administrator/frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2026-07-04 11:01:14 +03:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Store hwaccel errors with timeout so it can retry

Browse Source
This commit is contained in:
Nicolas Mowen 2026-05-27 09:08:20 -06:00
parent fc5fbad047
commit 26e25c159d
2 changed files with 27 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
frigate/stats/emitter.py
View File

@ -32,7 +32,7 @@ class StatsEmitter(threading.Thread):
self.config = config self.config = config
self.stats_tracking = stats_tracking self.stats_tracking = stats_tracking
self.stop_event = stop_event self.stop_event = stop_event
self.hwaccel_errors: list[str] = [] self.hwaccel_errors: dict[str, float] = {}
self.stats_history: list[dict[str, Any]] = [] self.stats_history: list[dict[str, Any]] = []
# create communication for stats # create communication for stats

37
frigate/stats/util.py
View File

@ -1,6 +1,7 @@
"""Utilities for stats.""" """Utilities for stats."""
import asyncio import asyncio
import logging
import os import os
import shutil import shutil
import time import time
@ -34,6 +35,10 @@ from frigate.util.services import (
) )
from frigate.version import VERSION from frigate.version import VERSION
logger = logging.getLogger(__name__)
HWACCEL_ERROR_COOLDOWN_SECONDS = 3600
def get_latest_version(config: FrigateConfig) -> str: def get_latest_version(config: FrigateConfig) -> str:
if not config.telemetry.version_check: if not config.telemetry.version_check:
@ -167,7 +172,9 @@ def get_detector_stats(
def get_processing_stats( def get_processing_stats(
config: FrigateConfig, stats: dict[str, str], hwaccel_errors: list[str] config: FrigateConfig,
stats: dict[str, str],
hwaccel_errors: dict[str, float],
) -> None: ) -> None:
"""Get stats for cpu / gpu.""" """Get stats for cpu / gpu."""
@ -206,7 +213,9 @@ async def set_bandwidth_stats(config: FrigateConfig, all_stats: dict[str, Any])
async def set_gpu_stats( async def set_gpu_stats(
config: FrigateConfig, all_stats: dict[str, Any], hwaccel_errors: list[str] config: FrigateConfig,
all_stats: dict[str, Any],
hwaccel_errors: dict[str, float],
) -> None: ) -> None:
"""Parse GPUs from hwaccel args and use for stats.""" """Parse GPUs from hwaccel args and use for stats."""
hwaccel_args = [] hwaccel_args = []
@ -231,12 +240,16 @@ async def set_gpu_stats(
stats: dict[str, dict] = {} stats: dict[str, dict] = {}
intel_gpu_collected = False intel_gpu_collected = False
now = time.monotonic()
for args in hwaccel_args: for args in hwaccel_args:
if args in hwaccel_errors: last_error = hwaccel_errors.get(args)
# known erroring args should automatically return as error if last_error is not None:
stats["error-gpu"] = {"gpu": "", "mem": ""} if now - last_error < HWACCEL_ERROR_COOLDOWN_SECONDS:
elif "cuvid" in args or "nvidia" in args: continue
hwaccel_errors.pop(args, None)
if "cuvid" in args or "nvidia" in args:
# nvidia GPU # nvidia GPU
nvidia_usage = get_nvidia_gpu_stats() nvidia_usage = get_nvidia_gpu_stats()
@ -253,7 +266,7 @@ async def set_gpu_stats(
else: else:
stats["nvidia-gpu"] = {"vendor": "nvidia", "gpu": "", "mem": ""} stats["nvidia-gpu"] = {"vendor": "nvidia", "gpu": "", "mem": ""}
hwaccel_errors.append(args) hwaccel_errors[args] = time.monotonic()
elif "nvmpi" in args or "jetson" in args: elif "nvmpi" in args or "jetson" in args:
# nvidia Jetson # nvidia Jetson
jetson_usage = get_jetson_stats() jetson_usage = get_jetson_stats()
@ -262,7 +275,7 @@ async def set_gpu_stats(
stats["jetson-gpu"] = {"vendor": "nvidia", **jetson_usage} stats["jetson-gpu"] = {"vendor": "nvidia", **jetson_usage}
else: else:
stats["jetson-gpu"] = {"vendor": "nvidia", "gpu": "", "mem": ""} stats["jetson-gpu"] = {"vendor": "nvidia", "gpu": "", "mem": ""}
hwaccel_errors.append(args) hwaccel_errors[args] = time.monotonic()
elif "qsv" in args or ("vaapi" in args and not is_vaapi_amd_driver()): elif "qsv" in args or ("vaapi" in args and not is_vaapi_amd_driver()):
if not config.telemetry.stats.intel_gpu_stats: if not config.telemetry.stats.intel_gpu_stats:
continue continue
@ -280,7 +293,7 @@ async def set_gpu_stats(
stats[name] = entry stats[name] = entry
else: else:
stats["intel-gpu"] = {"vendor": "intel", "gpu": "", "mem": ""} stats["intel-gpu"] = {"vendor": "intel", "gpu": "", "mem": ""}
hwaccel_errors.append(args) hwaccel_errors[args] = time.monotonic()
elif "vaapi" in args: elif "vaapi" in args:
if not config.telemetry.stats.amd_gpu_stats: if not config.telemetry.stats.amd_gpu_stats:
continue continue
@ -292,7 +305,7 @@ async def set_gpu_stats(
stats["amd-vaapi"] = {"vendor": "amd", **amd_usage} stats["amd-vaapi"] = {"vendor": "amd", **amd_usage}
else: else:
stats["amd-vaapi"] = {"vendor": "amd", "gpu": "", "mem": ""} stats["amd-vaapi"] = {"vendor": "amd", "gpu": "", "mem": ""}
hwaccel_errors.append(args) hwaccel_errors[args] = time.monotonic()
elif "preset-rk" in args: elif "preset-rk" in args:
rga_usage = get_rockchip_gpu_stats() rga_usage = get_rockchip_gpu_stats()
@ -328,7 +341,9 @@ async def set_npu_usages(config: FrigateConfig, all_stats: dict[str, Any]) -> No
def stats_snapshot( def stats_snapshot(
config: FrigateConfig, stats_tracking: StatsTrackingTypes, hwaccel_errors: list[str] config: FrigateConfig,
stats_tracking: StatsTrackingTypes,
hwaccel_errors: dict[str, float],
) -> dict[str, Any]: ) -> dict[str, Any]:
"""Get a snapshot of the current stats that are being tracked.""" """Get a snapshot of the current stats that are being tracked."""
camera_metrics = stats_tracking["camera_metrics"] camera_metrics = stats_tracking["camera_metrics"]