mirror of
https://github.com/netbirdio/netbird.git
synced 2026-10-10 07:29:06 +02:00
[management] Rework Agent Network endpoint identity and settings bootstrap (#7085)
Store the per-account gateway endpoint as {domain, proxy_address} with a
global unique index on the full hostname; dedicated = (domain ==
proxy_address). Bootstrap becomes an explicit POST carrying exactly one
of proxy_address (server allocates an adjective-noun label beneath it)
or endpoint (claimed verbatim, address-first); provider create loses its
bootstrap side effect. PUT is a full replace with every field required —
the immutable identity fields must be echoed unchanged and a mismatch is
rejected with 422. A guarded DELETE releases the endpoint: refused with
412 while providers exist or a proxy is actively serving the endpoint
hostname (matched case-insensitively); re-creating bootstraps fresh. A
self-addressed pin excludes its address from the account's cluster allow
list, and the live mapping update path now addresses the serving proxy
from the synthesized service. Existing rows are migrated on all three
store engines.
This commit is contained in:
@@ -22,7 +22,6 @@ import (
|
||||
"github.com/netbirdio/netbird/management/server/permissions/modules"
|
||||
"github.com/netbirdio/netbird/management/server/permissions/operations"
|
||||
"github.com/netbirdio/netbird/management/server/store"
|
||||
"github.com/netbirdio/netbird/shared/management/proto"
|
||||
"github.com/netbirdio/netbird/shared/management/status"
|
||||
)
|
||||
|
||||
@@ -48,7 +47,7 @@ func ensureSessionKeys(p *types.Provider) error {
|
||||
type Manager interface {
|
||||
GetAllProviders(ctx context.Context, accountID, userID string) ([]*types.Provider, error)
|
||||
GetProvider(ctx context.Context, accountID, userID, providerID string) (*types.Provider, error)
|
||||
CreateProvider(ctx context.Context, userID string, provider *types.Provider, bootstrapCluster string) (*types.Provider, error)
|
||||
CreateProvider(ctx context.Context, userID string, provider *types.Provider) (*types.Provider, error)
|
||||
UpdateProvider(ctx context.Context, userID string, provider *types.Provider) (*types.Provider, error)
|
||||
DeleteProvider(ctx context.Context, accountID, userID, providerID string) error
|
||||
|
||||
@@ -71,7 +70,9 @@ type Manager interface {
|
||||
DeleteBudgetRule(ctx context.Context, accountID, userID, ruleID string) error
|
||||
|
||||
GetSettings(ctx context.Context, accountID, userID string) (*types.Settings, error)
|
||||
CreateSettings(ctx context.Context, userID string, settings *types.Settings, proxyAddress, endpoint string) (*types.Settings, error)
|
||||
UpdateSettings(ctx context.Context, userID string, settings *types.Settings) (*types.Settings, error)
|
||||
DeleteSettings(ctx context.Context, accountID, userID string) error
|
||||
|
||||
ListConsumption(ctx context.Context, accountID, userID string) ([]*types.Consumption, error)
|
||||
ListAccessLogs(ctx context.Context, accountID, userID string, filter types.AgentNetworkAccessLogFilter) ([]*types.AgentNetworkAccessLog, int64, error)
|
||||
@@ -123,11 +124,10 @@ type managerImpl struct {
|
||||
proxyController proxy.Controller
|
||||
|
||||
// reconcileCache holds the last set of synthesised proxy mappings
|
||||
// per account so reconcile can emit precise Create/Update/Delete
|
||||
// updates instead of a full re-push on every mutation. Keyed by
|
||||
// accountID, then by synthesised service ID.
|
||||
// per account, each paired with the proxy that served it, so a change
|
||||
// of serving proxy can be diffed without re-deriving it.
|
||||
reconcileMu sync.Mutex
|
||||
reconcileCache map[string]map[string]*proto.ProxyMapping
|
||||
reconcileCache map[string]map[string]syntheticMapping
|
||||
|
||||
// labelRngMu guards labelRng. PickUnique consumes math/rand.Source
|
||||
// state; concurrent provider creates would otherwise race.
