Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 14 additions & 2 deletions cmd/fleetint/enroll.go
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@ import (
)

var (
performEnrollWorkflow = enrollment.EnrollWithConfig
performEnrollWorkflow = enrollment.EnrollWithConfigAndMetadata
fleetintEnvFilePath = config.DefaultEnvFilePath
)

Expand Down Expand Up @@ -84,6 +84,10 @@ func resolveToken(cliContext *cli.Context) (string, error) {
func enrollCommand(cliContext *cli.Context) error {
baseEndpoint := cliContext.String("endpoint")
force := cliContext.Bool("force")
metadata := &enrollment.EnrollMetadata{
NodeGroup: optionalFlagValue(cliContext, "node-group"),
ComputeZone: optionalFlagValue(cliContext, "compute-zone"),
}

sakToken, err := resolveToken(cliContext)
if err != nil {
Expand Down Expand Up @@ -117,5 +121,13 @@ func enrollCommand(cliContext *cli.Context) error {
return fmt.Errorf("failed to configure loop settings from environment variables: %w", err)
}

return performEnrollWorkflow(ctx, baseEndpoint, sakToken, cfg)
return performEnrollWorkflow(ctx, baseEndpoint, sakToken, cfg, metadata)
}

func optionalFlagValue(cliContext *cli.Context, name string) *string {
if !cliContext.IsSet(name) {
return nil
}
value := strings.TrimSpace(cliContext.String(name))
return &value
}
101 changes: 97 additions & 4 deletions cmd/fleetint/enroll_test.go
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,7 @@ import (
"github.com/stretchr/testify/require"

"github.com/NVIDIA/fleet-intelligence-agent/internal/config"
"github.com/NVIDIA/fleet-intelligence-agent/internal/enrollment"
"github.com/NVIDIA/fleet-intelligence-agent/internal/precheck"
)

Expand Down Expand Up @@ -107,8 +108,11 @@ func TestEnrollCommandBlocksOnFailedPrecheck(t *testing.T) {
},
}, nil
}
performEnrollWorkflow = func(ctx context.Context, baseEndpoint, sakToken string, cfg *config.Config) error {
performEnrollWorkflow = func(ctx context.Context, baseEndpoint, sakToken string, cfg *config.Config, metadata *enrollment.EnrollMetadata) error {
enrollmentCalled = true
require.NotNil(t, metadata)
require.Nil(t, metadata.NodeGroup)
require.Nil(t, metadata.ComputeZone)
return nil
}

Expand Down Expand Up @@ -142,8 +146,11 @@ func TestEnrollCommandForceBypassesFailedPrecheck(t *testing.T) {
},
}, nil
}
performEnrollWorkflow = func(ctx context.Context, baseEndpoint, sakToken string, cfg *config.Config) error {
performEnrollWorkflow = func(ctx context.Context, baseEndpoint, sakToken string, cfg *config.Config, metadata *enrollment.EnrollMetadata) error {
enrollmentCalled = true
require.NotNil(t, metadata)
require.Nil(t, metadata.NodeGroup)
require.Nil(t, metadata.ComputeZone)
return nil
}

Expand Down Expand Up @@ -174,11 +181,14 @@ func TestEnrollCommandPassesTimeoutContext(t *testing.T) {
}, nil
}

performEnrollWorkflow = func(ctx context.Context, baseEndpoint, sakToken string, cfg *config.Config) error {
performEnrollWorkflow = func(ctx context.Context, baseEndpoint, sakToken string, cfg *config.Config, metadata *enrollment.EnrollMetadata) error {
deadline, ok := ctx.Deadline()
require.True(t, ok)
require.LessOrEqual(t, time.Until(deadline), defaultEnrollTimeout)
require.Greater(t, time.Until(deadline), 55*time.Second)
require.NotNil(t, metadata)
require.Nil(t, metadata.NodeGroup)
require.Nil(t, metadata.ComputeZone)
return nil
}

