fluent-plugin-logzio 0.0.22 → 0.2.0.pre.test1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: f6e13567cce456b4bf9efe5ec2fcc72d9ab50648
-  data.tar.gz: 9c92ef500e341c040349be13f9ac4d2ea8a3ea96
+SHA256:
+  metadata.gz: 8ff307f46dc9f34f4f4cdd60374c340c81ab328c6e1485d8cf77d7c833709b9e
+  data.tar.gz: 286c954bb9c4a1e1ead99edf25e96a77556254b58afdb74dcccba4773e1a0a10
 SHA512:
-  metadata.gz: '09062c96178f0d3b42b2e5c9ace511b029ae3508e3beca477916b80b806e83f6ccb15bf94ce52eabebc2cce3e5a10d4b1009cf0c26e13752259578dac0e35479'
-  data.tar.gz: b84d592569e502023fb318fbe2f1408a9049156740233ab67aeca0b0c0333a5c8ca39cf79eb641494fde4c9326fa28b65ae472feecea8724418243906dceed32
+  metadata.gz: 85ff70985c0fda5b6220c8cf6e0fa1306525940828c03c75d097bebe9cda65e6e6097f020454c06e4b17137d02a7b77c1bf492c5e0261f2dad45336357e554ab
+  data.tar.gz: dafe99b38c2d4f9e33efa7c71334d21c6493318b9d407a90cb13a5d9b0877df36af0bc047f166697ec0b816be3b79018298a6a4742a78191c5836dfd275b0515

data/.pre-commit-config.yaml

@@ -0,0 +1,8 @@
+repos:
+  - repo: https://github.com/cycodehq-public/cycode-cli
+    rev: 0.1.6
+    hooks:
+      - id: cycode
+        language_version: python3
+        stages:
+          - commit

data/README.md

@@ -69,12 +69,24 @@ This is an **example** only. Your needs in production may vary!
 * **retry_sleep** How long to sleep initially between retries, exponential step-off. Initial default is 2s.
 * **bulk_limit** Limit to the size of the Logz.io upload bulk. Defaults to 1000000 bytes leaving about 24kB for overhead.
 * **bulk_limit_warning_limit** Limit to the size of the Logz.io warning message when a record exceeds bulk_limit to prevent a recursion when Fluent warnings are sent to the Logz.io output.  Defaults to nil (no truncation).
-* **proxy_uri** Your proxy uri. Default is nil
-* **proxy_cert** Your proxy cert. Default is nil
-* **gzip** should the plugin ship the logs in gzip compression. Default is false
+* **proxy_uri** Your proxy uri. Default is nil. For example: "`my.ip:12345`".
+* **proxy_cert** Your proxy cert. Default is nil.
+* **gzip** should the plugin ship the logs in gzip compression. Default is false.
+
+
+## Plugin metrics:
+
+| Metric Name | Description | Type | Example |
+| --- | --- | --- | --- |
+| `logzio_status_codes` | Status codes received from Logz.io | Gauge | `logzio_status_codes{type="logzio_buffered",plugin_id="out_logzio",status_code="500"}` |
 
 
 ## Release Notes
+- **0.2.0**:
+  - Do not retry on 400 and 401. For 400 - try to fix log and resend.
+  - Generate a metric (`logzio_status_codes`) for response codes from Logz.io.
+- **0.1.0**:
+  - Use fluentd's retry instead of retry in code (raise exception on non-2xx response).
 - 0.0.22: Update gem `net-http-persistent` to 4.x.
 - 0.0.21: Update gem `net-http-persistent` to 3.x.
 - 0.0.20: Support gzip compression

data/fluent-plugin-logzio.gemspec

@@ -4,8 +4,8 @@ $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
 
 Gem::Specification.new do |s|
   s.name        = 'fluent-plugin-logzio'
-  s.version     = '0.0.22'
-  s.authors     = ['Yury Kotov', 'Roi Rav-Hon', 'Arcadiy Ivanov', 'Miri Ignatiev']
+  s.version     = '0.2.0-test1'
+  s.authors     = ['Yury Kotov', 'Roi Rav-Hon', 'Arcadiy Ivanov', 'Miri Bar']
   s.email       = ['bairkan@gmail.com', 'roi@logz.io', 'arcadiy@ivanov.biz', 'miri.ignatiev@logz.io']
   s.homepage    = 'https://github.com/logzio/fluent-plugin-logzio'
   s.summary     = %q{Fluentd plugin for output to Logz.io}
@@ -21,6 +21,7 @@ Gem::Specification.new do |s|
 