|
||||
@@ -151,7 +151,7 @@ func NewManager(
|
||||
accountManager: accountManager,
|
||||
permissionsManager: permissionsManager,
|
||||
proxyController: proxyController,
|
||||
reconcileCache: make(map[string]map[string]*proto.ProxyMapping),
|
||||
reconcileCache: make(map[string]map[string]syntheticMapping),
|
||||
labelRng: rand.New(rand.NewSource(time.Now().UnixNano())),
|
||||
}
|
||||
}
|
||||
@@ -170,19 +170,14 @@ func (m *managerImpl) GetProvider(ctx context.Context, accountID, userID, provid
|
||||
return m.store.GetAgentNetworkProviderByID(ctx, store.LockingStrengthNone, accountID, providerID)
|
||||
}
|
||||
|
||||
// CreateProvider persists a new provider for the account. bootstrapCluster
|
||||
// is used only when the per-account agent-network Settings row hasn't
|
||||
// been created yet; otherwise it is ignored (the cluster is pinned on
|
||||
// Settings and every provider in the account routes through it).
|
||||
func (m *managerImpl) CreateProvider(ctx context.Context, userID string, provider *types.Provider, bootstrapCluster string) (*types.Provider, error) {
|
||||
// CreateProvider persists a new provider for the account. Providers have no
|
||||
// settings side effects: the account's endpoint is bootstrapped separately and
|
||||
// explicitly via CreateSettings, and every provider in the account routes
|
||||
// through it.
|
||||
func (m *managerImpl) CreateProvider(ctx context.Context, userID string, provider *types.Provider) (*types.Provider, error) {
|
||||
if err := m.requirePermission(ctx, provider.AccountID, userID, modules.AgentNetworkProviders, operations.Create); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if strings.TrimSpace(bootstrapCluster) != "" {
|
||||
if err := m.requireSettingsBootstrapPermission(ctx, provider.AccountID, userID); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
}
|
||||
|
||||
// An empty api_key would silently produce a synthesised service
|
||||
// that 401s on every upstream request. Surface the misconfiguration
|
||||
@@ -206,16 +201,6 @@ func (m *managerImpl) CreateProvider(ctx context.Context, userID string, provide
|
||||
return nil, fmt.Errorf("save agent network provider: %w", err)
|
||||
}
|
||||
|
||||
if strings.TrimSpace(bootstrapCluster) != "" {
|
||||
if _, err := m.bootstrapSettingsIfNeeded(ctx, m.store, provider.AccountID, bootstrapCluster); err != nil {
|
||||
// The provider create has already succeeded; logging the
|
||||
// bootstrap miss matches the plan's PoC behaviour. The synth
|
||||
// path treats a missing settings row as a no-op, and the next
|
||||
// provider create retries the bootstrap.
|
||||
log.WithContext(ctx).Debugf("agent-network bootstrap settings for account %s on cluster %s: %v", provider.AccountID, bootstrapCluster, err)
|
||||
}
|
||||
}
|
||||
|
||||
m.accountManager.StoreEvent(ctx, userID, provider.ID, provider.AccountID, activity.AgentNetworkProviderCreated, provider.EventMeta())
|
||||
m.reconcile(ctx, provider.AccountID)
|
||||
|
||||
@@ -560,52 +545,44 @@ func (m *managerImpl) DeleteBudgetRule(ctx context.Context, accountID, userID, r
|
||||
}
|
||||
|
||||
// UpdateSettings replaces the mutable account-level settings — the collection
|
||||
// toggles and retention — on the account's row. When the account has no
|
||||
// settings row yet, a non-empty settings.Cluster bootstraps one (same path as
|
||||
// first provider create); without it the update fails with NotFound. On an
|
||||
// existing row the cluster and subdomain are immutable: a differing
|
||||
// settings.Cluster is rejected rather than silently ignored so callers never
|
||||
// observe a value other than what they sent. Because the collection toggles
|
||||
// change the synthesised service config (prompt-capture gating, access-log
|
||||
// emission), a reconcile is triggered so the proxy and peer network maps
|
||||
// converge on the new state.
|
||||
// toggles and retention — on the account's row. The identity fields (Domain,
|
||||
// ProxyAddress) are assigned at bootstrap (CreateSettings) and immutable: the
|
||||
// request carries them, matching the PUT convention of every other endpoint,
|
||||
// but they are only compared against the stored row — a request carrying
|
||||
// different values is rejected, and the stored values are never overwritten.
