logstash-input-ow 0.1.2

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: ca0fc1b2a581cfa40a7a7ad8d1bd3f3f7937dcc3d4fec361c13e66738446976e
+  data.tar.gz: eeb904916e8c7d12cd09ebce82abf18b6cd3780499955b047c526b9c320ef39d
+SHA512:
+  metadata.gz: 1cf5f9fd40ed9ef4447e957e3ceebc7889292157f53b6fbb1ee56fc112288134a33d1e5e47cc61957dc20d459ade0aac6a76a12d1c7a95d8962786b7552034d5
+  data.tar.gz: b74b729873a0ad9448b374332891406cfccee7b906532087bfecf52adc277a129828409ea9fe33294d2e5d2b17d5db4b803de7c1d65b569981b95d29c8f66375

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in logstash-mass_effect.gemspec
+gemspec

data/LICENSE

@@ -0,0 +1,202 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "{}"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright {yyyy} {name of copyright owner}
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.
+

data/README.md

@@ -0,0 +1,122 @@
+# Logstash OpenWhisk input plugin
+
+This [Logstash](https://github.com/elastic/logstash) input plugin allows you to drain Activation logs from OpenWhisk. The HTTP polling service uses the [OpenWhisk API](https://github.com/openwhisk/openwhisk/blob/master/docs/reference.md) to retrieve logs, according to a user-defined schedule. Each activation instance is decoded to an event and forwarded into the system.
+
+This plugin is based off [logstash-input-http_poller](https://github.com/logstash-plugins/logstash-input-http_poller).
+
+## Config Example
+
+```
+input {
+  openwhisk {
+    # Mandatory Configuration Parameters
+    hostname => "openwhisk.ng.bluemix.net"
+    username => "sample_user@email.com"
+    password => "some_password"
+    # Supports "cron", "every", "at" and "in" schedules by rufus scheduler
+    schedule => { "every" => "15m"}
+
+    # Optional Configuration Parameters
+    # Namespace is optional, defaults to user's default namespace.
+    namespace => ""
+    request_timeout => 60
+    codec => "json"
+    # A hash of request metadata info (timing, response headers, etc.) will be sent here
+    metadata_target => "http_poller_metadata"
+  }
+}
+
+output {
+  stdout {
+    codec => rubydebug
+  }
+}
+```
+
+For configuration documentation, see `openwhisk.rb` in `lib/logstash/inputs/` in this repo.
+
+This plugin uses the [Rufus scheduler](https://github.com/jmettraux/rufus-scheduler) to manage the polling request schedule. The `schedule` parameter is parsed by this module and supports all the valid scheduling directives.
+
+More configuration files using this plugin are available in `examples`.
+
+## Installation
+
+`$ bin/logstash-plugin install logstash-input-openwhisk`
+
+## Docker Example
+
+See the `examples/docker` folder for details on building a Docker image for the Elasticsearch, Logstash and Kibaba with the Openwhisk plugin installed.
+
+## Need Help?
+
+Feel free to raise an issue on this project, add a question on [Stack Overflow](http://stackoverflow.com/questions/tagged/openwhisk) or come and talk to us in the [OpenWhisk Slack channel](https://developer.ibm.com/openwhisk/2016/06/15/talk-to-us-on-slack/).
+
+## Developing
+
+### 1. Plugin Developement and Testing
+
+#### Code
+- To get started, you'll need JRuby with the Bundler gem installed.
+
+- Create a new plugin or clone and existing from the GitHub [logstash-plugins](https://github.com/logstash-plugins) organization. We also provide [example plugins](https://github.com/logstash-plugins?query=example).
+
+- Install dependencies
+```sh
+bundle install
+```
+
+#### Test
+
+- Update your dependencies
+
+```sh
+bundle install
+```
+
+- Run tests
+
+```sh
+bundle exec rspec
+```
+
+### 2. Running your unpublished Plugin in Logstash
+
+#### 2.1 Run in a local Logstash clone
+
+- Edit Logstash `Gemfile` and add the local plugin path, for example:
+```ruby
+gem "logstash-input-openwhisk", :path => "/your/local/logstash-input-openwhisk"
+```
+- Install plugin
+```sh
+# Logstash 2.3 and higher
+bin/logstash-plugin install --no-verify
+
+# Prior to Logstash 2.3
+bin/plugin install --no-verify
+
+```
+- Run Logstash with your plugin
+```sh
+bin/logstash -e 'input {openwhisk {...}}'
+```
+At this point any modifications to the plugin code will be applied to this local Logstash setup. After modifying the plugin, simply rerun Logstash.
+
+#### 2.2 Run in an installed Logstash
+
+You can use the same **2.1** method to run your plugin in an installed Logstash by editing its `Gemfile` and pointing the `:path` to your local plugin development directory or you can build the gem and install it using:
+
+- Build your plugin gem
+```sh
+gem build logstash-input-openwhisk.gemspec
+```
+- Install the plugin from the Logstash home
+```sh
+# Logstash 2.3 and higher
+bin/logstash-plugin install --no-verify
+
+# Prior to Logstash 2.3
+bin/plugin install --no-verify
+
+```
+- Start Logstash and proceed to test the plugin