Expand Down Expand Up @@ -217,14 +227,17 @@ FLEETINT_ATTESTATION_INTERVAL="6h"
`), 0o600))
fleetintEnvFilePath = envFilePath

performEnrollWorkflow = func(ctx context.Context, baseEndpoint, sakToken string, cfg *config.Config) error {
performEnrollWorkflow = func(ctx context.Context, baseEndpoint, sakToken string, cfg *config.Config, metadata *enrollment.EnrollMetadata) error {
require.NotNil(t, cfg)
require.NotNil(t, cfg.Inventory)
require.False(t, cfg.Inventory.Enabled)
require.Equal(t, 15*time.Minute, cfg.Inventory.Interval.Duration)
require.NotNil(t, cfg.Attestation)
require.True(t, cfg.Attestation.Enabled)
require.Equal(t, 6*time.Hour, cfg.Attestation.Interval.Duration)
require.NotNil(t, metadata)
require.Nil(t, metadata.NodeGroup)
require.Nil(t, metadata.ComputeZone)
return nil
}

Expand All @@ -234,3 +247,83 @@ FLEETINT_ATTESTATION_INTERVAL="6h"
err := app.Run([]string{"fleetint", "enroll", "--endpoint", "https://example.com", "--token", "token"})
require.NoError(t, err)
}

func TestEnrollCommandPassesOptionalMetadata(t *testing.T) {
useMissingFleetintEnvFile(t)

originalRunPrecheck := runPrecheck
originalEnrollWorkflow := performEnrollWorkflow
t.Cleanup(func() {
runPrecheck = originalRunPrecheck
performEnrollWorkflow = originalEnrollWorkflow
})

runPrecheck = func() (precheck.Result, error) {
return precheck.Result{
Checks: []precheck.Check{
{Name: "gpu-present", Message: "ok", Passed: true},
},
}, nil
}

performEnrollWorkflow = func(ctx context.Context, baseEndpoint, sakToken string, cfg *config.Config, metadata *enrollment.EnrollMetadata) error {
require.NotNil(t, metadata)
require.NotNil(t, metadata.NodeGroup)
require.Equal(t, "prod-group", *metadata.NodeGroup)
require.NotNil(t, metadata.ComputeZone)
require.Equal(t, "us-east-1c", *metadata.ComputeZone)
return nil
}

app := App()
app.Writer = &bytes.Buffer{}

err := app.Run([]string{
"fleetint", "enroll",
"--endpoint", "https://example.com",
"--token", "token",
"--node-group", "prod-group",
"--compute-zone", "us-east-1c",
})
require.NoError(t, err)
}

func TestEnrollCommandTreatsExplicitEmptyMetadataAsClear(t *testing.T) {
useMissingFleetintEnvFile(t)

originalRunPrecheck := runPrecheck
originalEnrollWorkflow := performEnrollWorkflow
t.Cleanup(func() {
runPrecheck = originalRunPrecheck
performEnrollWorkflow = originalEnrollWorkflow
})

runPrecheck = func() (precheck.Result, error) {
return precheck.Result{
Checks: []precheck.Check{
{Name: "gpu-present", Message: "ok", Passed: true},
},
}, nil
}

performEnrollWorkflow = func(ctx context.Context, baseEndpoint, sakToken string, cfg *config.Config, metadata *enrollment.EnrollMetadata) error {
require.NotNil(t, metadata)
require.NotNil(t, metadata.NodeGroup)
require.Empty(t, *metadata.NodeGroup)
require.NotNil(t, metadata.ComputeZone)
require.Empty(t, *metadata.ComputeZone)
return nil
}