|
||||
// When the account has no settings row yet the update fails with NotFound.
|
||||
// Because the collection toggles change the synthesised service config
|
||||
// (prompt-capture gating, access-log emission), a reconcile is triggered so
|
||||
// the proxy and peer network maps converge on the new state.
|
||||
func (m *managerImpl) UpdateSettings(ctx context.Context, userID string, settings *types.Settings) (*types.Settings, error) {
|
||||
if err := m.requirePermission(ctx, settings.AccountID, userID, modules.AgentNetworkSettings, operations.Update); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
requestedCluster := strings.TrimSpace(settings.Cluster)
|
||||
|
||||
// The row lock from LockingStrengthUpdate only holds for the duration of
|
||||
// the surrounding transaction, so the read, the cluster-immutability
|
||||
// check, and the save must share one — otherwise concurrent PUTs could
|
||||
// interleave between them.
|
||||
// the surrounding transaction, so the read and the save must share one —
|
||||
// otherwise concurrent PUTs could interleave between them.
|
||||
var updated *types.Settings
|
||||
err := m.store.ExecuteInTransaction(ctx, func(tx store.Store) error {
|
||||
existing, err := tx.GetAgentNetworkSettings(ctx, store.LockingStrengthUpdate, settings.AccountID)
|
||||
switch {
|
||||
case err == nil:
|
||||
if requestedCluster != "" && requestedCluster != existing.Cluster {
|
||||
return status.Errorf(status.InvalidArgument, "cluster is immutable once assigned (current: %s)", existing.Cluster)
|
||||
}
|
||||
case isNotFound(err):
|
||||
if requestedCluster == "" {
|
||||
return status.Errorf(status.NotFound, "agent network settings have not been bootstrapped yet; pass cluster to bootstrap them, or create a provider with bootstrap_cluster set")
|
||||
}
|
||||
// Bootstrapping pins the cluster and subdomain — a settings
|
||||
// create on top of the update the caller already passed, matching
|
||||
// the gate on the provider-create bootstrap path.
|
||||
if err := m.requirePermission(ctx, settings.AccountID, userID, modules.AgentNetworkSettings, operations.Create); err != nil {
|
||||
return err
|
||||
}
|
||||
existing, err = m.bootstrapSettingsIfNeeded(ctx, tx, settings.AccountID, requestedCluster)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
return status.Errorf(status.NotFound, "agent network settings have not been bootstrapped yet; POST /api/agent-network/settings to bootstrap them")
|
||||
default:
|
||||
return fmt.Errorf("get agent network settings: %w", err)
|
||||
}
|
||||
|
||||
// The identity echo is compared leniently (trimmed, case-insensitive):
|
||||
// the stored values are normalized lowercase, and a client replaying a
|
||||
// GET response must never be rejected over casing it didn't choose.
|
||||
if !hostnamesEquivalent(settings.Domain, existing.Domain) {
|
||||
return status.Errorf(status.InvalidArgument, "endpoint is immutable: it must match the assigned endpoint %q; delete the settings to release it and bootstrap again", existing.Domain)
|
||||
}
|
||||
if !hostnamesEquivalent(settings.ProxyAddress, existing.ProxyAddress) {
|
||||
return status.Errorf(status.InvalidArgument, "proxy_address is immutable: it must match the assigned proxy address %q; delete the settings to release it and bootstrap again", existing.ProxyAddress)
|
||||
}
|
||||
|
||||
existing.EnableLogCollection = settings.EnableLogCollection
|
||||
existing.EnablePromptCollection = settings.EnablePromptCollection
|
||||
existing.RedactPii = settings.RedactPii
|
||||
@@ -632,6 +609,83 @@ func (m *managerImpl) UpdateSettings(ctx context.Context, userID string, setting
|
||||
return updated, nil
|
||||
}
|
||||
|
||||
// hostnamesEquivalent reports whether a caller-supplied hostname names the
|
||||
// same host as a stored (normalized, lowercase) one: equal after trimming and
|
||||
// case folding. No structural validation — an arbitrary mismatch and a
|
||||
// malformed value are both simply "not the assigned value".
|
||||
func hostnamesEquivalent(supplied, stored string) bool {
|
||||
return strings.EqualFold(strings.TrimSpace(supplied), stored)
|
||||
}
|
||||
|
||||
// DeleteSettings removes the account's settings row, releasing the endpoint.
