Skip to content

chore(aci): manually add spans for delayed workflow processing #91908

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
May 19, 2025
Merged

chore(aci): manually add spans for delayed workflow processing #91908

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
82 changes: 49 additions & 33 deletions src/sentry/workflow_engine/processors/delayed_workflow.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@
from datetime import timedelta
from typing import Any

import sentry_sdk
from celery import Task
from django.utils import timezone

Expand Down Expand Up @@ -512,21 +513,24 @@ def process_delayed_workflows(
"""
Grab workflows, groups, and data condition groups from the Redis buffer, evaluate the "slow" conditions in a bulk snuba query, and fire them if they pass
"""
project = fetch_project(project_id)
if not project:
return
with sentry_sdk.start_span(op="delayed_workflow.prepare_data"):
project = fetch_project(project_id)
if not project:
return

workflow_event_dcg_data = fetch_group_to_event_data(project_id, Workflow, batch_key)
workflow_event_dcg_data = fetch_group_to_event_data(project_id, Workflow, batch_key)

# Get mappings from DataConditionGroups to other info
dcg_to_groups, trigger_group_to_dcg_model = get_dcg_group_workflow_detector_data(
workflow_event_dcg_data
)
dcg_to_workflow = trigger_group_to_dcg_model[DataConditionHandler.Group.WORKFLOW_TRIGGER].copy()
dcg_to_workflow.update(trigger_group_to_dcg_model[DataConditionHandler.Group.ACTION_FILTER])
# Get mappings from DataConditionGroups to other info
dcg_to_groups, trigger_group_to_dcg_model = get_dcg_group_workflow_detector_data(
workflow_event_dcg_data
)
dcg_to_workflow = trigger_group_to_dcg_model[
DataConditionHandler.Group.WORKFLOW_TRIGGER
].copy()
Comment on lines +517 to +529
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

nit: should this be moved into a method to make it a little easier to read? perhaps naming it prepare_data? 🤔

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

hmm yeah i can

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

err well there's the early return if there's no project

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

the return type starts looking a little crazy if i put it all into a single function, so just going to keep it separate for now

dcg_to_workflow.update(trigger_group_to_dcg_model[DataConditionHandler.Group.ACTION_FILTER])

_, workflows_to_envs = fetch_workflows_envs(list(dcg_to_workflow.values()))
data_condition_groups = fetch_data_condition_groups(list(dcg_to_groups.keys()))
_, workflows_to_envs = fetch_workflows_envs(list(dcg_to_workflow.values()))
data_condition_groups = fetch_data_condition_groups(list(dcg_to_groups.keys()))

logger.info(
"delayed_workflow.workflows",
Expand All @@ -537,10 +541,11 @@ def process_delayed_workflows(
},
)

# Get unique query groups to query Snuba
condition_groups = get_condition_query_groups(
data_condition_groups, dcg_to_groups, dcg_to_workflow, workflows_to_envs
)
with sentry_sdk.start_span(op="delayed_workflow.get_condition_query_groups"):
# Get unique query groups to query Snuba
condition_groups = get_condition_query_groups(
data_condition_groups, dcg_to_groups, dcg_to_workflow, workflows_to_envs
)

if not condition_groups:
return
Expand All @@ -556,7 +561,8 @@ def process_delayed_workflows(
"project_id": project_id,
},
)
condition_group_results = get_condition_group_results(condition_groups)
with sentry_sdk.start_span(op="delayed_workflow.get_condition_group_results"):
condition_group_results = get_condition_group_results(condition_groups)

serialized_results = {
str(query): count_dict for query, count_dict in condition_group_results.items()
Expand All @@ -566,30 +572,40 @@ def process_delayed_workflows(
extra={"condition_group_results": serialized_results, "project_id": project_id},
)

# Evaluate DCGs
groups_to_dcgs = get_groups_to_fire(
data_condition_groups,
workflows_to_envs,
dcg_to_workflow,
dcg_to_groups,
condition_group_results,
)
with sentry_sdk.start_span(op="delayed_workflow.get_groups_to_fire"):
# Evaluate DCGs
groups_to_dcgs = get_groups_to_fire(
data_condition_groups,
workflows_to_envs,
dcg_to_workflow,
dcg_to_groups,
condition_group_results,
)

logger.info(
"delayed_workflow.groups_to_fire",
extra={"groups_to_dcgs": groups_to_dcgs, "project_id": project_id},
)

dcg_group_to_event_data, event_ids, occurrence_ids = parse_dcg_group_event_data(
workflow_event_dcg_data, groups_to_dcgs
)
group_to_groupevent = get_group_to_groupevent(
dcg_group_to_event_data, list(groups_to_dcgs.keys()), event_ids, occurrence_ids, project_id
)
with sentry_sdk.start_span(op="delayed_workflow.get_group_to_groupevent"):
dcg_group_to_event_data, event_ids, occurrence_ids = parse_dcg_group_event_data(
workflow_event_dcg_data, groups_to_dcgs
)
group_to_groupevent = get_group_to_groupevent(
dcg_group_to_event_data,
list(groups_to_dcgs.keys()),
event_ids,
occurrence_ids,
project_id,
)

fire_actions_for_groups(groups_to_dcgs, trigger_group_to_dcg_model, group_to_groupevent)
with sentry_sdk.start_span(op="delayed_workflow.fire_actions"):
fire_actions_for_groups(groups_to_dcgs, trigger_group_to_dcg_model, group_to_groupevent)

cleanup_redis_buffer(project_id, workflow_event_dcg_data, batch_key)
with sentry_sdk.start_span(
op="delayed_workflow.cleanup_redis_buffer",
):
cleanup_redis_buffer(project_id, workflow_event_dcg_data, batch_key)


@delayed_processing_registry.register("delayed_workflow")
Expand Down
Loading