-
Notifications
You must be signed in to change notification settings - Fork 47
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.
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
Ability to batch messages in topic reader #491
Changes from 3 commits
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -5,7 +5,7 @@ | |
import gzip | ||
import typing | ||
from asyncio import Task | ||
from collections import deque | ||
from collections import OrderedDict | ||
from typing import Optional, Set, Dict, Union, Callable | ||
|
||
import ydb | ||
|
@@ -264,7 +264,7 @@ class ReaderStream: | |
|
||
_state_changed: asyncio.Event | ||
_closed: bool | ||
_message_batches: typing.Deque[datatypes.PublicBatch] | ||
_message_batches: typing.Dict[int, datatypes.PublicBatch] | ||
_first_error: asyncio.Future[YdbError] | ||
|
||
_update_token_interval: Union[int, float] | ||
|
@@ -296,7 +296,7 @@ def __init__( | |
self._closed = False | ||
self._first_error = asyncio.get_running_loop().create_future() | ||
self._batches_to_decode = asyncio.Queue() | ||
self._message_batches = deque() | ||
self._message_batches = OrderedDict() | ||
|
||
self._update_token_interval = settings.update_token_interval | ||
self._get_token_function = get_token_function | ||
|
@@ -359,29 +359,38 @@ async def wait_messages(self): | |
await self._state_changed.wait() | ||
self._state_changed.clear() | ||
|
||
def _get_first_batch(self) -> typing.Tuple[int, datatypes.PublicBatch]: | ||
first_id, batch = self._message_batches.popitem(last=False) | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. first_id -> partition_session_id - for understand mean of the number |
||
return first_id, batch | ||
|
||
def receive_batch_nowait(self): | ||
if self._get_first_error(): | ||
raise self._get_first_error() | ||
|
||
if not self._message_batches: | ||
return None | ||
|
||
batch = self._message_batches.popleft() | ||
_, batch = self._get_first_batch() | ||
self._buffer_release_bytes(batch._bytes_size) | ||
|
||
return batch | ||
|
||
def receive_message_nowait(self): | ||
if self._get_first_error(): | ||
raise self._get_first_error() | ||
|
||
try: | ||
batch = self._message_batches[0] | ||
message = batch.pop_message() | ||
except IndexError: | ||
if not self._message_batches: | ||
return None | ||
|
||
if batch.empty(): | ||
self.receive_batch_nowait() | ||
part_sess_id, batch = self._get_first_batch() | ||
|
||
message = batch.messages.pop(0) | ||
|
||
if len(batch.messages) == 0: | ||
self._buffer_release_bytes(batch._bytes_size) | ||
else: | ||
# TODO: we should somehow release bytes from single message as well | ||
self._message_batches[part_sess_id] = batch | ||
|
||
return message | ||
|
||
|
@@ -605,9 +614,18 @@ async def _decode_batches_loop(self): | |
while True: | ||
batch = await self._batches_to_decode.get() | ||
await self._decode_batch_inplace(batch) | ||
self._message_batches.append(batch) | ||
self._add_batch_to_queue(batch) | ||
self._state_changed.set() | ||
|
||
def _add_batch_to_queue(self, batch: datatypes.PublicBatch): | ||
part_sess_id = batch._partition_session.id | ||
if part_sess_id in self._message_batches: | ||
self._message_batches[part_sess_id].messages.extend(batch.messages) | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. What about implement _push/_pop method for PublicBatch? it will be easer refctor internals in the future. |
||
self._message_batches[part_sess_id]._bytes_size += batch._bytes_size | ||
return | ||
|
||
self._message_batches[part_sess_id] = batch | ||
|
||
async def _decode_batch_inplace(self, batch): | ||
if batch._codec == Codec.CODEC_RAW: | ||
return | ||
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.