Merge branch 'master' into patch-2

.github/workflows/ci.yaml

@@ -13,7 +13,7 @@ jobs:
         run: |
           make binary-frontend-test-coverage
       - name: Upload coverage
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           name: coverage
           path: ${{ github.workspace }}/webapp/frontend/coverage/lcov.info
@@ -49,7 +49,7 @@ jobs:
         run: |
           make binary-clean binary-test-coverage
       - name: Upload coverage
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           name: coverage
           path: ${{ github.workspace }}/coverage.txt
@@ -64,7 +64,7 @@ jobs:
       - name: Checkout
         uses: actions/checkout@v2
       - name: Download coverage reports
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@v4
         with:
           name: coverage
       - name: Upload coverage reports
@@ -106,7 +106,7 @@ jobs:
         run: |
           make binary-clean binary-all
       - name: Archive
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v4
         with:
           name: binaries.zip
           path: |

.github/workflows/release.yaml

@@ -61,7 +61,7 @@ jobs:
         with:
           version_metadata_path: ${{ github.event.inputs.version_metadata_path }}
       - name: Upload workspace
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           name: workspace
           path: ${{ github.workspace }}/**/*
@@ -91,7 +91,7 @@ jobs:
           - { on: windows-latest, goos: windows,    goarch: arm64 }
     steps:
       - name: Download workspace
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@v4
         with:
           name: workspace
       - uses: actions/setup-go@v3
@@ -101,7 +101,7 @@ jobs:
         run: |
           make binary-clean binary-all
       - name: Archive
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v4
         with:
           name: binaries.zip
           path: |
@@ -114,11 +114,11 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Download workspace
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@v4
         with:
           name: workspace
       - name: Download binaries
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@v4
         with:
           name: binaries.zip
       - name: List

collector/pkg/collector/metrics.go

@@ -4,17 +4,19 @@ import (
 	"bytes"
 	"encoding/json"
 	"fmt"
+	"net/url"
+	"os"
+	"os/exec"
+	"strings"
+	"time"
+
 	"github.com/analogj/scrutiny/collector/pkg/common/shell"
 	"github.com/analogj/scrutiny/collector/pkg/config"
 	"github.com/analogj/scrutiny/collector/pkg/detect"
 	"github.com/analogj/scrutiny/collector/pkg/errors"
 	"github.com/analogj/scrutiny/collector/pkg/models"
 	"github.com/samber/lo"
 	"github.com/sirupsen/logrus"
-	"net/url"
-	"os"
-	"os/exec"
-	"strings"
 )
 
 type MetricsCollector struct {
@@ -90,8 +92,9 @@ func (mc *MetricsCollector) Run() error {
 			//go mc.Collect(&wg, device.WWN, device.DeviceName, device.DeviceType)
 			mc.Collect(device.WWN, device.DeviceName, device.DeviceType)
 
-			// TODO: we may need to sleep for between each call to smartctl -a
-			//time.Sleep(30 * time.Millisecond)
+			if mc.config.GetInt("commands.metrics_smartctl_wait") > 0 {
+				time.Sleep(time.Duration(mc.config.GetInt("commands.metrics_smartctl_wait")) * time.Second)
+			}
 		}
 
 		//mc.logger.Infoln("Main: Waiting for workers to finish")
@@ -113,7 +116,7 @@ func (mc *MetricsCollector) Validate() error {
 	return nil
 }
 
-//func (mc *MetricsCollector) Collect(wg *sync.WaitGroup, deviceWWN string, deviceName string, deviceType string) {
+// func (mc *MetricsCollector) Collect(wg *sync.WaitGroup, deviceWWN string, deviceName string, deviceType string) {
 func (mc *MetricsCollector) Collect(deviceWWN string, deviceName string, deviceType string) {
 	//defer wg.Done()
 	if len(deviceWWN) == 0 {

collector/pkg/config/config.go

@@ -20,7 +20,7 @@ import (
 type configuration struct {
 	*viper.Viper
 
-	deviceOverrides []models.ScanOverride
+	deviceOverrides    []models.ScanOverride
 }
 
 //Viper uses the following precedence order. Each item takes precedence over the item below it:
@@ -47,9 +47,12 @@ func (c *configuration) Init() error {
 	c.SetDefault("commands.metrics_scan_args", "--scan --json")
 	c.SetDefault("commands.metrics_info_args", "--info --json")
 	c.SetDefault("commands.metrics_smart_args", "--xall --json")
+	c.SetDefault("commands.metrics_smartctl_wait", 0)
 
 	//c.SetDefault("collect.short.command", "-a -o on -S on")
 
