mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-04-25 08:26:21 +02:00
8954fa3ad7
Native CLI i18n: The TrustGraph CLI has built-in translation support that dynamically loads language strings. You can test and use different languages by simply passing the --lang flag (e.g., --lang es for Spanish, --lang ru for Russian) or by configuring your environment's LANG variable. Automated Docs Translations: This PR introduces autonomously translated Markdown documentation into several target languages, including Spanish, Swahili, Portuguese, Turkish, Hindi, Hebrew, Arabic, Simplified Chinese, and Russian.
718 lines
32 KiB
Markdown
718 lines
32 KiB
Markdown
---
|
|
layout: default
|
|
title: "आयात/निर्यात के लिए सुचारू शटडाउन तकनीकी विनिर्देश"
|
|
parent: "Hindi (Beta)"
|
|
---
|
|
|
|
# आयात/निर्यात के लिए सुचारू शटडाउन तकनीकी विनिर्देश
|
|
|
|
> **Beta Translation:** This document was translated via Machine Learning and as such may not be 100% accurate. All non-English languages are currently classified as Beta.
|
|
|
|
## समस्या विवरण
|
|
|
|
<<<<<<< HEAD
|
|
ट्रस्टग्राफ गेटवे वर्तमान में आयात और निर्यात दोनों कार्यों के दौरान वेबसॉकेट बंद होने के समय संदेश हानि का अनुभव करता है। यह दौड़ की स्थितियों के कारण होता है जहां पारगमन में मौजूद संदेश अपने गंतव्य (आयात के लिए पल्सर कतारों, निर्यात के लिए वेबसॉकेट क्लाइंट) तक पहुंचने से पहले त्याग दिए जाते हैं।
|
|
=======
|
|
ट्रस्टग्राफ गेटवे वर्तमान में आयात और निर्यात दोनों कार्यों के दौरान वेबसॉकेट बंद होने के समय संदेशों के खो जाने की समस्या का सामना करता है। यह दौड़ की स्थितियों के कारण होता है, जिसमें रास्ते में मौजूद संदेशों को उनके गंतव्य (आयात के लिए पल्सर कतारों, निर्यात के लिए वेबसॉकेट क्लाइंट) तक पहुंचने से पहले त्याग दिया जाता है।
|
|
>>>>>>> 82edf2d (New md files from RunPod)
|
|
|
|
### आयात-पक्ष की समस्याएं
|
|
1. प्रकाशक का asyncio.Queue बफर शटडाउन पर खाली नहीं होता है।
|
|
2. वेबसॉकेट बंद होने से पहले यह सुनिश्चित नहीं किया जाता है कि कतारबद्ध संदेश पल्सर तक पहुंचें।
|
|
3. सफल संदेश वितरण के लिए कोई स्वीकृति तंत्र नहीं है।
|
|
|
|
### निर्यात-पक्ष की समस्याएं
|
|
1. संदेशों को क्लाइंट को सफलतापूर्वक वितरित होने से पहले पल्सर में स्वीकार किया जाता है।
|
|
2. हार्ड-कोडेड टाइमआउट के कारण संदेश ड्रॉप हो जाते हैं जब कतारें भरी होती हैं।
|
|
3. धीमी उपभोक्ताओं को संभालने के लिए कोई बैकप्रेशर तंत्र नहीं है।
|
|
<<<<<<< HEAD
|
|
4. कई बफर बिंदु जहां डेटा खो सकता है।
|
|
=======
|
|
4. कई बफर बिंदु हैं जहां डेटा खो सकता है।
|
|
>>>>>>> 82edf2d (New md files from RunPod)
|
|
|
|
## वास्तुकला अवलोकन
|
|
|
|
```
|
|
Import Flow:
|
|
Client -> Websocket -> TriplesImport -> Publisher -> Pulsar Queue
|
|
|
|
Export Flow:
|
|
Pulsar Queue -> Subscriber -> TriplesExport -> Websocket -> Client
|
|
```
|
|
|
|
## प्रस्तावित सुधार
|
|
|
|
### 1. प्रकाशक में सुधार (आयात पक्ष)
|
|
|
|
#### ए. सुचारू कतार खाली करना
|
|
|
|
**फ़ाइल**: `trustgraph-base/trustgraph/base/publisher.py`
|
|
|
|
```python
|
|
class Publisher:
|
|
def __init__(self, client, topic, schema=None, max_size=10,
|
|
chunking_enabled=True, drain_timeout=5.0):
|
|
self.client = client
|
|
self.topic = topic
|
|
self.schema = schema
|
|
self.q = asyncio.Queue(maxsize=max_size)
|
|
self.chunking_enabled = chunking_enabled
|
|
self.running = True
|
|
self.draining = False # New state for graceful shutdown
|
|
self.task = None
|
|
self.drain_timeout = drain_timeout
|
|
|
|
async def stop(self):
|
|
"""Initiate graceful shutdown with draining"""
|
|
self.running = False
|
|
self.draining = True
|
|
|
|
if self.task:
|
|
# Wait for run() to complete draining
|
|
await self.task
|
|
|
|
async def run(self):
|
|
"""Enhanced run method with integrated draining logic"""
|
|
while self.running or self.draining:
|
|
try:
|
|
producer = self.client.create_producer(
|
|
topic=self.topic,
|
|
schema=JsonSchema(self.schema),
|
|
chunking_enabled=self.chunking_enabled,
|
|
)
|
|
|
|
drain_end_time = None
|
|
|
|
while self.running or self.draining:
|
|
try:
|
|
# Start drain timeout when entering drain mode
|
|
if self.draining and drain_end_time is None:
|
|
drain_end_time = time.time() + self.drain_timeout
|
|
logger.info(f"Publisher entering drain mode, timeout={self.drain_timeout}s")
|
|
|
|
# Check drain timeout
|
|
if self.draining and time.time() > drain_end_time:
|
|
if not self.q.empty():
|
|
logger.warning(f"Drain timeout reached with {self.q.qsize()} messages remaining")
|
|
self.draining = False
|
|
break
|
|
|
|
# Calculate wait timeout based on mode
|
|
if self.draining:
|
|
# Shorter timeout during draining to exit quickly when empty
|
|
timeout = min(0.1, drain_end_time - time.time())
|
|
else:
|
|
# Normal operation timeout
|
|
timeout = 0.25
|
|
|
|
# Get message from queue
|
|
id, item = await asyncio.wait_for(
|
|
self.q.get(),
|
|
timeout=timeout
|
|
)
|
|
|
|
# Send the message (single place for sending)
|
|
if id:
|
|
producer.send(item, { "id": id })
|
|
else:
|
|
producer.send(item)
|
|
|
|
except asyncio.TimeoutError:
|
|
# If draining and queue is empty, we're done
|
|
if self.draining and self.q.empty():
|
|
logger.info("Publisher queue drained successfully")
|
|
self.draining = False
|
|
break
|
|
continue
|
|
|
|
except asyncio.QueueEmpty:
|
|
# If draining and queue is empty, we're done
|
|
if self.draining and self.q.empty():
|
|
logger.info("Publisher queue drained successfully")
|
|
self.draining = False
|
|
break
|
|
continue
|
|
|
|
# Flush producer before closing
|
|
if producer:
|
|
producer.flush()
|
|
producer.close()
|
|
|
|
except Exception as e:
|
|
logger.error(f"Exception in publisher: {e}", exc_info=True)
|
|
|
|
if not self.running and not self.draining:
|
|
return
|
|
|
|
# If handler drops out, sleep a retry
|
|
await asyncio.sleep(1)
|
|
|
|
async def send(self, id, item):
|
|
"""Send still works normally - just adds to queue"""
|
|
if self.draining:
|
|
# Optionally reject new messages during drain
|
|
raise RuntimeError("Publisher is shutting down, not accepting new messages")
|
|
await self.q.put((id, item))
|
|
```
|
|
|
|
**मुख्य डिज़ाइन लाभ:**
|
|
**एकल प्रेषण स्थान**: सभी `producer.send()` कॉल `run()` विधि के भीतर एक ही स्थान पर होते हैं।
|
|
**स्वच्छ स्टेट मशीन**: तीन स्पष्ट अवस्थाएँ - चल रही, खाली करने की प्रक्रिया में, बंद।
|
|
**टाइमआउट सुरक्षा**: खाली करने के दौरान अनिश्चित काल तक नहीं रुकेगा।
|
|
**बेहतर अवलोकन क्षमता**: खाली करने की प्रगति और अवस्था परिवर्तनों का स्पष्ट लॉगिंग।
|
|
**वैकल्पिक संदेश अस्वीकृति**: शटडाउन चरण के दौरान नए संदेशों को अस्वीकार किया जा सकता है।
|
|
|
|
#### बी. बेहतर शटडाउन क्रम
|
|
|
|
**फ़ाइल**: `trustgraph-flow/trustgraph/gateway/dispatch/triples_import.py`
|
|
|
|
```python
|
|
class TriplesImport:
|
|
async def destroy(self):
|
|
"""Enhanced destroy with proper shutdown order"""
|
|
# Step 1: Stop accepting new messages
|
|
self.running.stop()
|
|
|
|
# Step 2: Wait for publisher to drain its queue
|
|
logger.info("Draining publisher queue...")
|
|
await self.publisher.stop()
|
|
|
|
# Step 3: Close websocket only after queue is drained
|
|
if self.ws:
|
|
await self.ws.close()
|
|
```
|
|
|
|
### 2. ग्राहक सुधार (निर्यात पक्ष)
|
|
|
|
#### ए. एकीकृत जल निकासी पैटर्न
|
|
|
|
**फ़ाइल**: `trustgraph-base/trustgraph/base/subscriber.py`
|
|
|
|
```python
|
|
class Subscriber:
|
|
def __init__(self, client, topic, subscription, consumer_name,
|
|
schema=None, max_size=100, metrics=None,
|
|
backpressure_strategy="block", drain_timeout=5.0):
|
|
# ... existing init ...
|
|
self.backpressure_strategy = backpressure_strategy
|
|
self.running = True
|
|
self.draining = False # New state for graceful shutdown
|
|
self.drain_timeout = drain_timeout
|
|
self.pending_acks = {} # Track messages awaiting delivery
|
|
|
|
async def stop(self):
|
|
"""Initiate graceful shutdown with draining"""
|
|
self.running = False
|
|
self.draining = True
|
|
|
|
if self.task:
|
|
# Wait for run() to complete draining
|
|
await self.task
|
|
|
|
async def run(self):
|
|
"""Enhanced run method with integrated draining logic"""
|
|
while self.running or self.draining:
|
|
if self.metrics:
|
|
self.metrics.state("stopped")
|
|
|
|
try:
|
|
self.consumer = self.client.subscribe(
|
|
topic = self.topic,
|
|
subscription_name = self.subscription,
|
|
consumer_name = self.consumer_name,
|
|
schema = JsonSchema(self.schema),
|
|
)
|
|
|
|
if self.metrics:
|
|
self.metrics.state("running")
|
|
|
|
logger.info("Subscriber running...")
|
|
drain_end_time = None
|
|
|
|
while self.running or self.draining:
|
|
# Start drain timeout when entering drain mode
|
|
if self.draining and drain_end_time is None:
|
|
drain_end_time = time.time() + self.drain_timeout
|
|
logger.info(f"Subscriber entering drain mode, timeout={self.drain_timeout}s")
|
|
|
|
# Stop accepting new messages from Pulsar during drain
|
|
self.consumer.pause_message_listener()
|
|
|
|
# Check drain timeout
|
|
if self.draining and time.time() > drain_end_time:
|
|
async with self.lock:
|
|
total_pending = sum(
|
|
q.qsize() for q in
|
|
list(self.q.values()) + list(self.full.values())
|
|
)
|
|
if total_pending > 0:
|
|
logger.warning(f"Drain timeout reached with {total_pending} messages in queues")
|
|
self.draining = False
|
|
break
|
|
|
|
# Check if we can exit drain mode
|
|
if self.draining:
|
|
async with self.lock:
|
|
all_empty = all(
|
|
q.empty() for q in
|
|
list(self.q.values()) + list(self.full.values())
|
|
)
|
|
if all_empty and len(self.pending_acks) == 0:
|
|
logger.info("Subscriber queues drained successfully")
|
|
self.draining = False
|
|
break
|
|
|
|
# Process messages only if not draining
|
|
if not self.draining:
|
|
try:
|
|
msg = await asyncio.to_thread(
|
|
self.consumer.receive,
|
|
timeout_millis=250
|
|
)
|
|
except _pulsar.Timeout:
|
|
continue
|
|
except Exception as e:
|
|
logger.error(f"Exception in subscriber receive: {e}", exc_info=True)
|
|
raise e
|
|
|
|
if self.metrics:
|
|
self.metrics.received()
|
|
|
|
# Process the message
|
|
await self._process_message(msg)
|
|
else:
|
|
# During draining, just wait for queues to empty
|
|
await asyncio.sleep(0.1)
|
|
|
|
except Exception as e:
|
|
logger.error(f"Subscriber exception: {e}", exc_info=True)
|
|
|
|
finally:
|
|
# Negative acknowledge any pending messages
|
|
for msg in self.pending_acks.values():
|
|
self.consumer.negative_acknowledge(msg)
|
|
self.pending_acks.clear()
|
|
|
|
if self.consumer:
|
|
self.consumer.unsubscribe()
|
|
self.consumer.close()
|
|
self.consumer = None
|
|
|
|
if self.metrics:
|
|
self.metrics.state("stopped")
|
|
|
|
if not self.running and not self.draining:
|
|
return
|
|
|
|
# If handler drops out, sleep a retry
|
|
await asyncio.sleep(1)
|
|
|
|
async def _process_message(self, msg):
|
|
"""Process a single message with deferred acknowledgment"""
|
|
# Store message for later acknowledgment
|
|
msg_id = str(uuid.uuid4())
|
|
self.pending_acks[msg_id] = msg
|
|
|
|
try:
|
|
id = msg.properties()["id"]
|
|
except:
|
|
id = None
|
|
|
|
value = msg.value()
|
|
delivery_success = False
|
|
|
|
async with self.lock:
|
|
# Deliver to specific subscribers
|
|
if id in self.q:
|
|
delivery_success = await self._deliver_to_queue(
|
|
self.q[id], value
|
|
)
|
|
|
|
# Deliver to all subscribers
|
|
for q in self.full.values():
|
|
if await self._deliver_to_queue(q, value):
|
|
delivery_success = True
|
|
|
|
# Acknowledge only on successful delivery
|
|
if delivery_success:
|
|
self.consumer.acknowledge(msg)
|
|
del self.pending_acks[msg_id]
|
|
else:
|
|
# Negative acknowledge for retry
|
|
self.consumer.negative_acknowledge(msg)
|
|
del self.pending_acks[msg_id]
|
|
|
|
async def _deliver_to_queue(self, queue, value):
|
|
"""Deliver message to queue with backpressure handling"""
|
|
try:
|
|
if self.backpressure_strategy == "block":
|
|
# Block until space available (no timeout)
|
|
await queue.put(value)
|
|
return True
|
|
|
|
elif self.backpressure_strategy == "drop_oldest":
|
|
# Drop oldest message if queue full
|
|
if queue.full():
|
|
try:
|
|
queue.get_nowait()
|
|
if self.metrics:
|
|
self.metrics.dropped()
|
|
except asyncio.QueueEmpty:
|
|
pass
|
|
await queue.put(value)
|
|
return True
|
|
|
|
elif self.backpressure_strategy == "drop_new":
|
|
# Drop new message if queue full
|
|
if queue.full():
|
|
if self.metrics:
|
|
self.metrics.dropped()
|
|
return False
|
|
await queue.put(value)
|
|
return True
|
|
|
|
except Exception as e:
|
|
logger.error(f"Failed to deliver message: {e}")
|
|
return False
|
|
```
|
|
|
|
<<<<<<< HEAD
|
|
**मुख्य डिज़ाइन लाभ (प्रकाशक पैटर्न से मेल खाता):**
|
|
=======
|
|
**मुख्य डिज़ाइन लाभ (प्रकाशक पैटर्न से मेल खाता है):**
|
|
>>>>>>> 82edf2d (New md files from RunPod)
|
|
**एकल प्रसंस्करण स्थान**: सभी संदेश प्रसंस्करण `run()` विधि में होता है।
|
|
**स्वच्छ स्टेट मशीन**: तीन स्पष्ट अवस्थाएँ - चल रही, खाली करने की प्रक्रिया में, बंद।
|
|
**खाली करते समय विराम**: मौजूदा कतारों को खाली करते समय, पल्सर से नए संदेश स्वीकार करना बंद हो जाता है।
|
|
**समय-सीमा सुरक्षा**: खाली करने की प्रक्रिया के दौरान अनिश्चित काल तक नहीं रुकेगा।
|
|
<<<<<<< HEAD
|
|
**उचित सफाई**: शटडाउन पर, किसी भी अप्राप्त संदेश को नकारात्मक रूप से स्वीकार किया जाता है।
|
|
=======
|
|
**उचित सफाई**: शटडाउन पर किसी भी अप्राप्त संदेश को नकारात्मक रूप से स्वीकार करता है।
|
|
>>>>>>> 82edf2d (New md files from RunPod)
|
|
|
|
#### बी. एक्सपोर्ट हैंडलर में सुधार
|
|
|
|
**फ़ाइल**: `trustgraph-flow/trustgraph/gateway/dispatch/triples_export.py`
|
|
|
|
```python
|
|
class TriplesExport:
|
|
async def destroy(self):
|
|
"""Enhanced destroy with graceful shutdown"""
|
|
# Step 1: Signal stop to prevent new messages
|
|
self.running.stop()
|
|
|
|
# Step 2: Wait briefly for in-flight messages
|
|
await asyncio.sleep(0.5)
|
|
|
|
# Step 3: Unsubscribe and stop subscriber (triggers queue drain)
|
|
if hasattr(self, 'subs'):
|
|
await self.subs.unsubscribe_all(self.id)
|
|
await self.subs.stop()
|
|
|
|
# Step 4: Close websocket last
|
|
if self.ws and not self.ws.closed:
|
|
await self.ws.close()
|
|
|
|
async def run(self):
|
|
"""Enhanced run with better error handling"""
|
|
self.subs = Subscriber(
|
|
client = self.pulsar_client,
|
|
topic = self.queue,
|
|
consumer_name = self.consumer,
|
|
subscription = self.subscriber,
|
|
schema = Triples,
|
|
backpressure_strategy = "block" # Configurable
|
|
)
|
|
|
|
await self.subs.start()
|
|
|
|
self.id = str(uuid.uuid4())
|
|
q = await self.subs.subscribe_all(self.id)
|
|
|
|
consecutive_errors = 0
|
|
max_consecutive_errors = 5
|
|
|
|
while self.running.get():
|
|
try:
|
|
resp = await asyncio.wait_for(q.get(), timeout=0.5)
|
|
await self.ws.send_json(serialize_triples(resp))
|
|
consecutive_errors = 0 # Reset on success
|
|
|
|
except asyncio.TimeoutError:
|
|
continue
|
|
|
|
except queue.Empty:
|
|
continue
|
|
|
|
except Exception as e:
|
|
logger.error(f"Exception sending to websocket: {str(e)}")
|
|
consecutive_errors += 1
|
|
|
|
if consecutive_errors >= max_consecutive_errors:
|
|
logger.error("Too many consecutive errors, shutting down")
|
|
break
|
|
|
|
# Brief pause before retry
|
|
await asyncio.sleep(0.1)
|
|
|
|
# Graceful cleanup handled in destroy()
|
|
```
|
|
|
|
<<<<<<< HEAD
|
|
### 3. सॉकेट-स्तरीय सुधार
|
|
=======
|
|
### 3. सॉकेट-स्तर में सुधार
|
|
>>>>>>> 82edf2d (New md files from RunPod)
|
|
|
|
**फ़ाइल**: `trustgraph-flow/trustgraph/gateway/endpoint/socket.py`
|
|
|
|
```python
|
|
class SocketEndpoint:
|
|
async def listener(self, ws, dispatcher, running):
|
|
"""Enhanced listener with graceful shutdown"""
|
|
async for msg in ws:
|
|
if msg.type == WSMsgType.TEXT:
|
|
await dispatcher.receive(msg)
|
|
continue
|
|
elif msg.type == WSMsgType.BINARY:
|
|
await dispatcher.receive(msg)
|
|
continue
|
|
else:
|
|
# Graceful shutdown on close
|
|
logger.info("Websocket closing, initiating graceful shutdown")
|
|
running.stop()
|
|
|
|
# Allow time for dispatcher cleanup
|
|
await asyncio.sleep(1.0)
|
|
break
|
|
|
|
async def handle(self, request):
|
|
"""Enhanced handler with better cleanup"""
|
|
# ... existing setup code ...
|
|
|
|
try:
|
|
async with asyncio.TaskGroup() as tg:
|
|
running = Running()
|
|
|
|
dispatcher = await self.dispatcher(
|
|
ws, running, request.match_info
|
|
)
|
|
|
|
worker_task = tg.create_task(
|
|
self.worker(ws, dispatcher, running)
|
|
)
|
|
|
|
lsnr_task = tg.create_task(
|
|
self.listener(ws, dispatcher, running)
|
|
)
|
|
|
|
except ExceptionGroup as e:
|
|
logger.error("Exception group occurred:", exc_info=True)
|
|
|
|
# Attempt graceful dispatcher shutdown
|
|
try:
|
|
await asyncio.wait_for(
|
|
dispatcher.destroy(),
|
|
timeout=5.0
|
|
)
|
|
except asyncio.TimeoutError:
|
|
logger.warning("Dispatcher shutdown timed out")
|
|
except Exception as de:
|
|
logger.error(f"Error during dispatcher cleanup: {de}")
|
|
|
|
except Exception as e:
|
|
logger.error(f"Socket exception: {e}", exc_info=True)
|
|
|
|
finally:
|
|
# Ensure dispatcher cleanup
|
|
if dispatcher and hasattr(dispatcher, 'destroy'):
|
|
try:
|
|
await dispatcher.destroy()
|
|
except:
|
|
pass
|
|
|
|
# Ensure websocket is closed
|
|
if ws and not ws.closed:
|
|
await ws.close()
|
|
|
|
return ws
|
|
```
|
|
|
|
## कॉन्फ़िगरेशन विकल्प
|
|
|
|
व्यवहार को अनुकूलित करने के लिए कॉन्फ़िगरेशन समर्थन जोड़ें:
|
|
|
|
```python
|
|
# config.py
|
|
class GracefulShutdownConfig:
|
|
# Publisher settings
|
|
PUBLISHER_DRAIN_TIMEOUT = 5.0 # Seconds to wait for queue drain
|
|
PUBLISHER_FLUSH_TIMEOUT = 2.0 # Producer flush timeout
|
|
|
|
# Subscriber settings
|
|
SUBSCRIBER_DRAIN_TIMEOUT = 5.0 # Seconds to wait for queue drain
|
|
BACKPRESSURE_STRATEGY = "block" # Options: "block", "drop_oldest", "drop_new"
|
|
SUBSCRIBER_MAX_QUEUE_SIZE = 100 # Maximum queue size before backpressure
|
|
|
|
# Socket settings
|
|
SHUTDOWN_GRACE_PERIOD = 1.0 # Seconds to wait for graceful shutdown
|
|
MAX_CONSECUTIVE_ERRORS = 5 # Maximum errors before forced shutdown
|
|
|
|
# Monitoring
|
|
LOG_QUEUE_STATS = True # Log queue statistics on shutdown
|
|
METRICS_ENABLED = True # Enable metrics collection
|
|
```
|
|
|
|
## परीक्षण रणनीति
|
|
|
|
<<<<<<< HEAD
|
|
### यूनिट परीक्षण
|
|
=======
|
|
### इकाई परीक्षण
|
|
>>>>>>> 82edf2d (New md files from RunPod)
|
|
|
|
```python
|
|
async def test_publisher_queue_drain():
|
|
"""Verify Publisher drains queue on shutdown"""
|
|
publisher = Publisher(...)
|
|
|
|
# Fill queue with messages
|
|
for i in range(10):
|
|
await publisher.send(f"id-{i}", {"data": i})
|
|
|
|
# Stop publisher
|
|
await publisher.stop()
|
|
|
|
# Verify all messages were sent
|
|
assert publisher.q.empty()
|
|
assert mock_producer.send.call_count == 10
|
|
|
|
async def test_subscriber_deferred_ack():
|
|
"""Verify Subscriber only acks on successful delivery"""
|
|
subscriber = Subscriber(..., backpressure_strategy="drop_new")
|
|
|
|
# Fill queue to capacity
|
|
queue = await subscriber.subscribe("test")
|
|
for i in range(100):
|
|
await queue.put({"data": i})
|
|
|
|
# Try to add message when full
|
|
msg = create_mock_message()
|
|
await subscriber._process_message(msg)
|
|
|
|
# Verify negative acknowledgment
|
|
assert msg.negative_acknowledge.called
|
|
assert not msg.acknowledge.called
|
|
```
|
|
|
|
<<<<<<< HEAD
|
|
### एकीकरण परीक्षण (एकीकरण परीक्षण)
|
|
=======
|
|
### एकीकरण परीक्षण
|
|
>>>>>>> 82edf2d (New md files from RunPod)
|
|
|
|
```python
|
|
async def test_import_graceful_shutdown():
|
|
"""Test import path handles shutdown gracefully"""
|
|
# Setup
|
|
import_handler = TriplesImport(...)
|
|
await import_handler.start()
|
|
|
|
# Send messages
|
|
messages = []
|
|
for i in range(100):
|
|
msg = {"metadata": {...}, "triples": [...]}
|
|
await import_handler.receive(msg)
|
|
messages.append(msg)
|
|
|
|
# Shutdown while messages in flight
|
|
await import_handler.destroy()
|
|
|
|
# Verify all messages reached Pulsar
|
|
received = await pulsar_consumer.receive_all()
|
|
assert len(received) == 100
|
|
|
|
async def test_export_no_message_loss():
|
|
"""Test export path doesn't lose acknowledged messages"""
|
|
# Setup Pulsar with test messages
|
|
for i in range(100):
|
|
await pulsar_producer.send({"data": i})
|
|
|
|
# Start export handler
|
|
export_handler = TriplesExport(...)
|
|
export_task = asyncio.create_task(export_handler.run())
|
|
|
|
# Receive some messages
|
|
received = []
|
|
for _ in range(50):
|
|
msg = await websocket.receive()
|
|
received.append(msg)
|
|
|
|
# Force shutdown
|
|
await export_handler.destroy()
|
|
|
|
# Continue receiving until websocket closes
|
|
while not websocket.closed:
|
|
try:
|
|
msg = await websocket.receive()
|
|
received.append(msg)
|
|
except:
|
|
break
|
|
|
|
# Verify no acknowledged messages were lost
|
|
assert len(received) >= 50
|
|
```
|
|
|
|
## रोलआउट योजना
|
|
|
|
### चरण 1: महत्वपूर्ण सुधार (सप्ताह 1)
|
|
सब्सक्राइबर स्वीकृति समय को ठीक करें (संदेश हानि को रोकें)
|
|
पब्लिशर क्यू को खाली करने की सुविधा जोड़ें
|
|
स्टेजिंग वातावरण में तैनात करें
|
|
|
|
### चरण 2: सुचारू शटडाउन (सप्ताह 2)
|
|
शटडाउन समन्वय लागू करें
|
|
बैकप्रेशर रणनीतियों को जोड़ें
|
|
प्रदर्शन परीक्षण
|
|
|
|
### चरण 3: निगरानी और ट्यूनिंग (सप्ताह 3)
|
|
क्यू की गहराई के लिए मेट्रिक्स जोड़ें
|
|
संदेश ड्रॉप के लिए अलर्ट जोड़ें
|
|
उत्पादन डेटा के आधार पर टाइमआउट मानों को ट्यून करें
|
|
|
|
## निगरानी और अलर्ट
|
|
|
|
### ट्रैक करने के लिए मेट्रिक्स
|
|
`publisher.queue.depth` - वर्तमान पब्लिशर क्यू का आकार
|
|
`publisher.messages.dropped` - शटडाउन के दौरान खोए गए संदेश
|
|
`subscriber.messages.negatively_acknowledged` - विफल डिलीवरी
|
|
`websocket.graceful_shutdowns` - सफल सुचारू शटडाउन
|
|
`websocket.forced_shutdowns` - मजबूर/टाइमआउट शटडाउन
|
|
|
|
### अलर्ट
|
|
पब्लिशर क्यू की गहराई > 80% क्षमता
|
|
शटडाउन के दौरान कोई भी संदेश ड्रॉप
|
|
सब्सक्राइबर नकारात्मक स्वीकृति दर > 1%
|
|
शटडाउन टाइमआउट समाप्त
|
|
|
|
## पिछली अनुकूलता
|
|
|
|
सभी परिवर्तनों में पिछली अनुकूलता बनी हुई है:
|
|
कॉन्फ़िगरेशन के बिना डिफ़ॉल्ट व्यवहार अपरिवर्तित रहता है
|
|
मौजूदा डिप्लॉयमेंट सामान्य रूप से काम करना जारी रखते हैं
|
|
यदि नई सुविधाएँ अनुपलब्ध हैं तो सुचारू गिरावट
|
|
|
|
## सुरक्षा संबंधी विचार
|
|
|
|
कोई नया आक्रमण वेक्टर नहीं जोड़ा गया
|
|
बैकप्रेशर मेमोरी थकावट हमलों को रोकता है
|
|
कॉन्फ़िगर करने योग्य सीमाएँ संसाधन दुरुपयोग को रोकती हैं
|
|
|
|
## प्रदर्शन प्रभाव
|
|
|
|
सामान्य संचालन के दौरान न्यूनतम ओवरहेड
|
|
शटडाउन में 5 सेकंड तक अधिक समय लग सकता है (कॉन्फ़िगर करने योग्य)
|
|
मेमोरी उपयोग क्यू आकार सीमाओं द्वारा सीमित है
|
|
CPU पर प्रभाव नगण्य (<1% वृद्धि)
|