mirror of
https://github.com/mulgadc/spinifex.git
synced 2026-10-23 20:57:02 +00:00
Compare commits
2 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Josh Siviour
|
b4d4fa65f8 | ||
|
Josh Siviour
|
2e2465dd25 |
@@ -65,7 +65,7 @@ An incompatible change to the subject, fields or vocabulary needs a new major.
|
||||
|
||||
`SealAccountSettingsSubject` (`ec2.v1.SealAccountSettings`) is a request/reply route on which a daemon in the `spinifex-workers` queue group irreversibly seals one account's EC2 settings record.
|
||||
EC2 owns it: `domains/ec2/account` serves it through the daemon.
|
||||
`accountteardown` is the intended consumer from a later release; no teardown calls it yet.
|
||||
`accountteardown`'s StageAccount seal reaper is the consumer: it calls this subject only after the seal-capability probe below reports every configured node compatible, and completes only once it holds a successful sealed reply.
|
||||
|
||||
The request names the account in its body (`account_id`) and may carry an opaque `correlation_ref` that is echoed for logs.
|
||||
The daemon ignores `X-Account-ID` for this subject: the account sealed is the one named in the body.
|
||||
@@ -82,3 +82,20 @@ The subject name carries the contract major; `account_settings_seal_test.go` pre
|
||||
Producer and consumer are in the coordinated Spinifex release, so the window is N and N-1.
|
||||
A daemon that predates the subject has no subscription, so the request gets no responder.
|
||||
An incompatible change to the subject or fields needs a new major.
|
||||
|
||||
## Seal-account-settings capability
|
||||
|
||||
`AccountSettingsSealCapabilitySubject(node)` (`ec2.v1.AccountSettingsSealCapability.<node>`) is a per-node, read-only request/reply route on which `accountteardown` asks one configured daemon whether it supports the account-settings seal, immediately before every seal attempt.
|
||||
EC2 owns it: the daemon serves it with no queue group, so a request addressed to one node reaches only subscribers configured as that node, and two daemons sharing a node ID both answer.
|
||||
`accountteardown` is the consumer: its StageAccount seal reaper probes every configured node and sends no seal request unless every one answers compatible.
|
||||
|
||||
`AccountSettingsSealCapabilityVersion` is a claim about the whole binary's writers, not about the responder: version 1 means every EC2 account-settings writer in the binary is revision-guarded and refuses a sealed record, and the binary serves the seal subject.
|
||||
A daemon binary without this responder — predating the capability, or carrying only the seal subject without it — has no subscriber, so the probe for that node reads as incomplete (`no-reply`), the same as a stopped or partitioned node.
|
||||
The reply proves nothing beyond the moment it was sent: a daemon downgraded or replaced after a successful probe is outside the guarantee.
|
||||
|
||||
### Compatibility boundary
|
||||
|
||||
The subject name carries the contract major; `account_settings_seal_capability_test.go` preserves the version-1 JSON shape and the subject builder.
|
||||
Producer and consumer are in the coordinated Spinifex release, so the window is N and N-1.
|
||||
A daemon that predates the capability has no subscription, so the probe gets no responder for that node.
|
||||
An incompatible change to the subject or fields needs a new major.
|
||||
|
||||
@@ -0,0 +1,39 @@
|
||||
package ec2v1
|
||||
|
||||
import "strings"
|
||||
|
||||
// AccountSettingsSealCapabilityVersion is the version this binary reports.
|
||||
// Version 1: every EC2 account-settings writer in the binary is
|
||||
// revision-guarded and refuses a sealed record, and the seal subject is served.
|
||||
const AccountSettingsSealCapabilityVersion = 1
|
||||
|
||||
// AccountSettingsSealCapabilitySubject is one daemon's read-only
|
||||
// seal-capability route, addressed per node so a probe reaches exactly the
|
||||
// node it asks about.
|
||||
func AccountSettingsSealCapabilitySubject(node string) string {
|
||||
return "ec2.v1.AccountSettingsSealCapability." + node
|
||||
}
|
||||
|
||||
// ValidSealCapabilityNode reports whether node is exactly one NATS subject
|
||||
// token. Responder and probe both check it before building a subject, so
|
||||
// neither can address a wildcard or another node's route.
|
||||
func ValidSealCapabilityNode(node string) bool {
|
||||
return node != "" && !strings.ContainsAny(node, ".*>\t\n\r ")
|
||||
}
|
||||
|
||||
// AccountSettingsSealCapabilityRequest asks node whether it supports the
|
||||
// account-settings seal. CorrelationRef is an opaque caller reference echoed
|
||||
// for logs; it grants nothing and is never a fence or authority to write.
|
||||
type AccountSettingsSealCapabilityRequest struct {
|
||||
Node string `json:"node"`
|
||||
CorrelationRef string `json:"correlation_ref,omitempty"`
|
||||
}
|
||||
|
||||
// AccountSettingsSealCapabilityReply reports the responding node's capability
|
||||
// version. It carries no account data and proves nothing beyond the moment it
|
||||
// was sent.
|
||||
type AccountSettingsSealCapabilityReply struct {
|
||||
Node string `json:"node"`
|
||||
CapabilityVersion int `json:"capability_version"`
|
||||
CorrelationRef string `json:"correlation_ref,omitempty"`
|
||||
}
|
||||
@@ -0,0 +1,43 @@
|
||||
package ec2v1
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
func TestAccountSettingsSealCapabilitySubject(t *testing.T) {
|
||||
require.Equal(t, "ec2.v1.AccountSettingsSealCapability.node-1", AccountSettingsSealCapabilitySubject("node-1"))
|
||||
require.Equal(t, "ec2.v1.AccountSettingsSealCapability.node-2", AccountSettingsSealCapabilitySubject("node-2"))
|
||||
}
|
||||
|
||||
func TestAccountSettingsSealCapabilityRequestJSONContract(t *testing.T) {
|
||||
data, err := json.Marshal(AccountSettingsSealCapabilityRequest{Node: "node-1", CorrelationRef: "req-1"})
|
||||
require.NoError(t, err)
|
||||
require.JSONEq(t, `{"node":"node-1","correlation_ref":"req-1"}`, string(data))
|
||||
|
||||
data, err = json.Marshal(AccountSettingsSealCapabilityRequest{Node: "node-1"})
|
||||
require.NoError(t, err)
|
||||
require.JSONEq(t, `{"node":"node-1"}`, string(data))
|
||||
}
|
||||
|
||||
func TestAccountSettingsSealCapabilityReplyJSONContract(t *testing.T) {
|
||||
reply := AccountSettingsSealCapabilityReply{Node: "node-1", CapabilityVersion: 1, CorrelationRef: "req-1"}
|
||||
data, err := json.Marshal(reply)
|
||||
require.NoError(t, err)
|
||||
require.JSONEq(t, `{"node":"node-1","capability_version":1,"correlation_ref":"req-1"}`, string(data))
|
||||
|
||||
data, err = json.Marshal(AccountSettingsSealCapabilityReply{Node: "node-1", CapabilityVersion: 1})
|
||||
require.NoError(t, err)
|
||||
require.JSONEq(t, `{"node":"node-1","capability_version":1}`, string(data))
|
||||
}
|
||||
|
||||
func TestValidSealCapabilityNode(t *testing.T) {
|
||||
for _, node := range []string{"node-1", "node_2", "n3"} {
|
||||
require.True(t, ValidSealCapabilityNode(node), node)
|
||||
}
|
||||
for _, node := range []string{"", "a.b", "*", ">", "node-*", "node >", "node\t1", "node\n1"} {
|
||||
require.False(t, ValidSealCapabilityNode(node), "%q", node)
|
||||
}
|
||||
}
|
||||
@@ -446,7 +446,7 @@ These residuals were recorded by individual slices and must be resolved once the
|
||||
- `providers/ebs/viperblock` → `runtime/compute/nbd` and `runtime/host/process` (dependency, moved unchanged from `services/viperblockd`): the adapter formats NBD endpoints and manages nbdkit processes through runtime packages. ADR-0001 does not list providers → runtime as forbidden and the layering test does not enforce it (same category as `providers/ebs/conformance` → `runtime/compute/nbd`), but a provider should not depend on node runtime. Clears when NBD endpoint naming has a provider-facing home (a candidate for `contracts/ebs/v1`) and process supervision is injected by the role. The adapter also imports `providers/objectstore`, a provider-to-provider edge that is allowed.
|
||||
- `gateway/ec2.go` (registration): the EC2 dispatch map stays a `GatewayConfig` method in `gateway` and imports every `domains/ec2/awsapi/*` package; `gateway/ec2_idempotency.go` also imports `domains/ec2/awsapi/idem` (`KVBucket`, `TTL`, `TokenAndParams`) for the dispatch-time idempotency wrapper. ADR-0001 makes the domain own its action registration; moving the map waits on the generic ingress registration seam and must not be done as a package move.
|
||||
- `gateway/requestaudit.go`: the outermost request-audit middleware records AWS fields and is updated from four places in the gateway's authentication flow through the gateway's own context key. Moving it would export about seven names used only by that flow, so it stays in `gateway` until the generic ingress registration seam defines how ingress middleware receives authentication results.
