Improve Intel Stats (#23190)

* Implement per intel-gpu stats collection

* Improve device naming

* Improve GPU vendor handling

* Cleanup

frigate/stats/intel_gpu_info.py

@@ -0,0 +1,109 @@
+"""Resolve human-readable names for Intel GPUs via OpenVINO."""
+
+import logging
+import re
+from typing import Optional
+
+logger = logging.getLogger(__name__)
+
+
+class IntelGpuNameResolver:
+    """Build a pdev -> normalized device name map by enumerating OpenVINO GPUs.
+
+    The lookup is performed once on first access and cached for the process
+    lifetime. OpenVINO exposes DEVICE_PCI_INFO (domain/bus/device/function) and
+    FULL_DEVICE_NAME for each GPU it can see, which is enough to associate the
+    name with the pdev string used by DRM fdinfo.
+    """
+
+    _names: Optional[dict[str, str]] = None
+
+    def get_names(self) -> dict[str, str]:
+        if self._names is not None:
+            return self._names
+
+        names: dict[str, str] = {}
+
+        try:
+            from openvino import Core
+        except ImportError:
+            logger.debug("OpenVINO unavailable; cannot resolve Intel GPU names")
+            self._names = names
+            return names
+
+        try:
+            core = Core()
+            devices = core.available_devices
+        except Exception as exc:
+            logger.debug(f"OpenVINO Core initialization failed: {exc}")
+            self._names = names
+            return names
+
+        cpu_name: Optional[str] = None
+        if "CPU" in devices:
+            try:
+                cpu_name = self._strip_trademarks(
+                    core.get_property("CPU", "FULL_DEVICE_NAME")
+                )
+            except Exception as exc:
+                logger.debug(f"Failed to read CPU FULL_DEVICE_NAME: {exc}")
+
+        for device in devices:
+            if not device.startswith("GPU"):
+                continue
+
+            try:
+                pci = core.get_property(device, "DEVICE_PCI_INFO")
+                raw_name = core.get_property(device, "FULL_DEVICE_NAME")
+                device_type = core.get_property(device, "DEVICE_TYPE")
+            except Exception as exc:
+                logger.debug(f"Failed to read properties for {device}: {exc}")
+                continue
+
+            pdev = self._format_pdev(pci)
+            if not pdev:
+                continue
+
+            names[pdev] = self._resolve_name(raw_name, device_type, cpu_name)
+
+        self._names = names
+        return names
+
+    @staticmethod
+    def _format_pdev(pci) -> Optional[str]:
+        try:
+            return f"{pci.domain:04x}:{pci.bus:02x}:{pci.device:02x}.{pci.function:x}"
+        except AttributeError:
+            return None
+
+    @classmethod
+    def _resolve_name(cls, raw_name: str, device_type, cpu_name: Optional[str]) -> str:
+        """Build a display name for a GPU.
+
+        Modern integrated Intel GPUs are reported by OpenVINO with a generic
+        FULL_DEVICE_NAME like "Intel(R) Graphics (iGPU)" that gives no model
+        information. Since the iGPU is part of the CPU on these platforms, fall
+        back to the CPU name (which OpenVINO does report specifically) and
+        suffix it with "iGPU" so it's clear what the entry is.
+        """
+        is_integrated = "INTEGRATED" in str(device_type).upper()
+
+        if is_integrated and cpu_name:
+            short_cpu = re.sub(r"^Intel\s+", "", cpu_name)
+            return f"{short_cpu} iGPU"
+
+        return cls._normalize_name(raw_name)
+
+    @classmethod
+    def _normalize_name(cls, name: str) -> str:
+        cleaned = cls._strip_trademarks(name)
+        cleaned = re.sub(r"\s*\((?:i|d)GPU\)\s*$", "", cleaned, flags=re.IGNORECASE)
+        return " ".join(cleaned.split())
+
+    @staticmethod
+    def _strip_trademarks(name: str) -> str:
+        cleaned = re.sub(r"\(R\)|\(TM\)", "", name)
+        return " ".join(cleaned.split())
+
+
+intel_gpu_name_resolver = IntelGpuNameResolver()

