karafka 2.0.0 → 2.1.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (246) hide show
  1. checksums.yaml +4 -4
  2. checksums.yaml.gz.sig +0 -0
  3. data/.github/FUNDING.yml +1 -0
  4. data/.github/workflows/ci.yml +40 -16
  5. data/.rspec +4 -0
  6. data/.ruby-version +1 -1
  7. data/CHANGELOG.md +459 -796
  8. data/Gemfile +3 -2
  9. data/Gemfile.lock +44 -32
  10. data/LICENSE +1 -1
  11. data/README.md +22 -17
  12. data/bin/integrations +86 -26
  13. data/bin/karafka +1 -13
  14. data/bin/rspecs +6 -0
  15. data/bin/verify_license_integrity +37 -0
  16. data/certs/cert_chain.pem +26 -0
  17. data/config/{errors.yml → locales/errors.yml} +34 -6
  18. data/config/locales/pro_errors.yml +34 -0
  19. data/docker-compose.yml +4 -30
  20. data/karafka.gemspec +17 -10
  21. data/lib/active_job/karafka.rb +3 -7
  22. data/lib/active_job/queue_adapters/karafka_adapter.rb +7 -1
  23. data/lib/karafka/active_job/consumer.rb +29 -6
  24. data/lib/karafka/active_job/current_attributes/loading.rb +36 -0
  25. data/lib/karafka/active_job/current_attributes/persistence.rb +28 -0
  26. data/lib/karafka/active_job/current_attributes.rb +42 -0
  27. data/lib/karafka/active_job/dispatcher.rb +34 -3
  28. data/lib/karafka/active_job/job_options_contract.rb +13 -2
  29. data/lib/karafka/admin.rb +246 -0
  30. data/lib/karafka/app.rb +30 -7
  31. data/lib/karafka/base_consumer.rb +124 -82
  32. data/lib/karafka/cli/base.rb +20 -0
  33. data/lib/karafka/cli/console.rb +13 -8
  34. data/lib/karafka/cli/info.rb +3 -2
  35. data/lib/karafka/cli/server.rb +55 -8
  36. data/lib/karafka/cli/topics.rb +146 -0
  37. data/lib/karafka/connection/client.rb +118 -61
  38. data/lib/karafka/connection/consumer_group_coordinator.rb +48 -0
  39. data/lib/karafka/connection/listener.rb +78 -30
  40. data/lib/karafka/connection/listeners_batch.rb +18 -2
  41. data/lib/karafka/connection/rebalance_manager.rb +3 -0
  42. data/lib/karafka/contracts/config.rb +1 -1
  43. data/lib/karafka/contracts/consumer_group.rb +22 -9
  44. data/lib/karafka/contracts/server_cli_options.rb +71 -11
  45. data/lib/karafka/contracts/topic.rb +65 -0
  46. data/lib/karafka/contracts.rb +1 -1
  47. data/lib/karafka/embedded.rb +36 -0
  48. data/lib/karafka/errors.rb +6 -4
  49. data/lib/karafka/helpers/colorize.rb +6 -0
  50. data/lib/karafka/instrumentation/callbacks/error.rb +3 -4
  51. data/lib/karafka/instrumentation/callbacks/statistics.rb +14 -4
  52. data/lib/karafka/instrumentation/logger_listener.rb +151 -22
  53. data/lib/karafka/instrumentation/notifications.rb +26 -7
  54. data/lib/karafka/instrumentation/proctitle_listener.rb +7 -16
  55. data/lib/karafka/instrumentation/vendors/datadog/dashboard.json +1 -1
  56. data/lib/karafka/instrumentation/vendors/datadog/logger_listener.rb +153 -0
  57. data/lib/karafka/instrumentation/vendors/datadog/{listener.rb → metrics_listener.rb} +62 -35
  58. data/lib/karafka/instrumentation/vendors/kubernetes/liveness_listener.rb +166 -0
  59. data/lib/karafka/licenser.rb +53 -50
  60. data/lib/karafka/messages/builders/batch_metadata.rb +8 -8
  61. data/lib/karafka/messages/builders/messages.rb +6 -2
  62. data/lib/karafka/messages/message.rb +14 -2
  63. data/lib/karafka/messages/messages.rb +5 -0
  64. data/lib/karafka/messages/parser.rb +14 -0
  65. data/lib/karafka/patches/rdkafka/bindings.rb +132 -0
  66. data/lib/karafka/pro/active_job/consumer.rb +10 -9
  67. data/lib/karafka/pro/active_job/dispatcher.rb +28 -3
  68. data/lib/karafka/pro/active_job/job_options_contract.rb +16 -3
  69. data/lib/karafka/pro/encryption/cipher.rb +58 -0
  70. data/lib/karafka/pro/encryption/contracts/config.rb +79 -0
  71. data/lib/karafka/pro/encryption/errors.rb +24 -0
  72. data/lib/karafka/pro/encryption/messages/middleware.rb +46 -0
  73. data/lib/karafka/pro/encryption/messages/parser.rb +56 -0
  74. data/lib/karafka/pro/encryption/setup/config.rb +48 -0
  75. data/lib/karafka/pro/encryption.rb +47 -0
  76. data/lib/karafka/pro/iterator.rb +253 -0
  77. data/lib/karafka/pro/loader.rb +52 -26
  78. data/lib/karafka/pro/performance_tracker.rb +10 -6
  79. data/lib/karafka/pro/processing/collapser.rb +62 -0
  80. data/lib/karafka/pro/processing/coordinator.rb +92 -16
  81. data/lib/karafka/pro/processing/filters/base.rb +61 -0
  82. data/lib/karafka/pro/processing/filters/delayer.rb +70 -0
  83. data/lib/karafka/pro/processing/filters/expirer.rb +51 -0
  84. data/lib/karafka/pro/processing/filters/throttler.rb +84 -0
  85. data/lib/karafka/pro/processing/filters/virtual_limiter.rb +52 -0
  86. data/lib/karafka/pro/processing/filters_applier.rb +104 -0
  87. data/lib/karafka/pro/processing/jobs/consume_non_blocking.rb +7 -5
  88. data/lib/karafka/pro/processing/jobs/revoked_non_blocking.rb +37 -0
  89. data/lib/karafka/pro/processing/jobs_builder.rb +22 -4
  90. data/lib/karafka/pro/processing/partitioner.rb +33 -24
  91. data/lib/karafka/pro/processing/scheduler.rb +27 -8
  92. data/lib/karafka/pro/processing/strategies/aj/dlq_ftr_lrj_mom.rb +68 -0
  93. data/lib/karafka/pro/processing/strategies/aj/dlq_ftr_lrj_mom_vp.rb +74 -0
  94. data/lib/karafka/pro/processing/strategies/aj/dlq_ftr_mom.rb +72 -0
  95. data/lib/karafka/pro/processing/strategies/aj/dlq_ftr_mom_vp.rb +76 -0
  96. data/lib/karafka/pro/processing/strategies/aj/dlq_lrj_mom.rb +64 -0
  97. data/lib/karafka/pro/processing/strategies/aj/dlq_lrj_mom_vp.rb +68 -0
  98. data/lib/karafka/pro/processing/strategies/aj/dlq_mom.rb +64 -0
  99. data/lib/karafka/pro/processing/strategies/aj/dlq_mom_vp.rb +69 -0
  100. data/lib/karafka/pro/processing/strategies/aj/ftr_lrj_mom.rb +38 -0
  101. data/lib/karafka/pro/processing/strategies/aj/ftr_lrj_mom_vp.rb +64 -0
  102. data/lib/karafka/pro/processing/strategies/aj/ftr_mom.rb +38 -0
  103. data/lib/karafka/pro/processing/strategies/aj/ftr_mom_vp.rb +58 -0
  104. data/lib/karafka/pro/processing/strategies/aj/lrj_mom.rb +37 -0
  105. data/lib/karafka/pro/processing/strategies/aj/lrj_mom_vp.rb +79 -0
  106. data/lib/karafka/pro/processing/strategies/aj/mom.rb +36 -0
  107. data/lib/karafka/pro/processing/strategies/aj/mom_vp.rb +52 -0
  108. data/lib/karafka/pro/processing/strategies/base.rb +26 -0
  109. data/lib/karafka/pro/processing/strategies/default.rb +105 -0
  110. data/lib/karafka/pro/processing/strategies/dlq/default.rb +131 -0
  111. data/lib/karafka/pro/processing/strategies/dlq/ftr.rb +61 -0
  112. data/lib/karafka/pro/processing/strategies/dlq/ftr_lrj.rb +75 -0
  113. data/lib/karafka/pro/processing/strategies/dlq/ftr_lrj_mom.rb +71 -0
  114. data/lib/karafka/pro/processing/strategies/dlq/ftr_lrj_mom_vp.rb +43 -0
  115. data/lib/karafka/pro/processing/strategies/dlq/ftr_lrj_vp.rb +41 -0
  116. data/lib/karafka/pro/processing/strategies/dlq/ftr_mom.rb +69 -0
  117. data/lib/karafka/pro/processing/strategies/dlq/ftr_mom_vp.rb +41 -0
  118. data/lib/karafka/pro/processing/strategies/dlq/ftr_vp.rb +40 -0
  119. data/lib/karafka/pro/processing/strategies/dlq/lrj.rb +63 -0
  120. data/lib/karafka/pro/processing/strategies/dlq/lrj_mom.rb +63 -0
  121. data/lib/karafka/pro/processing/strategies/dlq/lrj_mom_vp.rb +36 -0
  122. data/lib/karafka/pro/processing/strategies/dlq/lrj_vp.rb +39 -0
  123. data/lib/karafka/pro/processing/strategies/dlq/mom.rb +68 -0
  124. data/lib/karafka/pro/processing/strategies/dlq/mom_vp.rb +37 -0
  125. data/lib/karafka/pro/processing/strategies/dlq/vp.rb +40 -0
  126. data/lib/karafka/pro/processing/strategies/ftr/default.rb +104 -0
  127. data/lib/karafka/pro/processing/strategies/ftr/vp.rb +40 -0
  128. data/lib/karafka/pro/processing/strategies/lrj/default.rb +87 -0
  129. data/lib/karafka/pro/processing/strategies/lrj/ftr.rb +69 -0
  130. data/lib/karafka/pro/processing/strategies/lrj/ftr_mom.rb +67 -0
  131. data/lib/karafka/pro/processing/strategies/lrj/ftr_mom_vp.rb +40 -0
  132. data/lib/karafka/pro/processing/strategies/lrj/ftr_vp.rb +39 -0
  133. data/lib/karafka/pro/processing/strategies/lrj/mom.rb +80 -0
  134. data/lib/karafka/pro/processing/strategies/lrj/mom_vp.rb +38 -0
  135. data/lib/karafka/pro/processing/strategies/lrj/vp.rb +36 -0
  136. data/lib/karafka/pro/processing/strategies/mom/default.rb +46 -0
  137. data/lib/karafka/pro/processing/strategies/mom/ftr.rb +53 -0
  138. data/lib/karafka/pro/processing/strategies/mom/ftr_vp.rb +37 -0
  139. data/lib/karafka/pro/processing/strategies/mom/vp.rb +35 -0
  140. data/lib/karafka/pro/processing/strategies/vp/default.rb +104 -0
  141. data/lib/karafka/pro/{contracts/base.rb → processing/strategies.rb} +6 -5
  142. data/lib/karafka/pro/processing/strategy_selector.rb +84 -0
  143. data/lib/karafka/pro/processing/virtual_offset_manager.rb +147 -0
  144. data/lib/karafka/pro/routing/features/base.rb +24 -0
  145. data/lib/karafka/pro/routing/features/dead_letter_queue/contract.rb +50 -0
  146. data/lib/karafka/pro/routing/features/dead_letter_queue.rb +27 -0
  147. data/lib/karafka/pro/routing/{builder_extensions.rb → features/delaying/config.rb} +8 -11
  148. data/lib/karafka/pro/routing/features/delaying/contract.rb +38 -0
