Skip to content
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

Speed up corpus_pruning task #4659

Merged
merged 1 commit into from
Feb 4, 2025
Merged

Speed up corpus_pruning task #4659

Show file tree
Hide file tree
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
2 changes: 1 addition & 1 deletion src/clusterfuzz/_internal/bot/tasks/utasks/corpus_pruning_task.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -156,7 +156,7 @@ async def delete_gcs_blobs_batch(session, bucket, blobs_to_delete, token):
num_deleted = 0
blobs_to_delete = []
delete_tasks = []
num_batches
num_batches = 0
for blob in storage.get_blobs_no_retry(corpus_url, recursive=True):
idx += 1
if not deleting:
Expand Down
14 changes: 4 additions & 10 deletions src/clusterfuzz/_internal/fuzzing/corpus_manager.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -666,13 +666,7 @@ def get_proto_corpus(bucket_name,
corpus_urls = storage.sign_urls_for_existing_files(urls, include_delete_urls)
upload_urls = storage.get_arbitrary_signed_upload_urls(
gcs_url, num_uploads=max_upload_urls)
corpus = uworker_msg_pb2.Corpus( # pylint: disable=no-member
gcs_url=gcs_url,)
last_updated = _last_updated(_get_gcs_url(bucket_name, bucket_path))
if last_updated:
timestamp = timestamp_pb2.Timestamp() # pylint: disable=no-member
timestamp.FromDatetime(last_updated)
corpus.last_updated_time.CopyFrom(timestamp)
corpus = uworker_msg_pb2.Corpus(gcs_url=gcs_url) # pylint: disable=no-member
# Iterate over imap_unordered results.
for upload_url in upload_urls:
corpus.upload_urls.append(upload_url)
Expand Down Expand Up @@ -756,8 +750,8 @@ def get_corpuses_for_pruning(engine, project_qualified_name):
project_qualified_name,
include_regressions=True,
include_delete_urls=True,
max_upload_urls=5000,
max_download_urls=40000)
max_upload_urls=3_000,
max_download_urls=30_000)
# We will never need to upload more than the number of testcases in the
# corpus to the quarantine. But add a max of 500 to avoid spending
# too much time on crazy edge cases.
Expand All @@ -768,5 +762,5 @@ def get_corpuses_for_pruning(engine, project_qualified_name):
quarantine=True,
include_delete_urls=True,
max_upload_urls=max_upload_urls,
max_download_urls=5000)
max_download_urls=1_000)
return corpus, quarantine_corpus
Loading