|
||||
- `accountteardown` (dependency): its EC2 reapers call `domains/ec2/awsapi/*` action adapters directly, as they did under `gateway/ec2`. The ADR's `accountteardown` current-to-target map row replaces this with domain-owned cleanup capabilities before the package moves. It also holds a read-only consumer of the EC2 platform-inventory contract (`contracts/ec2/v1`, `ec2.v1.PlatformInventory`), served by `domains/ec2/accountinventory`; only the explicit dry run (`Engine.DryRun`) calls it, to log a shadow comparison, and the key-pair, placement-group and launch-template reapers still use the `awsapi` adapters. A domain-owned cleanup capability for the proven-safe subset of those three kinds (key pairs and empty placement groups no instance, spot request or live launch-template version names, and launch-template residue; never live launch templates) exists as `domains/ec2/accountcleanup` (a Go interface with injected owners and reference readers, no NATS subject); nothing calls it yet.
|
||||
- `accountteardown` (dependency): its EC2 reapers call `domains/ec2/awsapi/*` action adapters directly, as they did under `gateway/ec2`. The ADR's `accountteardown` current-to-target map row replaces this with domain-owned cleanup capabilities before the package moves. It also holds a read-only consumer of the EC2 platform-inventory contract (`contracts/ec2/v1`, `ec2.v1.PlatformInventory`), served by `domains/ec2/accountinventory`; only the explicit dry run (`Engine.DryRun`) calls it, to log a shadow comparison, and the key-pair, placement-group and launch-template reapers still use the `awsapi` adapters. A domain-owned cleanup capability for the proven-safe subset of those three kinds (key pairs and empty placement groups no instance, spot request or live launch-template version names, and launch-template residue; never live launch templates) exists as `domains/ec2/accountcleanup` (a Go interface with injected owners and reference readers, no NATS subject); nothing calls it yet. It also holds the StageAccount settings-seal reaper, a consumer of `contracts/ec2/v1`'s `ec2.v1.SealAccountSettings` and per-node `ec2.v1.AccountSettingsSealCapability.<node>` subjects, served by `domains/ec2/account` through the daemon; the reaper reads no KV and imports no domain package, reaching both subjects only through NATS and the configured node set `NewClusterEngine` already receives.
|
||||
- `domains/admission/quota` (dependency, moved from `handlers/quota` unchanged): `live.go` imports `gateway/elbv2` and `handlers/rds` for its live ELBv2 and RDS counters; `records.go` imports `runtime/compute/vm` for the instance-record vCPU sweep; `live.go`, `vcpu.go` and `storage.go` call `domains/ec2/awsapi/{vpc,eip,volume}` describe adapters to count VPCs, subnets, addresses and volumes, as they did under `gateway/ec2`. The ADR's `handlers/quota` current-to-target map row replaces these with reader capabilities once their final locations exist.
|
||||
- `domains/ec2/awsapi/instance` (dependency): imports `handlers/iam` (`IAMService` in `DescribeInstances.go`, `RunInstances.go` and `IamInstanceProfileAssociation.go`; `InstanceProfile` in the latter two), `runtime/compute/cache` (`NodeState`, `NodeUnknown`, `NodeLive`) and `runtime/compute/vm` (`VM`), both in `status_synthesis.go`. The IAM edge needs an IAM capability; the runtime edges are domain-to-runtime and need the instance record and node liveness exposed through an EC2-owned projection.
|
||||
- `domains/ec2/awsapi/spotinstance` (dependency): imports `handlers/iam.IAMService` and `domains/admission/quota.Service` in `RequestSpotInstances.go`.
|
||||
|
||||
@@ -70,6 +70,11 @@ func NewClusterEngine(
|
||||
reapers = append(reapers, S3Reapers(buckets)...)
|
||||
reapers = append(reapers, ACMReapers(nc)...)
|
||||
reapers = append(reapers, IAMReapers(svc)...)
|
||||
|
||||
// Before the account counters and reservations: the seal must still be
|
||||
// able to find the account IAM holds as TERMINATING, which the account
|
||||
// record reaper does not remove.
|
||||
reapers = append(reapers, EC2AccountSettingsReapers(nc, nodeIDs)...)
|
||||
reapers = append(reapers, AccountReapers(svc, names, usage)...)
|
||||
|
||||
engine := NewEngine(NewIAMAccounts(svc), reapers...)
|
||||
|
||||
@@ -41,6 +41,27 @@ func TestNewClusterEngineCoversEveryStage(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// The EC2 settings seal reaper must be registered in StageAccount on every
|
||||
// surface that builds a cluster engine, or teardown would finalise accounts
|
||||
// without ever sealing their settings.
|
||||
func TestNewClusterEngineRegistersTheEC2SettingsSealReaper(t *testing.T) {
|
||||
_, nc, _ := testutil.StartTestJetStream(t)
|
||||
|
||||
masterKey, err := handlers_iam.GenerateMasterKey()
|
||||
require.NoError(t, err)
|
||||
svc, err := handlers_iam.NewIAMServiceImpl(t.Context(), nc, masterKey)
|
||||
require.NoError(t, err)
|
||||
|
||||
engine, err := NewClusterEngine(t.Context(), nc, 1, []string{"node-1"}, svc, newFakeBuckets())
|
||||
require.NoError(t, err)
|
||||
|
||||
var kinds []string
|
||||
for _, reaper := range engine.reapersFor(StageAccount) {
|
||||
kinds = append(kinds, reaper.Kind())
|
||||
}
|
||||
assert.Contains(t, kinds, "ec2-account-settings")
|
||||
}
|
||||
|
||||
// A teardown must refuse the accounts no credential may delete before it reads
|
||||
// anything, and refuse a name confirmation that does not match the record.
|
||||
func TestClusterEnginePrechecks(t *testing.T) {
|
||||
|
||||
@@ -0,0 +1,125 @@
|
||||
package accountteardown
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
ec2v1 "github.com/mulgadc/spinifex/contracts/ec2/v1"
|
||||
natsmsg "github.com/mulgadc/spinifex/spinifex/foundation/messaging/nats"
|
||||
"github.com/nats-io/nats.go"
|
||||
)
|
||||
|
||||
// ec2AccountSettingsSealTimeout bounds one seal request; an earlier caller
|
||||
// deadline wins.
|
||||
const ec2AccountSettingsSealTimeout = 30 * time.Second
|
||||
|
||||
// ec2AccountSettingsSealer is EC2's seal of one account's settings record.
|
||||
type ec2AccountSettingsSealer interface {
|
||||
SealAccountSettings(ctx context.Context, accountID string) (revision uint64, err error)
|
||||
}
|
||||
|
||||
// ec2AccountSettingsSealClient reaches the EC2 settings-seal contract over
|
||||
// NATS. Only a reply for this account, disposition sealed and a non-zero
|
||||
// revision is a seal; anything else, including no responder, is an error.
|
||||
type ec2AccountSettingsSealClient struct {
|
||||
nc *nats.Conn
|
||||
timeout time.Duration
|
||||
}
|
||||
|
||||
var _ ec2AccountSettingsSealer = (*ec2AccountSettingsSealClient)(nil)
|
||||
|
||||
func newEC2AccountSettingsSealClient(nc *nats.Conn) *ec2AccountSettingsSealClient {
|
||||
return &ec2AccountSettingsSealClient{nc: nc, timeout: ec2AccountSettingsSealTimeout}
|
||||
}
|
||||
|
||||
func (c *ec2AccountSettingsSealClient) SealAccountSettings(ctx context.Context, accountID string) (uint64, error) {
|
||||
timeout := c.timeout
|
||||
if deadline, ok := ctx.Deadline(); ok {
|
||||
timeout = min(timeout, time.Until(deadline))
|
||||
}
|
||||
if ctx.Err() != nil || timeout <= 0 {
|
||||
return 0, fmt.Errorf("seal account settings: %w", context.DeadlineExceeded)
|
||||
}
|
||||
|
||||
reply, err := natsmsg.NATSRequest[ec2v1.SealAccountSettingsReply](ctx, c.nc, ec2v1.SealAccountSettingsSubject,
|
||||
&ec2v1.SealAccountSettingsRequest{AccountID: accountID}, timeout, accountID)
|
||||
if err != nil {
|
||||
return 0, fmt.Errorf("seal account settings: %w", err)
|
||||
}
|
||||
if reply.AccountID != accountID {
|
||||
return 0, fmt.Errorf("seal account settings: reply named account %q, not %q", reply.AccountID, accountID)
|
||||
}
|
||||
if reply.Disposition != ec2v1.AccountSettingsDispositionSealed {
|
||||
return 0, fmt.Errorf("seal account settings: unexpected disposition %q", reply.Disposition)
|
||||
}
|
||||
if reply.Revision == 0 {
|
||||
return 0, errors.New("seal account settings: reply carried no revision")
|
||||
}
|
||||
return reply.Revision, nil
|
||||
}
|
||||
|
||||
// accountSettingsSealReaper seals EC2's settings record in StageAccount. List
|
||||
// does no I/O and stays pending until this instance has sealed, so DryRun never
|
||||
// seals; state is per engine, so every fresh teardown run seals again.
