Add configuration of filestream input (elastic#21565)

(cherry picked from commit d35dfb5)

filebeat/_meta/config/filebeat.inputs.reference.yml.tmpl

@@ -11,6 +11,7 @@ filebeat.inputs:
 #
 # Possible options are:
 # * log: Reads every line of the log file (default)
+# * filestream: Improved version of log input. Experimental.
 # * stdin: Reads the standard in
 
 #------------------------------ Log input --------------------------------
@@ -231,6 +232,145 @@ filebeat.inputs:
   # Defines if inputs is enabled
   #enabled: true
 
+#--------------------------- Filestream input ----------------------------
+- type: filestream
+
+  # Change to true to enable this input configuration.
+  enabled: false
+
+  # Paths that should be crawled and fetched. Glob based paths.
+  # To fetch all ".log" files from a specific level of subdirectories
+  # /var/log/*/*.log can be used.
+  # For each file found under this path, a harvester is started.
+  # Make sure not file is defined twice as this can lead to unexpected behaviour.
+  paths:
+    - /var/log/*.log
+    #- c:\programdata\elasticsearch\logs\*
+
+  # Configure the file encoding for reading files with international characters
+  # following the W3C recommendation for HTML5 (http://www.w3.org/TR/encoding).
+  # Some sample encodings:
+  #   plain, utf-8, utf-16be-bom, utf-16be, utf-16le, big5, gb18030, gbk,
+  #    hz-gb-2312, euc-kr, euc-jp, iso-2022-jp, shift-jis, ...
+  #encoding: plain
+
+
+  # Exclude lines. A list of regular expressions to match. It drops the lines that are
+  # matching any regular expression from the list. The include_lines is called before
+  # exclude_lines. By default, no lines are dropped.
+  #exclude_lines: ['^DBG']
+
+  # Include lines. A list of regular expressions to match. It exports the lines that are
+  # matching any regular expression from the list. The include_lines is called before
+  # exclude_lines. By default, all the lines are exported.
+  #include_lines: ['^ERR', '^WARN']
+
+  ### Prospector options
+
+  # How often the input checks for new files in the paths that are specified
+  # for harvesting. Specify 1s to scan the directory as frequently as possible
+  # without causing Filebeat to scan too frequently. Default: 10s.
+  #prospector.scanner.check_interval: 10s
+
+  # Exclude files. A list of regular expressions to match. Filebeat drops the files that
+  # are matching any regular expression from the list. By default, no files are dropped.
+  #prospector.scanner.exclude_files: ['.gz$']
+
+  # Expand "**" patterns into regular glob patterns.
+  #prospector.scanner.recursive_glob: true
+
+  # If symlinks is enabled, symlinks are opened and harvested. The harvester is opening the
+  # original for harvesting but will report the symlink name as source.
+  #prospector.scanner.symlinks: false
+
+  ### State options
+
+  # Files for the modification data is older then clean_inactive the state from the registry is removed
+  # By default this is disabled.
+  #clean_inactive: 0
+
+  # Removes the state for file which cannot be found on disk anymore immediately
+  #clean_removed: true
+
+  # Method to determine if two files are the same or not. By default
+  # the Beat considers two files the same if their inode and device id are the same.
+  #file_identity.native: ~
+
+  # Optional additional fields. These fields can be freely picked
+  # to add additional information to the crawled log files for filtering
+  #fields:
+  #  level: debug
+  #  review: 1
+
+  # Set to true to publish fields with null values in events.
+  #keep_null: false
+
+  # By default, all events contain `host.name`. This option can be set to true
+  # to disable the addition of this field to all events. The default value is
+  # false.
+  #publisher_pipeline.disable_host: false
+
+  # Ignore files which were modified more then the defined timespan in the past.
+  # ignore_older is disabled by default, so no files are ignored by setting it to 0.
+  # Time strings like 2h (2 hours), 5m (5 minutes) can be used.
+  #ignore_older: 0
+
+  # Defines the buffer size every harvester uses when fetching the file
+  #harvester_buffer_size: 16384
+
+  # Maximum number of bytes a single log event can have
+  # All bytes after max_bytes are discarded and not sent. The default is 10MB.
+  # This is especially useful for multiline log messages which can get large.
+  #message_max_bytes: 10485760
+
+  # Characters which separate the lines. Valid values: auto, line_feed, vertical_tab, form_feed,
+  # carriage_return, carriage_return_line_feed, next_line, line_separator, paragraph_separator.
+  #line_terminator: auto
+
+  # The Ingest Node pipeline ID associated with this input. If this is set, it
+  # overwrites the pipeline option from the Elasticsearch output.
+  #pipeline:
+
+  # Backoff values define how aggressively filebeat crawls new files for updates
+  # The default values can be used in most cases. Backoff defines how long it is waited
+  # to check a file again after EOF is reached. Default is 1s which means the file
+  # is checked every second if new lines were added. This leads to a near real time crawling.
+  # Every time a new line appears, backoff is reset to the initial value.
+  #backoff.init: 1s
+
+  # Max backoff defines what the maximum backoff time is. After having backed off multiple times
+  # from checking the files, the waiting time will never exceed max_backoff independent of the
+  # backoff factor. Having it set to 10s means in the worst case a new line can be added to a log
+  # file after having backed off multiple times, it takes a maximum of 10s to read the new line
+  #backoff.max: 10s
+
+  ### Harvester closing options
+
+  # Close inactive closes the file handler after the predefined period.
+  # The period starts when the last line of the file was, not the file ModTime.
+  # Time strings like 2h (2 hours), 5m (5 minutes) can be used.
+  #close.on_state_change.inactive: 5m
+
+  # Close renamed closes a file handler when the file is renamed or rotated.
+  # Note: Potential data loss. Make sure to read and understand the docs for this option.
+  #close.on_state_change.renamed: false
+
+  # When enabling this option, a file handler is closed immediately in case a file can't be found
+  # any more. In case the file shows up again later, harvesting will continue at the last known position
+  # after scan_frequency.
+  #close.on_state_change.removed: true
+
+  # Closes the file handler as soon as the harvesters reaches the end of the file.
+  # By default this option is disabled.
+  # Note: Potential data loss. Make sure to read and understand the docs for this option.
+  #close.reader.eof: false
+
+  # Close timeout closes the harvester after the predefined time.
+  # This is independent if the harvester did finish reading the file or not.
+  # By default this option is disabled.
+  # Note: Potential data loss. Make sure to read and understand the docs for this option.
+  #close.reader.after_interval: 0
+
 #----------------------------- Stdin input -------------------------------
 # Configuration to use stdin input
 #- type: stdin

