From b0558ea9296017b9160d76331c8dc10f3a702eec Mon Sep 17 00:00:00 2001 From: moshederri <38216041+moshederri@users.noreply.github.com> Date: Mon, 9 May 2022 20:07:14 +0300 Subject: [PATCH 1/5] Update README.md Adjusting airflow matching pattern to include missing `airflow.`, as well as unifying tags for dag and task id (dag_id / task_id) as they were different between mapping --- airflow/README.md | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/airflow/README.md b/airflow/README.md index a7e8de53636af..e60620af64cd5 100644 --- a/airflow/README.md +++ b/airflow/README.md @@ -108,11 +108,11 @@ Connect Airflow to DogStatsD (included in the Datadog Agent) by using the Airflo name: "airflow.pool.open_slots" tags: pool_name: "$1" - - match: "pool.queued_slots.*" + - match: "airflow.pool.queued_slots.*" name: "airflow.pool.queued_slots" tags: pool_name: "$1" - - match: "pool.running_slots.*" + - match: "airflow.pool.running_slots.*" name: "airflow.pool.running_slots" tags: pool_name: "$1" @@ -155,11 +155,11 @@ Connect Airflow to DogStatsD (included in the Datadog Agent) by using the Airflo name: "airflow.dagrun.schedule_delay" tags: dag_id: "$1" - - match: 'scheduler.tasks.running' + - match: 'airflow.scheduler.tasks.running' name: "airflow.scheduler.tasks.running" - - match: 'scheduler.tasks.starving' + - match: 'airflow.scheduler.tasks.starving' name: "airflow.scheduler.tasks.starving" - - match: sla_email_notification_failure + - match: airflow.sla_email_notification_failure name: 'airflow.sla_email_notification_failure' - match: 'airflow\.task_removed_from_dag\.(.*)' match_type: "regex" @@ -175,16 +175,16 @@ Connect Airflow to DogStatsD (included in the Datadog Agent) by using the Airflo name: "airflow.task.instance_created" tags: task_class: "$1" - - match: "ti.start.*.*" + - match: "airflow.ti.start.*.*" name: "airflow.ti.start" tags: - dagid: "$1" - taskid: "$2" - - match: "ti.finish.*.*.*" + dag_id: "$1" + task_id: "$2" + - match: "airflow.ti.finish.*.*.*" name: "airflow.ti.finish" tags: - dagid: "$1" - taskid: "$2" + dag_id: "$1" + task_id: "$2" state: "$3" ``` From ab3b42849fd3c4f90fe21d4fd6bd1e466fee6e0d Mon Sep 17 00:00:00 2001 From: moshederri <38216041+moshederri@users.noreply.github.com> Date: Wed, 11 May 2022 11:21:26 +0300 Subject: [PATCH 2/5] Update README.md --- airflow/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/airflow/README.md b/airflow/README.md index e60620af64cd5..2c77bd40ce3cc 100644 --- a/airflow/README.md +++ b/airflow/README.md @@ -310,7 +310,7 @@ This should direct the StatsD traffic from the Airflow container to a Datadog Ag env: - name: DD_DOGSTATSD_MAPPER_PROFILES value: > - [{"prefix":"airflow.","name":"airflow","mappings":[{"name":"airflow.job.start","match":"airflow.*_start","tags":{"job_name":"$1"}},{"name":"airflow.job.end","match":"airflow.*_end","tags":{"job_name":"$1"}},{"name":"airflow.job.heartbeat.failure","match":"airflow.*_heartbeat_failure","tags":{"job_name":"$1"}},{"name":"airflow.operator_failures","match":"airflow.operator_failures_*","tags":{"operator_name":"$1"}},{"name":"airflow.operator_successes","match":"airflow.operator_successes_*","tags":{"operator_name":"$1"}},{"match_type":"regex","name":"airflow.dag_processing.last_runtime","match":"airflow\\.dag_processing\\.last_runtime\\.