|
||||
type accountSettingsSealReaper struct {
|
||||
sealer ec2AccountSettingsSealer
|
||||
capability sealCapabilityChecker
|
||||
|
||||
mu sync.Mutex
|
||||
sealed map[string]uint64 // account ID -> leader revision, this run only
|
||||
}
|
||||
|
||||
func (r *accountSettingsSealReaper) Kind() string { return "ec2-account-settings" }
|
||||
func (r *accountSettingsSealReaper) Stage() Stage { return StageAccount }
|
||||
|
||||
func (r *accountSettingsSealReaper) alreadySealed(accountID string) bool {
|
||||
r.mu.Lock()
|
||||
defer r.mu.Unlock()
|
||||
_, ok := r.sealed[accountID]
|
||||
return ok
|
||||
}
|
||||
|
||||
func (r *accountSettingsSealReaper) List(_ context.Context, accountID string) ([]Resource, error) {
|
||||
if r.alreadySealed(accountID) {
|
||||
return nil, nil
|
||||
}
|
||||
return []Resource{{Kind: r.Kind(), ID: accountID, Detail: "seal"}}, nil
|
||||
}
|
||||
|
||||
// Delete probes every configured daemon immediately before each seal attempt,
|
||||
// never reusing an earlier probe. Incomplete capability sends no seal and is
|
||||
// retryable; force is ignored, since nothing may force past the probe.
|
||||
func (r *accountSettingsSealReaper) Delete(ctx context.Context, accountID string, _ Resource, _ bool) error {
|
||||
report := r.capability.CheckSealCapability(ctx, accountID)
|
||||
if !report.Complete {
|
||||
return errSealCapabilityIncomplete(report)
|
||||
}
|
||||
|
||||
revision, err := r.sealer.SealAccountSettings(ctx, accountID)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
r.mu.Lock()
|
||||
if r.sealed == nil {
|
||||
r.sealed = map[string]uint64{}
|
||||
}
|
||||
r.sealed[accountID] = revision
|
||||
r.mu.Unlock()
|
||||
slog.InfoContext(ctx, "Account teardown sealed EC2 account settings", "accountID", accountID, "revision", revision)
|
||||
return nil
|
||||
}
|
||||
|
||||
// EC2AccountSettingsReapers returns the StageAccount reaper that seals EC2's
|
||||
// settings record. nodeIDs is the configured node set the capability probe
|
||||
// treats as "every relevant writer"; an empty set is unknown, never complete.
|
||||
func EC2AccountSettingsReapers(nc *nats.Conn, nodeIDs []string) []Reaper {
|
||||
return []Reaper{&accountSettingsSealReaper{
|
||||
sealer: newEC2AccountSettingsSealClient(nc),
|
||||
capability: newSealCapabilityClient(nc, nodeIDs),
|
||||
}}
|
||||
}
|
||||
@@ -0,0 +1,190 @@
|
||||
package accountteardown
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"sort"
|
||||
"strings"
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
ec2v1 "github.com/mulgadc/spinifex/contracts/ec2/v1"
|
||||
awserrors "github.com/mulgadc/spinifex/spinifex/foundation/aws/errors"
|
||||
natsmsg "github.com/mulgadc/spinifex/spinifex/foundation/messaging/nats"
|
||||
"github.com/nats-io/nats.go"
|
||||
)
|
||||
|
||||
// sealCapabilityWait bounds the whole probe; shortened by the caller's
|
||||
// deadline. Every configured node is probed in parallel against this one
|
||||
// wait, so N nodes cost one wait, not N.
|
||||
const sealCapabilityWait = 3 * time.Second
|
||||
|
||||
// sealCapabilityGrace is how long a node's probe keeps listening after its
|
||||
// one expected responder has answered, long enough for a genuine second
|
||||
// subscriber on the same node to be caught as a duplicate.
|
||||
const sealCapabilityGrace = 150 * time.Millisecond
|
||||
|
||||
// Seal capability reasons, one per failing node. Each names a category, never
|
||||
// wire error text.
|
||||
const (
|
||||
sealCapabilityReasonNoReply = "no-reply"
|
||||
sealCapabilityReasonDuplicate = "duplicate"
|
||||
sealCapabilityReasonWrongIdentity = "wrong-identity"
|
||||
sealCapabilityReasonErrorReply = "error-reply"
|
||||
sealCapabilityReasonMalformed = "malformed"
|
||||
sealCapabilityReasonOldVersion = "old-version"
|
||||
sealCapabilityReasonTransport = "transport"
|
||||
sealCapabilityReasonInvalidNodeID = "invalid-node-id"
|
||||
sealCapabilityReasonSetUnknown = "configured-node-set-unknown"
|
||||
)
|
||||
|
||||
// sealCapabilityChecker reports whether every configured daemon supports the
|
||||
// seal.
|
||||
type sealCapabilityChecker interface {
|
||||
CheckSealCapability(ctx context.Context, correlationRef string) sealCapabilityReport
|
||||
}
|
||||
|
||||
// sealCapabilityReport is one probe's result, one entry per configured node.
|
||||
type sealCapabilityReport struct {
|
||||
Complete bool
|
||||
Nodes []nodeSealCapability // one per configured node, sorted by node
|
||||
}
|
||||
|
||||
// nodeSealCapability is one configured node's compatibility. Reason is ""
|
||||
// when the node is compatible.
|
||||
type nodeSealCapability struct {
|
||||
Node string
|
||||
Version int // 0 unless a valid reply arrived
|
||||
Reason string // "" when compatible
|
||||
}
|
||||
|
||||
// sealCapabilityClient probes every configured node's seal-capability subject
|
||||
// in parallel. "Configured" is the same node set NewClusterEngine already
|
||||
// receives; there is no separate liveness or membership source.
|
||||
type sealCapabilityClient struct {
|
||||
nc *nats.Conn
|
||||
nodeIDs []string
|
||||
wait time.Duration // 3 s, shortened by the caller's deadline
|
||||
grace time.Duration // 150 ms ResponderGrace
|
||||
}
|
||||
|
||||
var _ sealCapabilityChecker = (*sealCapabilityClient)(nil)
|
||||
|
||||
func newSealCapabilityClient(nc *nats.Conn, nodeIDs []string) *sealCapabilityClient {
|
||||
return &sealCapabilityClient{nc: nc, nodeIDs: nodeIDs, wait: sealCapabilityWait, grace: sealCapabilityGrace}
|
||||
}
|
||||
|
||||
// CheckSealCapability probes every configured node in parallel, bounded by
|
||||
// one shared deadline, run immediately before each seal attempt. A cached or
|
||||
// earlier result is never reused.
|
||||
func (c *sealCapabilityClient) CheckSealCapability(ctx context.Context, correlationRef string) sealCapabilityReport {
|
||||
if len(c.nodeIDs) == 0 {
|
||||
return sealCapabilityReport{Complete: false}
|
||||
}
|
||||
|
||||
wait := c.wait
|
||||
if deadline, ok := ctx.Deadline(); ok {
|
||||
wait = min(wait, time.Until(deadline))
|
||||
}
|
||||
|
||||
nodes := append([]string(nil), c.nodeIDs...)
|
||||
sort.Strings(nodes)
|
||||
|
||||
results := make([]nodeSealCapability, len(nodes))
|
||||
if ctx.Err() != nil || wait <= 0 {
|
||||
for i, node := range nodes {
|
||||
results[i] = nodeSealCapability{Node: node, Reason: sealCapabilityReasonNoReply}
|
||||
}
|
||||
return sealCapabilityReport{Complete: false, Nodes: results}
|
||||
}
|
||||
|
||||
var wg sync.WaitGroup
|
||||
for i, node := range nodes {
|
||||
wg.Add(1)
|
||||
go func(i int, node string) {
|
||||
defer wg.Done()
|
||||
results[i] = c.checkNode(ctx, node, correlationRef, wait)
|
||||
}(i, node)
|
||||
}
|
||||
wg.Wait()
|
||||
|
||||
complete := true
|
||||
for _, r := range results {
|
||||
if r.Reason != "" {
|
||||
complete = false
|
||||
break
|
||||
}
|
||||
}
|
||||
return sealCapabilityReport{Complete: complete, Nodes: results}
|
||||
}
|
||||
|
||||
// checkNode probes one node and classifies the result. A node is compatible
|
||||
// only when exactly one identified, decodable, matching, version >= 1 frame
|
||||
// arrived, with no duplicate, conflict or cap hit.