filebeat/_meta/config/filebeat.inputs.yml.tmpl

@@ -49,3 +49,32 @@ filebeat.inputs:
   # that was (not) matched before or after or as long as a pattern is not matched based on negate.
   # Note: After is the equivalent to previous and before is the equivalent to to next in Logstash
   #multiline.match: after
+
+# filestream is an experimental input. It is going to replace log input in the future.
+- type: filestream
+
+  # Change to true to enable this input configuration.
+  enabled: false
+
+  # Paths that should be crawled and fetched. Glob based paths.
+  paths:
+    - /var/log/*.log
+    #- c:\programdata\elasticsearch\logs\*
+
+  # Exclude lines. A list of regular expressions to match. It drops the lines that are
+  # matching any regular expression from the list.
+  #exclude_lines: ['^DBG']
+
+  # Include lines. A list of regular expressions to match. It exports the lines that are
+  # matching any regular expression from the list.
+  #include_lines: ['^ERR', '^WARN']
+
+  # Exclude files. A list of regular expressions to match. Filebeat drops the files that
+  # are matching any regular expression from the list. By default, no files are dropped.
+  #prospector.scanner.exclude_files: ['.gz$']
+
+  # Optional additional fields. These fields can be freely picked
+  # to add additional information to the crawled log files for filtering
+  #fields:
+  #  level: debug
+  #  review: 1

filebeat/filebeat.reference.yml

@@ -398,6 +398,7 @@ filebeat.inputs:
 #
 # Possible options are:
 # * log: Reads every line of the log file (default)
+# * filestream: Improved version of log input. Experimental.
 # * stdin: Reads the standard in
 
