Skip to content

fix: keep last_updated_ms from preceding the latest metadata-log entry #4273

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

fix: keep last_updated_ms from preceding the latest metadata-log entry #4273

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
4 changes: 2 additions & 2 deletions pyiceberg/table/update/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -746,11 +746,11 @@ def update_table_metadata(
for update in updates:
new_metadata = _apply_table_update(update, new_metadata, context)

# Update last_updated_ms if it was not updated by update operations
# last_updated_ms must not precede the base's, which becomes the latest metadata-log entry
if context.has_changes():
if metadata_location:
new_metadata = _update_table_metadata_log(new_metadata, metadata_location, base_metadata.last_updated_ms)
if base_metadata.last_updated_ms == new_metadata.last_updated_ms:
if new_metadata.last_updated_ms <= base_metadata.last_updated_ms:
new_metadata = new_metadata.model_copy(update={"last_updated_ms": datetime_to_millis(datetime.now().astimezone())})

# Check correctness of partition spec, and sort order
Expand Down
21 changes: 19 additions & 2 deletions tests/table/test_init.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1252,7 +1252,7 @@ def test_update_metadata_with_multiple_updates(table_v1: Table) -> None:
snapshot_id=25,
parent_snapshot_id=19,
sequence_number=200,
timestamp_ms=1602638573590,
timestamp_ms=1602638593590,
manifest_list="s3:/a/b/c.avro",
summary=Summary(Operation.APPEND),
schema_id=3,
Expand Down Expand Up @@ -1295,7 +1295,7 @@ def test_update_metadata_with_multiple_updates(table_v1: Table) -> None:
assert len(new_metadata.snapshot_log) == 1
assert new_metadata.snapshot_log[0].snapshot_id == 25
assert new_metadata.current_snapshot_id == 25
assert new_metadata.last_updated_ms == 1602638573590
assert new_metadata.last_updated_ms == 1602638593590
assert new_metadata.refs["main"] == SnapshotRef(
snapshot_id=25,
snapshot_ref_type="branch",
Expand Down Expand Up @@ -1683,6 +1683,23 @@ def test_update_metadata_log(table_v2: Table) -> None:
assert len(new_metadata.metadata_log) == 2


def test_update_metadata_last_updated_ms_not_before_metadata_log(table_v2: Table) -> None:
stale_snapshot = Snapshot(
snapshot_id=25,
parent_snapshot_id=19,
sequence_number=200,
timestamp_ms=table_v2.metadata.last_updated_ms - 61_000,
manifest_list="s3:/a/b/c.avro",
summary=Summary(Operation.APPEND),
schema_id=3,
)

new_metadata = update_table_metadata(
table_v2.metadata, (AddSnapshotUpdate(snapshot=stale_snapshot),), False, table_v2.metadata_location
)
assert new_metadata.last_updated_ms > new_metadata.metadata_log[-1].timestamp_ms


def test_update_metadata_log_overflow(table_v2: Table) -> None:
metadata_log = [
MetadataLogEntry(
Expand Down
Loading