data/lib/logstash/inputs/openwhisk.rb

@@ -0,0 +1,302 @@
+# encoding: utf-8
+require "logstash/inputs/base"
+require "logstash/namespace"
+require "logstash/plugin_mixins/http_client"
+require "socket" # for Socket.gethostname
+require "manticore"
+require "rufus/scheduler"
+require 'json'
+
+# This Logstash input plugin allows you to drain OpenWhisk Activation logs, decoding the output into event(s), and
+# send them on their merry way. Using the OpenWhisk platform API, we poll the activation logs API according to the config schedule.
+# This plugin borrows heavily from the HTTP Poller input plugin. 
+#
+# ==== Example
+# Drain logs from an OpenWhisk platform instance.
+# The config should look like this:
+#
+# [source,ruby]
+# ----------------------------------
+# input {
+#   openwhisk {
+#     # Mandatory Configuration Parameters
+#     hostname => "openwhisk.ng.bluemix.net"
+#     username => "sample_user@email.com"
+#     password => "some_password"
+#     # Supports "cron", "every", "at" and "in" schedules by rufus scheduler
+#     schedule => { cron => "* * * * * UTC"}
+#
+#     # Optional Configuration Parameters
+#     # Namespace is optional, defaults to user's default namespace.
+#     namespace => ""
+#     request_timeout => 60
+#     codec => "json"
+#     # A hash of request metadata info (timing, response headers, etc.) will be sent here
+#     metadata_target => "http_poller_metadata"
+#   }
+# }
+#
+# output {
+#   stdout {
+#     codec => rubydebug
+#   }
+# }
+# ----------------------------------
+#
+
+class LogStash::Inputs::OpenWhisk < LogStash::Inputs::Base
+  include LogStash::PluginMixins::HttpClient
+
+  config_name "openwhisk"
+
+  default :codec, "json"
+
+  # OpenWhisk Platform Parameters
+  config :hostname, :validate => :string, :required => true
+  config :username, :validate => :string, :required => true
+  config :password, :validate => :string, :required => true
+
+  # Optional OpenWhisk namespace, defaults to user account namespace.
+  config :namespace, :validate => :string, :default => '_'
+
+  # How often (in seconds) the urls will be called
+  # DEPRECATED. Use 'schedule' option instead.
+  # If both interval and schedule options are specified, interval
+  # option takes higher precedence
+  config :interval, :validate => :number, :deprecated => true
+
+  # Schedule of when to periodically poll from the urls
+  # Format: A hash with
+  #   + key: "cron" | "every" | "in" | "at"
+  #   + value: string
+  # Examples:
+  #   a) { "every" => "1h" }
+  #   b) { "cron" => "* * * * * UTC" }
+  # See: rufus/scheduler for details about different schedule options and value string format
+  config :schedule, :validate => :hash
+
+  # Define the target field for placing the received data. If this setting is omitted, the data will be stored at the root (top level) of the event.
+  config :target, :validate => :string
+
+  # If you'd like to work with the request/response metadata.
+  # Set this value to the name of the field you'd like to store a nested
+  # hash of metadata.
+  config :metadata_target, :validate => :string, :default => '@metadata'
+
+  public
+  Schedule_types = %w(cron every at in)
+  def register
+    @host = Socket.gethostname.force_encoding(Encoding::UTF_8)
+
+    @logger.info("Registering openwhisk Input", :type => @type,
+                 :hostname=> @hostname, :interval => @interval, :schedule => @schedule, :timeout => @timeout)
+
+    # we will start polling for logs since the current epoch
+    @logs_since = Time.now.to_i * 1000
+
+    # activation ids from previous poll used to control what is indexed,