|
||||
func (c *sealCapabilityClient) checkNode(ctx context.Context, node, correlationRef string, wait time.Duration) nodeSealCapability {
|
||||
if !ec2v1.ValidSealCapabilityNode(node) {
|
||||
return nodeSealCapability{Node: node, Reason: sealCapabilityReasonInvalidNodeID}
|
||||
}
|
||||
|
||||
data, err := json.Marshal(ec2v1.AccountSettingsSealCapabilityRequest{Node: node, CorrelationRef: correlationRef})
|
||||
if err != nil {
|
||||
return nodeSealCapability{Node: node, Reason: sealCapabilityReasonMalformed}
|
||||
}
|
||||
|
||||
frames, sum, err := natsmsg.Gather(ctx, c.nc, ec2v1.AccountSettingsSealCapabilitySubject(node), data, natsmsg.GatherOpts{
|
||||
Timeout: wait,
|
||||
ExpectedResponders: 1,
|
||||
Mode: natsmsg.CollectUntilDeadline,
|
||||
ResponderGrace: c.grace,
|
||||
})
|
||||
if err != nil {
|
||||
return nodeSealCapability{Node: node, Reason: sealCapabilityReasonTransport}
|
||||
}
|
||||
|
||||
switch {
|
||||
case sum.CapHit, len(sum.ConflictNodes) > 0, sum.DuplicateFrames > 0:
|
||||
return nodeSealCapability{Node: node, Reason: sealCapabilityReasonDuplicate}
|
||||
case sum.Unidentified > 0:
|
||||
return nodeSealCapability{Node: node, Reason: sealCapabilityReasonWrongIdentity}
|
||||
case len(sum.ErrorResponders) > 0:
|
||||
return nodeSealCapability{Node: node, Reason: sealCapabilityReasonErrorReply}
|
||||
case sum.Received == 0, len(frames) == 0:
|
||||
return nodeSealCapability{Node: node, Reason: sealCapabilityReasonNoReply}
|
||||
}
|
||||
|
||||
frame := frames[0]
|
||||
if frame.NodeID != node {
|
||||
return nodeSealCapability{Node: node, Reason: sealCapabilityReasonWrongIdentity}
|
||||
}
|
||||
|
||||
var reply ec2v1.AccountSettingsSealCapabilityReply
|
||||
if json.Unmarshal(frame.Data, &reply) != nil {
|
||||
return nodeSealCapability{Node: node, Reason: sealCapabilityReasonMalformed}
|
||||
}
|
||||
if reply.Node != node {
|
||||
return nodeSealCapability{Node: node, Reason: sealCapabilityReasonWrongIdentity}
|
||||
}
|
||||
if reply.CapabilityVersion < 1 {
|
||||
return nodeSealCapability{Node: node, Version: reply.CapabilityVersion, Reason: sealCapabilityReasonOldVersion}
|
||||
}
|
||||
return nodeSealCapability{Node: node, Version: reply.CapabilityVersion}
|
||||
}
|
||||
|
||||
// errSealCapabilityIncomplete builds the retryable refusal from report. It
|
||||
// names node IDs and reason categories only, never wire error text.
|
||||
func errSealCapabilityIncomplete(report sealCapabilityReport) error {
|
||||
detail := sealCapabilityReasonSetUnknown
|
||||
var parts []string
|
||||
for _, n := range report.Nodes {
|
||||
if n.Reason != "" {
|
||||
parts = append(parts, n.Node+"="+n.Reason)
|
||||
}
|
||||
}
|
||||
if len(parts) > 0 {
|
||||
detail = strings.Join(parts, ", ")
|
||||
}
|
||||
return awserrors.WithRetryAfter(
|
||||
awserrors.Errorf(awserrors.ErrorServiceUnavailable, "EC2 account-settings seal capability incomplete: %s", detail),
|
||||
5*time.Second,
|
||||
)
|
||||
}
|
||||
@@ -0,0 +1,311 @@
|
||||
package accountteardown
|
||||
|
||||
//test:in-package — the probe client, its report types and reason constants
|
||||
// are unexported, and what they guarantee (incomplete never seals, complete
|
||||
// does) is only observable from inside the package.
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"sync/atomic"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
ec2v1 "github.com/mulgadc/spinifex/contracts/ec2/v1"
|
||||
"github.com/mulgadc/spinifex/internal/testkit"
|
||||
awserrors "github.com/mulgadc/spinifex/spinifex/foundation/aws/errors"
|
||||
natsmsg "github.com/mulgadc/spinifex/spinifex/foundation/messaging/nats"
|
||||
"github.com/nats-io/nats.go"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// testCapabilityClient builds a probe client with test-sized timeouts so the
|
||||
// incomplete cases below do not each pay the production 3 s wait.
|
||||
func testCapabilityClient(nc *nats.Conn, nodeIDs []string) *sealCapabilityClient {
|
||||
c := newSealCapabilityClient(nc, nodeIDs)
|
||||
c.wait = 200 * time.Millisecond
|
||||
c.grace = 30 * time.Millisecond
|
||||
return c
|
||||
}
|
||||
|
||||
// serveCapability subscribes reply on subject with no queue group, which is
|
||||
// how the real responder is addressed: per node, so two subscribers on the
|
||||
// same node's subject both answer.
|
||||
func serveCapability(t *testing.T, nc *nats.Conn, subject string, reply nats.MsgHandler) *nats.Subscription {
|
||||
t.Helper()
|
||||
sub, err := nc.Subscribe(subject, reply)
|
||||
require.NoError(t, err)
|
||||
t.Cleanup(func() { _ = sub.Unsubscribe() })
|
||||
require.NoError(t, nc.Flush())
|
||||
return sub
|
||||
}
|
||||
|
||||
// capabilityReply answers with a well-formed reply naming replyNode (which
|
||||
// may deliberately differ from the subject's node) and headerNode as the
|
||||
// X-Node-ID ("" omits the header).
|
||||
func capabilityReply(replyNode, headerNode string, version int) nats.MsgHandler {
|
||||
return func(msg *nats.Msg) {
|
||||
data, _ := json.Marshal(ec2v1.AccountSettingsSealCapabilityReply{Node: replyNode, CapabilityVersion: version})
|
||||
reply := nats.NewMsg(msg.Reply)
|
||||
reply.Data = data
|
||||
if headerNode != "" {
|
||||
reply.Header.Set(natsmsg.NodeIDHeader, headerNode)
|
||||
}
|
||||
_ = msg.RespondMsg(reply)
|
||||
}
|
||||
}
|
||||
|
||||
func nodeResult(t *testing.T, report sealCapabilityReport, node string) nodeSealCapability {
|
||||
t.Helper()
|
||||
for _, n := range report.Nodes {
|
||||
if n.Node == node {
|
||||
return n
|
||||
}
|
||||
}
|
||||
t.Fatalf("no result for node %q in %+v", node, report)
|
||||
return nodeSealCapability{}
|
||||
}
|
||||
|
||||
// Each sub-case names exactly one way a node fails to prove capability
|
||||
// version 1, and that failure alone makes the whole probe incomplete.