(.*)","tags":{"dag_file":"$1"}},{"match_type":"regex","name":"airflow.dag_processing.last_run.seconds_ago","match":"airflow\\.dag_processing\\.last_run\\.seconds_ago\\.(.*)","tags":{"dag_file":"$1"}},{"match_type":"regex","name":"airflow.dag.loading_duration","match":"airflow\\.dag\\.loading-duration\\.(.*)","tags":{"dag_file":"$1"}},{"name":"airflow.dagrun.first_task_scheduling_delay","match":"airflow.dagrun.*.first_task_scheduling_delay","tags":{"dag_id":"$1"}},{"name":"airflow.pool.open_slots","match":"airflow.pool.open_slots.*","tags":{"pool_name":"$1"}},{"name":"airflow.pool.queued_slots","match":"pool.queued_slots.*","tags":{"pool_name":"$1"}},{"name":"airflow.pool.running_slots","match":"pool.running_slots.*","tags":{"pool_name":"$1"}},{"name":"airflow.pool.used_slots","match":"airflow.pool.used_slots.*","tags":{"pool_name":"$1"}},{"name":"airflow.pool.starving_tasks","match":"airflow.pool.starving_tasks.*","tags":{"pool_name":"$1"}},{"match_type":"regex","name":"airflow.dagrun.dependency_check","match":"airflow\\.dagrun\\.dependency-check\\.(.*)","tags":{"dag_id":"$1"}},{"match_type":"regex","name":"airflow.dag.task.duration","match":"airflow\\.dag\\.(.*)\\.([^.]*)\\.duration","tags":{"dag_id":"$1","task_id":"$2"}},{"match_type":"regex","name":"airflow.dag_processing.last_duration","match":"airflow\\.dag_processing\\.last_duration\\.(.*)","tags":{"dag_file":"$1"}},{"match_type":"regex","name":"airflow.dagrun.duration.success","match":"airflow\\.dagrun\\.duration\\.success\\.(.*)","tags":{"dag_id":"$1"}},{"match_type":"regex","name":"airflow.dagrun.duration.failed","match":"airflow\\.dagrun\\.duration\\.failed\\.(.*)","tags":{"dag_id":"$1"}},{"match_type":"regex","name":"airflow.dagrun.schedule_delay","match":"airflow\\.dagrun\\.schedule_delay\\.(.*)","tags":{"dag_id":"$1"}},{"name":"airflow.scheduler.tasks.running","match":"scheduler.tasks.running"},{"name":"airflow.scheduler.tasks.starving","match":"scheduler.tasks.starving"},{"name":"airflow.sla_email_notification_failure","match":"sla_email_notification_failure"},{"match_type":"regex","name":"airflow.dag.task_removed","match":"airflow\\.task_removed_from_dag\\.(.*)","tags":{"dag_id":"$1"}},{"match_type":"regex","name":"airflow.dag.task_restored","match":"airflow\\.task_restored_to_dag\\.(.*)","tags":{"dag_id":"$1"}},{"name":"airflow.task.instance_created","match":"airflow.task_instance_created-*","tags":{"task_class":"$1"}},{"name":"airflow.ti.start","match":"ti.start.*.*","tags":{"dagid":"$1","taskid":"$2"}},{"name":"airflow.ti.finish","match":"ti.finish.*.*.*","tags":{"dagid":"$1","state":"$3","taskid":"$2"}}]}] + [{"prefix":"airflow.","name":"airflow","mappings":[{"name":"airflow.job.start","match":"airflow.*_start","tags":{"job_name":"$1"}},{"name":"airflow.job.end","match":"airflow.*_end","tags":{"job_name":"$1"}},{"name":"airflow.job.heartbeat.failure","match":"airflow.*_heartbeat_failure","tags":{"job_name":"$1"}},{"name":"airflow.operator_failures","match":"airflow.operator_failures_*","tags":{"operator_name":"$1"}},{"name":"airflow.operator_successes","match":"airflow.operator_successes_*","tags":{"operator_name":"$1"}},{"match_type":"regex","name":"airflow.dag_processing.last_runtime","match":"airflow\\.dag_processing\\.last_runtime\\.