+    # we might have overlapping results and don't want to index the same
+    # activations twice.
+    @activation_ids = Set.new
+  end
+
+  def stop
+    Stud.stop!(@interval_thread) if @interval_thread
+    @scheduler.stop if @scheduler
+  end
+
+  # generate HTTP request options for current platform host.
+  private
+  def construct_request(opts)
+    url = "https://#{opts['hostname']}/api/v1/namespaces/#{opts['namespace']}/activations"
+    auth = {user: opts['username'], pass: opts['password']} 
+    query = {docs: true, limit: 0, skip: 0, since: @logs_since}
+    res = [:get, url, {:auth => auth, :query => query}]
+  end
+
+  public
+  def run(queue)
+    #interval or schedule must be provided. Must be exclusively either one. Not neither. Not both.
+    raise LogStash::ConfigurationError, "Invalid config. Neither interval nor schedule was specified." \
+      unless @interval ||  @schedule
+    raise LogStash::ConfigurationError, "Invalid config. Specify only interval or schedule. Not both." \
+      if @interval && @schedule
+
+    if @interval
+      setup_interval(queue)
+    elsif @schedule
+      setup_schedule(queue)
+    else
+      #should not reach here
+      raise LogStash::ConfigurationError, "Invalid config. Neither interval nor schedule was specified."
+    end
+  end
+
+  private
+  def setup_interval(queue)
+    @interval_thread = Thread.current
+    Stud.interval(@interval) do
+      run_once(queue)
+    end
+  end
+
+  def setup_schedule(queue)
+    #schedule hash must contain exactly one of the allowed keys
+    msg_invalid_schedule = "Invalid config. schedule hash must contain " +
+      "exactly one of the following keys - cron, at, every or in"
+    raise Logstash::ConfigurationError, msg_invalid_schedule if @schedule.keys.length !=1
+    schedule_type = @schedule.keys.first
+    schedule_value = @schedule[schedule_type]
+    raise LogStash::ConfigurationError, msg_invalid_schedule unless Schedule_types.include?(schedule_type)
+
+    @scheduler = Rufus::Scheduler.new(:max_work_threads => 1)
+    #as of v3.0.9, :first_in => :now doesn't work. Use the following workaround instead
+    opts = schedule_type == "every" ? { :first_in => 0.01 } : {} 
+    @scheduler.send(schedule_type, schedule_value, opts) { run_once(queue) }
+    @scheduler.join
+  end
+
+  def run_once(queue)
+    request = construct_request({"hostname" => @hostname, "username" => @username, "password" => @password, "namespace" => @namespace})
+
+    request_async(queue, "openwhisk", request)
+    client.execute!
+  end
+
+  private
+  def request_async(queue, name, request)
+    @logger.debug? && @logger.debug("Fetching URL", :name => name, :url => request)
+    started = Time.now
+
+    method, *request_opts = request
+    client.async.send(method, *request_opts).
+      on_success {|response| handle_success(queue, name, request, response, Time.now - started)}.
+      on_failure {|exception|
+      handle_failure(queue, name, request, exception, Time.now - started)
+    }
+  end
+
+  private
+  def handle_success(queue, name, request, response, execution_time)
+    activation_ids = Set.new
+
+    @codec.decode(response.body) do |decoded|
+      activation_id = decoded.to_hash["activationId"]
+
+      ## ignore results we have previously seen
+      if !@activation_ids.include?(activation_id)
+        sanitize(decoded)
+        event = @target ? LogStash::Event.new(@target => decoded.to_hash) : decoded
+        update_logs_since(decoded.to_hash["end"])
+        handle_decoded_event(queue, name, request, response, event, execution_time)
+      end
+
+      activation_ids.add(activation_id)
+    end
+