|
||||
func TestSealCapabilityIncomplete(t *testing.T) {
|
||||
t.Run("missing", func(t *testing.T) {
|
||||
_, nc, _ := testutil.StartTestJetStream(t)
|
||||
report := testCapabilityClient(nc, []string{"node-1"}).CheckSealCapability(testCtx(t), "req")
|
||||
assert.False(t, report.Complete)
|
||||
assert.Equal(t, sealCapabilityReasonNoReply, nodeResult(t, report, "node-1").Reason)
|
||||
})
|
||||
|
||||
t.Run("duplicate", func(t *testing.T) {
|
||||
_, nc, _ := testutil.StartTestJetStream(t)
|
||||
serveCapability(t, nc, ec2v1.AccountSettingsSealCapabilitySubject("node-1"), capabilityReply("node-1", "node-1", 1))
|
||||
serveCapability(t, nc, ec2v1.AccountSettingsSealCapabilitySubject("node-1"), capabilityReply("node-1", "node-1", 1))
|
||||
report := testCapabilityClient(nc, []string{"node-1"}).CheckSealCapability(testCtx(t), "req")
|
||||
assert.False(t, report.Complete)
|
||||
assert.Equal(t, sealCapabilityReasonDuplicate, nodeResult(t, report, "node-1").Reason)
|
||||
})
|
||||
|
||||
t.Run("unreachable timeout", func(t *testing.T) {
|
||||
_, nc, _ := testutil.StartTestJetStream(t)
|
||||
serveCapability(t, nc, ec2v1.AccountSettingsSealCapabilitySubject("node-1"), func(msg *nats.Msg) {
|
||||
time.Sleep(time.Second)
|
||||
_ = msg.Respond(nil)
|
||||
})
|
||||
client := testCapabilityClient(nc, []string{"node-1"})
|
||||
report := client.CheckSealCapability(testCtx(t), "req")
|
||||
assert.False(t, report.Complete)
|
||||
assert.Equal(t, sealCapabilityReasonNoReply, nodeResult(t, report, "node-1").Reason)
|
||||
})
|
||||
|
||||
t.Run("transport closed connection", func(t *testing.T) {
|
||||
_, nc, _ := testutil.StartTestJetStream(t)
|
||||
nc.Close()
|
||||
report := testCapabilityClient(nc, []string{"node-1"}).CheckSealCapability(testCtx(t), "req")
|
||||
assert.False(t, report.Complete)
|
||||
assert.Equal(t, sealCapabilityReasonTransport, nodeResult(t, report, "node-1").Reason)
|
||||
})
|
||||
|
||||
t.Run("malformed body", func(t *testing.T) {
|
||||
_, nc, _ := testutil.StartTestJetStream(t)
|
||||
serveCapability(t, nc, ec2v1.AccountSettingsSealCapabilitySubject("node-1"), func(msg *nats.Msg) {
|
||||
reply := nats.NewMsg(msg.Reply)
|
||||
reply.Data = []byte("not json")
|
||||
reply.Header.Set(natsmsg.NodeIDHeader, "node-1")
|
||||
_ = msg.RespondMsg(reply)
|
||||
})
|
||||
report := testCapabilityClient(nc, []string{"node-1"}).CheckSealCapability(testCtx(t), "req")
|
||||
assert.False(t, report.Complete)
|
||||
assert.Equal(t, sealCapabilityReasonMalformed, nodeResult(t, report, "node-1").Reason)
|
||||
})
|
||||
|
||||
t.Run("error reply", func(t *testing.T) {
|
||||
_, nc, _ := testutil.StartTestJetStream(t)
|
||||
serveCapability(t, nc, ec2v1.AccountSettingsSealCapabilitySubject("node-1"), func(msg *nats.Msg) {
|
||||
reply := nats.NewMsg(msg.Reply)
|
||||
reply.Data = awserrors.GenerateErrorPayload(awserrors.ErrorServerInternal)
|
||||
reply.Header.Set(natsmsg.NodeIDHeader, "node-1")
|
||||
_ = msg.RespondMsg(reply)
|
||||
})
|
||||
report := testCapabilityClient(nc, []string{"node-1"}).CheckSealCapability(testCtx(t), "req")
|
||||
assert.False(t, report.Complete)
|
||||
assert.Equal(t, sealCapabilityReasonErrorReply, nodeResult(t, report, "node-1").Reason)
|
||||
})
|
||||
|
||||
t.Run("wrong identity no header", func(t *testing.T) {
|
||||
_, nc, _ := testutil.StartTestJetStream(t)
|
||||
serveCapability(t, nc, ec2v1.AccountSettingsSealCapabilitySubject("node-1"), capabilityReply("node-1", "", 1))
|
||||
report := testCapabilityClient(nc, []string{"node-1"}).CheckSealCapability(testCtx(t), "req")
|
||||
assert.False(t, report.Complete)
|
||||
assert.Equal(t, sealCapabilityReasonWrongIdentity, nodeResult(t, report, "node-1").Reason)
|
||||
})
|
||||
|
||||
t.Run("wrong identity another node header", func(t *testing.T) {
|
||||
_, nc, _ := testutil.StartTestJetStream(t)
|
||||
serveCapability(t, nc, ec2v1.AccountSettingsSealCapabilitySubject("node-1"), capabilityReply("node-1", "node-9", 1))
|
||||
report := testCapabilityClient(nc, []string{"node-1"}).CheckSealCapability(testCtx(t), "req")
|
||||
assert.False(t, report.Complete)
|
||||
assert.Equal(t, sealCapabilityReasonWrongIdentity, nodeResult(t, report, "node-1").Reason)
|
||||
})
|
||||
|
||||
t.Run("wrong identity body node differs", func(t *testing.T) {
|
||||
_, nc, _ := testutil.StartTestJetStream(t)
|
||||
serveCapability(t, nc, ec2v1.AccountSettingsSealCapabilitySubject("node-1"), capabilityReply("node-9", "node-1", 1))
|
||||
report := testCapabilityClient(nc, []string{"node-1"}).CheckSealCapability(testCtx(t), "req")
|
||||
assert.False(t, report.Complete)
|
||||
assert.Equal(t, sealCapabilityReasonWrongIdentity, nodeResult(t, report, "node-1").Reason)
|
||||
})
|
||||
|
||||
t.Run("lower version", func(t *testing.T) {
|
||||
_, nc, _ := testutil.StartTestJetStream(t)
|
||||
serveCapability(t, nc, ec2v1.AccountSettingsSealCapabilitySubject("node-1"), capabilityReply("node-1", "node-1", 0))
|
||||
report := testCapabilityClient(nc, []string{"node-1"}).CheckSealCapability(testCtx(t), "req")
|
||||
assert.False(t, report.Complete)
|
||||
assert.Equal(t, sealCapabilityReasonOldVersion, nodeResult(t, report, "node-1").Reason)
|
||||
})
|
||||
|
||||
t.Run("configured set empty", func(t *testing.T) {
|
||||
_, nc, _ := testutil.StartTestJetStream(t)
|
||||
report := testCapabilityClient(nc, nil).CheckSealCapability(testCtx(t), "req")
|
||||
assert.False(t, report.Complete)
|
||||
assert.Empty(t, report.Nodes)
|
||||
})
|
||||
|
||||
t.Run("invalid node id", func(t *testing.T) {
|
||||
_, nc, _ := testutil.StartTestJetStream(t)
|
||||
report := testCapabilityClient(nc, []string{"bad.node"}).CheckSealCapability(testCtx(t), "req")
|
||||
assert.False(t, report.Complete)
|
||||
assert.Equal(t, sealCapabilityReasonInvalidNodeID, nodeResult(t, report, "bad.node").Reason)
|
||||
})
|
||||
}
|
||||
|
||||
// Every configured node answering version 1 or later makes the probe
|
||||
// complete, and the reaper sends exactly one seal request.
|
||||
func TestSealCapabilityCompleteAllowsSeal(t *testing.T) {
|
||||
_, nc, _ := testutil.StartTestJetStream(t)
|
||||
serveCapability(t, nc, ec2v1.AccountSettingsSealCapabilitySubject("node-1"), capabilityReply("node-1", "node-1", 1))
|
||||
serveCapability(t, nc, ec2v1.AccountSettingsSealCapabilitySubject("node-2"), capabilityReply("node-2", "node-2", 2))
|
||||
|
||||
client := testCapabilityClient(nc, []string{"node-1", "node-2"})
|
||||
report := client.CheckSealCapability(testCtx(t), "req")
|
||||
require.True(t, report.Complete)
|
||||
assert.Equal(t, 1, nodeResult(t, report, "node-1").Version)
|
||||
assert.Equal(t, 2, nodeResult(t, report, "node-2").Version)
|
||||
|
||||
sealer := &fakeSealer{}
|
||||
reaper := &accountSettingsSealReaper{sealer: sealer, capability: client}
|
||||
require.NoError(t, reaper.Delete(testCtx(t), testAccountID, Resource{Kind: reaper.Kind(), ID: testAccountID}, false))
|
||||
assert.Equal(t, []string{testAccountID}, sealer.calls)
|
||||
}
|
||||
|
||||
// An incomplete probe keeps the account TERMINATING through the full engine,
|
||||
// names the silent node and its reason, sends no seal request, and leaves the
|
||||
// settings record untouched (the fake sealer records no call).
|
||||
func TestSealCapabilityIncompleteKeepsAccountTerminating(t *testing.T) {
|
||||
_, nc, _ := testutil.StartTestJetStream(t)
|
||||
serveCapability(t, nc, ec2v1.AccountSettingsSealCapabilitySubject("node-1"), capabilityReply("node-1", "node-1", 1))
|
||||
// node-2 has no subscriber.
|
||||
|
||||
sealer := &fakeSealer{}
|
||||
reaper := &accountSettingsSealReaper{sealer: sealer, capability: testCapabilityClient(nc, []string{"node-1", "node-2"})}
|
||||
accounts := newFakeAccounts()
|
||||
engine := quietEngine(accounts, reaper)
|
||||
|
||||
result, err := engine.Teardown(testCtx(t), request())
|
||||
require.ErrorIs(t, err, ErrResourcesStuck)
|
||||
assert.False(t, result.AccountDeleted)
|
||||
assert.Equal(t, AccountStatusTerminating, accounts.account.Status)
|
||||
assert.Empty(t, sealer.calls)
|
||||
|
||||
var reason string
|
||||
for _, stage := range result.Stages {
|
||||
for _, stuck := range stage.Stuck {
|
||||
if stuck.Resource.Kind == "ec2-account-settings" {
|
||||
reason = stuck.Reason
|
||||
}
|
||||
}
|
||||
}
|
||||
assert.Contains(t, reason, "node-2="+sealCapabilityReasonNoReply)
|
||||
}
|
||||
|
||||
// The silent node starting to answer during the drain makes the very next
|
||||
// Delete re-probe and succeed, which proves the result is retryable and the
|
||||
// probe is never cached across attempts.