  149. data/lib/karafka/pro/routing/features/delaying/topic.rb +59 -0
  150. data/lib/karafka/pro/routing/features/delaying.rb +29 -0
  151. data/lib/karafka/pro/routing/features/expiring/config.rb +27 -0
  152. data/lib/karafka/pro/routing/features/expiring/contract.rb +38 -0
  153. data/lib/karafka/pro/routing/features/expiring/topic.rb +59 -0
  154. data/lib/karafka/pro/routing/features/expiring.rb +27 -0
  155. data/lib/karafka/pro/routing/features/filtering/config.rb +40 -0
  156. data/lib/karafka/pro/routing/features/filtering/contract.rb +41 -0
  157. data/lib/karafka/pro/routing/features/filtering/topic.rb +51 -0
  158. data/lib/karafka/pro/routing/features/filtering.rb +27 -0
  159. data/lib/karafka/pro/routing/features/long_running_job/config.rb +28 -0
  160. data/lib/karafka/pro/routing/features/long_running_job/contract.rb +37 -0
  161. data/lib/karafka/pro/routing/features/long_running_job/topic.rb +42 -0
  162. data/lib/karafka/pro/routing/features/long_running_job.rb +28 -0
  163. data/lib/karafka/pro/routing/features/throttling/config.rb +32 -0
  164. data/lib/karafka/pro/routing/features/throttling/contract.rb +41 -0
  165. data/lib/karafka/pro/routing/features/throttling/topic.rb +69 -0
  166. data/lib/karafka/pro/routing/features/throttling.rb +30 -0
  167. data/lib/karafka/pro/routing/features/virtual_partitions/config.rb +30 -0
  168. data/lib/karafka/pro/routing/features/virtual_partitions/contract.rb +52 -0
  169. data/lib/karafka/pro/routing/features/virtual_partitions/topic.rb +56 -0
  170. data/lib/karafka/pro/routing/features/virtual_partitions.rb +27 -0
  171. data/lib/karafka/process.rb +23 -8
  172. data/lib/karafka/processing/coordinator.rb +102 -23
  173. data/lib/karafka/processing/coordinators_buffer.rb +5 -1
  174. data/lib/karafka/processing/executor.rb +51 -21
  175. data/lib/karafka/processing/executors_buffer.rb +10 -26
  176. data/lib/karafka/processing/jobs/base.rb +6 -2
  177. data/lib/karafka/processing/jobs/consume.rb +8 -5
  178. data/lib/karafka/processing/jobs/idle.rb +24 -0
  179. data/lib/karafka/processing/jobs_builder.rb +2 -3
  180. data/lib/karafka/processing/jobs_queue.rb +14 -8
  181. data/lib/karafka/processing/partitioner.rb +3 -1
  182. data/lib/karafka/processing/result.rb +14 -1
  183. data/lib/karafka/processing/strategies/aj_dlq_mom.rb +44 -0
  184. data/lib/karafka/processing/strategies/aj_mom.rb +21 -0
  185. data/lib/karafka/processing/strategies/base.rb +52 -0
  186. data/lib/karafka/processing/strategies/default.rb +142 -0
  187. data/lib/karafka/processing/strategies/dlq.rb +88 -0
  188. data/lib/karafka/processing/strategies/dlq_mom.rb +49 -0
  189. data/lib/karafka/processing/strategies/mom.rb +29 -0
  190. data/lib/karafka/processing/strategy_selector.rb +47 -0
  191. data/lib/karafka/processing/worker.rb +8 -3
  192. data/lib/karafka/railtie.rb +24 -12
  193. data/lib/karafka/routing/activity_manager.rb +84 -0
  194. data/lib/karafka/routing/builder.rb +20 -0
  195. data/lib/karafka/routing/consumer_group.rb +38 -4
  196. data/lib/karafka/routing/consumer_mapper.rb +0 -10
  197. data/lib/karafka/routing/features/active_job/builder.rb +33 -0
  198. data/lib/karafka/routing/features/active_job/config.rb +15 -0
  199. data/lib/karafka/routing/features/active_job/contract.rb +41 -0
  200. data/lib/karafka/routing/features/active_job/topic.rb +33 -0
  201. data/lib/karafka/routing/features/active_job.rb +13 -0
  202. data/lib/karafka/routing/features/base/expander.rb +53 -0
  203. data/lib/karafka/routing/features/base.rb +34 -0
  204. data/lib/karafka/routing/features/dead_letter_queue/config.rb +19 -0
  205. data/lib/karafka/routing/features/dead_letter_queue/contract.rb +42 -0
  206. data/lib/karafka/routing/features/dead_letter_queue/topic.rb +41 -0
  207. data/lib/karafka/routing/features/dead_letter_queue.rb +16 -0
  208. data/lib/karafka/routing/features/declaratives/config.rb +18 -0
  209. data/lib/karafka/routing/features/declaratives/contract.rb +30 -0
  210. data/lib/karafka/routing/features/declaratives/topic.rb +44 -0
  211. data/lib/karafka/routing/features/declaratives.rb +14 -0
  212. data/lib/karafka/routing/features/manual_offset_management/config.rb +15 -0
  213. data/lib/karafka/routing/features/manual_offset_management/contract.rb +24 -0
  214. data/lib/karafka/routing/features/manual_offset_management/topic.rb +35 -0
  215. data/lib/karafka/routing/features/manual_offset_management.rb +18 -0
  216. data/lib/karafka/routing/proxy.rb +18 -20
  217. data/lib/karafka/routing/router.rb +27 -2
  218. data/lib/karafka/routing/subscription_group.rb +43 -5
  219. data/lib/karafka/routing/subscription_groups_builder.rb +6 -1
  220. data/lib/karafka/routing/topic.rb +17 -5
  221. data/lib/karafka/routing/topics.rb +8 -0
  222. data/lib/karafka/runner.rb +1 -0
  223. data/lib/karafka/serialization/json/deserializer.rb +1 -0
  224. data/lib/karafka/server.rb +58 -28
  225. data/lib/karafka/setup/attributes_map.rb +344 -0
  226. data/lib/karafka/setup/config.rb +48 -19
  227. data/lib/karafka/status.rb +35 -7
  228. data/lib/karafka/templates/karafka.rb.erb +14 -6
  229. data/lib/karafka/time_trackers/base.rb +1 -6
  230. data/lib/karafka/time_trackers/pause.rb +49 -19
  231. data/lib/karafka/time_trackers/poll.rb +7 -3
  232. data/lib/karafka/version.rb +1 -1
  233. data/lib/karafka.rb +56 -3
  234. data/renovate.json +6 -0
  235. data.tar.gz.sig +0 -0
  236. metadata +189 -61
  237. metadata.gz.sig +0 -0
  238. data/bin/wait_for_kafka +0 -20
  239. data/certs/mensfeld.pem +0 -25
  240. data/lib/karafka/active_job/routing/extensions.rb +0 -31
  241. data/lib/karafka/contracts/consumer_group_topic.rb +0 -42
  242. data/lib/karafka/instrumentation.rb +0 -21
  243. data/lib/karafka/pro/base_consumer.rb +0 -82
  244. data/lib/karafka/pro/contracts/consumer_group.rb +0 -34
  245. data/lib/karafka/pro/contracts/consumer_group_topic.rb +0 -33
  246. data/lib/karafka/pro/routing/topic_extensions.rb +0 -38
@@ -1 +1 @@
1
- {"title":"Karafka monitoring dashboard","description":"","widgets":[{"id":7444969424381053,"definition":{"title":"Stability & errors","type":"group","show_title":true,"layout_type":"ordered","widgets":[{"id":8304008422587936,"definition":{"title":"Client connects and disconnects","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"alias":"Connects","formula":"query1"},{"alias":"Disconnects","formula":"query2"}],"response_format":"timeseries","queries":[{"query":"sum:karafka.connection.connects{*} by {host}.as_count()","data_source":"metrics","name":"query1"},{"query":"sum:karafka.connection.disconnects{*} by {host}.as_count()","data_source":"metrics","name":"query2"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"bars"}]},"layout":{"x":0,"y":0,"width":4,"height":2}},{"id":3722865443336921,"definition":{"title":"Errors encountered (any)","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"alias":"in-karafka errors","formula":"query1"},{"alias":"librdkafka consume errors","formula":"query2"},{"alias":"librdkafka receive errors","formula":"query3"}],"response_format":"timeseries","queries":[{"query":"sum:karafka.error_occurred{*} by {type}.as_count()","data_source":"metrics","name":"query1"},{"query":"sum:karafka.consume.errors{*}.as_count()","data_source":"metrics","name":"query2"},{"query":"sum:karafka.receive.errors{*}.as_count()","data_source":"metrics","name":"query3"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":4,"y":0,"width":4,"height":2}},{"id":5477381252952760,"definition":{"title":"Processing errors","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"formula":"query1"}],"response_format":"timeseries","queries":[{"query":"sum:karafka.error_occurred{type:consumer.consume.error} by {partition,topic}.as_count()","data_source":"metrics","name":"query1"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":8,"y":0,"width":4,"height":2}},{"id":2357301680769076,"definition":{"title":"Processing errors rate per topic","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"alias":"% error rate per topic","formula":"(query1 / (query1 + query2)) * 100"}],"response_format":"timeseries","queries":[{"query":"sum:karafka.error_occurred{type:consumer.consume.error} by {topic,partition}.as_count()","data_source":"metrics","name":"query1"},{"query":"sum:karafka.consumer.batches{*} by {topic,partition}.as_count()","data_source":"metrics","name":"query2"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"bars"}]},"layout":{"x":0,"y":2,"width":4,"height":2}},{"id":3902930069982135,"definition":{"title":"Batches successful vs failures","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"alias":"Successfully processed batch","formula":"query1"},{"alias":"Batch processing with error","formula":"query2"}],"response_format":"timeseries","queries":[{"query":"sum:karafka.consumer.batches{*} by {partition,topic}.as_count()","data_source":"metrics","name":"query1"},{"query":"avg:karafka.error_occurred{type:consumer.consume.error} by {partition,topic}.as_count()","data_source":"metrics","name":"query2"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":4,"y":2,"width":4,"height":2}},{"id":718749162159145,"definition":{"title":"Consumer