app := App()
app.Writer = &bytes.Buffer{}

err := app.Run([]string{
"fleetint", "enroll",
"--endpoint", "https://example.com",
"--token", "token",
"--node-group=",
"--compute-zone=",
})
require.NoError(t, err)
}
8 changes: 8 additions & 0 deletions cmd/fleetint/root.go
Original file line number Diff line number Diff line change
Expand Up @@ -214,6 +214,14 @@ func App() *cli.App {
Name: "force",
Usage: "continue enrollment even when precheck fails",
},
&cli.StringFlag{
Name: "node-group",
Usage: "optional node group metadata associated with this node",
},
&cli.StringFlag{
Name: "compute-zone",
Usage: "optional compute zone metadata associated with this node",
},
},
},
{
Expand Down
2 changes: 2 additions & 0 deletions cmd/fleetint/unenroll.go
Original file line number Diff line number Diff line change
Expand Up @@ -71,6 +71,8 @@ func removeEnrollmentMetadata(ctx context.Context, dbRW *sql.DB) error {
agentstate.MetadataKeySAKToken,
agentstate.MetadataKeyBackendBaseURL,
agentstate.MetadataKeyEnrolledAt,
agentstate.MetadataKeyNodeGroup,
agentstate.MetadataKeyComputeZone,
"enroll_endpoint",
"metrics_endpoint",
"logs_endpoint",
Expand Down
26 changes: 16 additions & 10 deletions cmd/fleetint/unenroll_test.go
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,8 @@ import (
pkgmetadata "github.com/NVIDIA/fleet-intelligence-sdk/pkg/metadata"
"github.com/NVIDIA/fleet-intelligence-sdk/pkg/sqlite"
"github.com/stretchr/testify/require"

"github.com/NVIDIA/fleet-intelligence-agent/internal/agentstate"
)

func TestRemoveEnrollmentMetadata(t *testing.T) {
Expand All @@ -36,14 +38,16 @@ func TestRemoveEnrollmentMetadata(t *testing.T) {
require.NoError(t, pkgmetadata.CreateTableMetadata(ctx, db))

for key, value := range map[string]string{
pkgmetadata.MetadataKeyToken: "jwt-token",
"sak_token": "sak-token",
"backend_base_url": "https://backend.example.com",
"enroll_endpoint": "https://backend.example.com/api/v1/enroll",
"metrics_endpoint": "https://backend.example.com/api/v1/health/metrics",
"logs_endpoint": "https://backend.example.com/api/v1/health/logs",
"nonce_endpoint": "https://backend.example.com/api/v1/attest/nonce",
"keep_me": "still-here",
pkgmetadata.MetadataKeyToken: "jwt-token",
agentstate.MetadataKeySAKToken: "sak-token",
agentstate.MetadataKeyBackendBaseURL: "https://backend.example.com",
agentstate.MetadataKeyNodeGroup: "group-a",
agentstate.MetadataKeyComputeZone: "zone-a",
"enroll_endpoint": "https://backend.example.com/api/v1/enroll",
"metrics_endpoint": "https://backend.example.com/api/v1/health/metrics",
"logs_endpoint": "https://backend.example.com/api/v1/health/logs",
"nonce_endpoint": "https://backend.example.com/api/v1/attest/nonce",
"keep_me": "still-here",
} {
require.NoError(t, pkgmetadata.SetMetadata(ctx, db, key, value))
}
Expand All @@ -52,8 +56,10 @@ func TestRemoveEnrollmentMetadata(t *testing.T) {

for _, key := range []string{
pkgmetadata.MetadataKeyToken,
"sak_token",
"backend_base_url",
agentstate.MetadataKeySAKToken,
agentstate.MetadataKeyBackendBaseURL,
agentstate.MetadataKeyNodeGroup,
agentstate.MetadataKeyComputeZone,
"enroll_endpoint",
"metrics_endpoint",
"logs_endpoint",
Expand Down
9 changes: 8 additions & 1 deletion docs/usage.md
Original file line number Diff line number Diff line change
Expand Up @@ -128,12 +128,19 @@ One of `--token` or `--token-file` is required.

**Optional Flags:**
- `--force`: Continue enrollment even if `fleetint precheck` fails
- `--node-group`: Optional node group metadata persisted in local agent metadata
- `--compute-zone`: Optional compute zone metadata persisted in local agent metadata

Metadata update behavior for `--node-group` and `--compute-zone`:
- If the flag is omitted, the existing stored value is preserved.
- If the flag is provided, the stored value is overwritten with the provided value.
- Providing an empty value (for example `--node-group=""`) clears the stored value.

