feat(gpud): rename/add "run --web-enable --enable-auto-update" flags

Signed-off-by: Gyuho Lee <[email protected]>

README.md

@@ -69,6 +69,8 @@ sudo gpud login --token <LEPTON_AI_TOKEN>
 
 To access the local web UI, open https://localhost:15132 in your browser.
 
+If run with `gpud up`, you may disable this local web UI by setting `FLAGS="--web-enable=false"` to the `/etc/default/gpud` environment file and restart the service.
+
 #### If your system doesn't have systemd
 
 To run on Mac (without systemd):
@@ -91,9 +93,6 @@ sudo rm /usr/sbin/gpud
 sudo rm /etc/systemd/system/gpud.service
 ```
 
-## Integration
-
-For users looking to set up a platform to collect and process data from gpud, please refer to [INTEGRATION](./docs/INTEGRATION.md).
 ## Key Features
 
 - Monitor critical GPU and GPU fabric metrics (power, temperature).
@@ -103,14 +102,22 @@ For users looking to set up a platform to collect and process data from gpud, pl
 
 Check out [*components*](./docs/COMPONENTS.md) for a detailed list of components and their features.
 
+## Integration
+
+For users looking to set up a platform to collect and process data from gpud, please refer to [INTEGRATION](./docs/INTEGRATION.md).
+
 ## FAQs
 
 ### Does GPUd send data to lepton.ai?
 
-GPUd collects a small anonymous usage signal by default to help the engineering team better understand usage frequencies. The data is strictly anonymized and **does not contain any senstive data**. You can disable this behavior by setting `GPUD_NO_USAGE_STATS=true`. If GPUd is run with systemd (default option for the `gpud up` command), you can add `GPUD_NO_USAGE_STATS=true` to the `/etc/default/gpud` environment file.
+GPUd collects a small anonymous usage signal by default to help the engineering team better understand usage frequencies. The data is strictly anonymized and **does not contain any senstive data**. You can disable this behavior by setting `GPUD_NO_USAGE_STATS=true`. If GPUd is run with systemd (default option for the `gpud up` command), you can add the line `GPUD_NO_USAGE_STATS=true` to the `/etc/default/gpud` environment file and restart the service.
 
 If you opt-in to log in to the Lepton AI platform, to assist you with more helpful GPU health states, GPUd periodically sends system runtime related information about the host to the platform. All these info are system workload and health info, and contain no user data. The data are sent via secure channels.
 
+### How to update GPUd?
+
+GPUd is still in active development, regularly releasing new versions for critical bug fixes and new features. We strongly recommend always being on the latest version of GPUd. When GPUd is registered with the Lepton platform, the platform will automatically update GPUd to the latest version. To enable auto-updates, if GPUd is run with systemd (default option for the `gpud up` command), you may add the flag `FLAGS="--enable-auto-update=false"` to the `/etc/default/gpud` environment file and restart the service.
+
 ## Learn more
 
 - [Why GPUd](./docs/WHY.md)

cmd/gpud/command/command.go

@@ -29,12 +29,12 @@ var (
 
 	retentionPeriod time.Duration
 
-	webDisable       bool
+	webEnable        bool
 	webAdmin         bool
 	webRefreshPeriod time.Duration
 
-	tailLines      int
-	disableArchive bool
+	tailLines     int
+	createArchive bool
 
 	enableAutoUpdate bool
 )
@@ -138,7 +138,7 @@ sudo rm /etc/systemd/system/gpud.service
 				},
 				&cli.BoolFlag{
 					Name:        "pprof",
-					Usage:       "enable pprof",
+					Usage:       "enable pprof (default: false)",
 					Destination: &pprof,
 				},
 				&cli.DurationFlag{
@@ -147,14 +147,14 @@ sudo rm /etc/systemd/system/gpud.service
 					Destination: &retentionPeriod,
 					Value:       config.DefaultRetentionPeriod.Duration,
 				},
-				&cli.BoolFlag{
-					Name:        "web-disable",