+	c.SetDefault("allow_listed_devices", []string{})
+
 	//if you want to load a non-standard location system config file (~/drawbridge.yml), use ReadConfig
 	c.SetConfigType("yaml")
 	//c.SetConfigName("drawbridge")
@@ -186,3 +189,18 @@ func (c *configuration) GetCommandMetricsSmartArgs(deviceName string) string {
 	}
 	return c.GetString("commands.metrics_smart_args")
 }
+
+func (c *configuration) IsAllowlistedDevice(deviceName string) bool {
+	allowList := c.GetStringSlice("allow_listed_devices")
+	if len(allowList) == 0 {
+		return true
+	}
+
+	for _, item := range allowList {
+		if item == deviceName {
+			return true
+		}
+	}
+
+	return false
+}

collector/pkg/config/config_test.go

@@ -144,3 +144,29 @@ func TestConfiguration_OverrideDeviceCommands_MetricsInfoArgs(t *testing.T) {
 	require.Equal(t, "--info --json", testConfig.GetCommandMetricsInfoArgs("/dev/sdb"))
 	//require.Equal(t, []models.ScanOverride{{Device: "/dev/sda", DeviceType: nil, Commands: {MetricsInfoArgs: "--info --json -T "}}}, scanOverrides)
 }
+
+func TestConfiguration_DeviceAllowList(t *testing.T) {
+	t.Parallel()
+
+	t.Run("present", func(t *testing.T) {
+		testConfig, err := config.Create()
+		require.NoError(t, err)
+
+		require.NoError(t, testConfig.ReadConfig(path.Join("testdata", "allow_listed_devices_present.yaml")))
+
+		require.True(t, testConfig.IsAllowlistedDevice("/dev/sda"), "/dev/sda should be allow listed")
+		require.False(t, testConfig.IsAllowlistedDevice("/dev/sdc"), "/dev/sda should not be allow listed")
+	})
+
+	t.Run("missing", func(t *testing.T) {
+		testConfig, err := config.Create()
+		require.NoError(t, err)
+
+		// Really just any other config where the key is full missing
+		require.NoError(t, testConfig.ReadConfig(path.Join("testdata", "override_device_commands.yaml")))
+
+		// Anything should be allow listed if the key isnt there
+		require.True(t, testConfig.IsAllowlistedDevice("/dev/sda"), "/dev/sda should be allow listed")
+		require.True(t, testConfig.IsAllowlistedDevice("/dev/sdc"), "/dev/sda should be allow listed")
+	})
+}

collector/pkg/config/interface.go

@@ -25,4 +25,6 @@ type Interface interface {
 	GetDeviceOverrides() []models.ScanOverride
 	GetCommandMetricsInfoArgs(deviceName string) string
 	GetCommandMetricsSmartArgs(deviceName string) string
+
+	IsAllowlistedDevice(deviceName string) bool
 }

collector/pkg/config/testdata/allow_listed_devices_present.yaml

@@ -0,0 +1,3 @@
+allow_listed_devices:
+- /dev/sda
+- /dev/sdb

collector/pkg/detect/detect.go

@@ -124,6 +124,11 @@ func (d *Detect) TransformDetectedDevices(detectedDeviceConns models.Scan) []mod
 
 		deviceFile := strings.ToLower(scannedDevice.Name)
 
+		// If the user has defined a device allow list, and this device isnt there, then ignore it
+		if !d.Config.IsAllowlistedDevice(deviceFile) {
+			continue
+		}
+
 		detectedDevice := models.Device{
 			HostId:     d.Config.GetString("host.id"),
 			DeviceType: scannedDevice.Type,

collector/pkg/detect/detect_test.go

@@ -24,6 +24,7 @@ func TestDetect_SmartctlScan(t *testing.T) {
 	fakeConfig.EXPECT().GetDeviceOverrides().AnyTimes().Return([]models.ScanOverride{})
 	fakeConfig.EXPECT().GetString("commands.metrics_smartctl_bin").AnyTimes().Return("smartctl")
 	fakeConfig.EXPECT().GetString("commands.metrics_scan_args").AnyTimes().Return("--scan --json")
+	fakeConfig.EXPECT().IsAllowlistedDevice(gomock.Any()).AnyTimes().Return(true)
 
 	fakeShell := mock_shell.NewMockInterface(mockCtrl)
 	testScanResults, err := os.ReadFile("testdata/smartctl_scan_simple.json")
@@ -53,6 +54,7 @@ func TestDetect_SmartctlScan_Megaraid(t *testing.T) {
 	fakeConfig.EXPECT().GetDeviceOverrides().AnyTimes().Return([]models.ScanOverride{})
 	fakeConfig.EXPECT().GetString("commands.metrics_smartctl_bin").AnyTimes().Return("smartctl")
 	fakeConfig.EXPECT().GetString("commands.metrics_scan_args").AnyTimes().Return("--scan --json")
+	fakeConfig.EXPECT().IsAllowlistedDevice(gomock.Any()).AnyTimes().Return(true)
 