|
||||
// Two guards make this a bootstrap-repair operation rather than a way to tear
|
||||
// down a serving gateway, both re-checked under the row lock:
|
||||
//
|
||||
// - No Agent Network providers may exist for the account. Providers route
|
||||
// through the endpoint; delete them first.
|
||||
// - No proxy may be actively serving the endpoint — that is, no active proxy
|
||||
// declares the endpoint hostname as its cluster address. This is the
|
||||
// dedicated (self-addressed) shape's guard: the proxy at the address IS
|
||||
// this account's gateway. A labeled endpoint hangs beneath a shared
|
||||
// cluster's address, and with the account's providers already gone the
|
||||
// shared proxy serves nothing of the account's, so the parent cluster
|
||||
// being up does not block the delete.
|
||||
//
|
||||
// Bootstrapping again after a delete allocates fresh — the released hostname
|
||||
// is not reserved. That full-reset semantic is what gives clients that model
|
||||
// immutability as replace-on-change (e.g. Terraform's RequiresReplace) a real
|
||||
// path: tear down providers, delete, re-create.
|
||||
func (m *managerImpl) DeleteSettings(ctx context.Context, accountID, userID string) error {
|
||||
if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkSettings, operations.Delete); err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
var deleted *types.Settings
|
||||
err := m.store.ExecuteInTransaction(ctx, func(tx store.Store) error {
|
||||
existing, err := tx.GetAgentNetworkSettings(ctx, store.LockingStrengthUpdate, accountID)
|
||||
switch {
|
||||
case err == nil:
|
||||
case isNotFound(err):
|
||||
return status.Errorf(status.NotFound, "agent network settings have not been bootstrapped yet; there is nothing to delete")
|
||||
default:
|
||||
return fmt.Errorf("get agent network settings: %w", err)
|
||||
}
|
||||
|
||||
providers, err := tx.GetAccountAgentNetworkProviders(ctx, store.LockingStrengthNone, accountID)
|
||||
if err != nil {
|
||||
return fmt.Errorf("get agent network providers: %w", err)
|
||||
}
|
||||
if len(providers) > 0 {
|
||||
return status.Errorf(status.PreconditionFailed, "agent network settings cannot be deleted while %d provider(s) exist; delete the providers first", len(providers))
|
||||
}
|
||||
|
||||
serving, err := tx.HasActiveProxyAtClusterAddress(ctx, existing.Domain)
|
||||
if err != nil {
|
||||
return fmt.Errorf("check for a proxy serving the endpoint: %w", err)
|
||||
}
|
||||
if serving {
|
||||
return status.Errorf(status.PreconditionFailed, "agent network settings cannot be deleted while a proxy is actively serving the endpoint %q", existing.Domain)
|
||||
}
|
||||
|
||||
if err := tx.DeleteAgentNetworkSettings(ctx, accountID); err != nil {
|
||||
return fmt.Errorf("delete agent network settings: %w", err)
|
||||
}
|
||||
deleted = existing
|
||||
return nil
|
||||
})
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
m.accountManager.StoreEvent(ctx, userID, accountID, accountID, activity.AgentNetworkSettingsDeleted, map[string]any{
|
||||
"endpoint": deleted.Domain,
|
||||
"proxy_address": deleted.ProxyAddress,
|
||||
})
|
||||
m.reconcile(ctx, accountID)
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
// isNotFound reports whether err is a status.NotFound error.
|
||||
func isNotFound(err error) bool {
|
||||
var sErr *status.Error
|
||||
@@ -678,74 +732,162 @@ func (m *managerImpl) GetSettings(ctx context.Context, accountID, userID string)
|
||||
}
|
||||
}
|
||||
|
||||
// requireSettingsBootstrapPermission gates the one-time settings bootstrap a
|
||||
// first provider create performs. Pinning the account's cluster and subdomain
|
||||
// is a settings write, so it needs the settings permission on top of the
|
||||
// provider one. No-op once the settings row exists.