instances revocations and shutdowns","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"alias":"Consumer instances revokations","formula":"query1"},{"alias":"Consumer instances shutdowns","formula":"query2"}],"response_format":"timeseries","queries":[{"query":"sum:karafka.consumer.revoked{*}.as_count()","data_source":"metrics","name":"query1"},{"query":"sum:karafka.consumer.shutdown{*}.as_count()","data_source":"metrics","name":"query2"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":8,"y":2,"width":4,"height":2}}]},"layout":{"x":0,"y":0,"width":12,"height":5}},{"id":5988438511387100,"definition":{"title":"Workers poll","type":"group","show_title":true,"layout_type":"ordered","widgets":[{"id":8769294644934352,"definition":{"title":"Enqueued jobs","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"alias":"Enqueued jobs","formula":"query1"}],"response_format":"timeseries","queries":[{"query":"sum:karafka.worker.enqueued_jobs.avg{*}","data_source":"metrics","name":"query1"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":0,"y":0,"width":4,"height":2}},{"id":2714502141463873,"definition":{"title":"Workers usage","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"alias":"Busy workers (p95)","formula":"query1"},{"alias":"Total workers","formula":"query2"}],"response_format":"timeseries","queries":[{"query":"sum:karafka.worker.processing.95percentile{*}","data_source":"metrics","name":"query1"},{"query":"sum:karafka.worker.total_threads{*}","data_source":"metrics","name":"query2"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":4,"y":0,"width":4,"height":2}},{"id":5370086629441984,"definition":{"title":"Workers % utilization","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"alias":"% workers utilization","formula":"(query1 / query2) * 100"}],"response_format":"timeseries","queries":[{"query":"sum:karafka.worker.processing.95percentile{*}","data_source":"metrics","name":"query1"},{"query":"sum:karafka.worker.total_threads{*}","data_source":"metrics","name":"query2"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":8,"y":0,"width":4,"height":2}}]},"layout":{"x":0,"y":5,"width":12,"height":3}},{"id":8544040083223278,"definition":{"title":"Throughput ","type":"group","show_title":true,"layout_type":"ordered","widgets":[{"id":3740207481939733,"definition":{"title":"Offset lag changes","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"formula":"derivative(query1)"}],"response_format":"timeseries","queries":[{"query":"max:karafka.consumer.offset{*} by {topic,partition}","data_source":"metrics","name":"query1"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":0,"y":0,"width":4,"height":2}},{"id":6319110548544878,"definition":{"title":"Batches processed per topic","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"formula":"query1"}],"response_format":"timeseries","queries":[{"query":"sum:karafka.consumer.batches{*} by {partition,topic}.as_count()","data_source":"metrics","name":"query1"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":4,"y":0,"width":4,"height":2}},{"id":6232784865331443,"definition":{"title":"Messages consumed per topic","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"alias":"Messages consumed","formula":"query1"},{"alias":"Average batch size","formula":"query1 / query2"}],"response_format":"timeseries","queries":[{"query":"sum:karafka.consumer.messages{*} by {partition,topic}.as_count()","data_source":"metrics","name":"query1"},{"query":"sum:karafka.consumer.batches{*} by {partition,topic}.as_count()","data_source":"metrics","name":"query2"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":8,"y":0,"width":4,"height":2}},{"id":2321394598982770,"definition":{"title":"Consumption lag (in seconds)","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"alias":"Consumption lag in s (max)","formula":"query2 / 1000"},{"alias":"Consumption lag in s (avg)","formula":"query3 / 1000"},{"alias":"Consumption lag in s (p95)","formula":"query1 / 1000"}],"response_format":"timeseries","queries":[{"query":"max:karafka.consumer.consumption_lag.max{*}","data_source":"metrics","name":"query2"},{"query":"max:karafka.consumer.consumption_lag.avg{*}","data_source":"metrics","name":"query3"},{"query":"max:karafka.consumer.consumption_lag.95percentile{*}","data_source":"metrics","name":"query1"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":0,"y":2,"width":4,"height":2}},{"id":1062074781483741,"definition":{"title":"Processing lag (in ms)","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"alias":"Processing lag in ms (p95)","formula":"query1"},{"alias":"Processing lag in ms (max)","formula":"query2"},{"alias":"Processing lag in ms (avg)","formula":"query3"}],"response_format":"timeseries","queries":[{"query":"max:karafka.consumer.processing_lag.95percentile{*}","data_source":"metrics","name":"query1"},{"query":"max:karafka.consumer.processing_lag.max{*}","data_source":"metrics","name":"query2"},{"query":"max:karafka.consumer.processing_lag.avg{*}","data_source":"metrics","name":"query3"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":4,"y":2,"width":4,"height":2}},{"id":7497794728674267,"definition":{"title":"Batch processing time","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"formula":"query1"},{"formula":"query2"},{"formula":"query3"}],"response_format":"timeseries","queries":[{"query":"max:karafka.consumer.consumed.time_taken.95percentile{*} by {topic,partition}","data_source":"metrics","name":"query1"},{"query":"max:karafka.consumer.consumed.time_taken.max{*} by {topic,partition}","data_source":"metrics","name":"query2"},{"query":"max:karafka.consumer.consumed.time_taken.avg{*} by {topic,partition}","data_source":"metrics","name":"query3"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":8,"y":2,"width":4,"height":2}},{"id":4192833027984161,"definition":{"title":"Batch size per topic","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"alias":"Batch size p95","formula":"query1"},{"alias":"Batch size avg","formula":"query2"},{"alias":"Batch size max","formula":"query3"}],"response_format":"timeseries","queries":[{"query":"sum:karafka.consumer.batch_size.95percentile{*} by {partition,topic}","data_source":"metrics","name":"query1"},{"query":"sum:karafka.consumer.batch_size.avg{*} by {partition,topic}","data_source":"metrics","name":"query2"},{"query":"sum:karafka.consumer.batch_size.max{*} by {partition,topic}","data_source":"metrics","name":"query3"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":0,"y":4,"width":4,"height":2}},{"id":4741598444771147,"definition":{"title":"Messages consumed overall","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"alias":"Messages consumed","formula":"query1"},{"alias":"Average batch size","formula":"query1 / query2"}],"response_format":"timeseries","queries":[{"query":"sum:karafka.consumer.messages{*}.as_count()","data_source":"metrics","name":"query1"},{"query":"sum:karafka.consumer.batches{*}.as_count()","data_source":"metrics","name":"query2"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":4,"y":4,"width":4,"height":2}},{"id":4502534794102513,"definition":{"title":"Polling times (ms)","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"time":{},"type":"timeseries","requests":[{"formulas":[{"alias":"p95 ms polling time","formula":"query1"},{"alias":"max ms polling time","formula":"query2"},{"alias":"average ms polling time","formula":"query3"}],"queries":[{"name":"query1","data_source":"metrics","query":"avg:karafka.listener.polling.time_taken.95percentile{*}"},{"name":"query2","data_source":"metrics","query":"avg:karafka.listener.polling.time_taken.max{*}"},{"name":"query3","data_source":"metrics","query":"avg:karafka.listener.polling.time_taken.avg{*}"}],"response_format":"timeseries","style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":8,"y":4,"width":4,"height":2}}]},"layout":{"x":0,"y":0,"width":12,"height":7,"is_column_break":true}}],"template_variables":[],"layout_type":"ordered","is_read_only":false,"notify_list":[],"reflow_type":"fixed","id":"s3u-z47-i6u"}
1
