Skip to content

perf(worker): Optimize flake processing N+1 query #1238

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

Closed
sentry wants to merge 1 commit into from
Closed

perf(worker): Optimize flake processing N+1 query #1238

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
29 changes: 17 additions & 12 deletions apps/worker/services/test_analytics/ta_process_flakes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,12 +33,11 @@ def fetch_current_flakes(repo_id: int) -> dict[bytes, Flake]:
}


def get_testruns(upload: ReportSession) -> QuerySet[Testrun]:
upload_filter = Q(upload_id=upload.id)

def get_testruns(upload_ids: list[int]) -> QuerySet[Testrun]:
# we won't process flakes for testruns older than 1 day
return Testrun.objects.filter(
Q(timestamp__gte=timezone.now() - timedelta(days=1)) & upload_filter
Q(timestamp__gte=timezone.now() - timedelta(days=1))
& Q(upload_id__in=upload_ids)
).order_by("timestamp")


Expand Down Expand Up @@ -81,10 +80,8 @@ def handle_failure(

@sentry_sdk.trace
def process_single_upload(
upload: ReportSession, curr_flakes: dict[bytes, Flake], repo_id: int
testruns: list[Testrun], curr_flakes: dict[bytes, Flake], repo_id: int
):
testruns = get_testruns(upload)

for testrun in testruns:
test_id = bytes(testrun.test_id)
match testrun.outcome:
Expand All @@ -98,19 +95,18 @@ def process_single_upload(
case _:
continue

Testrun.objects.bulk_update(testruns, ["outcome"])


@sentry_sdk.trace
def process_flakes_for_commit(repo_id: int, commit_id: str):
log.info(
"process_flakes_for_commit: starting processing",
)
uploads = get_relevant_uploads(repo_id, commit_id)
uploads = list(get_relevant_uploads(repo_id, commit_id))
upload_ids = [upload.id for upload in uploads]

log.info(
"process_flakes_for_commit: fetched uploads",
extra={"uploads": [upload.id for upload in uploads]},
extra={"uploads": upload_ids},
)

curr_flakes = fetch_current_flakes(repo_id)
Expand All @@ -120,13 +116,22 @@ def process_flakes_for_commit(repo_id: int, commit_id: str):
extra={"flakes": [flake.test_id.hex() for flake in curr_flakes.values()]},
)

# Fetch all testruns for all uploads in a single query, then group by upload_id
all_testruns = list(get_testruns(upload_ids))
testruns_by_upload: dict[int, list[Testrun]] = {}
for testrun in all_testruns:
testruns_by_upload.setdefault(testrun.upload_id, []).append(testrun)

for upload in uploads:
process_single_upload(upload, curr_flakes, repo_id)
process_single_upload(testruns_by_upload.get(upload.id, []), curr_flakes, repo_id)
log.info(
"process_flakes_for_commit: processed upload",
extra={"upload": upload.id},
)

# Bulk-update all mutated testruns in a single call
Testrun.objects.bulk_update(all_testruns, ["outcome"])

log.info(
"process_flakes_for_commit: bulk creating flakes",
extra={"flakes": [flake.test_id.hex() for flake in curr_flakes.values()]},
Expand Down
Loading