|
||||
func (m *managerImpl) requireSettingsBootstrapPermission(ctx context.Context, accountID, userID string) error {
|
||||
_, err := m.store.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, accountID)
|
||||
if err == nil {
|
||||
return nil
|
||||
}
|
||||
if !isNotFound(err) {
|
||||
return fmt.Errorf("get agent network settings: %w", err)
|
||||
}
|
||||
return m.requirePermission(ctx, accountID, userID, modules.AgentNetworkSettings, operations.Create)
|
||||
}
|
||||
// maxDomainAllocationAttempts bounds the label search when bootstrapping a
|
||||
// labeled endpoint. Package-level (rather than function-local) so tests can
|
||||
// assert on the exhaustion path without duplicating the literal.
|
||||
const maxDomainAllocationAttempts = 10
|
||||
|
||||
// bootstrapSettingsIfNeeded creates the per-account agent-network
|
||||
// settings row when missing. The cluster comes from the create-time
|
||||
// hint the dashboard sends (auto-picked from the active cluster list);
|
||||
// the subdomain is picked from the curated wordlist avoiding
|
||||
// collisions on the same cluster. Idempotent: if a row already exists
|
||||
// it is returned untouched and the hint is ignored. st is the store to
|
||||
// operate on — pass the transaction store when calling from within one.
|
||||
func (m *managerImpl) bootstrapSettingsIfNeeded(ctx context.Context, st store.Store, accountID, providerCluster string) (*types.Settings, error) {
|
||||
if accountID == "" {
|
||||
return nil, fmt.Errorf("bootstrap settings: account id is required")
|
||||
// CreateSettings bootstraps the per-account settings row, assigning the
|
||||
// account's immutable endpoint. Exactly one of proxyAddress and endpoint must
|
||||
// be non-empty: proxyAddress allocates a labeled endpoint one label beneath
|
||||
// the given cluster address; endpoint claims the given hostname verbatim as a
|
||||
// self-addressed (dedicated) endpoint — a legitimate claim before any proxy
|
||||
// declares the address (address-first). settings carries the account ID and
|
||||
// the initial collection toggles; its identity fields are assigned here.
|
||||
func (m *managerImpl) CreateSettings(ctx context.Context, userID string, settings *types.Settings, proxyAddress, endpoint string) (*types.Settings, error) {
|
||||
if settings == nil || settings.AccountID == "" {
|
||||
return nil, status.Errorf(status.InvalidArgument, "account id is required")
|
||||
}
|
||||
if strings.TrimSpace(providerCluster) == "" {
|
||||
return nil, fmt.Errorf("bootstrap settings: provider cluster is required")
|
||||
if err := m.requirePermission(ctx, settings.AccountID, userID, modules.AgentNetworkSettings, operations.Create); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
existing, err := st.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, accountID)
|
||||
if err == nil {
|
||||
return existing, nil
|
||||
hasProxyAddress := strings.TrimSpace(proxyAddress) != ""
|
||||
hasEndpoint := strings.TrimSpace(endpoint) != ""
|
||||
if hasProxyAddress == hasEndpoint {
|
||||
return nil, status.Errorf(status.InvalidArgument, "exactly one of proxy_address and endpoint is required")
|
||||
}
|
||||
if !isNotFound(err) {
|
||||
|
||||
// Fail fast on an existing row for a clean 409; the insert below stays
|
||||
// the authority against concurrent bootstraps (the primary key wins).
