Spaces:
Runtime error
Runtime error
File size: 6,200 Bytes
05b45a5 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 |
import threading
import time
from datetime import datetime
import psutil
import torch
from fastapi import APIRouter
try:
import GPUtil
GPU_AVAILABLE = True
except ImportError:
GPU_AVAILABLE = False
router = APIRouter(tags=["debug"])
@router.get("/debug/threads")
async def get_thread_info():
process = psutil.Process()
current_threads = threading.enumerate()
# Get per-thread CPU times
thread_details = []
for thread in current_threads:
thread_info = {
"name": thread.name,
"id": thread.ident,
"alive": thread.is_alive(),
"daemon": thread.daemon,
}
thread_details.append(thread_info)
return {
"total_threads": process.num_threads(),
"active_threads": len(current_threads),
"thread_names": [t.name for t in current_threads],
"thread_details": thread_details,
"memory_mb": process.memory_info().rss / 1024 / 1024,
}
@router.get("/debug/storage")
async def get_storage_info():
# Get disk partitions
partitions = psutil.disk_partitions()
storage_info = []
for partition in partitions:
try:
usage = psutil.disk_usage(partition.mountpoint)
storage_info.append(
{
"device": partition.device,
"mountpoint": partition.mountpoint,
"fstype": partition.fstype,
"total_gb": usage.total / (1024**3),
"used_gb": usage.used / (1024**3),
"free_gb": usage.free / (1024**3),
"percent_used": usage.percent,
}
)
except PermissionError:
continue
return {"storage_info": storage_info}
@router.get("/debug/system")
async def get_system_info():
process = psutil.Process()
# CPU Info
cpu_info = {
"cpu_count": psutil.cpu_count(),
"cpu_percent": psutil.cpu_percent(interval=1),
"per_cpu_percent": psutil.cpu_percent(interval=1, percpu=True),
"load_avg": psutil.getloadavg(),
}
# Memory Info
virtual_memory = psutil.virtual_memory()
swap_memory = psutil.swap_memory()
memory_info = {
"virtual": {
"total_gb": virtual_memory.total / (1024**3),
"available_gb": virtual_memory.available / (1024**3),
"used_gb": virtual_memory.used / (1024**3),
"percent": virtual_memory.percent,
},
"swap": {
"total_gb": swap_memory.total / (1024**3),
"used_gb": swap_memory.used / (1024**3),
"free_gb": swap_memory.free / (1024**3),
"percent": swap_memory.percent,
},
}
# Process Info
process_info = {
"pid": process.pid,
"status": process.status(),
"create_time": datetime.fromtimestamp(process.create_time()).isoformat(),
"cpu_percent": process.cpu_percent(),
"memory_percent": process.memory_percent(),
}
# Network Info
network_info = {
"connections": len(process.net_connections()),
"network_io": psutil.net_io_counters()._asdict(),
}
# GPU Info if available
gpu_info = None
if torch.backends.mps.is_available():
gpu_info = {
"type": "MPS",
"available": True,
"device": "Apple Silicon",
"backend": "Metal",
}
elif GPU_AVAILABLE:
try:
gpus = GPUtil.getGPUs()
gpu_info = [
{
"id": gpu.id,
"name": gpu.name,
"load": gpu.load,
"memory": {
"total": gpu.memoryTotal,
"used": gpu.memoryUsed,
"free": gpu.memoryFree,
"percent": (gpu.memoryUsed / gpu.memoryTotal) * 100,
},
"temperature": gpu.temperature,
}
for gpu in gpus
]
except Exception:
gpu_info = "GPU information unavailable"
return {
"cpu": cpu_info,
"memory": memory_info,
"process": process_info,
"network": network_info,
"gpu": gpu_info,
}
@router.get("/debug/session_pools")
async def get_session_pool_info():
"""Get information about ONNX session pools."""
from ..inference.model_manager import get_manager
manager = await get_manager()
pools = manager._session_pools
current_time = time.time()
pool_info = {}
# Get CPU pool info
if "onnx_cpu" in pools:
cpu_pool = pools["onnx_cpu"]
pool_info["cpu"] = {
"active_sessions": len(cpu_pool._sessions),
"max_sessions": cpu_pool._max_size,
"sessions": [
{"model": path, "age_seconds": current_time - info.last_used}
for path, info in cpu_pool._sessions.items()
],
}
# Get GPU pool info
if "onnx_gpu" in pools:
gpu_pool = pools["onnx_gpu"]
pool_info["gpu"] = {
"active_sessions": len(gpu_pool._sessions),
"max_streams": gpu_pool._max_size,
"available_streams": len(gpu_pool._available_streams),
"sessions": [
{
"model": path,
"age_seconds": current_time - info.last_used,
"stream_id": info.stream_id,
}
for path, info in gpu_pool._sessions.items()
],
}
# Add GPU memory info if available
if GPU_AVAILABLE:
try:
gpus = GPUtil.getGPUs()
if gpus:
gpu = gpus[0] # Assume first GPU
pool_info["gpu"]["memory"] = {
"total_mb": gpu.memoryTotal,
"used_mb": gpu.memoryUsed,
"free_mb": gpu.memoryFree,
"percent_used": (gpu.memoryUsed / gpu.memoryTotal) * 100,
}
except Exception:
pass
return pool_info
|