Add Deck dashboard with Athena telemetry history

collect_hardware.py

@@ -3,8 +3,14 @@ import csv
 import json
 import time
 import subprocess
+import os
+import shutil
 from pathlib import Path
 
+PROC = Path(os.environ.get('DECK_HOST_PROC', '/proc'))
+DATA_DISK = Path(os.environ.get('DECK_HOST_DATA_DISK', '/var/lib/deck'))
+_network_previous = None
+
 
 def read(path):
     try:
@@ -21,11 +27,12 @@ def number(value):
 
 
 def ticks():
-    values = list(map(int, read('/proc/stat').splitlines()[0].split()[1:9]))
+    values = list(map(int, read(PROC/'stat').splitlines()[0].split()[1:9]))
     return sum(values), sum(values[3:5])
 
 
 def collect():
+    global _network_previous
     errors = []
     cpu = {'name': None, 'percent': None, 'temperature_c': None}
     try:
@@ -35,7 +42,7 @@ def collect():
         cpu['percent'] = round(100 * (1 - (bi-ai)/(b-a)), 1) if b > a else None
     except (ValueError, IndexError):
         errors.append('CPU-Auslastung nicht verfügbar')
-    for line in read('/proc/cpuinfo').splitlines():
+    for line in read(PROC/'cpuinfo').splitlines():
         if line.startswith('model name'):
             cpu['name'] = line.split(':', 1)[1].strip()
             break
@@ -45,7 +52,7 @@ def collect():
             cpu['temperature_c'] = value / 1000 if value is not None else None
             break
     mem = {}
-    for line in read('/proc/meminfo').splitlines():
+    for line in read(PROC/'meminfo').splitlines():
         parts = line.split()
         if parts[0] in ('MemTotal:', 'MemAvailable:'):
             mem[parts[0][:-1]] = int(parts[1]) * 1024
@@ -53,13 +60,45 @@ def collect():
     ram = {'total_bytes': total, 'used_bytes': total-available if total is not None and available is not None else None}
     gpus = []
     try:
-        result = subprocess.run(['nvidia-smi', '--query-gpu=index,name,uuid,memory.total,memory.used,utilization.gpu,temperature.gpu', '--format=csv,noheader,nounits'], capture_output=True, text=True, timeout=4, check=True)
+        result = subprocess.run(['nvidia-smi', '--query-gpu=index,name,uuid,memory.total,memory.used,utilization.gpu,temperature.gpu,utilization.memory,memory.free,power.draw,power.limit,clocks.current.graphics,clocks.current.memory,fan.speed,pstate', '--format=csv,noheader,nounits'], capture_output=True, text=True, timeout=4, check=True)
         for row in csv.reader(result.stdout.splitlines(), skipinitialspace=True):
-            index, name, uuid, total, used, usage, temp = row
-            gpus.append(dict(index=int(index), name=name, uuid=uuid, total_mib=number(total), used_mib=number(used), percent=number(usage), temperature_c=number(temp)))
+            if len(row)!=15:continue
+            index, name, uuid, total, used, usage, temp, memory_usage, free, power, power_limit, graphics_clock, memory_clock, fan, pstate = row
+            gpus.append(dict(index=int(index), name=name, uuid=uuid, total_mib=number(total), used_mib=number(used), percent=number(usage), temperature_c=number(temp),memory_controller_percent=number(memory_usage),free_mib=number(free),power_w=number(power),power_limit_w=number(power_limit),graphics_clock_mhz=number(graphics_clock),memory_clock_mhz=number(memory_clock),fan_percent=number(fan),pstate=pstate))
     except (OSError, subprocess.SubprocessError, ValueError):
         errors.append('GPU-Messwerte nicht verfügbar')
-    return dict(source='Debian-Server · /proc + hwmon + nvidia-smi', sampled_at=time.time(), cpu=cpu, ram=ram, gpus=gpus, errors=errors)
+    gpu_processes=[]
+    try:
+        result=subprocess.run(['nvidia-smi','--query-compute-apps=gpu_uuid,pid,process_name,used_memory','--format=csv,noheader,nounits'],capture_output=True,text=True,timeout=4,check=True)
+        for row in csv.reader(result.stdout.splitlines(),skipinitialspace=True):
+            if len(row)==4:gpu_processes.append(dict(gpu_uuid=row[0],pid=number(row[1]),name=row[2],memory_mib=number(row[3])))
+    except (OSError,subprocess.SubprocessError):pass
+    try:load=[float(x) for x in read(PROC/'loadavg').split()[:3]]
+    except ValueError:load=[]
+    try:uptime=float(read(PROC/'uptime').split()[0])
+    except (ValueError,IndexError):uptime=None
+    try:
+        disk=shutil.disk_usage(DATA_DISK)
+        disk_data=dict(total=disk.total,used=disk.used,free=disk.free)
+    except OSError:disk_data={}
+    rx=tx=interfaces=0
+    # A bind-mounted /proc/net is a self/net symlink and would show the
+    # container namespace. PID 1 in the host proc mount has the host network.
+    host_net=PROC/'1/net/dev' if (PROC/'1/net/dev').exists() else PROC/'net/dev'
+    for line in read(host_net).splitlines()[2:]:
+        if ':' not in line:continue
+        name,raw=line.split(':',1)
+        if name.strip()=='lo':continue
+        parts=raw.split()
+        if len(parts)<9:continue
+        try:rx+=int(parts[0]);tx+=int(parts[8]);interfaces+=1
+        except ValueError:pass
+    now=time.monotonic();rates=dict(rx_bytes_per_second=None,tx_bytes_per_second=None)
+    if _network_previous and now>_network_previous[0]:
+        elapsed=now-_network_previous[0]
+        rates=dict(rx_bytes_per_second=round(max(0,rx-_network_previous[1])/elapsed,1),tx_bytes_per_second=round(max(0,tx-_network_previous[2])/elapsed,1))
+    _network_previous=(now,rx,tx)
+    return dict(source='Debian-Server · /proc + hwmon + nvidia-smi', sampled_at=time.time(), cpu={**cpu,'logical_cpus':os.cpu_count(),'load':load,'host_uptime_seconds':uptime,'disk_data':disk_data,'network':dict(interfaces=interfaces,rx_bytes=rx,tx_bytes=tx,**rates)}, ram=ram, gpus=gpus,gpu_processes=gpu_processes, errors=errors)
 
 
 if __name__ == '__main__':