROCESS_MONITOR_NAME_SUFFIX:-}"
+    process_names = "${PROCESS_MONITOR_PROCESS_NAMES:-}"
+
+[[inputs.test]]
+    interval = "${TEST_INTERVAL:-1s}"
+    name_suffix = "${TEST_NAME_SUFFIX:-}"
+    exit_process = ${TEST_EXIT_PROCESS:-false}
+    allocate_memory = ${TEST_ALLOCATE_MEMORY:-false}
+    high_cpu = ${TEST_HIGH_CPU:-false}
+
+[[inputs.dns]]
+    interval = "${DNS_INTERVAL:-180s}"
+    name_suffix = "${DNS_NAME_SUFFIX:-}"
+    dns_names = "${DNS_NAMES:-www.msftconnecttest.com}"
+
+[[inputs.imds]]
+    interval = "${IMDS_INTERVAL:-180s}"
+    name_suffix = "${IMDS_NAME_SUFFIX:-}"
+    imds_endpoint = "${IMDS_ENDPOINT:-http://169.254.169.254/metadata/instance/compute}"
+    timeout_in_seconds = ${IMDS_TIMEOUT_IN_SECONDS:-10}
+    retry_interval_in_seconds = ${IMDS_RETRY_INTERVAL_IN_SEONDS:-15}
+    query_Total_attempts = ${IMDS_QUERY_TOTAL_ATTEMPTS:-4} 
+
+[[inputs.tcp_stats]]
+    interval = "${TCP_STATS_INTERVAL:-180s}"
+    name_suffix = "${TCP_STATS_NAME_SUFFIX:-}"
+
+[[inputs.process_cpu]]
+    interval = "${PROCESS_CPU_INTERVAL:-180s}"
+    name_suffix = "${PROCESS_CPU_NAME_SUFFIX:-}"
+
+[[inputs.disk_iops]]
+    interval = "${DISK_IOPS_INTERVAL:-180s}"
+    name_suffix = "${DISK_IOPS_NAME_SUFFIX:-}"
+    devices = "${DISK_IOPS_DEVICES:-}"
+    ignore_device_regex = "${DISK_IOPS_IGNORE_DEVICE_REGEX:-loop}"
+
+[[inputs.hardware_health_monitor]]
+  interval = "${HARDWARE_HEALTH_MONITOR_INTERVAL:-180s}"
+  name_override = "hardware_health_monitor"
+
+[[aggregators.check_aggregator]]
+    period = "${CHECK_AGGREGATION_INTERVAL:-300s}"
+    drop_original = true
+    [aggregators.check_aggregator.tagpass]
+      EventLevel = ["Check"]
+
+[[aggregators.metric_aggregator]]
+    period = "${METRIC_AGGREGATION_INTERVAL:-300s}"
+    drop_original = true
+    [aggregators.metric_aggregator.tagpass]
+      EventLevel = ["Metric"]
+
+[[aggregators.eventlog_aggregator]]
+    period = "${EVENTLOG_AGGREGATION_INTERVAL:-300s}"
+    drop_original = true
+    max_allowed_count =  ${EVENTLOG_AGGREGATION_MAX_ALLOWED_COUNT:-3}
+    [aggregators.eventlog_aggregator.tagpass]
+      EventLevel = ["EventLog"]
+
+[[processors.event_processor]]
+    period = "${EVENT_PROCESSOR_INTERVAL:-300s}"
+    namepass = ["hardware_health_monitor"]
+    [processors.event_processor.tagdrop]
+      EventLevel = ["EventLog"]  # Telegraf processor processes signals sent from both inputs and aggregators. To prevent signals from feeding into the processor again after aggregation, excluding signals with tag EventLevel=EventLog as the processor adds this tag after processing.
+
+# Send telegraf metrics to file(s)
+[[outputs.file]]
+  flush_interval = "30s"
+  ## Files to write to, "stdout" is a specially handled file.
+  folder = "${SIGNAL_FOLDER:-stdout}"
+
+  ## 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 = false
+
+  ## The file will be rotated after the time interval specified.  When set
+  ## to 0 no time based rotation is performed.
+  rotation_interval = "10s"
+
+  ## max number of files that can be present in the folder, if exceeded new files will not be written
+  rotation_max_file_count = 1000
+
+  ## 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_nested_fields_include = ["RuntimeParameters", "Errors", "Stats", "Contents"]
+  json_transformation = '''
+    $merge([{"Timestamp": timestamp, "Message": $string( $merge([{"Name": name}, fields]) )}, tags])
+  '''
+[[outputs.file]]
+  flush_interval = "30s"
+  ## this output will be enabled if this variable is set otherwise it is a no-op
+  ## it specifies and additional location to write the events to for troubleshooting
+  folder = "${ADDITIONAL_SIGNAL_FOLDER_FOR_TROUBLESHOOTING:-}"
+
+  ## 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 = false
+
+  ## The file will be rotated after the time interval specified.  When set
+  ## to 0 no time based rotation is performed.
+  rotation_interval = "10s"
+
+  ## max number of files that can be present in the folder, if exceeded new files will not be written
+  rotation_max_file_count = 1000
+
+  ## 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_nested_fields_include = ["RuntimeParameters", "Errors", "Stats", "Contents"]
+  json_transformation = '''
+    $merge([{"Timestamp": timestamp, "Message": $string( $merge([{"Name": name}, fields]) )}, tags])
+  '''
+

misc/manifest.xml

@@ -2,7 +2,7 @@
 <ExtensionImage xmlns="http://schemas.microsoft.com/windowsazure">
   <ProviderNameSpace>Microsoft.ManagedServices</ProviderNameSpace>
   <Type>ApplicationHealthLinux</Type>
-  <Version>2.0.12</Version>
+  <Version>2.0.13</Version>
   <Label>Microsoft Azure Application Health Extension for Linux Virtual Machines</Label>
   <HostingResources>VmRole</HostingResources>
   <MediaLink></MediaLink>