Skip to content

perf: Remove redundant entity key serialization in online_read #6006

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
abhijeet-dhumal wants to merge 1 commit into
base: master
Choose a base branch
from
+14 −17
Open

perf: Remove redundant entity key serialization in online_read #6006

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
25 changes: 13 additions & 12 deletions sdk/python/feast/infra/online_stores/snowflake.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,3 @@
import itertools
import os
from binascii import hexlify
from datetime import datetime
Expand Down Expand Up @@ -168,20 +167,26 @@ def online_read(

requested_features = requested_features if requested_features else []

# Pre-compute serialized entity keys to avoid redundant serialization
serialized_entity_keys = [
serialize_entity_key(
entity_key,
entity_key_serialization_version=config.entity_key_serialization_version,
)
for entity_key in entity_keys
]

entity_fetch_str = ",".join(
[
(
"TO_BINARY("
+ hexlify(
serialize_entity_key(
combo[0],
entity_key_serialization_version=config.entity_key_serialization_version,
)
+ bytes(combo[1], encoding="utf-8")
serialized_entity_key + bytes(feature, encoding="utf-8")
).__str__()[1:]
+ ")"
)
for combo in itertools.product(entity_keys, requested_features)
for serialized_entity_key in serialized_entity_keys
for feature in requested_features
]
)

Expand All @@ -197,11 +202,7 @@ def online_read(
"""
df = execute_snowflake_statement(conn, query).fetch_pandas_all()

for entity_key in entity_keys:
entity_key_bin = serialize_entity_key(
entity_key,
entity_key_serialization_version=config.entity_key_serialization_version,
)
for entity_key_bin in serialized_entity_keys:
res = {}
res_ts = None
for index, row in df[df["entity_key"] == entity_key_bin].iterrows():
Expand Down
6 changes: 1 addition & 5 deletions sdk/python/feast/infra/online_stores/sqlite.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -263,11 +263,7 @@ def online_read(
rows = {
k: list(group) for k, group in itertools.groupby(rows, key=lambda r: r[0])
}
for entity_key in entity_keys:
entity_key_bin = serialize_entity_key(
entity_key,
entity_key_serialization_version=config.entity_key_serialization_version,
)
for entity_key_bin in serialized_entity_keys:
res = {}
res_ts = None
for _, feature_name, val_bin, ts in rows.get(entity_key_bin, []):
Expand Down
Loading