 #------------------------------ Log input --------------------------------
@@ -618,6 +619,145 @@ filebeat.inputs:
   # Defines if inputs is enabled
   #enabled: true
 
+#--------------------------- Filestream input ----------------------------
+- type: filestream
+
+  # Change to true to enable this input configuration.
+  enabled: false
+
+  # Paths that should be crawled and fetched. Glob based paths.
+  # To fetch all ".log" files from a specific level of subdirectories
+  # /var/log/*/*.log can be used.
+  # For each file found under this path, a harvester is started.
+  # Make sure not file is defined twice as this can lead to unexpected behaviour.
+  paths:
+    - /var/log/*.log
+    #- c:\programdata\elasticsearch\logs\*
+
+  # Configure the file encoding for reading files with international characters
+  # following the W3C recommendation for HTML5 (http://www.w3.org/TR/encoding).
+  # Some sample encodings:
+  #   plain, utf-8, utf-16be-bom, utf-16be, utf-16le, big5, gb18030, gbk,
+  #    hz-gb-2312, euc-kr, euc-jp, iso-2022-jp, shift-jis, ...
+  #encoding: plain
+
+
+  # Exclude lines. A list of regular expressions to match. It drops the lines that are
+  # matching any regular expression from the list. The include_lines is called before
+  # exclude_lines. By default, no lines are dropped.
+  #exclude_lines: ['^DBG']
+
+  # Include lines. A list of regular expressions to match. It exports the lines that are
+  # matching any regular expression from the list. The include_lines is called before
+  # exclude_lines. By default, all the lines are exported.
+  #include_lines: ['^ERR', '^WARN']
+
+  ### Prospector options
+
+  # How often the input checks for new files in the paths that are specified
+  # for harvesting. Specify 1s to scan the directory as frequently as possible
+  # without causing Filebeat to scan too frequently. Default: 10s.
+  #prospector.scanner.check_interval: 10s
+
+  # Exclude files. A list of regular expressions to match. Filebeat drops the files that
+  # are matching any regular expression from the list. By default, no files are dropped.
+  #prospector.scanner.exclude_files: ['.gz$']
+
+  # Expand "**" patterns into regular glob patterns.
+  #prospector.scanner.recursive_glob: true
+
+  # If symlinks is enabled, symlinks are opened and harvested. The harvester is opening the
+  # original for harvesting but will report the symlink name as source.
+  #prospector.scanner.symlinks: false
+
+  ### State options
+
+  # Files for the modification data is older then clean_inactive the state from the registry is removed
+  # By default this is disabled.
+  #clean_inactive: 0
+
+  # Removes the state for file which cannot be found on disk anymore immediately
+  #clean_removed: true
+
+  # Method to determine if two files are the same or not. By default
+  # the Beat considers two files the same if their inode and device id are the same.
+  #file_identity.native: ~
+
+  # Optional additional fields. These fields can be freely picked
+  # to add additional information to the crawled log files for filtering
+  #fields:
+  #  level: debug
+  #  review: 1
+
+  # Set to true to publish fields with null values in events.
+  #keep_null: false
+
+  # By default, all events contain `host.name`. This option can be set to true
+  # to disable the addition of this field to all events. The default value is
+  # false.
+  #publisher_pipeline.disable_host: false
+
+  # Ignore files which were modified more then the defined timespan in the past.
+  # ignore_older is disabled by default, so no files are ignored by setting it to 0.
+  # Time strings like 2h (2 hours), 5m (5 minutes) can be used.
+  #ignore_older: 0
+
+  # Defines the buffer size every harvester uses when fetching the file
+  #harvester_buffer_size: 16384
+
+  # Maximum number of bytes a single log event can have
+  # All bytes after max_bytes are discarded and not sent. The default is 10MB.
+  # This is especially useful for multiline log messages which can get large.
+  #message_max_bytes: 10485760
+
+  # Characters which separate the lines. Valid values: auto, line_feed, vertical_tab, form_feed,
+  # carriage_return, carriage_return_line_feed, next_line, line_separator, paragraph_separator.
+  #line_terminator: auto
+
+  # The Ingest Node pipeline ID associated with this input. If this is set, it
+  # overwrites the pipeline option from the Elasticsearch output.
+  #pipeline:
+
+  # Backoff values define how aggressively filebeat crawls new files for updates
+  # The default values can be used in most cases. Backoff defines how long it is waited
+  # to check a file again after EOF is reached. Default is 1s which means the file
+  # is checked every second if new lines were added. This leads to a near real time crawling.
+  # Every time a new line appears, backoff is reset to the initial value.
+  #backoff.init: 1s
+
+  # Max backoff defines what the maximum backoff time is. After having backed off multiple times
+  # from checking the files, the waiting time will never exceed max_backoff independent of the
+  # backoff factor. Having it set to 10s means in the worst case a new line can be added to a log
+  # file after having backed off multiple times, it takes a maximum of 10s to read the new line
+  #backoff.max: 10s
+
+  ### Harvester closing options
+
+  # Close inactive closes the file handler after the predefined period.
+  # The period starts when the last line of the file was, not the file ModTime.
+  # Time strings like 2h (2 hours), 5m (5 minutes) can be used.
+  #close.on_state_change.inactive: 5m
+
+  # Close renamed closes a file handler when the file is renamed or rotated.
+  # Note: Potential data loss. Make sure to read and understand the docs for this option.
+  #close.on_state_change.renamed: false
+
+  # When enabling this option, a file handler is closed immediately in case a file can't be found
+  # any more. In case the file shows up again later, harvesting will continue at the last known position
+  # after scan_frequency.
+  #close.on_state_change.removed: true
+
+  # Closes the file handler as soon as the harvesters reaches the end of the file.
+  # By default this option is disabled.
+  # Note: Potential data loss. Make sure to read and understand the docs for this option.
+  #close.reader.eof: false
+
+  # Close timeout closes the harvester after the predefined time.
+  # This is independent if the harvester did finish reading the file or not.
+  # By default this option is disabled.
+  # Note: Potential data loss. Make sure to read and understand the docs for this option.
+  #close.reader.after_interval: 0
+
 #----------------------------- Stdin input -------------------------------
 # Configuration to use stdin input
 #- type: stdin