|
||||
func TestSealCapabilityRetriesThenSeals(t *testing.T) {
|
||||
_, nc, _ := testutil.StartTestJetStream(t)
|
||||
serveCapability(t, nc, ec2v1.AccountSettingsSealCapabilitySubject("node-1"), capabilityReply("node-1", "node-1", 1))
|
||||
|
||||
var node2Up atomic.Bool
|
||||
sub, err := nc.Subscribe(ec2v1.AccountSettingsSealCapabilitySubject("node-2"), func(msg *nats.Msg) {
|
||||
if !node2Up.Load() {
|
||||
return
|
||||
}
|
||||
capabilityReply("node-2", "node-2", 1)(msg)
|
||||
})
|
||||
require.NoError(t, err)
|
||||
t.Cleanup(func() { _ = sub.Unsubscribe() })
|
||||
require.NoError(t, nc.Flush())
|
||||
|
||||
sealer := &fakeSealer{}
|
||||
reaper := &accountSettingsSealReaper{sealer: sealer, capability: testCapabilityClient(nc, []string{"node-1", "node-2"})}
|
||||
accounts := newFakeAccounts()
|
||||
engine := quietEngine(accounts, reaper)
|
||||
engine.Timeouts = Timeouts{StageDrain: time.Second, DrainPoll: 5 * time.Millisecond}
|
||||
|
||||
go func() {
|
||||
time.Sleep(80 * time.Millisecond)
|
||||
node2Up.Store(true)
|
||||
}()
|
||||
|
||||
result, err := engine.Teardown(testCtx(t), request())
|
||||
require.NoError(t, err)
|
||||
assert.True(t, result.AccountDeleted)
|
||||
assert.Equal(t, []string{testAccountID}, sealer.calls)
|
||||
}
|
||||
|
||||
// Two Delete calls on one reaper probe twice: the probe runs in Delete
|
||||
// itself, never cached from a previous attempt.
|
||||
func TestSealCapabilityProbedBeforeEverySeal(t *testing.T) {
|
||||
_, nc, _ := testutil.StartTestJetStream(t)
|
||||
var probes int
|
||||
serveCapability(t, nc, ec2v1.AccountSettingsSealCapabilitySubject("node-1"), func(msg *nats.Msg) {
|
||||
probes++
|
||||
capabilityReply("node-1", "node-1", 1)(msg)
|
||||
})
|
||||
|
||||
sealer := &fakeSealer{}
|
||||
client := testCapabilityClient(nc, []string{"node-1"})
|
||||
reaper := &accountSettingsSealReaper{sealer: sealer, capability: client}
|
||||
|
||||
require.NoError(t, reaper.Delete(testCtx(t), testAccountID, Resource{Kind: reaper.Kind(), ID: testAccountID}, false))
|
||||
// alreadySealed now makes List empty, but Delete itself does not consult
|
||||
// it, so a second direct call still probes and seals again.
|
||||
require.NoError(t, reaper.Delete(testCtx(t), testAccountID, Resource{Kind: reaper.Kind(), ID: testAccountID}, false))
|
||||
assert.Equal(t, 2, probes)
|
||||
assert.Len(t, sealer.calls, 2)
|
||||
}
|
||||
|
||||
// Five silent nodes still return within one deadline, not five: every node
|
||||
// is probed in parallel against the same wait.
|
||||
func TestSealCapabilityBoundedByOneDeadline(t *testing.T) {
|
||||
_, nc, _ := testutil.StartTestJetStream(t)
|
||||
client := testCapabilityClient(nc, []string{"node-1", "node-2", "node-3", "node-4", "node-5"})
|
||||
|
||||
started := time.Now()
|
||||
report := client.CheckSealCapability(testCtx(t), "req")
|
||||
elapsed := time.Since(started)
|
||||
|
||||
assert.False(t, report.Complete)
|
||||
assert.Less(t, elapsed, client.wait+time.Second, "five silent nodes must not cost five deadlines")
|
||||
}
|
||||
|
||||
// The stuck reason is logged and stored as one line naming each failing node;
|
||||
// the retry hint and the ServiceUnavailable code travel with it.
|
||||
func TestSealCapabilityIncompleteErrorIsOneLine(t *testing.T) {
|
||||
err := errSealCapabilityIncomplete(sealCapabilityReport{Nodes: []nodeSealCapability{{Node: "node-1", Reason: sealCapabilityReasonDuplicate}}})
|
||||
|
||||
assert.Equal(t, "EC2 account-settings seal capability incomplete: node-1=duplicate: ServiceUnavailable", err.Error())
|
||||
d, ok := awserrors.ResolveRetryAfter(err)
|
||||
assert.True(t, ok)
|
||||
assert.Equal(t, 5*time.Second, d)
|
||||
assert.True(t, awserrors.IsErrorCode(err, awserrors.ErrorServiceUnavailable))
|
||||
}
|
||||
@@ -0,0 +1,273 @@
|
||||
package accountteardown
|
||||
|
||||
//test:in-package — the reaper, sealer and capability checker are unexported;
|
||||
// no seal without a complete probe, completion only after a sealed reply and
|
||||
// idempotent fresh runs are only observable from inside the package.
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"sync"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/aws/aws-sdk-go/service/ec2"
|
||||
ec2v1 "github.com/mulgadc/spinifex/contracts/ec2/v1"
|
||||
"github.com/mulgadc/spinifex/internal/testkit"
|
||||
ec2account "github.com/mulgadc/spinifex/spinifex/domains/ec2/account"
|
||||
awserrors "github.com/mulgadc/spinifex/spinifex/foundation/aws/errors"
|
||||
natsmsg "github.com/mulgadc/spinifex/spinifex/foundation/messaging/nats"
|
||||
"github.com/nats-io/nats.go"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// fakeSealer is a recording ec2AccountSettingsSealer. Each call beyond
|
||||
// failFor succeeds with a fresh, strictly increasing revision, unless err is
|
||||
// set, in which case every call after failFor fails with it.
|
||||
type fakeSealer struct {
|
||||
mu sync.Mutex
|
||||
calls []string
|
||||
failFor int
|
||||
err error
|
||||
revision uint64
|
||||
}
|
||||
|
||||
func (f *fakeSealer) SealAccountSettings(_ context.Context, accountID string) (uint64, error) {
|
||||
f.mu.Lock()
|
||||
defer f.mu.Unlock()
|
||||
f.calls = append(f.calls, accountID)
|
||||
if len(f.calls) <= f.failFor {
|
||||
return 0, errors.New("account settings owner temporarily unavailable")
|
||||
}
|
||||
if f.err != nil {
|
||||
return 0, f.err
|
||||
}
|
||||
f.revision++
|
||||
return f.revision, nil
|
||||
}
|
||||
|
||||
// fakeSealCapability is a recording sealCapabilityChecker returning a fixed report.
|
||||
type fakeSealCapability struct {
|
||||
calls int
|
||||
report sealCapabilityReport
|
||||
}
|
||||
|
||||
func (f *fakeSealCapability) CheckSealCapability(context.Context, string) sealCapabilityReport {
|
||||
f.calls++
|
||||
return f.report
|
||||
}
|
||||
|
||||
// completeReport builds a sealCapabilityReport where every named node answers
|
||||
// compatible at version 1.
|
||||
func completeReport(nodeIDs ...string) sealCapabilityReport {
|
||||
var nodes []nodeSealCapability
|
||||
for _, node := range nodeIDs {
|
||||
nodes = append(nodes, nodeSealCapability{Node: node, Version: 1})
|
||||
}
|
||||
return sealCapabilityReport{Complete: true, Nodes: nodes}
|
||||
}
|
||||
|
||||
// alwaysTerminatingChecker stands in for IAM in the end-to-end test: the
|
||||
// account under test is always TERMINATING.
|
||||
type alwaysTerminatingChecker struct{}
|
||||
|
||||
func (alwaysTerminatingChecker) AccountTerminating(context.Context, string) (bool, error) {
|
||||
return true, nil
|
||||
}
|
||||
|
||||
// No subscriber on either subject makes the capability probe incomplete, so
|
||||
// no seal request is ever sent and the account stays TERMINATING with one
|
||||
// stuck ec2-account-settings item.
|
||||
func TestSealReaperNoResponderKeepsAccountTerminating(t *testing.T) {
|
||||
_, nc, _ := testutil.StartTestJetStream(t)
|
||||
|
||||
capability := newSealCapabilityClient(nc, []string{"node-1"})
|
||||
capability.wait = 50 * time.Millisecond
|
||||
capability.grace = 10 * time.Millisecond
|
||||
sealer := newEC2AccountSettingsSealClient(nc)
|
||||
sealer.timeout = 50 * time.Millisecond
|
||||
|
||||
reaper := &accountSettingsSealReaper{sealer: sealer, capability: capability}
|
||||
accounts := newFakeAccounts()
|
||||
engine := quietEngine(accounts, reaper)
|
||||
|
||||
result, err := engine.Teardown(testCtx(t), request())
|
||||
require.ErrorIs(t, err, ErrResourcesStuck)
|
||||
assert.False(t, result.AccountDeleted)
|
||||
assert.Equal(t, AccountStatusTerminating, accounts.account.Status)
|
||||
|
||||
var stuck []Stuck
|
||||
for _, stage := range result.Stages {
|
||||
stuck = append(stuck, stage.Stuck...)
|
||||
}
|
||||
require.Len(t, stuck, 1)
|
||||
assert.Equal(t, "ec2-account-settings", stuck[0].Resource.Kind)
|
||||
}
|
||||
|
||||
// Whatever the owner refuses with, the account stays TERMINATING: an owner
|
||||
// refusal, a timeout, and each reply shape the client rejects (wrong account,
|
||||
// wrong disposition, no revision).