**What it does:**
1. Runs the same prerequisite validation as `fleetint precheck`
2. Validates the endpoint URL (must be HTTPS)
3. Makes an enrollment request to exchange the SAK token for a JWT token
4. Stores the JWT token and backend endpoints (metrics, logs, nonce) in the local metadata database
4. Stores the JWT token, backend endpoints (metrics, logs, nonce), and optional enrollment metadata (`node_group`, `compute_zone`) in the local metadata database
5. The stored credentials are used automatically by the agent for data export

**Example output:**
Expand Down
8 changes: 4 additions & 4 deletions go.mod
Original file line number Diff line number Diff line change
Expand Up @@ -99,12 +99,12 @@ require (
go4.org/mem v0.0.0-20220726221520-4f986261bf13 // indirect
go4.org/netipx v0.0.0-20231129151722-fdeea329fbba // indirect
golang.org/x/arch v0.22.0 // indirect
golang.org/x/crypto v0.50.0 // indirect
golang.org/x/crypto v0.52.0 // indirect
golang.org/x/exp v0.0.0-20240119083558-1b970713d09a // indirect
golang.org/x/net v0.53.0 // indirect
golang.org/x/net v0.55.0 // indirect
golang.org/x/sync v0.20.0 // indirect
golang.org/x/sys v0.43.0 // indirect
golang.org/x/text v0.36.0 // indirect
golang.org/x/sys v0.45.0 // indirect
golang.org/x/text v0.37.0 // indirect
golang.org/x/time v0.12.0 // indirect
golang.zx2c4.com/wireguard/windows v0.5.3 // indirect
google.golang.org/genproto/googleapis/rpc v0.0.0-20251202230838-ff82c1b0f217 // indirect
Expand Down
20 changes: 10 additions & 10 deletions go.sum
Original file line number Diff line number Diff line change
Expand Up @@ -248,20 +248,20 @@ golang.org/x/arch v0.22.0/go.mod h1:dNHoOeKiyja7GTvF9NJS1l3Z2yntpQNzgrjh1cU103A=
golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
golang.org/x/crypto v0.0.0-20191011191535-87dc89f01550/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
golang.org/x/crypto v0.50.0 h1:zO47/JPrL6vsNkINmLoo/PH1gcxpls50DNogFvB5ZGI=
golang.org/x/crypto v0.50.0/go.mod h1:3muZ7vA7PBCE6xgPX7nkzzjiUq87kRItoJQM1Yo8S+Q=
golang.org/x/crypto v0.52.0 h1:RMs7fP2rXdep0CftQlK8Uf+kibLm7qkCcradZWYz988=
golang.org/x/crypto v0.52.0/go.mod h1:1QgfPxDqh0T2M/elOJtp9RvuR95kVjir0e6/BvEmGbc=
golang.org/x/exp v0.0.0-20240119083558-1b970713d09a h1:Q8/wZp0KX97QFTc2ywcOE0YRjZPVIx+MXInMzdvQqcA=
golang.org/x/exp v0.0.0-20240119083558-1b970713d09a/go.mod h1:idGWGoKP1toJGkd5/ig9ZLuPcZBC3ewk7SzmH0uou08=
golang.org/x/mod v0.2.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
golang.org/x/mod v0.3.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
golang.org/x/mod v0.34.0 h1:xIHgNUUnW6sYkcM5Jleh05DvLOtwc6RitGHbDk4akRI=
golang.org/x/mod v0.34.0/go.mod h1:ykgH52iCZe79kzLLMhyCUzhMci+nQj+0XkbXpNYtVjY=
golang.org/x/mod v0.35.0 h1:Ww1D637e6Pg+Zb2KrWfHQUnH2dQRLBQyAtpr/haaJeM=
golang.org/x/mod v0.35.0/go.mod h1:+GwiRhIInF8wPm+4AoT6L0FA1QWAad3OMdTRx4tFYlU=
golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