filebeat/filebeat.yml

@@ -62,6 +62,35 @@ filebeat.inputs:
   # Note: After is the equivalent to previous and before is the equivalent to to next in Logstash
   #multiline.match: after
 
+# filestream is an experimental input. It is going to replace log input in the future.
+- type: filestream
+
+  # Change to true to enable this input configuration.
+  enabled: false
+
+  # Paths that should be crawled and fetched. Glob based paths.
+  paths:
+    - /var/log/*.log
+    #- c:\programdata\elasticsearch\logs\*
+
+  # Exclude lines. A list of regular expressions to match. It drops the lines that are
+  # matching any regular expression from the list.
+  #exclude_lines: ['^DBG']
+
+  # Include lines. A list of regular expressions to match. It exports the lines that are
+  # matching any regular expression from the list.
+  #include_lines: ['^ERR', '^WARN']
+
+  # Exclude files. A list of regular expressions to match. Filebeat drops the files that
+  # are matching any regular expression from the list. By default, no files are dropped.
+  #prospector.scanner.exclude_files: ['.gz$']
+
+  # Optional additional fields. These fields can be freely picked
+  # to add additional information to the crawled log files for filtering
+  #fields:
+  #  level: debug
+  #  review: 1
+
 # ============================== Filebeat modules ==============================
 
 filebeat.config.modules: