Spaces:
Sleeping
Sleeping
File size: 5,911 Bytes
d8d19cc | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 | """
Performance monitoring utilities for tracking query execution times and database operations.
"""
import time
import logging
from functools import wraps
from typing import Dict, Any, Optional
from contextlib import asynccontextmanager
logger = logging.getLogger(__name__)
class PerformanceMetrics:
"""Class to track and store performance metrics."""
def __init__(self):
self.query_times = []
self.slow_queries = []
self.total_queries = 0
self.total_time = 0.0
def add_query_time(self, collection: str, pipeline_length: int, execution_time: float, query_type: str = "aggregation"):
"""Add a query execution time to metrics."""
self.query_times.append({
"collection": collection,
"pipeline_length": pipeline_length,
"execution_time": execution_time,
"query_type": query_type,
"timestamp": time.time()
})
self.total_queries += 1
self.total_time += execution_time
# Track slow queries (> 1 second)
if execution_time > 1.0:
self.slow_queries.append({
"collection": collection,
"pipeline_length": pipeline_length,
"execution_time": execution_time,
"query_type": query_type,
"timestamp": time.time()
})
logger.warning(f"Slow query detected: {collection} took {execution_time:.3f}s")
def get_average_time(self) -> float:
"""Get average query execution time."""
return self.total_time / self.total_queries if self.total_queries > 0 else 0.0
def get_slow_query_count(self) -> int:
"""Get count of slow queries."""
return len(self.slow_queries)
def get_metrics_summary(self) -> Dict[str, Any]:
"""Get a summary of performance metrics."""
return {
"total_queries": self.total_queries,
"total_time": round(self.total_time, 3),
"average_time": round(self.get_average_time(), 3),
"slow_queries": self.get_slow_query_count(),
"recent_queries": self.query_times[-10:] if self.query_times else []
}
# Global performance metrics instance
performance_metrics = PerformanceMetrics()
def monitor_query_performance(func):
"""Decorator to monitor query performance."""
@wraps(func)
async def wrapper(*args, **kwargs):
start_time = time.time()
try:
result = await func(*args, **kwargs)
execution_time = time.time() - start_time
# Extract collection and pipeline info from args
collection = args[0] if args else "unknown"
pipeline_length = len(args[1]) if len(args) > 1 and isinstance(args[1], list) else 0
performance_metrics.add_query_time(
collection=collection,
pipeline_length=pipeline_length,
execution_time=execution_time,
query_type="aggregation"
)
logger.info(f"Query executed: {collection} in {execution_time:.3f}s (pipeline length: {pipeline_length})")
return result
except Exception as e:
execution_time = time.time() - start_time
logger.error(f"Query failed after {execution_time:.3f}s: {str(e)}")
raise
return wrapper
@asynccontextmanager
async def performance_timer(operation_name: str):
"""Context manager for timing operations."""
start_time = time.time()
try:
yield
finally:
execution_time = time.time() - start_time
logger.info(f"Operation '{operation_name}' completed in {execution_time:.3f}s")
def log_pipeline_complexity(pipeline: list, collection: str, operation: str):
"""Log pipeline complexity metrics."""
complexity_score = 0
stage_counts = {}
for stage in pipeline:
stage_type = list(stage.keys())[0] if stage else "unknown"
stage_counts[stage_type] = stage_counts.get(stage_type, 0) + 1
# Assign complexity scores to different stages
complexity_weights = {
"$match": 1,
"$project": 1,
"$sort": 2,
"$group": 3,
"$lookup": 4,
"$facet": 5,
"$unwind": 2,
"$addFields": 1,
"$limit": 1,
"$skip": 1
}
complexity_score += complexity_weights.get(stage_type, 2)
logger.info(f"Pipeline complexity for {operation} on {collection}: "
f"score={complexity_score}, stages={len(pipeline)}, "
f"breakdown={stage_counts}")
# Warn about high complexity
if complexity_score > 15:
logger.warning(f"High complexity pipeline detected: {operation} on {collection} "
f"(score: {complexity_score})")
return complexity_score
def get_performance_report() -> Dict[str, Any]:
"""Get a comprehensive performance report."""
return {
"metrics": performance_metrics.get_metrics_summary(),
"recommendations": _generate_recommendations()
}
def _generate_recommendations() -> list:
"""Generate performance recommendations based on metrics."""
recommendations = []
avg_time = performance_metrics.get_average_time()
slow_query_count = performance_metrics.get_slow_query_count()
if avg_time > 0.5:
recommendations.append("Consider adding indexes for frequently queried fields")
if slow_query_count > 0:
recommendations.append(f"Optimize {slow_query_count} slow queries detected")
if performance_metrics.total_queries > 100:
recommendations.append("Consider implementing query result caching")
return recommendations |