Skip to content

perf: Bulk-fetch testruns and update flakes in ProcessFlakesTask #1413

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

Open
sentry wants to merge 1 commit into
base: main
Choose a base branch
from
Open

perf: Bulk-fetch testruns and update flakes in ProcessFlakesTask #1413

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
48 changes: 39 additions & 9 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 @@ -42,7 +42,28 @@ def get_testruns(upload: ReportSession) -> QuerySet[Testrun]:
).order_by("timestamp")


def handle_pass(curr_flakes: dict[bytes, Flake], test_id: bytes):
def get_testruns_for_uploads(
uploads: list[ReportSession],
) -> dict[int, list[Testrun]]:
"""Bulk-fetch all testruns for a list of uploads in a single query,
returning a dict keyed by upload_id."""
upload_ids = [upload.id for upload in uploads]
testruns = Testrun.objects.filter(
Q(timestamp__gte=timezone.now() - timedelta(days=1))
& Q(upload_id__in=upload_ids)
).order_by("timestamp")

grouped: dict[int, list[Testrun]] = {uid: [] for uid in upload_ids}
for testrun in testruns:
grouped[testrun.upload_id].append(testrun)
return grouped


def handle_pass(
curr_flakes: dict[bytes, Flake],
test_id: bytes,
expired_flakes: list[Flake],
):
# possible that we expire it and stop caring about it
if test_id not in curr_flakes:
return
Expand All @@ -51,8 +72,7 @@ def handle_pass(curr_flakes: dict[bytes, Flake], test_id: bytes):
curr_flakes[test_id].count += 1
if curr_flakes[test_id].recent_passes_count == 30:
curr_flakes[test_id].end_date = timezone.now()
curr_flakes[test_id].save()
del curr_flakes[test_id]
expired_flakes.append(curr_flakes.pop(test_id))


def handle_failure(
Expand Down Expand Up @@ -81,18 +101,19 @@ 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],
expired_flakes: list[Flake],
repo_id: int,
):
testruns = get_testruns(upload)

for testrun in testruns:
test_id = bytes(testrun.test_id)
match testrun.outcome:
case "pass":
if test_id not in curr_flakes:
continue

handle_pass(curr_flakes, test_id)
handle_pass(curr_flakes, test_id, expired_flakes)
case "failure" | "flaky_fail" | "error":
handle_failure(curr_flakes, test_id, testrun, repo_id)
case _:
Expand Down Expand Up @@ -120,8 +141,13 @@ def process_flakes_for_commit(repo_id: int, commit_id: str):
extra={"flakes": [flake.test_id.hex() for flake in curr_flakes.values()]},
)

for upload in uploads:
process_single_upload(upload, curr_flakes, repo_id)
uploads_list = list(uploads)
testruns_by_upload = get_testruns_for_uploads(uploads_list)
expired_flakes: list[Flake] = []

for upload in uploads_list:
testruns = testruns_by_upload.get(upload.id, [])
process_single_upload(testruns, curr_flakes, expired_flakes, repo_id)
log.info(
"process_flakes_for_commit: processed upload",
extra={"upload": upload.id},
Expand All @@ -132,6 +158,10 @@ def process_flakes_for_commit(repo_id: int, commit_id: str):
extra={"flakes": [flake.test_id.hex() for flake in curr_flakes.values()]},
)

# Bulk-save expired flakes (those that reached 30 recent passes) in one query
if expired_flakes:
Flake.objects.bulk_update(expired_flakes, ["end_date", "count", "recent_passes_count"])

Flake.objects.bulk_create(
curr_flakes.values(),
update_conflicts=True,
Expand Down
Loading