include GTT memory in AMD GPU metrics (#1569)

agent/gpu_amd_linux.go

@@ -103,8 +103,17 @@ func (gm *GPUManager) updateAmdGpuData(cardPath string) bool {
 
 	// Read all sysfs values first (no lock needed - these can be slow)
 	usage, usageErr := readSysfsFloat(filepath.Join(devicePath, "gpu_busy_percent"))
-	memUsed, memUsedErr := readSysfsFloat(filepath.Join(devicePath, "mem_info_vram_used"))
+	vramUsed, memUsedErr := readSysfsFloat(filepath.Join(devicePath, "mem_info_vram_used"))
-	memTotal, _ := readSysfsFloat(filepath.Join(devicePath, "mem_info_vram_total"))
+	vramTotal, _ := readSysfsFloat(filepath.Join(devicePath, "mem_info_vram_total"))
+	memUsed := vramUsed
+	memTotal := vramTotal
+	// if gtt is present, add it to the memory used and total (https://github.com/henrygd/beszel/issues/1569#issuecomment-3837640484)
+	if gttUsed, err := readSysfsFloat(filepath.Join(devicePath, "mem_info_gtt_used")); err == nil && gttUsed > 0 {
+		if gttTotal, err := readSysfsFloat(filepath.Join(devicePath, "mem_info_gtt_total")); err == nil {
+			memUsed += gttUsed
+			memTotal += gttTotal
+		}
+	}
 
 	var temp, power float64
 	hwmons, _ := filepath.Glob(filepath.Join(devicePath, "hwmon/hwmon*"))

agent/gpu_amd_linux_test.go

@@ -119,6 +119,28 @@ func TestAmdgpuNameCacheRoundTrip(t *testing.T) {
 }
 
 func TestUpdateAmdGpuDataWithFakeSysfs(t *testing.T) {
+	tests := []struct {
+		name            string
+		writeGTT        bool
+		wantMemoryUsed  float64
+		wantMemoryTotal float64
+	}{
+		{
+			name:            "sums vram and gtt when gtt is present",
+			writeGTT:        true,
+			wantMemoryUsed:  bytesToMegabytes(1073741824 + 536870912),
+			wantMemoryTotal: bytesToMegabytes(2147483648 + 4294967296),
+		},
+		{
+			name:            "falls back to vram when gtt is missing",
+			writeGTT:        false,
+			wantMemoryUsed:  bytesToMegabytes(1073741824),
+			wantMemoryTotal: bytesToMegabytes(2147483648),
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
 			dir := t.TempDir()
 			cardPath := filepath.Join(dir, "card0")
 			devicePath := filepath.Join(cardPath, "device")
@@ -134,6 +156,10 @@ func TestUpdateAmdGpuDataWithFakeSysfs(t *testing.T) {
 			write("gpu_busy_percent", "25")
 			write("mem_info_vram_used", "1073741824")
 			write("mem_info_vram_total", "2147483648")
+			if tt.writeGTT {
+				write("mem_info_gtt_used", "536870912")
+				write("mem_info_gtt_total", "4294967296")
+			}
 			require.NoError(t, os.WriteFile(filepath.Join(hwmonPath, "temp1_input"), []byte("45000"), 0o644))
 			require.NoError(t, os.WriteFile(filepath.Join(hwmonPath, "power1_input"), []byte("20000000"), 0o644))
 
@@ -148,11 +174,13 @@ func TestUpdateAmdGpuDataWithFakeSysfs(t *testing.T) {
 			require.True(t, ok)
 			assert.Equal(t, "AMD Radeon 610M", gpu.Name)
 			assert.Equal(t, 25.0, gpu.Usage)
-	assert.Equal(t, bytesToMegabytes(1073741824), gpu.MemoryUsed)
+			assert.Equal(t, tt.wantMemoryUsed, gpu.MemoryUsed)
-	assert.Equal(t, bytesToMegabytes(2147483648), gpu.MemoryTotal)
+			assert.Equal(t, tt.wantMemoryTotal, gpu.MemoryTotal)
 			assert.Equal(t, 45.0, gpu.Temperature)
 			assert.Equal(t, 20.0, gpu.Power)
 			assert.Equal(t, 1.0, gpu.Count)
+		})
+	}
 }
 
 func TestLookupAmdgpuNameInFile(t *testing.T) {