+    @activation_ids = activation_ids
+  end
+
+  # elastic search cannot handle attributes which change types.
+  # serialise annotations to JSON strings
+  private
+  def sanitize(activation)
+    annotations = activation.get("annotations")
+    annotations.each {|a| a["value"] = a["value"].to_json}
+    activation.set("annotations", annotations)
+  end
+
+  # updates the query parameter for the next request
+  # based upon the last activation's end time.
+  private
+  def update_logs_since(ms_since_epoch)
+    # actions have a maximum timeout for five minutes
+    max_action_time_ms = 5 * 60 * 1000
+    next_logs_since = ms_since_epoch - max_action_time_ms
+
+    if (next_logs_since > @logs_since)
+      @logs_since = next_logs_since
+    end
+  end
+
+  private
+  def handle_decoded_event(queue, name, request, response, event, execution_time)
+    apply_metadata(event, name, request, response, execution_time)
+    decorate(event)
+    queue << event
+  rescue StandardError, java.lang.Exception => e
+    @logger.error? && @logger.error("Error eventifying response!",
+                                    :exception => e,
+                                    :exception_message => e.message,
+                                    :name => name,
+                                    :url => request,
+                                    :response => response
+    )
+  end
+
+  private
+  # Beware, on old versions of manticore some uncommon failures are not handled
+  def handle_failure(queue, name, request, exception, execution_time)
+    event = LogStash::Event.new
+    apply_metadata(event, name, request)
+
+    event.tag("_http_request_failure")
+
+    # This is also in the metadata, but we send it anyone because we want this
+    # persisted by default, whereas metadata isn't. People don't like mysterious errors
+    event.set("http_request_failure", {
+      "request" => structure_request(request),
+      "name" => name,
+      "error" => exception.to_s,
+      "backtrace" => exception.backtrace,
+      "runtime_seconds" => execution_time
+   })
+
+    queue << event
+  rescue StandardError, java.lang.Exception => e
+      @logger.error? && @logger.error("Cannot read URL or send the error as an event!",
+                                      :exception => e,
+                                      :exception_message => e.message,
+                                      :exception_backtrace => e.backtrace,
+                                      :name => name,
+                                      :url => request
+      )
+  end
+
+  private
+  def apply_metadata(event, name, request, response=nil, execution_time=nil)
+    return unless @metadata_target
+    event.set(@metadata_target, event_metadata(name, request, response, execution_time))
+  end
+
+  private
+  def event_metadata(name, request, response=nil, execution_time=nil)
+    m = {
+        "name" => name,
+        "hostname" => @hostname,
+        "request" => structure_request(request),
+      }
+
+    m["runtime_seconds"] = execution_time
+
+    if response
+      m["code"] = response.code
+      m["response_headers"] = response.headers
+      m["response_message"] = response.message
+      m["times_retried"] = response.times_retried
+    end
+
+    m
+  end
+
+  private
+  # Turn [method, url, spec] requests into a hash for friendlier logging / ES indexing
+  def structure_request(request)
+    method, url, spec = request
+    # Flatten everything into the 'spec' hash, also stringify any keys to normalize
+    Hash[(spec||{}).merge({
+      "method" => method.to_s,
+      "url" => url,
+    }).map {|k,v| [k.to_s,v] }]
+  end
+end