+ {"title":"Karafka monitoring dashboard","description":"","widgets":[{"id":5988438511387100,"definition":{"title":"Workers poll","type":"group","show_title":true,"layout_type":"ordered","widgets":[{"id":8769294644934352,"definition":{"title":"Enqueued jobs","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"alias":"Enqueued jobs","formula":"query1"}],"response_format":"timeseries","queries":[{"query":"sum:karafka.worker.enqueued_jobs.avg{*}","data_source":"metrics","name":"query1"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":0,"y":0,"width":4,"height":2}},{"id":2714502141463873,"definition":{"title":"Workers usage","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"alias":"Busy workers (p95)","formula":"query1"},{"alias":"Total workers","formula":"query2"}],"response_format":"timeseries","queries":[{"query":"sum:karafka.worker.processing.95percentile{*}","data_source":"metrics","name":"query1"},{"query":"sum:karafka.worker.total_threads{*}","data_source":"metrics","name":"query2"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":4,"y":0,"width":4,"height":2}},{"id":5370086629441984,"definition":{"title":"Workers % utilization","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"alias":"% workers utilization","formula":"(query1 / query2) * 100"}],"response_format":"timeseries","queries":[{"query":"sum:karafka.worker.processing.95percentile{*}","data_source":"metrics","name":"query1"},{"query":"sum:karafka.worker.total_threads{*}","data_source":"metrics","name":"query2"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":8,"y":0,"width":4,"height":2}}]},"layout":{"x":0,"y":0,"width":12,"height":3}},{"id":7444969424381053,"definition":{"title":"Stability & errors","type":"group","show_title":true,"layout_type":"ordered","widgets":[{"id":8304008422587936,"definition":{"title":"Client connects and disconnects","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"time":{},"type":"timeseries","requests":[{"formulas":[{"alias":"Connects","formula":"query1"},{"alias":"Disconnects","formula":"query2"}],"queries":[{"query":"sum:karafka.connection.connects{*} by {host,consumer_group}.as_count()","data_source":"metrics","name":"query1"},{"query":"sum:karafka.connection.disconnects{*} by {host,consumer_group}.as_count()","data_source":"metrics","name":"query2"}],"response_format":"timeseries","style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"bars"}]},"layout":{"x":0,"y":0,"width":4,"height":2}},{"id":3722865443336921,"definition":{"title":"Errors encountered (any)","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"time":{},"type":"timeseries","requests":[{"formulas":[{"alias":"in-karafka errors","formula":"query1"},{"alias":"librdkafka consume errors","formula":"query2"},{"alias":"librdkafka receive errors","formula":"query3"}],"queries":[{"query":"sum:karafka.error_occurred{*} by {type,consumer_group}.as_count()","data_source":"metrics","name":"query1"},{"query":"sum:karafka.consume.errors{*} by {consumer_group}.as_count()","data_source":"metrics","name":"query2"},{"query":"sum:karafka.receive.errors{*} by {consumer_group}.as_count()","data_source":"metrics","name":"query3"}],"response_format":"timeseries","style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":4,"y":0,"width":4,"height":2}},{"id":5477381252952760,"definition":{"title":"Processing errors","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"time":{},"type":"timeseries","requests":[{"formulas":[{"formula":"query1"}],"queries":[{"query":"sum:karafka.error_occurred{type:consumer.consume.error} by {partition,topic,consumer_group}.as_count()","data_source":"metrics","name":"query1"}],"response_format":"timeseries","style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":8,"y":0,"width":4,"height":2}},{"id":2357301680769076,"definition":{"title":"Processing errors rate per topic","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"time":{},"type":"timeseries","requests":[{"formulas":[{"alias":"% error rate per topic","formula":"(query1 / (query1 + query2)) * 100"}],"queries":[{"query":"sum:karafka.error_occurred{type:consumer.consume.error} by {topic,partition,consumer_group}.as_count()","data_source":"metrics","name":"query1"},{"query":"sum:karafka.consumer.batches{*} by {topic,partition,consumer_group}.as_count()","data_source":"metrics","name":"query2"}],"response_format":"timeseries","style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"bars"}]},"layout":{"x":0,"y":2,"width":4,"height":2}},{"id":3902930069982135,"definition":{"title":"Batches successful vs failures","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"time":{},"type":"timeseries","requests":[{"formulas":[{"alias":"Successfully processed batch","formula":"query1"},{"alias":"Batch processing with error","formula":"query2"}],"queries":[{"query":"sum:karafka.consumer.batches{*} by {partition,topic,consumer_group}.as_count()","data_source":"metrics","name":"query1"},{"query":"avg:karafka.error_occurred{type:consumer.consume.error} by {partition,topic,consumer_group}.as_count()","data_source":"metrics","name":"query2"}],"response_format":"timeseries","style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":4,"y":2,"width":4,"height":2}},{"id":718749162159145,"definition":{"title":"Consumer instances revocations and shutdowns","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"time":{},"type":"timeseries","requests":[{"formulas":[{"alias":"Consumer instances revokations","formula":"query1"},{"alias":"Consumer instances shutdowns","formula":"query2"}],"queries":[{"query":"sum:karafka.consumer.revoked{*} by {consumer_group}.as_count()","data_source":"metrics","name":"query1"},{"query":"sum:karafka.consumer.shutdown{*} by {consumer_group}.as_count()","data_source":"metrics","name":"query2"}],"response_format":"timeseries","style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":8,"y":2,"width":4,"height":2}}]},"layout":{"x":0,"y":3,"width":12,"height":5}},{"id":7288186528768428,"definition":{"title":"Topics overview","type":"group","show_title":true,"layout_type":"ordered","widgets":[{"id":1533435157804573,"definition":{"title":"Topics lags","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"time":{},"type":"timeseries","requests":[{"formulas":[{"alias":"Messages lag per topic partition","formula":"query1"}],"queries":[{"query":"avg:karafka.consumer.lags{*} by {partition,topic,consumer_group}","data_source":"metrics","name":"query1"}],"response_format":"timeseries","style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":0,"y":0,"width":6,"height":2}},{"id":1411506453982604,"definition":{"title":"Topics lag trends","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"time":{},"type":"timeseries","requests":[{"formulas":[{"alias":"Topic partition consumption trend","formula":"query1"}],"queries":[{"query":"avg:karafka.consumer.lags_delta{*} by {partition,topic,consumer_group}","data_source":"metrics","name":"query1"}],"response_format":"timeseries","style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":6,"y":0,"width":6,"height":2}}]},"layout":{"x":0,"y":0,"width":12,"height":3,"is_column_break":true}},{"id":8544040083223278,"definition":{"title":"Throughput ","type":"group","show_title":true,"layout_type":"ordered","widgets":[{"id":3740207481939733,"definition":{"title":"Offset lag changes","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"time":{},"type":"timeseries","requests":[{"formulas":[{"formula":"derivative(query1)"}],"queries":[{"query":"max:karafka.consumer.offset{*} by {topic,partition,consumer_group}","data_source":"metrics","name":"query1"}],"response_format":"timeseries","style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":0,"y":0,"width":4,"height":2}},{"id":6319110548544878,"definition":{"title":"Batches processed per topic","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"time":{},"type":"timeseries","requests":[{"formulas":[{"alias":"Topic batches processed","formula":"query1"}],"queries":[{"query":"sum:karafka.consumer.batches{*} by {partition,topic,consumer_group}.as_count()","data_source":"metrics","name":"query1"}],"response_format":"timeseries","style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":4,"y":0,"width":4,"height":2}},{"id":6232784865331443,"definition":{"title":"Messages consumed per topic","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"time":{},"type":"timeseries","requests":[{"formulas":[{"alias":"Messages consumed","formula":"query1"},{"alias":"Average batch size","formula":"query1 / query2"}],"queries":[{"query":"sum:karafka.consumer.messages{*} by {partition,topic,consumer_group}.as_count()","data_source":"metrics","name":"query1"},{"query":"sum:karafka.consumer.batches{*} by {partition,topic,consumer_group}.as_count()","data_source":"metrics","name":"query2"}],"response_format":"timeseries","style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":8,"y":0,"width":4,"height":2}},{"id":2321394598982770,"definition":{"title":"Consumption lag (in seconds)","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"time":{},"type":"timeseries","requests":[{"formulas":[{"alias":"Consumption lag in s (max)","formula":"query2 / 1000"},{"alias":"Consumption lag in s (avg)","formula":"query3 / 1000"},{"alias":"Consumption lag in s (p95)","formula":"query1 / 1000"}],"queries":[{"query":"max:karafka.consumer.consumption_lag.max{*} by {consumer_group}","data_source":"metrics","name":"query2"},{"query":"max:karafka.consumer.consumption_lag.avg{*} by {consumer_group}","data_source":"metrics","name":"query3"},{"query":"max:karafka.consumer.consumption_lag.95percentile{*} by {consumer_group}","data_source":"metrics","name":"query1"}],"response_format":"timeseries","style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":0,"y":2,"width":4,"height":2}},{"id":1062074781483741,"definition":{"title":"Processing lag (in ms)","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"time":{},"type":"timeseries","requests":[{"formulas":[{"alias":"Lag in ms (p95)","formula":"query1"},{"alias":"Lag in ms (max)","formula":"query2"},{"alias":"Lag in ms (avg)","formula":"query3"}],"queries":[{"query":"max:karafka.consumer.processing_lag.95percentile{*} by {consumer_group}","data_source":"metrics","name":"query1"},{"query":"max:karafka.consumer.processing_lag.max{*} by {consumer_group}","data_source":"metrics","name":"query2"},{"query":"max:karafka.consumer.processing_lag.avg{*} by {consumer_group}","data_source":"metrics","name":"query3"}],"response_format":"timeseries","style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":4,"y":2,"width":4,"height":2}},{"id":7497794728674267,"definition":{"title":"Batch processing time","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"time":{},"type":"timeseries","requests":[{"formulas":[{"alias":"p95 time","formula":"query1"},{"alias":"max time","formula":"query2"},{"alias":"avg time","formula":"query3"}],"queries":[{"query":"max:karafka.consumer.consumed.time_taken.95percentile{*} by {topic,partition,consumer_group}","data_source":"metrics","name":"query1"},{"query":"max:karafka.consumer.consumed.time_taken.max{*} by {topic,partition,consumer_group}","data_source":"metrics","name":"query2"},{"query":"max:karafka.consumer.consumed.time_taken.avg{*} by {topic,partition,consumer_group}","data_source":"metrics","name":"query3"}],"response_format":"timeseries","style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":8,"y":2,"width":4,"height":2}},{"id":4192833027984161,"definition":{"title":"Batch size per topic","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"time":{},"type":"timeseries","requests":[{"formulas":[{"alias":"Batch size p95","formula":"query1"},{"alias":"Batch size avg","formula":"query2"},{"alias":"Batch size max","formula":"query3"}],"queries":[{"query":"sum:karafka.consumer.batch_size.95percentile{*} by {partition,topic,consumer_group}","data_source":"metrics","name":"query1"},{"query":"sum:karafka.consumer.batch_size.avg{*} by {partition,topic,consumer_group}","data_source":"metrics","name":"query2"},{"query":"sum:karafka.consumer.batch_size.max{*} by {partition,topic,consumer_group}","data_source":"metrics","name":"query3"}],"response_format":"timeseries","style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":0,"y":4,"width":4,"height":2}},{"id":4741598444771147,"definition":{"title":"Messages consumed overall","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"time":{},"type":"timeseries","requests":[{"formulas":[{"alias":"Messages consumed","formula":"query1"},{"alias":"Average batch size","formula":"query1 / query2"}],"queries":[{"query":"sum:karafka.consumer.messages{*} by {consumer_group}.as_count()","data_source":"metrics","name":"query1"},{"query":"sum:karafka.consumer.batches{*} by {consumer_group}.as_count()","data_source":"metrics","name":"query2"}],"response_format":"timeseries","style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":4,"y":4,"width":4,"height":2}},{"id":4502534794102513,"definition":{"title":"Polling times (ms)","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"time":{},"type":"timeseries","requests":[{"formulas":[{"alias":"p95 ms","formula":"query1"},{"alias":"max ms","formula":"query2"},{"alias":"average ms","formula":"query3"}],"queries":[{"query":"avg:karafka.listener.polling.time_taken.95percentile{*} by {consumer_group}","data_source":"metrics","name":"query1"},{"query":"avg:karafka.listener.polling.time_taken.max{*} by {consumer_group}","data_source":"metrics","name":"query2"},{"query":"avg:karafka.listener.polling.time_taken.avg{*} by {consumer_group}","data_source":"metrics","name":"query3"}],"response_format":"timeseries","style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":8,"y":4,"width":4,"height":2}}]},"layout":{"x":0,"y":3,"width":12,"height":7}}],"template_variables":[],"layout_type":"ordered","is_read_only":false,"notify_list":[],"reflow_type":"fixed","id":"s3u-z47-i6u"}
@@ -0,0 +1,153 @@
1
+ # frozen_string_literal: true
2
+
3
+ module Karafka
4
+ module Instrumentation
5
+ # Namespace for vendor specific instrumentation
6
+ module Vendors
7
+ # Datadog specific instrumentation
8
+ module Datadog
9
+ # A karafka's logger listener for Datadog
10
+ # It depends on the 'ddtrace' gem
11
+ class LoggerListener
12
+ include ::Karafka::Core::Configurable
13
+ extend Forwardable
14
+
15
+ def_delegators :config, :client
16
+
17
+ # `Datadog::Tracing` client that we should use to trace stuff
18
+ setting :client
19
+
20
+ configure
21
+
22
+ # Log levels that we use in this particular listener
23
+ USED_LOG_LEVELS = %i[
24
+ info
25
+ error
26
+ fatal
27
+ ].freeze
28
+
29
+ private_constant :USED_LOG_LEVELS
30
+
31
+ # @param block [Proc] configuration block
32
+ def initialize(&block)
33
+ configure
34
+ setup(&block) if block
35
+ end
36
+
37
+ # @param block [Proc] configuration block
38
+ # @note We define this alias to be consistent with `WaterDrop#setup`
39
+ def setup(&block)
40
+ configure(&block)
41
+ end
42
+
43
+ # Prints info about the fact that a given job has started
44
+ #
45
+ # @param event [Karafka::Core::Monitoring::Event] event details including payload
46
+ def on_worker_process(event)
47
+ current_span = client.trace('karafka.consumer')
48
+ push_tags
49
+
50
+ job = event[:job]
51
+ job_type = job.class.to_s.split('::').last
52
+ consumer = job.executor.topic.consumer
53
+ topic = job.executor.topic.name
54
+
55
+ current_span.resource = "#{consumer}#consume"
56
+ info "[#{job.id}] #{job_type} job for #{consumer} on #{topic} started"
57
+
58
+ pop_tags
59
+ end
60
+
61
+ # Prints info about the fact that a given job has finished
62
+ #
63
+ # @param event [Karafka::Core::Monitoring::Event] event details including payload
64
+ def on_worker_processed(event)
65
+ push_tags
66
+
67
+ job = event[:job]
68
+ time = event[:time]
69
+ job_type = job.class.to_s.split('::').last
70
+ consumer = job.executor.topic.consumer
71
+ topic = job.executor.topic.name
72
+
73
+ info "[#{job.id}] #{job_type} job for #{consumer} on #{topic} finished in #{time}ms"
74
+
75
+ current_span = client.active_span
76
+ current_span.finish if current_span.present?
77
+
78
+ pop_tags
79
+ end
80
+
81
+ # There are many types of errors that can occur in many places, but we provide a single
82
+ # handler for all of them to simplify error instrumentation.
83
+ # @param event [Karafka::Core::Monitoring::Event] event details including payload
84
+ def on_error_occurred(event)
85
+ push_tags
86
+
87
+ error = event[:error]
88
+ client.active_span&.set_error(error)
89
+
90
+ case event[:type]
91
+ when 'consumer.consume.error'
92
+ error "Consumer consuming error: #{error}"
93
+ when 'consumer.revoked.error'
94
+ error "Consumer on revoked failed due to an error: #{error}"
95
+ when 'consumer.before_enqueue.error'
96
+ error "Consumer before enqueue failed due to an error: #{error}"
97
+ when 'consumer.before_consume.error'
98
+ error "Consumer before consume failed due to an error: #{error}"
99
+ when 'consumer.after_consume.error'
100
+ error "Consumer after consume failed due to an error: #{error}"
101
+ when 'consumer.shutdown.error'
102
+ error "Consumer on shutdown failed due to an error: #{error}"
103
+ when 'worker.process.error'
104
+ fatal "Worker processing failed due to an error: #{error}"
105
+ when 'connection.listener.fetch_loop.error'
106
+ error "Listener fetch loop error: #{error}"
107
+ when 'runner.call.error'
108
+ fatal "Runner crashed due to an error: #{error}"
109
+ when 'app.stopping.error'
110
+ error 'Forceful Karafka server stop'
111
+ when 'librdkafka.error'
112
+ error "librdkafka internal error occurred: #{error}"
113
+ # Those will only occur when retries in the client fail and when they did not stop
114
+ # after back-offs
115
+ when 'connection.client.poll.error'
116
+ error "Data polling error occurred: #{error}"
117
+ else
118
+ pop_tags
119
+ # This should never happen. Please contact the maintainers
120
+ raise Errors::UnsupportedCaseError, event
121
+ end
122
+
123
+ pop_tags
124
+ end
125
+
126
+ USED_LOG_LEVELS.each do |log_level|
127
+ define_method log_level do |*args|
128
+ Karafka.logger.send(log_level, *args)
129
+ end
130
+ end
131
+
132
+ # Pushes datadog's tags to the logger
133
+ # This is required when tracing log lines asynchronously to correlate logs of the same
134
+ # process together
135
+ def push_tags
136
+ return unless Karafka.logger.respond_to?(:push_tags)
137
+
138
+ Karafka.logger.push_tags(client.log_correlation)
139
+ end
140
+
141
+ # Pops datadog's tags from the logger
142
+ # This is required when tracing log lines asynchronously to avoid the logs of the
143
+ # different processes to be correlated
144
+ def pop_tags
145
+ return unless Karafka.logger.respond_to?(:pop_tags)
146
+
147
+ Karafka.logger.pop_tags
148
+ end
149
+ end
150
+ end
151
+ end
152
+ end
153
+ end
@@ -10,7 +10,7 @@ module Karafka
10
10
  # and/or Datadog
11
11
  #
12
12
  # @note You need to setup the `dogstatsd-ruby` client and assign it
13
- class Listener
13
+ class MetricsListener
14
14
  include ::Karafka::Core::Configurable
15
15
  extend Forwardable
16
16
 