   s.add_dependency 'net-http-persistent', '~> 4.0'
   s.add_runtime_dependency 'fluentd', ['>= 0.14.0', '< 2']
+  s.add_runtime_dependency 'prometheus-client', '>= 2.1.0'
   s.add_development_dependency 'rake', '~> 12.3'
   s.add_development_dependency 'bundler', '~> 1.16'
   s.add_development_dependency 'rspec', '~> 3.7'

data/lib/fluent/plugin/out_logzio_buffered.rb

@@ -6,6 +6,7 @@ require 'stringio'
 module Fluent::Plugin
   class LogzioOutputBuffered < Output
     Fluent::Plugin.register_output('logzio_buffered', self)
+    class RetryableResponse < StandardError; end
 
     helpers :compat_parameters
 
@@ -37,7 +38,21 @@ module Fluent::Plugin
         log.debug "Proxy #{@proxy_cert}"
         ENV['SSL_CERT_FILE'] = @proxy_cert
       end
+      @metric_labels = {
+        type: 'logzio_buffered',
+        plugin_id: 'out_logzio',
+      }
+      @metrics = {
+        status_codes: get_gauge(
+          :logzio_status_codes,
+          'Status codes received from Logz.io', {"status_code":""}),
+      }
+
+    end
 
+    def initialize
+      super
+      @registry = ::Prometheus::Client.registry
     end
 
     def start
@@ -121,6 +136,27 @@ module Fluent::Plugin
     end
 
     def send_bulk(bulk_records, bulk_size)
+      response = do_post(bulk_records, bulk_size)
+      
+      @metrics[:status_codes].increment(labels: merge_labels({'status_code': response.code.to_s}))
+      log.info "Status code from logzio: #{response.code}"
+
+      if not response.code.start_with?('2')
+        log.info "here here here"
+        if response.code == '400'
+          log.warn "Received #{response.code} from Logzio. Some logs may be malformed or too long. Valid logs were succesfully sent into the system. Will try to proccess and send oversized logs. Response body: #{response.body}"
+          process_code_400(bulk_records, Yajl.load(response.body))
+        elsif response.code == '401'
+          log.error "Received #{response.code} from Logzio. Unauthorized, please check your logs shipping token. Will not retry sending. Response body: #{response.body}"
+        else
+          log.debug "Failed request body: #{post.body}"
+          log.error "Error while sending POST to #{@uri}: #{response.body}"
+          raise RetryableResponse, "Logzio listener returned (#{response.code}) for #{@uri}:  #{response.body}", []
+        end
+      end
+    end
+
+    def do_post(bulk_records, bulk_size)
       log.debug "Sending a bulk of #{bulk_records.size} records, size #{bulk_size}B to Logz.io"
 
       # Setting our request
@@ -131,44 +167,43 @@ module Fluent::Plugin
       if gzip
         post.body = compress(post.body)
       end
-      sleep_interval = @retry_sleep
 
       begin
-        @retry_count.times do |counter|
-          should_retry = true
-          begin
-            response = @http.request @uri, post
-            if response.code != '200'
-              if response.code == '401'
-                log.error "You are not authorized with Logz.io! Token OK? dropping logs..."
-                should_retry = false
-              elsif response.code == '400'
-                log.info "Got 400 code from Logz.io. This means that some of your logs are too big, or badly formatted. Response: #{response.body}"
-                should_retry = false
-              else
-                log.warn "Got HTTP #{response.code} from Logz.io, not giving up just yet (Try #{counter + 1}/#{@retry_count})"
-              end
-            else
-              log.debug "Successfully sent bulk of #{bulk_records.size} records, size #{bulk_size}B to Logz.io"
-              should_retry = false
-            end
-          rescue StandardError => e
-            log.warn "Error connecting to Logz.io. Got exception: #{e} (Try #{counter + 1}/#{@retry_count})"
-          end
+        response = @http.request @uri, post
+        rescue Net::HTTP::Persistent::Error => e
+          raise e.cause
+        return response
+      end
+    end
 