-					Usage:       "disable local web interface",
-					Destination: &webDisable,
+				&cli.BoolTFlag{
+					Name:        "web-enable",
+					Usage:       "enable local web interface (default: true)",
+					Destination: &webEnable,
 				},
 				&cli.BoolFlag{
 					Name:        "web-admin",
-					Usage:       "enable admin interface",
+					Usage:       "enable admin interface (default: false)",
 					Destination: &webAdmin,
 				},
 				&cli.DurationFlag{
@@ -170,7 +170,7 @@ sudo rm /etc/systemd/system/gpud.service
 				},
 				&cli.BoolTFlag{
 					Name:        "enable-auto-update",
-					Usage:       "enable auto update",
+					Usage:       "enable auto update of gpud (default: true)",
 					Destination: &enableAutoUpdate,
 				},
 			},
@@ -210,11 +210,11 @@ sudo rm /etc/systemd/system/gpud.service
 					Action: cmdReleaseGenKey,
 					Flags: []cli.Flag{
 						cli.BoolFlag{
-							Name:  "root",
+							Name:  "root (default: false)",
 							Usage: "generate root key",
 						},
 						cli.BoolFlag{
-							Name:  "signing",
+							Name:  "signing (default: false)",
 							Usage: "generate signing key",
 						},
 						cli.StringFlag{
@@ -339,10 +339,10 @@ cat summary.txt
 			Action:  cmdDiagnose,
 			Aliases: []string{"d"},
 			Flags: []cli.Flag{
-				&cli.BoolFlag{
-					Name:        "disable-archive",
-					Usage:       "disable archive of diagnose information",
-					Destination: &disableArchive,
+				&cli.BoolTFlag{
+					Name:        "create-archive (default: true)",
+					Usage:       "create .tar archive of diagnose information",
+					Destination: &createArchive,
 				},
 			},
 		},
@@ -359,7 +359,7 @@ cat summary.txt
 				},
 				&cli.BoolFlag{
 					Name:        "debug",
-					Usage:       "enable debug mode",
+					Usage:       "enable debug mode (default: false)",
 					Destination: &debug,
 				},
 			},

cmd/gpud/command/diagnose.go

@@ -18,7 +18,7 @@ func cmdDiagnose(cliContext *cli.Context) error {
 
 	ctx, cancel := context.WithTimeout(context.Background(), 2*time.Minute)
 	defer cancel()
-	err := diagnose.Run(ctx)
+	err := diagnose.Run(ctx, diagnose.WithCreateArchive(createArchive))
 	if err != nil {
 		return err
 	}

cmd/gpud/command/run.go

@@ -61,9 +61,8 @@ func cmdRun(cliContext *cli.Context) error {
 		cfg.RetentionPeriod = metav1.Duration{Duration: retentionPeriod}
 		cfg.Web.SincePeriod = metav1.Duration{Duration: retentionPeriod}
 	}
-	if webDisable {
-		cfg.Web.Enable = false
-	}
+
+	cfg.Web.Enable = webEnable
 	if webAdmin {
 		cfg.Web.Admin = true
 	}

components/diagnose/diagnose.go

@@ -20,7 +20,7 @@ import (
 )
 
 type Op struct {
-	disableArchive bool
+	createArchive bool
 }
 
 type OpOption func(*Op)
@@ -32,9 +32,9 @@ func (op *Op) applyOpts(opts []OpOption) error {
 	return nil
 }
 
-func WithDisableArchive(b bool) OpOption {
+func WithCreateArchive(b bool) OpOption {
 	return func(op *Op) {
-		op.disableArchive = b
+		op.createArchive = b
 	}
 }
 
@@ -393,7 +393,7 @@ func run(ctx context.Context, dir string, opts ...OpOption) error {
 		return err
 	}
 
-	if !op.disableArchive {
+	if op.createArchive {
 		// tar the directory into a single file
 		tarFileName := dir + ".tar"
 		if err := tarDirectory(dir, tarFileName); err != nil {

e2e/e2e_test.go

@@ -41,7 +41,7 @@ func TestGpudHealthzInfo(t *testing.T) {
 	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
 	defer cancel()
 
-	cmd := exec.CommandContext(ctx, os.Getenv("GPUD_BIN"), "run", "--log-level=debug", "--web-disable", "--annotations", fmt.Sprintf("{%q:%q}", randKey, randVal), fmt.Sprintf("--listen-address=%s", ep))
+	cmd := exec.CommandContext(ctx, os.Getenv("GPUD_BIN"), "run", "--log-level=debug", "--web-enable=false", "--enable-auto-update=false", "--annotations", fmt.Sprintf("{%q:%q}", randKey, randVal), fmt.Sprintf("--listen-address=%s", ep))
 	cmd.Stdout = os.Stdout
 	cmd.Stderr = os.Stderr