(.*)","tags":{"dag_file":"$1"}},{"match_type":"regex","name":"airflow.dag_processing.last_run.seconds_ago","match":"airflow\\.dag_processing\\.last_run\\.seconds_ago\\.(.*)","tags":{"dag_file":"$1"}},{"match_type":"regex","name":"airflow.dag.loading_duration","match":"airflow\\.dag\\.loading-duration\\.(.*)","tags":{"dag_file":"$1"}},{"name":"airflow.dagrun.first_task_scheduling_delay","match":"airflow.dagrun.*.first_task_scheduling_delay","tags":{"dag_id":"$1"}},{"name":"airflow.pool.open_slots","match":"airflow.pool.open_slots.*","tags":{"pool_name":"$1"}},{"name":"airflow.pool.queued_slots","match":"airflow.pool.queued_slots.*","tags":{"pool_name":"$1"}},{"name":"airflow.pool.running_slots","match":"airflow.pool.running_slots.*","tags":{"pool_name":"$1"}},{"name":"airflow.pool.used_slots","match":"airflow.pool.used_slots.*","tags":{"pool_name":"$1"}},{"name":"airflow.pool.starving_tasks","match":"airflow.pool.starving_tasks.*","tags":{"pool_name":"$1"}},{"match_type":"regex","name":"airflow.dagrun.dependency_check","match":"airflow\\.dagrun\\.dependency-check\\.(.*)","tags":{"dag_id":"$1"}},{"match_type":"regex","name":"airflow.dag.task.duration","match":"airflow\\.dag\\.(.*)\\.([^.]*)\\.duration","tags":{"dag_id":"$1","task_id":"$2"}},{"match_type":"regex","name":"airflow.dag_processing.last_duration","match":"airflow\\.dag_processing\\.last_duration\\.(.*)","tags":{"dag_file":"$1"}},{"match_type":"regex","name":"airflow.dagrun.duration.success","match":"airflow\\.dagrun\\.duration\\.success\\.(.*)","tags":{"dag_id":"$1"}},{"match_type":"regex","name":"airflow.dagrun.duration.failed","match":"airflow\\.dagrun\\.duration\\.failed\\.(.*)","tags":{"dag_id":"$1"}},{"match_type":"regex","name":"airflow.dagrun.schedule_delay","match":"airflow\\.dagrun\\.schedule_delay\\.(.*)","tags":{"dag_id":"$1"}},{"name":"airflow.scheduler.tasks.running","match":"airflow.scheduler.tasks.running"},{"name":"airflow.scheduler.tasks.starving","match":"airflow.scheduler.tasks.starving"},{"name":"airflow.sla_email_notification_failure","match":"airflow.sla_email_notification_failure"},{"match_type":"regex","name":"airflow.dag.task_removed","match":"airflow\\.task_removed_from_dag\\.(.*)","tags":{"dag_id":"$1"}},{"match_type":"regex","name":"airflow.dag.task_restored","match":"airflow\\.task_restored_to_dag\\.(.*)","tags":{"dag_id":"$1"}},{"name":"airflow.task.instance_created","match":"airflow.task_instance_created-*","tags":{"task_class":"$1"}},{"name":"airflow.ti.start","match":"airflow.ti.start.*.*","tags":{"dag_id":"$1","task_id":"$2"}},{"name":"airflow.ti.finish","match":"airflow.ti.finish.*.*.*","tags":{"dag_id":"$1","state":"$3","task_id":"$2"}}]}] ``` See the Datadog `integrations-core` repo for an [example setup][14]. From 3979f0d373ae86efe6207e3e64fe29c5e78bae3d Mon Sep 17 00:00:00 2001 From: moshederri <38216041+moshederri@users.noreply.github.com> Date: Thu, 12 May 2022 08:30:24 +0300 Subject: [PATCH 3/5] Update README.md --- airflow/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/airflow/README.md b/airflow/README.md index 2c77bd40ce3cc..6f22f237df204 100644 --- a/airflow/README.md +++ b/airflow/README.md @@ -159,7 +159,7 @@ Connect Airflow to DogStatsD (included in the Datadog Agent) by using the Airflo name: "airflow.scheduler.tasks.running" - match: 'airflow.scheduler.tasks.starving' name: "airflow.scheduler.tasks.starving" - - match: airflow.sla_email_notification_failure + - match: 'airflow.sla_email_notification_failure' name: 'airflow.sla_email_notification_failure' - match: 'airflow\.task_removed_from_dag\.