golang.org/x/net v0.0.0-20200226121028-0de0cce0169b/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
golang.org/x/net v0.0.0-20201021035429-f5854403a974/go.mod h1:sp8m0HH+o8qH0wwXwYZr8TS3Oi6o0r6Gce1SSxlDquU=
golang.org/x/net v0.53.0 h1:d+qAbo5L0orcWAr0a9JweQpjXF19LMXJE8Ey7hwOdUA=
golang.org/x/net v0.53.0/go.mod h1:JvMuJH7rrdiCfbeHoo3fCQU24Lf5JJwT9W3sJFulfgs=
golang.org/x/net v0.55.0 h1:bcvxaJn3e1U6InsFWt1JUq1aSjnRxLzT2rtD2KfkDF8=
golang.org/x/net v0.55.0/go.mod h1:L5U2KuzuOe1lY7Z+aWVIKK6qEeJXnXV9yzGA+WCHJww=
golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.0.0-20190911185100-cd5d95a43a6e/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.0.0-20201020160332-67f06af15bc9/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
Expand All @@ -278,12 +278,12 @@ golang.org/x/sys v0.0.0-20201204225414-ed752295db88/go.mod h1:h1NjWce9XRLGQEsW7w
golang.org/x/sys v0.1.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.4.1-0.20230131160137-e7d7f63158de/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.43.0 h1:Rlag2XtaFTxp19wS8MXlJwTvoh8ArU6ezoyFsMyCTNI=
golang.org/x/sys v0.43.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw=
golang.org/x/sys v0.45.0 h1:dO4czNzziLiiXplLQgBCEpCvXQ3dnkn0SdaZSYdQ+FY=
golang.org/x/sys v0.45.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw=
golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
golang.org/x/text v0.36.0 h1:JfKh3XmcRPqZPKevfXVpI1wXPTqbkE5f7JA92a55Yxg=
golang.org/x/text v0.36.0/go.mod h1:NIdBknypM8iqVmPiuco0Dh6P5Jcdk8lJL0CUebqK164=
golang.org/x/text v0.37.0 h1:Cqjiwd9eSg8e0QAkyCaQTNHFIIzWtidPahFWR83rTrc=
golang.org/x/text v0.37.0/go.mod h1:a5sjxXGs9hsn/AJVwuElvCAo9v8QYLzvavO5z2PiM38=
golang.org/x/time v0.12.0 h1:ScB/8o8olJvc+CQPWrK3fPZNfh7qgwCrY0zJmoEQLSE=
golang.org/x/time v0.12.0/go.mod h1:CDIdPxbZBQxdj6cxyCIdrNogrJKMJ7pr37NYpMcMDSg=
golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
Expand Down
16 changes: 16 additions & 0 deletions internal/agentstate/sqlite.go
Original file line number Diff line number Diff line change
Expand Up @@ -112,6 +112,22 @@ func (s *sqliteState) SetNodeUUID(ctx context.Context, value string) error {
return s.setMetadata(ctx, pkgmetadata.MetadataKeyMachineID, value)
}

func (s *sqliteState) GetNodeGroup(ctx context.Context) (string, bool, error) {
return s.getMetadata(ctx, MetadataKeyNodeGroup)
}

func (s *sqliteState) SetNodeGroup(ctx context.Context, value string) error {
return s.setMetadata(ctx, MetadataKeyNodeGroup, value)
}

func (s *sqliteState) GetComputeZone(ctx context.Context) (string, bool, error) {
return s.getMetadata(ctx, MetadataKeyComputeZone)
}

func (s *sqliteState) SetComputeZone(ctx context.Context, value string) error {
return s.setMetadata(ctx, MetadataKeyComputeZone, value)
}

func (s *sqliteState) GetEnrollmentTime(ctx context.Context) (time.Time, bool, error) {
value, ok, err := s.getMetadata(ctx, MetadataKeyEnrolledAt)
if err != nil || !ok {
Expand Down
Loading
Loading