|
||||
func TestSealReaperOwnerFailureKeepsAccountTerminating(t *testing.T) {
|
||||
cases := []struct {
|
||||
name string
|
||||
err error
|
||||
}{
|
||||
{"incorrect-state", errors.New(awserrors.ErrorIncorrectState)},
|
||||
{"internal-error", errors.New(awserrors.ErrorInternalError)},
|
||||
{"timeout", context.DeadlineExceeded},
|
||||
{"wrong-account", errors.New(`seal account settings: reply named account "999999999999", not "000000000042"`)},
|
||||
{"wrong-disposition", errors.New(`seal account settings: unexpected disposition "pending"`)},
|
||||
{"zero-revision", errors.New("seal account settings: reply carried no revision")},
|
||||
}
|
||||
for _, tc := range cases {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
sealer := &fakeSealer{err: tc.err}
|
||||
reaper := &accountSettingsSealReaper{sealer: sealer, capability: &fakeSealCapability{report: completeReport("node-1")}}
|
||||
accounts := newFakeAccounts()
|
||||
engine := quietEngine(accounts, reaper)
|
||||
|
||||
result, err := engine.Teardown(testCtx(t), request())
|
||||
require.ErrorIs(t, err, ErrResourcesStuck)
|
||||
assert.False(t, result.AccountDeleted)
|
||||
assert.Equal(t, AccountStatusTerminating, accounts.account.Status)
|
||||
assert.NotEmpty(t, sealer.calls)
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// The reaper retries through the engine's own drain mechanics: it fails
|
||||
// twice, then succeeds, and only the success lets the account be deleted.
|
||||
// List is non-empty before the success and empty only after it.
|
||||
func TestSealReaperCompletesOnlyAfterSealed(t *testing.T) {
|
||||
sealer := &fakeSealer{failFor: 2}
|
||||
reaper := &accountSettingsSealReaper{sealer: sealer, capability: &fakeSealCapability{report: completeReport("node-1")}}
|
||||
accounts := newFakeAccounts()
|
||||
engine := quietEngine(accounts, reaper)
|
||||
|
||||
before, err := reaper.List(testCtx(t), testAccountID)
|
||||
require.NoError(t, err)
|
||||
require.Len(t, before, 1)
|
||||
|
||||
result, err := engine.Teardown(testCtx(t), request())
|
||||
require.NoError(t, err)
|
||||
assert.True(t, result.AccountDeleted)
|
||||
assert.GreaterOrEqual(t, len(sealer.calls), 3)
|
||||
|
||||
after, err := reaper.List(testCtx(t), testAccountID)
|
||||
require.NoError(t, err)
|
||||
assert.Empty(t, after)
|
||||
}
|
||||
|
||||
// Each teardown builds a fresh engine and a fresh reaper, so a retried or
|
||||
// taken-over run seals again: two engines against the same owner both
|
||||
// succeed, each with a higher revision than the last.
|
||||
func TestSealReaperFreshRunSealsAgain(t *testing.T) {
|
||||
sealer := &fakeSealer{}
|
||||
capability := &fakeSealCapability{report: completeReport("node-1")}
|
||||
|
||||
firstEngine := quietEngine(newFakeAccounts(), &accountSettingsSealReaper{sealer: sealer, capability: capability})
|
||||
firstResult, err := firstEngine.Teardown(testCtx(t), request())
|
||||
require.NoError(t, err)
|
||||
assert.True(t, firstResult.AccountDeleted)
|
||||
|
||||
secondEngine := quietEngine(newFakeAccounts(), &accountSettingsSealReaper{sealer: sealer, capability: capability})
|
||||
secondResult, err := secondEngine.Teardown(testCtx(t), request())
|
||||
require.NoError(t, err)
|
||||
assert.True(t, secondResult.AccountDeleted)
|
||||
|
||||
require.Len(t, sealer.calls, 2)
|
||||
assert.Equal(t, uint64(2), sealer.revision)
|
||||
}
|
||||
|
||||
// Inventory and the explicit dry run, and a Teardown request marked dry run,
|
||||
// all list the pending seal and send no seal request: only a real teardown
|
||||
// may seal.
|
||||
func TestSealReaperInventoryDoesNotSeal(t *testing.T) {
|
||||
sealer := &fakeSealer{}
|
||||
capability := &fakeSealCapability{report: completeReport("node-1")}
|
||||
reaper := &accountSettingsSealReaper{sealer: sealer, capability: capability}
|
||||
accounts := newFakeAccounts()
|
||||
engine := quietEngine(accounts, reaper)
|
||||
|
||||
inventory, err := engine.Inventory(testCtx(t), testAccountID)
|
||||
require.NoError(t, err)
|
||||
assert.Empty(t, sealer.calls)
|
||||
assert.Zero(t, capability.calls)
|
||||
found := false
|
||||
for _, stage := range inventory.Stages {
|
||||
for _, resource := range stage.Deleted {
|
||||
if resource.Kind == "ec2-account-settings" {
|
||||
found = true
|
||||
}
|
||||
}
|
||||
}
|
||||
assert.True(t, found, "inventory must still list the pending seal")
|
||||
|
||||
dryRun := request()
|
||||
dryRun.DryRun = true
|
||||
_, err = engine.Teardown(testCtx(t), dryRun)
|
||||
require.NoError(t, err)
|
||||
assert.Empty(t, sealer.calls)
|
||||
assert.Zero(t, capability.calls)
|
||||
}
|
||||
|
||||
// A real settings service subscribed on the real seal subject, behind a real
|
||||
// engine: teardown seals the record, replacing the characterisation test that
|
||||
// showed it used to survive.
|
||||
func TestTeardownSealsAccountSettings(t *testing.T) {
|
||||
_, nc, js := testutil.StartTestJetStream(t)
|
||||
ctx := testCtx(t)
|
||||
|
||||
settings, err := ec2account.NewAccountSettingsServiceImplWithNATS(ctx, nil, nc)
|
||||
require.NoError(t, err)
|
||||
settings.SetAccountTerminationChecker(alwaysTerminatingChecker{})
|
||||
_, err = settings.EnableEbsEncryptionByDefault(ctx, &ec2.EnableEbsEncryptionByDefaultInput{}, testAccountID)
|
||||
require.NoError(t, err)
|
||||
|
||||
sealSub, err := nc.QueueSubscribe(ec2v1.SealAccountSettingsSubject, "spinifex-workers", func(msg *nats.Msg) {
|
||||
natsmsg.ServeNATSRequestCtx(msg, func(ctx context.Context, req *ec2v1.SealAccountSettingsRequest) (*ec2v1.SealAccountSettingsReply, error) {
|
||||
seal, err := settings.SealAccount(ctx, req.AccountID)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return &ec2v1.SealAccountSettingsReply{
|
||||
AccountID: req.AccountID, Disposition: ec2v1.AccountSettingsDispositionSealed, Revision: seal.Revision,
|
||||
}, nil
|
||||
})
|
||||
})
|
||||
require.NoError(t, err)
|
||||
t.Cleanup(func() { _ = sealSub.Unsubscribe() })
|
||||
|
||||
capSub, err := nc.Subscribe(ec2v1.AccountSettingsSealCapabilitySubject("node-1"), func(msg *nats.Msg) {
|
||||
reply, err := json.Marshal(ec2v1.AccountSettingsSealCapabilityReply{Node: "node-1", CapabilityVersion: 1})
|
||||
require.NoError(t, err)
|
||||
out := nats.NewMsg("")
|
||||
out.Data = reply
|
||||
out.Header.Set(natsmsg.NodeIDHeader, "node-1")
|
||||
require.NoError(t, msg.RespondMsg(out))
|
||||
})
|
||||
require.NoError(t, err)
|
||||
t.Cleanup(func() { _ = capSub.Unsubscribe() })
|
||||
require.NoError(t, nc.Flush())
|
||||
|
||||
accounts := newFakeAccounts()
|
||||
engine := quietEngine(accounts, EC2AccountSettingsReapers(nc, []string{"node-1"})...)
|
||||
// The real capability probe holds CollectUntilDeadline's full ResponderGrace
|
||||
// (150 ms) even when the one expected node answers instantly, so the quiet
|
||||
// engine's default 200 ms StageDrain leaves no room for the sweep after it.
|
||||
engine.Timeouts = Timeouts{StageDrain: 2 * time.Second, DrainPoll: 10 * time.Millisecond}
|
||||
|
||||
result, err := engine.Teardown(ctx, request())
|
||||
require.NoError(t, err)
|
||||
assert.True(t, result.AccountDeleted)
|
||||
|
||||
bucket, err := js.KeyValue(ctx, ec2account.KVBucketAccountSettings)
|
||||
require.NoError(t, err)
|
||||
entry, err := bucket.Get(ctx, testAccountID)
|
||||
require.NoError(t, err)
|
||||
var rec ec2account.AccountSettingsRecord
|
||||
require.NoError(t, json.Unmarshal(entry.Value(), &rec))
|
||||
assert.Equal(t, ec2account.AccountSettingsStateSealed, rec.State)
|
||||
}
|
||||
@@ -1,50 +0,0 @@
|
||||
package accountteardown
|
||||
|
||||
//test:in-package — drives the real final-stage reapers against the real
|
||||
// EC2 account-settings service to pin that teardown leaves the bucket alone.