 	fakeShell := mock_shell.NewMockInterface(mockCtrl)
 	testScanResults, err := os.ReadFile("testdata/smartctl_scan_megaraid.json")
@@ -85,6 +87,7 @@ func TestDetect_SmartctlScan_Nvme(t *testing.T) {
 	fakeConfig.EXPECT().GetDeviceOverrides().AnyTimes().Return([]models.ScanOverride{})
 	fakeConfig.EXPECT().GetString("commands.metrics_smartctl_bin").AnyTimes().Return("smartctl")
 	fakeConfig.EXPECT().GetString("commands.metrics_scan_args").AnyTimes().Return("--scan --json")
+	fakeConfig.EXPECT().IsAllowlistedDevice(gomock.Any()).AnyTimes().Return(true)
 
 	fakeShell := mock_shell.NewMockInterface(mockCtrl)
 	testScanResults, err := os.ReadFile("testdata/smartctl_scan_nvme.json")
@@ -116,6 +119,7 @@ func TestDetect_TransformDetectedDevices_Empty(t *testing.T) {
 	fakeConfig.EXPECT().GetDeviceOverrides().AnyTimes().Return([]models.ScanOverride{})
 	fakeConfig.EXPECT().GetString("commands.metrics_smartctl_bin").AnyTimes().Return("smartctl")
 	fakeConfig.EXPECT().GetString("commands.metrics_scan_args").AnyTimes().Return("--scan --json")
+	fakeConfig.EXPECT().IsAllowlistedDevice(gomock.Any()).AnyTimes().Return(true)
 
 	detectedDevices := models.Scan{
 		Devices: []models.ScanDevice{
@@ -149,6 +153,7 @@ func TestDetect_TransformDetectedDevices_Ignore(t *testing.T) {
 	fakeConfig.EXPECT().GetDeviceOverrides().AnyTimes().Return([]models.ScanOverride{{Device: "/dev/sda", DeviceType: nil, Ignore: true}})
 	fakeConfig.EXPECT().GetString("commands.metrics_smartctl_bin").AnyTimes().Return("smartctl")
 	fakeConfig.EXPECT().GetString("commands.metrics_scan_args").AnyTimes().Return("--scan --json")
+	fakeConfig.EXPECT().IsAllowlistedDevice(gomock.Any()).AnyTimes().Return(true)
 
 	detectedDevices := models.Scan{
 		Devices: []models.ScanDevice{
@@ -180,6 +185,7 @@ func TestDetect_TransformDetectedDevices_Raid(t *testing.T) {
 	fakeConfig.EXPECT().GetString("host.id").AnyTimes().Return("")
 	fakeConfig.EXPECT().GetString("commands.metrics_smartctl_bin").AnyTimes().Return("smartctl")
 	fakeConfig.EXPECT().GetString("commands.metrics_scan_args").AnyTimes().Return("--scan --json")
+	fakeConfig.EXPECT().IsAllowlistedDevice(gomock.Any()).AnyTimes().Return(true)
 	fakeConfig.EXPECT().GetDeviceOverrides().AnyTimes().Return([]models.ScanOverride{
 		{
 			Device:     "/dev/bus/0",
@@ -223,6 +229,7 @@ func TestDetect_TransformDetectedDevices_Simple(t *testing.T) {
 	fakeConfig.EXPECT().GetString("commands.metrics_smartctl_bin").AnyTimes().Return("smartctl")
 	fakeConfig.EXPECT().GetString("commands.metrics_scan_args").AnyTimes().Return("--scan --json")
 	fakeConfig.EXPECT().GetDeviceOverrides().AnyTimes().Return([]models.ScanOverride{{Device: "/dev/sda", DeviceType: []string{"sat+megaraid"}}})
+	fakeConfig.EXPECT().IsAllowlistedDevice(gomock.Any()).AnyTimes().Return(true)
 	detectedDevices := models.Scan{
 		Devices: []models.ScanDevice{
 			{
@@ -256,6 +263,7 @@ func TestDetect_TransformDetectedDevices_WithoutDeviceTypeOverride(t *testing.T)
 	fakeConfig.EXPECT().GetString("commands.metrics_smartctl_bin").AnyTimes().Return("smartctl")
 	fakeConfig.EXPECT().GetString("commands.metrics_scan_args").AnyTimes().Return("--scan --json")
 	fakeConfig.EXPECT().GetDeviceOverrides().AnyTimes().Return([]models.ScanOverride{{Device: "/dev/sda"}})
+	fakeConfig.EXPECT().IsAllowlistedDevice(gomock.Any()).AnyTimes().Return(true)
 	detectedDevices := models.Scan{
 		Devices: []models.ScanDevice{
 			{
@@ -302,6 +310,46 @@ func TestDetect_TransformDetectedDevices_WhenDeviceNotDetected(t *testing.T) {
 	require.Equal(t, "ata", transformedDevices[0].DeviceType)
 }
 