frigate/stats/util.py

@@ -230,6 +230,7 @@ async def set_gpu_stats(
                 hwaccel_args.append(args)
 
     stats: dict[str, dict] = {}
+    intel_gpu_collected = False
 
     for args in hwaccel_args:
         if args in hwaccel_errors:
@@ -242,6 +243,7 @@ async def set_gpu_stats(
             if nvidia_usage:
                 for i in range(len(nvidia_usage)):
                     stats[nvidia_usage[i]["name"]] = {
+                        "vendor": "nvidia",
                         "gpu": str(round(float(nvidia_usage[i]["gpu"]), 2)) + "%",
                         "mem": str(round(float(nvidia_usage[i]["mem"]), 2)) + "%",
                         "enc": str(round(float(nvidia_usage[i]["enc"]), 2)) + "%",
@@ -250,31 +252,34 @@ async def set_gpu_stats(
                     }
 
             else:
-                stats["nvidia-gpu"] = {"gpu": "", "mem": ""}
+                stats["nvidia-gpu"] = {"vendor": "nvidia", "gpu": "", "mem": ""}
                 hwaccel_errors.append(args)
         elif "nvmpi" in args or "jetson" in args:
             # nvidia Jetson
             jetson_usage = get_jetson_stats()
 
             if jetson_usage:
-                stats["jetson-gpu"] = jetson_usage
+                stats["jetson-gpu"] = {"vendor": "nvidia", **jetson_usage}
             else:
-                stats["jetson-gpu"] = {"gpu": "", "mem": ""}
+                stats["jetson-gpu"] = {"vendor": "nvidia", "gpu": "", "mem": ""}
                 hwaccel_errors.append(args)
         elif "qsv" in args or ("vaapi" in args and not is_vaapi_amd_driver()):
             if not config.telemetry.stats.intel_gpu_stats:
                 continue
 
-            if "intel-gpu" not in stats:
+            if not intel_gpu_collected:
                 # intel GPU (QSV or VAAPI both use the same physical GPU)
+                intel_gpu_collected = True
                 intel_usage = get_intel_gpu_stats(
                     config.telemetry.stats.intel_gpu_device
                 )
 
-                if intel_usage is not None:
-                    stats["intel-gpu"] = intel_usage or {"gpu": "", "mem": ""}
+                if intel_usage:
+                    for entry in intel_usage.values():
+                        name = entry.pop("name")
+                        stats[name] = entry
                 else:
-                    stats["intel-gpu"] = {"gpu": "", "mem": ""}
+                    stats["intel-gpu"] = {"vendor": "intel", "gpu": "", "mem": ""}
                     hwaccel_errors.append(args)
         elif "vaapi" in args:
             if not config.telemetry.stats.amd_gpu_stats:
@@ -284,18 +289,18 @@ async def set_gpu_stats(
             amd_usage = get_amd_gpu_stats()
 
             if amd_usage:
-                stats["amd-vaapi"] = amd_usage
+                stats["amd-vaapi"] = {"vendor": "amd", **amd_usage}
             else:
-                stats["amd-vaapi"] = {"gpu": "", "mem": ""}
+                stats["amd-vaapi"] = {"vendor": "amd", "gpu": "", "mem": ""}
                 hwaccel_errors.append(args)
         elif "preset-rk" in args:
             rga_usage = get_rockchip_gpu_stats()
 
             if rga_usage:
-                stats["rockchip"] = rga_usage
+                stats["rockchip"] = {"vendor": "rockchip", **rga_usage}
         elif "v4l2m2m" in args or "rpi" in args:
             # RPi v4l2m2m is currently not able to get usage stats
-            stats["rpi-v4l2m2m"] = {"gpu": "", "mem": ""}
+            stats["rpi-v4l2m2m"] = {"vendor": "rpi", "gpu": "", "mem": ""}
 
     if stats:
         all_stats["gpu_usages"] = stats