@@ -46,7 +46,11 @@ module Karafka
46
46
  RdKafkaMetric.new(:count, :brokers, 'connection.disconnects', 'disconnects_d'),
47
47
  RdKafkaMetric.new(:gauge, :brokers, 'network.latency.avg', %w[rtt avg]),
48
48
  RdKafkaMetric.new(:gauge, :brokers, 'network.latency.p95', %w[rtt p95]),
49
- RdKafkaMetric.new(:gauge, :brokers, 'network.latency.p99', %w[rtt p99])
49
+ RdKafkaMetric.new(:gauge, :brokers, 'network.latency.p99', %w[rtt p99]),
50
+
51
+ # Topics metrics
52
+ RdKafkaMetric.new(:gauge, :topics, 'consumer.lags', 'consumer_lag_stored'),
53
+ RdKafkaMetric.new(:gauge, :topics, 'consumer.lags_delta', 'consumer_lag_stored_d')
50
54
  ].freeze
51
55
 
52
56
  configure
@@ -68,9 +72,12 @@ module Karafka
68
72
  # @param event [Karafka::Core::Monitoring::Event]
69
73
  def on_statistics_emitted(event)
70
74
  statistics = event[:statistics]
75
+ consumer_group_id = event[:consumer_group_id]
76
+
77
+ base_tags = default_tags + ["consumer_group:#{consumer_group_id}"]
71
78
 