+func TestDetect_TransformDetectedDevices_AllowListFilters(t *testing.T) {
+	mockCtrl := gomock.NewController(t)
+	defer mockCtrl.Finish()
+
+	fakeConfig := mock_config.NewMockInterface(mockCtrl)
+	fakeConfig.EXPECT().GetString("host.id").AnyTimes().Return("")
+	fakeConfig.EXPECT().GetString("commands.metrics_smartctl_bin").AnyTimes().Return("smartctl")
+	fakeConfig.EXPECT().GetString("commands.metrics_scan_args").AnyTimes().Return("--scan --json")
+	fakeConfig.EXPECT().GetDeviceOverrides().AnyTimes().Return([]models.ScanOverride{{Device: "/dev/sda", DeviceType: []string{"sat+megaraid"}}})
+	fakeConfig.EXPECT().IsAllowlistedDevice("/dev/sda").Return(true)
+	fakeConfig.EXPECT().IsAllowlistedDevice("/dev/sdb").Return(false)
+	detectedDevices := models.Scan{
+		Devices: []models.ScanDevice{
+			{
+				Name:     "/dev/sda",
+				InfoName: "/dev/sda",
+				Protocol: "ata",
+				Type:     "ata",
+			},
+			{
+				Name:     "/dev/sdb",
+				InfoName: "/dev/sdb",
+				Protocol: "ata",
+				Type:     "ata",
+			},
+		},
+	}
+
+	d := detect.Detect{
+		Config: fakeConfig,
+	}
+
+	// test
+	transformedDevices := d.TransformDetectedDevices(detectedDevices)
+
+	// assert
+	require.Equal(t, 1, len(transformedDevices))
+	require.Equal(t, "sda", transformedDevices[0].DeviceName)
+}
+
 func TestDetect_SmartCtlInfo(t *testing.T) {
 	t.Run("should report nvme info", func(t *testing.T) {
 		ctrl := gomock.NewController(t)

docker/example.hubspoke.docker-compose.yml

@@ -41,6 +41,9 @@ services:
     environment:
       COLLECTOR_API_ENDPOINT: 'http://web:8080'
       COLLECTOR_HOST_ID: 'scrutiny-collector-hostname'
+      # If true forces the collector to run on startup (cron will be started after the collector completes)
+      # see: https://github.com/AnalogJ/scrutiny/blob/master/docs/TROUBLESHOOTING_DEVICE_COLLECTOR.md#collector-trigger-on-startup
+      COLLECTOR_RUN_STARTUP: false
     depends_on:
       web:
         condition: service_healthy

docs/TESTERS.md

@@ -8,7 +8,7 @@ Thankfully the following users have been gracious enough to test/validate Scruti
 
 | Architecture Name | Binaries | Docker |
 | --- | --- | --- |
-| linux-amd64 | -- | @feroxy @rshxyz |
+| linux-amd64 | @TizzAmmazz | @feroxy @rshxyz |
 | linux-arm-5 | -- |  |
 | linux-arm-6 | -- |  |
 | linux-arm-7 | @Zorlin | @martini1992  |
@@ -17,4 +17,4 @@ Thankfully the following users have been gracious enough to test/validate Scruti
 | macos-amd64 | -- | -- |
 | macos-arm64 | -- | -- |
 | windows-amd64 | @gabrielv33 | -- |
-| windows-arm64 | -- | -- |
+| windows-arm64 | -- | -- |

docs/TROUBLESHOOTING_DOCKER.md

@@ -17,3 +17,11 @@ So changing from `master-omnibus -> latest` will be the same thing for all inten
 > NOTE: Previously, there was a `automated cron build` that ran on the `master` and `beta` branches. 
 They used to trigger a `nightly` build, even if nothing has changed on the branch. This has a couple of benefits, but one is to 
 ensure that there's no broken external dependencies in our (unchanged) code. This `nightly` build no longer updates the `master-omnibus` tag. 
+
+# Running Docker `rootless`
+
+To avoid that the container(s) restart when you installed Docker as `rootless` you need to isssue the following commands to allow the session to stay alive even after you close your (SSH) sesssion:
+
+`sudo loginctl enable-linger $(whoami)`
+
+`systemctl --user enable docker`