Skip to content

Performance enhancement by caching fastavro schema parsed on every message serialized & deserialized #627

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
Aug 7, 2019
Merged

Performance enhancement by caching fastavro schema parsed on every message serialized & deserialized #627

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
12 changes: 7 additions & 5 deletions confluent_kafka/avro/serializer/message_serializer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,6 +40,7 @@
HAS_FAST = False
try:
from fastavro import schemaless_reader, schemaless_writer
from fastavro.schema import parse_schema

HAS_FAST = True
except ImportError:
Expand Down Expand Up @@ -79,7 +80,8 @@ def __init__(self, registry_client, reader_key_schema=None, reader_value_schema=
def _get_encoder_func(self, writer_schema):
if HAS_FAST:
schema = writer_schema.to_json()
return lambda record, fp: schemaless_writer(fp, schema, record)
parsed_schema = parse_schema(schema)
return lambda record, fp: schemaless_writer(fp, parsed_schema, record)
writer = avro.io.DatumWriter(writer_schema)
return lambda record, fp: writer.write(record, avro.io.BinaryEncoder(fp))

Expand Down Expand Up @@ -169,9 +171,9 @@ def _get_decoder_func(self, schema_id, payload, is_key=False):
if HAS_FAST:
# try to use fast avro
try:
writer_schema = writer_schema_obj.to_json()
reader_schema = reader_schema_obj.to_json()
schemaless_reader(payload, writer_schema)
fast_avro_writer_schema = parse_schema(writer_schema_obj.to_json())
fast_avro_reader_schema = parse_schema(reader_schema_obj.to_json())
schemaless_reader(payload, fast_avro_writer_schema)

# If we reach this point, this means we have fastavro and it can
# do this deserialization. Rewind since this method just determines
Expand All @@ -180,7 +182,7 @@ def _get_decoder_func(self, schema_id, payload, is_key=False):
payload.seek(curr_pos)

self.id_to_decoder_func[schema_id] = lambda p: schemaless_reader(
p, writer_schema, reader_schema)
p, fast_avro_writer_schema, fast_avro_reader_schema)
return self.id_to_decoder_func[schema_id]
except Exception:
# Fast avro failed, fall thru to standard avro below.
Expand Down