72
79
  rd_kafka_metrics.each do |metric|
73
- report_metric(metric, statistics)
80
+ report_metric(metric, statistics, base_tags)
74
81
  end
75
82
  end
76
83
 
@@ -81,12 +88,7 @@ module Karafka
81
88
  extra_tags = ["type:#{event[:type]}"]
82
89
 
83
90
  if event.payload[:caller].respond_to?(:messages)
84
- metadata = event.payload[:caller].messages.metadata
85
-
86
- extra_tags += [
87
- "topic:#{metadata.topic}",
88
- "partition:#{metadata.partition}"
89
- ]
91
+ extra_tags += consumer_tags(event.payload[:caller])
90
92
  end
91
93
 
92
94
  count('error_occurred', 1, tags: default_tags + extra_tags)
@@ -99,21 +101,23 @@ module Karafka
99
101
  time_taken = event[:time]
100
102
  messages_count = event[:messages_buffer].size
101
103
 
102
- histogram('listener.polling.time_taken', time_taken, tags: default_tags)
103
- histogram('listener.polling.messages', messages_count, tags: default_tags)
104
+ consumer_group_id = event[:subscription_group].consumer_group_id
105
+
106
+ extra_tags = ["consumer_group:#{consumer_group_id}"]
107
+
108
+ histogram('listener.polling.time_taken', time_taken, tags: default_tags + extra_tags)
109
+ histogram('listener.polling.messages', messages_count, tags: default_tags + extra_tags)
104
110
  end
105
111
 
106
112
  # Here we report majority of things related to processing as we have access to the
107
113
  # consumer
108
114
  # @param event [Karafka::Core::Monitoring::Event]
109
115
  def on_consumer_consumed(event)
110
- messages = event.payload[:caller].messages
116
+ consumer = event.payload[:caller]
117
+ messages = consumer.messages
111
118
  metadata = messages.metadata
112
119
 
113
- tags = default_tags + [
114
- "topic:#{metadata.topic}",
115
- "partition:#{metadata.partition}"
116
- ]
120
+ tags = default_tags + consumer_tags(consumer)
117
121
 
118
122
  count('consumer.messages', messages.count, tags: tags)
119
123
  count('consumer.batches', 1, tags: tags)
@@ -126,26 +130,14 @@ module Karafka
126
130
 
127
131
  # @param event [Karafka::Core::Monitoring::Event]
128
132
  def on_consumer_revoked(event)
129
- messages = event.payload[:caller].messages
130
- metadata = messages.metadata
131
-
132
- tags = default_tags + [
133
- "topic:#{metadata.topic}",
134
- "partition:#{metadata.partition}"
135
- ]
133
+ tags = default_tags + consumer_tags(event.payload[:caller])
136
134
 
137
135
  count('consumer.revoked', 1, tags: tags)
138
136
  end
139
137
 
140
138
  # @param event [Karafka::Core::Monitoring::Event]
141
139
  def on_consumer_shutdown(event)
142
- messages = event.payload[:caller].messages
143
- metadata = messages.metadata
144
-
145
- tags = default_tags + [
146
- "topic:#{metadata.topic}",
147
- "partition:#{metadata.partition}"
148
- ]
140
+ tags = default_tags + consumer_tags(event.payload[:caller])
149
141
 
150
142
  count('consumer.shutdown', 1, tags: tags)
151
143
  end
@@ -156,7 +148,7 @@ module Karafka
156
148
  jq_stats = event[:jobs_queue].statistics
157
149
 
158
150
  gauge('worker.total_threads', Karafka::App.config.concurrency, tags: default_tags)
159
- histogram('worker.processing', jq_stats[:processing], tags: default_tags)
151
+ histogram('worker.processing', jq_stats[:busy], tags: default_tags)
160
152
  histogram('worker.enqueued_jobs', jq_stats[:enqueued], tags: default_tags)
161
153
  end
162
154
 
@@ -166,7 +158,7 @@ module Karafka
166
158
  def on_worker_processed(event)
167
159
  jq_stats = event[:jobs_queue].statistics
168
160
 
169
- histogram('worker.processing', jq_stats[:processing], tags: default_tags)
161
+ histogram('worker.processing', jq_stats[:busy], tags: default_tags)
170
162
  end
171
163
 