|
||||
if _, err := m.store.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, settings.AccountID); err == nil {
|
||||
return nil, status.Errorf(status.AlreadyExists, "agent network settings already bootstrapped for account %s", settings.AccountID)
|
||||
} else if !isNotFound(err) {
|
||||
return nil, fmt.Errorf("get agent network settings: %w", err)
|
||||
}
|
||||
|
||||
siblings, err := st.GetAgentNetworkSettingsByCluster(ctx, store.LockingStrengthNone, providerCluster)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("list agent network settings on cluster: %w", err)
|
||||
}
|
||||
taken := make(map[string]struct{}, len(siblings))
|
||||
for _, s := range siblings {
|
||||
taken[s.Subdomain] = struct{}{}
|
||||
}
|
||||
|
||||
suffix := accountID
|
||||
if len(suffix) > 4 {
|
||||
suffix = suffix[:4]
|
||||
}
|
||||
|
||||
m.labelRngMu.Lock()
|
||||
subdomain := labelgen.PickUnique(m.labelRng, taken, suffix)
|
||||
m.labelRngMu.Unlock()
|
||||
|
||||
now := time.Now().UTC()
|
||||
settings := types.DefaultSettings(accountID)
|
||||
settings.Cluster = providerCluster
|
||||
settings.Subdomain = subdomain
|
||||
settings.CreatedAt = now
|
||||
settings.UpdatedAt = now
|
||||
if err := st.SaveAgentNetworkSettings(ctx, settings); err != nil {
|
||||
return nil, fmt.Errorf("save agent network settings: %w", err)
|
||||
|
||||
var err error
|
||||
if hasEndpoint {
|
||||
err = m.bootstrapSelfAddressed(ctx, settings, endpoint)
|
||||
} else {
|
||||
err = m.bootstrapLabeled(ctx, settings, proxyAddress)
|
||||
}
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
m.accountManager.StoreEvent(ctx, userID, settings.AccountID, settings.AccountID, activity.AgentNetworkSettingsUpdated, map[string]any{
|
||||
"bootstrapped": true,
|
||||
"endpoint": settings.Domain,
|
||||
"dedicated": settings.Dedicated(),
|
||||
})
|
||||
m.reconcile(ctx, settings.AccountID)
|
||||
|
||||
return settings, nil
|
||||
}
|
||||
|
||||
// bootstrapSelfAddressed claims the given hostname as the account's endpoint,
|
||||
// served only by a proxy declaring exactly that address (Domain ==
|
||||
// ProxyAddress). The domain unique index is the arbiter of availability.
|
||||
func (m *managerImpl) bootstrapSelfAddressed(ctx context.Context, settings *types.Settings, endpoint string) error {
|
||||
hostname, err := types.NormalizeHostname(endpoint)
|
||||
if err != nil {
|
||||
return status.Errorf(status.InvalidArgument, "invalid endpoint: %s", err)
|
||||
}
|
||||
|
||||
settings.Domain = hostname
|
||||
settings.ProxyAddress = hostname
|
||||
if err := m.store.CreateAgentNetworkSettings(ctx, settings); err != nil {
|
||||
if isUniqueConstraintError(err) {
|
||||
// The violation is either the account primary key (a concurrent
|
||||
// bootstrap for the same account won) or the domain index
|
||||
// (another account holds the hostname). Distinguish by re-read.
|
||||
if _, getErr := m.store.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, settings.AccountID); getErr == nil {
|
||||
return status.Errorf(status.AlreadyExists, "agent network settings already bootstrapped for account %s", settings.AccountID)
|
||||
}
|
||||
return status.Errorf(status.AlreadyExists, "endpoint %s is already taken", hostname)
|
||||
}
|
||||
return fmt.Errorf("create agent network settings: %w", err)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// bootstrapLabeled allocates a labeled endpoint one label beneath the given
|
||||
// cluster address: Domain = <label>.<proxyAddress>, served by whichever proxy
|
||||
// declares the parent. Labels are adjective-noun tuples; a candidate is
|
||||
// checked by read and the domain unique index stays the authority, so a
|
||||
// concurrent allocation of the same tuple surfaces as a unique violation and
|
||||
// another tuple is drawn.
|
||||
func (m *managerImpl) bootstrapLabeled(ctx context.Context, settings *types.Settings, proxyAddress string) error {
|
||||
parent, err := types.NormalizeHostname(proxyAddress)
|
||||
if err != nil {
|
||||
return status.Errorf(status.InvalidArgument, "invalid proxy_address: %s", err)
|
||||
}
|
||||
|
||||
for attempt := 1; attempt <= maxDomainAllocationAttempts; attempt++ {
|
||||
m.labelRngMu.Lock()
|
||||
label := labelgen.PickTuple(m.labelRng)
|
||||
m.labelRngMu.Unlock()
|
||||
if label == "" {
|
||||
// Only reachable if either word pool were emptied. An empty label
|
||||
// would produce a broken endpoint like ".example.com", so fail
|
||||
// loudly rather than looping or inserting.