(.*)' match_type: "regex" From f25430520032b722a7535712a73536ee505ab392 Mon Sep 17 00:00:00 2001 From: moshederri <38216041+moshederri@users.noreply.github.com> Date: Sat, 14 May 2022 11:30:13 +0300 Subject: [PATCH 4/5] Update datadog_values.yaml --- airflow/tests/k8s_sample/datadog_values.yaml | 22 ++++++++++---------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/airflow/tests/k8s_sample/datadog_values.yaml b/airflow/tests/k8s_sample/datadog_values.yaml index c8e97310e2920..81cdfbce10a2c 100644 --- a/airflow/tests/k8s_sample/datadog_values.yaml +++ b/airflow/tests/k8s_sample/datadog_values.yaml @@ -849,11 +849,11 @@ agents: name: "airflow.pool.open_slots" tags: pool_name: "$1" - - match: "pool.queued_slots.*" + - match: "airflow.pool.queued_slots.*" name: "airflow.pool.queued_slots" tags: pool_name: "$1" - - match: "pool.running_slots.*" + - match: "airflow.pool.running_slots.*" name: "airflow.pool.running_slots" tags: pool_name: "$1" @@ -896,11 +896,11 @@ agents: name: "airflow.dagrun.schedule_delay" tags: dag_id: "$1" - - match: 'scheduler.tasks.running' + - match: 'airflow.scheduler.tasks.running' name: "airflow.scheduler.tasks.running" - - match: 'scheduler.tasks.starving' + - match: 'airflow.scheduler.tasks.starving' name: "airflow.scheduler.tasks.starving" - - match: sla_email_notification_failure + - match: 'airflow.sla_email_notification_failure' name: 'airflow.sla_email_notification_failure' - match: 'airflow\.task_removed_from_dag\.(.*)' match_type: "regex" @@ -916,16 +916,16 @@ agents: name: "airflow.task.instance_created" tags: task_class: "$1" - - match: "ti.start.*.*" + - match: "airflow.ti.start.*.*" name: "airflow.ti.start" tags: - dagid: "$1" - taskid: "$2" - - match: "ti.finish.*.*.*" + dag_id: "$1" + task_id: "$2" + - match: "airflow.ti.finish.*.*.*" name: "airflow.ti.finish" tags: - dagid: "$1" - taskid: "$2" + dag_id: "$1" + task_id: "$2" state: "$3" clusterChecksRunner: From 32a32ab4f6b8e447ffb0dd733047008f3ead1aa5 Mon Sep 17 00:00:00 2001 From: moshederri <38216041+moshederri@users.noreply.github.com> Date: Sat, 14 May 2022 11:33:10 +0300 Subject: [PATCH 5/5] Update test_check_metrics_up_to_date.py --- airflow/tests/test_check_metrics_up_to_date.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/airflow/tests/test_check_metrics_up_to_date.py b/airflow/tests/test_check_metrics_up_to_date.py index e7ee2f0ab6c2a..0fb06637f36a7 100644 --- a/airflow/tests/test_check_metrics_up_to_date.py +++ b/airflow/tests/test_check_metrics_up_to_date.py @@ -28,12 +28,12 @@ 'scheduler.orphaned_tasks.adopted', 'scheduler.critical_section_busy', 'sla_email_notification_failure', - 'ti.start..', - 'ti.finish...', + 'ti.start..', + 'ti.finish...', 'dag.callback_exceptions', 'celery.task_timeout_error', - 'task_removed_from_dag.', - 'task_restored_to_dag.', + 'task_removed_from_dag.', + 'task_restored_to_dag.', 'task_instance_created-', 'dagbag_size', 'dag_processing.import_errors',