172
164
  private
@@ -198,14 +190,15 @@ module Karafka
198
190
  # Reports a given metric statistics to Datadog
199
191
  # @param metric [RdKafkaMetric] metric value object
200
192
  # @param statistics [Hash] hash with all the statistics emitted
201
- def report_metric(metric, statistics)
193
+ # @param base_tags [Array<String>] base tags we want to start with
194
+ def report_metric(metric, statistics, base_tags)
202
195
  case metric.scope
203
196
  when :root
204
197
  public_send(
205
198
  metric.type,
206
199
  metric.name,
207
200
  statistics.fetch(*metric.key_location),
208
- tags: default_tags
201
+ tags: base_tags
209
202
  )
210
203
  when :brokers
211
204
  statistics.fetch('brokers').each_value do |broker_statistics|
@@ -218,13 +211,47 @@ module Karafka
218
211
  metric.type,
219
212
  metric.name,
220
213
  broker_statistics.dig(*metric.key_location),
221
- tags: default_tags + ["broker:#{broker_statistics['nodename']}"]
214
+ tags: base_tags + ["broker:#{broker_statistics['nodename']}"]
222
215
  )
223
216
  end
217
+ when :topics
218
+ statistics.fetch('topics').each do |topic_name, topic_values|
219
+ topic_values['partitions'].each do |partition_name, partition_statistics|
220
+ next if partition_name == '-1'
221
+ # Skip until lag info is available
222
+ next if partition_statistics['consumer_lag'] == -1
223
+
224
+ public_send(
225
+ metric.type,
226
+ metric.name,
227
+ partition_statistics.dig(*metric.key_location),
228
+ tags: base_tags + [
229
+ "topic:#{topic_name}",
230
+ "partition:#{partition_name}"
231
+ ]
232
+ )
233
+ end
234
+ end
224
235
  else
225
236
  raise ArgumentError, metric.scope
226
237
  end
227
238
  end
239
+
240
+ # Builds basic per consumer tags for publication
241
+ #
242
+ # @param consumer [Karafka::BaseConsumer]
243
+ # @return [Array<String>]
244
+ def consumer_tags(consumer)
245
+ messages = consumer.messages
246
+ metadata = messages.metadata
247
+ consumer_group_id = consumer.topic.consumer_group.id
248
+
249
+ [
250
+ "topic:#{metadata.topic}",
251
+ "partition:#{metadata.partition}",
252
+ "consumer_group:#{consumer_group_id}"
253
+ ]
254
+ end
228
255
  end
229
256
  end
230
257
  end
@@ -0,0 +1,166 @@
1
+ # frozen_string_literal: true
2
+
3
+ require 'socket'
4
+
5
+ module Karafka
6
+ module Instrumentation
7
+ module Vendors
8
+ # Namespace for instrumentation related with Kubernetes
9
+ module Kubernetes
10
+ # Kubernetes HTTP listener that does not only reply when process is not fully hanging, but
11
+ # also allows to define max time of processing and looping.
12
+ #
13
+ # Processes like Karafka server can hang while still being reachable. For example, in case
14
+ # something would hang inside of the user code, Karafka could stop polling and no new
15
+ # data would be processed, but process itself would still be active. This listener allows
16
+ # for defining of a ttl that gets bumped on each poll loop and before and after processing
17
+ # of a given messages batch.
18
+ class LivenessListener
19
+ include ::Karafka::Core::Helpers::Time
20
+
21
+ # @param hostname [String, nil] hostname or nil to bind on all
22
+ # @param port [Integer] TCP port on which we want to run our HTTP status server
23
+ # @param consuming_ttl [Integer] time in ms after which we consider consumption hanging.
24
+ # It allows us to define max consumption time after which k8s should consider given
25
+ # process as hanging
26
+ # @param polling_ttl [Integer] max time in ms for polling. If polling (any) does not
27
+ # happen that often, process should be considered dead.
28
+ # @note The default TTL matches the default `max.poll.interval.ms`
29
+ def initialize(
30
+ hostname: nil,
31
+ port: 3000,
32
+ consuming_ttl: 5 * 60 * 1_000,
33
+ polling_ttl: 5 * 60 * 1_000
34
+ )
35
+ @server = TCPServer.new(*[hostname, port].compact)
36
+ @polling_ttl = polling_ttl
37
+ @consuming_ttl = consuming_ttl
38
+ @mutex = Mutex.new
39
+ @pollings = {}
40
+ @consumptions = {}
41
+
42
+ Thread.new do
43
+ loop do
44
+ break unless respond
45
+ end
46
+ end
47
+ end
48
+
49
+ # Tick on each fetch
50
+ # @param _event [Karafka::Core::Monitoring::Event]
51
+ def on_connection_listener_fetch_loop(_event)
52
+ mark_polling_tick
53
+ end
54
+
55
+ # Tick on starting work
56
+ # @param _event [Karafka::Core::Monitoring::Event]
57
+ def on_consumer_consume(_event)
58
+ mark_consumption_tick
59
+ end
60
+
61
+ # Tick on finished work
62
+ # @param _event [Karafka::Core::Monitoring::Event]
63
+ def on_consumer_consumed(_event)
64
+ clear_consumption_tick
65
+ end
66
+
67
+ # @param _event [Karafka::Core::Monitoring::Event]
68
+ def on_consumer_revoke(_event)
69
+ mark_consumption_tick
70
+ end
71
+
72
+ # @param _event [Karafka::Core::Monitoring::Event]
73
+ def on_consumer_revoked(_event)
74
+ clear_consumption_tick
75
+ end
76
+
77
+ # @param _event [Karafka::Core::Monitoring::Event]
78
+ def on_consumer_shutting_down(_event)
79
+ mark_consumption_tick
80
+ end
81
+
82
+ # @param _event [Karafka::Core::Monitoring::Event]
83
+ def on_consumer_shutdown(_event)
84
+ clear_consumption_tick
85
+ end
86
+
87
+ # @param _event [Karafka::Core::Monitoring::Event]
88
+ def on_error_occurred(_event)
89
+ clear_consumption_tick
90
+ clear_polling_tick
91
+ end
92
+
93
+ # Stop the http server when we stop the process
94
+ # @param _event [Karafka::Core::Monitoring::Event]
95
+ def on_app_stopped(_event)
96
+ @server.close
97
+ end
98
+
99
+ private
100
+
101
+ # Wraps the logic with a mutex
102
+ # @param block [Proc] code we want to run in mutex
103
+ def synchronize(&block)
104
+ @mutex.synchronize(&block)
105
+ end
106
+
107
+ # @return [Integer] object id of the current thread
108
+ def thread_id
109
+ Thread.current.object_id
110
+ end
111
+
112
+ # Update the polling tick time for current thread
113
+ def mark_polling_tick
114
+ synchronize do
115
+ @pollings[thread_id] = monotonic_now
116
+ end
117
+ end
118
+
119
+ # Clear current thread polling time tracker
120
+ def clear_polling_tick
121
+ synchronize do
122
+ @pollings.delete(thread_id)
123
+ end
124
+ end
125
+
126
+ # Update the processing tick time
127
+ def mark_consumption_tick
128
+ synchronize do
129
+ @consumptions[thread_id] = monotonic_now
130
+ end
131
+ end
132
+
133
+ # Clear current thread consumption time tracker
134
+ def clear_consumption_tick
135
+ synchronize do
136
+ @consumptions.delete(thread_id)
137
+ end
138
+ end
139
+
140
+ # Responds to a HTTP request with the process liveness status
141
+ def respond
142
+ client = @server.accept
143
+ client.gets
144
+ client.print "HTTP/1.1 #{status}\r\n"
145
+ client.close
146
+
147
+ true
148
+ rescue Errno::ECONNRESET, Errno::EPIPE, IOError
149
+ !@server.closed?
150
+ end
151
+
152
+ # Did we exceed any of the ttls
153
+ # @return [String] 204 string if ok, 500 otherwise
154
+ def status
155
+ time = monotonic_now
156
+
157
+ return '500' if @pollings.values.any? { |tick| (time - tick) > @polling_ttl }
158
+ return '500' if @consumptions.values.any? { |tick| (time - tick) > @consuming_ttl }
159
+
160
+ '204'
161
+ end
162
+ end
163
+ end
164
+ end
165
+ end
166
+ end