|
||||
return fmt.Errorf("allocate agent network endpoint for account %s: label generator returned an empty label", settings.AccountID)
|
||||
}
|
||||
|
||||
candidate, err := types.NormalizeHostname(label + "." + parent)
|
||||
if err != nil {
|
||||
return status.Errorf(status.InvalidArgument, "proxy_address leaves no room for a label: %s", err)
|
||||
}
|
||||
|
||||
_, err = m.store.GetAgentNetworkSettingsByDomain(ctx, store.LockingStrengthNone, candidate)
|
||||
if err == nil {
|
||||
log.WithContext(ctx).Tracef("agent-network endpoint %q taken, retrying (attempt %d/%d)", candidate, attempt, maxDomainAllocationAttempts)
|
||||
continue
|
||||
}
|
||||
if !isNotFound(err) {
|
||||
return fmt.Errorf("check agent network endpoint availability: %w", err)
|
||||
}
|
||||
|
||||
settings.Domain = candidate
|
||||
settings.ProxyAddress = parent
|
||||
if err := m.store.CreateAgentNetworkSettings(ctx, settings); err != nil {
|
||||
if isUniqueConstraintError(err) {
|
||||
// A concurrent bootstrap for the same account may have won on
|
||||
// the primary key — return the conflict. A lost race on the
|
||||
// domain index just means the tuple was taken between the
|
||||
// read and the insert: draw another.
|
||||
if _, getErr := m.store.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, settings.AccountID); getErr == nil {
|
||||
return status.Errorf(status.AlreadyExists, "agent network settings already bootstrapped for account %s", settings.AccountID)
|
||||
}
|
||||
log.WithContext(ctx).Tracef("agent-network endpoint %q lost an allocation race, retrying (attempt %d/%d)", candidate, attempt, maxDomainAllocationAttempts)
|
||||
continue
|
||||
}
|
||||
return fmt.Errorf("create agent network settings: %w", err)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
return fmt.Errorf("allocate agent network endpoint for account %s: %d attempts exhausted", settings.AccountID, maxDomainAllocationAttempts)
|
||||
}
|
||||
|
||||
// isUniqueConstraintError reports whether err is a database unique-constraint
|
||||
// violation, matched on the driver message because CreateAgentNetworkSettings
|
||||
// deliberately returns the driver error unwrapped.
|
||||
func isUniqueConstraintError(err error) bool {
|
||||
if err == nil {
|
||||
return false
|
||||
}
|
||||
msg := err.Error()
|
||||
return strings.Contains(msg, "(SQLSTATE 23505)") || // postgres
|
||||
strings.Contains(msg, "Error 1062 (23000)") || // mysql
|
||||
strings.Contains(msg, "UNIQUE constraint failed") // sqlite
|
||||
}
|
||||
|
||||
// ListConsumption returns every consumption row recorded for the
|
||||
// account, ordered window-newest-first. Backs the dashboard's basic
|
||||
// counter view; permission gate is the same Read role that gates
|
||||
@@ -879,7 +1021,7 @@ func (*mockManager) GetProvider(_ context.Context, _, _, _ string) (*types.Provi
|
||||
return &types.Provider{}, nil
|
||||
}
|
||||
|
||||
func (*mockManager) CreateProvider(_ context.Context, _ string, p *types.Provider, _ string) (*types.Provider, error) {
|
||||
func (*mockManager) CreateProvider(_ context.Context, _ string, p *types.Provider) (*types.Provider, error) {
|
||||
return p, nil
|
||||
}
|
||||
|
||||
@@ -947,10 +1089,23 @@ func (*mockManager) GetSettings(_ context.Context, accountID, _ string) (*types.
|
||||
return types.DefaultSettings(accountID), nil
|
||||
}
|
||||
|
||||
func (*mockManager) CreateSettings(_ context.Context, _ string, s *types.Settings, proxyAddress, endpoint string) (*types.Settings, error) {
|
||||
if endpoint != "" {
|
||||
s.Domain = endpoint
|
||||
s.ProxyAddress = endpoint
|
||||
} else {
|
||||
s.Domain = "mock." + proxyAddress
|
||||
s.ProxyAddress = proxyAddress
|
||||
}
|
||||
return s, nil
|
||||
}
|
||||
|
||||
func (*mockManager) UpdateSettings(_ context.Context, _ string, s *types.Settings) (*types.Settings, error) {
|
||||
return s, nil
|
||||
}
|
||||
|
||||
func (*mockManager) DeleteSettings(_ context.Context, _, _ string) error { return nil }
|
||||
|
||||
func (*mockManager) ListConsumption(_ context.Context, _, _ string) ([]*types.Consumption, error) {
|
||||
return nil, nil
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user