-          if should_retry
-            if counter == @retry_count - 1
-              log.error "Could not send your bulk after #{retry_count} tries Sorry! Your bulk is: #{post.body}"
-              break
-            end
-            sleep(sleep_interval)
-            sleep_interval *= 2
-          else
-            return
-          end
+    def process_code_400(bulk_records, response_body)
+      max_log_field_size_bytes = 32000
+      oversized_logs_counter = response_body['oversizedLines'].to_i
+      new_bulk = []
+      for log_record in bulk_records
+        log.info "Oversized lines: #{oversized_logs_counter}" # todo
+        if oversized_logs_counter == 0
+          log.debug "No malformed lines, breaking"
+          break
+        end
+        new_log = Yajl.load(log_record)
+        msg_size = new_log['message'].size
+        # Handle oversized log:
+        if msg_size >= max_log_field_size_bytes
+          new_log['message'] = new_log['message'][0,  max_log_field_size_bytes - 1]
+          log.debug "new log: #{new_log}"
+          new_bulk.append(Yajl.dump(new_log))
+          oversized_logs_counter -= 1
+        end
+      end
+      if new_bulk.size > 0
+        log.debug "Number of fixed bad logs to send: #{new_bulk.size}"
+        response = do_post(new_bulk, new_bulk.size)
+        if response.code.start_with?('2')
+          log.info "Succesfully sent bad logs"
+        else
+          log.warn "While trying to send fixed bad logs, got #{response.code} from Logz.io, will not try to re-send"
         end
-      rescue Exception => e
-        log.error "Got unexpected exception! Here: #{e}"
       end
     end
 
@@ -179,5 +214,17 @@ module Fluent::Plugin
       w_gz.close
       wio.string
     end
+
+    def merge_labels(extra_labels= {})
+      @metric_labels.merge extra_labels
+    end
+
+    def get_gauge(name, docstring, extra_labels = {})
+      if @registry.exist?(name)
+        @registry.get(name)
+      else
+        @registry.gauge(name, docstring: docstring, labels: @metric_labels.keys + extra_labels.keys)
+      end
+    end
   end
 end

metadata

@@ -1,17 +1,17 @@
 --- !ruby/object:Gem::Specification
 name: fluent-plugin-logzio
 version: !ruby/object:Gem::Version
-  version: 0.0.22
+  version: 0.2.0.pre.test1
 platform: ruby
 authors:
 - Yury Kotov
 - Roi Rav-Hon
 - Arcadiy Ivanov
-- Miri Ignatiev
+- Miri Bar
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2022-06-19 00:00:00.000000000 Z
+date: 2023-07-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: net-http-persistent
@@ -47,6 +47,20 @@ dependencies:
     - - "<"
       - !ruby/object:Gem::Version
         version: '2'
+- !ruby/object:Gem::Dependency
+  name: prometheus-client
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2.1.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2.1.0
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -113,8 +127,8 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- ".github/workflows/git-secrets.yml"
 - ".gitignore"
+- ".pre-commit-config.yaml"
 - ".rspec"
 - ".whitesource"
 - Gemfile
@@ -142,12 +156,11 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: 2.1.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ">="
+  - - ">"
     - !ruby/object:Gem::Version
-      version: '0'
+      version: 1.3.1
 requirements: []
-rubyforge_project: fluent-plugin-logzio
-rubygems_version: 2.5.2.3
+rubygems_version: 3.0.3.1
 signing_key: 
 specification_version: 4
 summary: Fluentd plugin for output to Logz.io

data/.github/workflows/git-secrets.yml

@@ -1,33 +0,0 @@
-name: git-secrets
-
-# Controls when the workflow will run
-# Triggers the workflow on push or pull request events but only for the main branch
-on: [push]
-
-# A workflow run is made up of one or more jobs that can run sequentially or in parallel
-jobs:
-  # This workflow contains a single job called "main"
-  git-secrets:
-    # The type of runner that the job will run on
-    runs-on: ubuntu-18.04
-
-    # Steps represent a sequence of tasks that will be executed as part of the job
-    steps:
-      - name: Check Out Source Code
-        uses: actions/checkout@v2
-
-      - name: Set up Python 3.8
-        uses: actions/setup-python@v2
-        with:
-          python-version: 3.8
-      - name: Installing dependencies
-        run:
-          sudo apt-get install git less openssh-server
-      - name: Installing scanning tool
-        run: |
-          brew install git-secrets
-          git secrets --install
-          git secrets --register-aws 
-      - name: Running scanning tool
-        run:
-          git secrets --scan