|
||||
|
||||
import (
|
||||
"testing"
|
||||
|
||||
"github.com/aws/aws-sdk-go/service/ec2"
|
||||
"github.com/mulgadc/spinifex/internal/testkit"
|
||||
ec2account "github.com/mulgadc/spinifex/spinifex/domains/ec2/account"
|
||||
handlers_iam "github.com/mulgadc/spinifex/spinifex/handlers/iam"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// No reaper in this package references the EC2 account-settings bucket or
|
||||
// calls a settings delete. Running the real engine and the real StageAccount
|
||||
// reapers against an account with settings enabled shows the consequence:
|
||||
// the settings record outlives the account record it belongs to.
|
||||
func TestCurrentBehaviour_AccountTermination_EC2AccountSettingsSurviveTeardown(t *testing.T) {
|
||||
_, nc, js := testutil.StartTestJetStream(t)
|
||||
ctx := testCtx(t)
|
||||
|
||||
settings, err := ec2account.NewAccountSettingsServiceImplWithNATS(ctx, nil, nc)
|
||||
require.NoError(t, err)
|
||||
_, err = settings.EnableEbsEncryptionByDefault(ctx, &ec2.EnableEbsEncryptionByDefaultInput{}, testAccountID)
|
||||
require.NoError(t, err)
|
||||
_, err = settings.EnableSerialConsoleAccess(ctx, &ec2.EnableSerialConsoleAccessInput{}, testAccountID)
|
||||
require.NoError(t, err)
|
||||
|
||||
accounts := newFakeAccounts()
|
||||
iam := &accountIAM{account: &handlers_iam.Account{AccountID: testAccountID, AccountName: testAccountName}}
|
||||
engine := quietEngine(accounts, AccountReapers(iam, nil, nil)...)
|
||||
|
||||
result, err := engine.Teardown(ctx, request())
|
||||
require.NoError(t, err)
|
||||
assert.True(t, result.AccountDeleted)
|
||||
assert.True(t, accounts.deleted)
|
||||
assert.Zero(t, result.StuckCount())
|
||||
|
||||
bucket, err := js.KeyValue(ctx, ec2account.KVBucketAccountSettings)
|
||||
require.NoError(t, err)
|
||||
_, err = bucket.Get(ctx, testAccountID)
|
||||
require.NoError(t, err, "the settings key must still be present after the account is torn down")
|
||||
|
||||
out, err := settings.GetEbsEncryptionByDefault(ctx, &ec2.GetEbsEncryptionByDefaultInput{}, testAccountID)
|
||||
require.NoError(t, err)
|
||||
assert.True(t, *out.EbsEncryptionByDefault)
|
||||
}
|
||||
@@ -0,0 +1,89 @@
|
||||
package accountteardown
|
||||
|
||||
//test:in-package — pins ADR-0003:S4 and ADR-0001 Context item 2 for the EC2
|
||||
// settings seal: the legacy engine must reach the owner only through the
|
||||
// versioned contract and NATS, never by reading the settings bucket itself.
|
||||
|
||||
import (
|
||||
"go/ast"
|
||||
"go/parser"
|
||||
"go/token"
|
||||
"io/fs"
|
||||
"path/filepath"
|
||||
"runtime"
|
||||
"strconv"
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// forbiddenSettingsImports are imports that would let this package reach the
|
||||
// EC2 settings owner or the configured node set by a path other than the
|
||||
// versioned contract and NewClusterEngine's parameters.
|
||||
var forbiddenSettingsImports = []string{
|
||||
"github.com/mulgadc/spinifex/spinifex/domains/ec2/account",
|
||||
"github.com/mulgadc/spinifex/spinifex/bootstrap/config",
|
||||
}
|
||||
|
||||
// forbiddenSettingsIdentifiers would let this package name the settings
|
||||
// bucket or its key directly instead of reaching it only through
|
||||
// contracts/ec2/v1 and NATS.
|
||||
var forbiddenSettingsIdentifiers = []string{"spinifex-ec2-account-settings", "KVBucketAccountSettings"}
|
||||
|
||||
// Teardown reaches EC2 settings only over contracts/ec2/v1: no import of the
|
||||
// settings owner or bootstrap/config (nodes arrive via NewClusterEngine), and
|
||||
// no literal naming the settings bucket or its constant.
|
||||
func TestAccountTeardownHasNoSettingsKVAccess(t *testing.T) {
|
||||
_, file, _, ok := runtime.Caller(0)
|
||||
if !ok {
|
||||
t.Fatal("cannot locate test source")
|
||||
}
|
||||
root := filepath.Dir(file)
|
||||
|
||||
fset := token.NewFileSet()
|
||||
scanned := 0
|
||||
err := filepath.WalkDir(root, func(path string, d fs.DirEntry, err error) error {
|
||||
if err != nil || d.IsDir() || !strings.HasSuffix(path, ".go") || strings.HasSuffix(path, "_test.go") {
|
||||
return err
|
||||
}
|
||||
f, perr := parser.ParseFile(fset, path, nil, parser.ParseComments)
|
||||
if perr != nil {
|
||||
return perr
|
||||
}
|
||||
scanned++
|
||||
|
||||
for _, imp := range f.Imports {
|
||||
p, _ := strconv.Unquote(imp.Path.Value)
|
||||
for _, bad := range forbiddenSettingsImports {
|
||||
if p == bad {
|
||||
t.Errorf("%s: imports %s; the legacy engine must reach the EC2 settings owner only through contracts/ec2/v1 and the configured node set NewClusterEngine already receives",
|
||||
fset.Position(imp.Pos()), p)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
ast.Inspect(f, func(n ast.Node) bool {
|
||||
lit, ok := n.(*ast.BasicLit)
|
||||
if !ok || lit.Kind != token.STRING {
|
||||
return true
|
||||
}
|
||||
value, uerr := strconv.Unquote(lit.Value)
|
||||
if uerr != nil {
|
||||
return true
|
||||
}
|
||||
for _, bad := range forbiddenSettingsIdentifiers {
|
||||
if value == bad {
|
||||
t.Errorf("%s: names %q; the settings bucket and its key are the owner's own, never this package's",
|
||||
fset.Position(lit.Pos()), value)
|
||||
}
|
||||
}
|
||||
return true
|
||||
})
|
||||
return nil
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if scanned == 0 {
|
||||
t.Fatalf("scanned no Go files under %s; the invariant would pass vacuously", root)
|
||||
}
|
||||
}
|
||||
@@ -1289,6 +1289,15 @@ func (d *Daemon) subscribeAll() error {
|
||||
natsSub{viperblocklegacyv1.VolumeFencedSubject(d.node), d.handleVolumeFenced, ""},
|
||||
)
|
||||
|
||||
// Per-node, no queue group: a second daemon claiming this node ID also
|
||||
// answers, so the teardown probe sees a duplicate and refuses to seal. An
|
||||
// invalid node ID serves nothing, so this daemon reads as incompatible.
|
||||
if ec2v1.ValidSealCapabilityNode(d.node) {
|
||||
subs = append(subs, natsSub{ec2v1.AccountSettingsSealCapabilitySubject(d.node), handleNATSRequest(d.node, d.accountSettingsSealCapability), ""})
|
||||
} else {
|
||||
slog.Error("Not serving account-settings seal capability: node ID is not a single NATS subject token", "node", d.node)
|
||||
}
|
||||
|
||||
return d.registerNatsSubs(subs)
|
||||
}
|
||||
|
||||
|
||||
@@ -0,0 +1,23 @@
|
||||
package daemon
|
||||
|
||||
import (
|
||||
"context"
|
||||
|
||||
ec2v1 "github.com/mulgadc/spinifex/contracts/ec2/v1"
|
||||
awserrors "github.com/mulgadc/spinifex/spinifex/foundation/aws/errors"
|
||||
)
|
||||
|
||||
// accountSettingsSealCapability serves this daemon's read-only seal capability.
|
||||
// It reads no KV and takes no account; a request naming another node is a
|
||||
// caller mistake, since the subject is already addressed to this node.
|
||||
func (d *Daemon) accountSettingsSealCapability(_ context.Context, req *ec2v1.AccountSettingsSealCapabilityRequest, _ string) (*ec2v1.AccountSettingsSealCapabilityReply, error) {
|
||||
if req.Node != d.node {
|
||||
return nil, awserrors.Errorf(awserrors.ErrorInvalidParameterValue,
|
||||
"seal capability request for node %q answered by node %q", req.Node, d.node)
|
||||
}
|
||||
return &ec2v1.AccountSettingsSealCapabilityReply{
|
||||
Node: d.node,
|
||||
CapabilityVersion: ec2v1.AccountSettingsSealCapabilityVersion,
|
||||
CorrelationRef: req.CorrelationRef,
|
||||
}, nil
|
||||
}
|
||||
@@ -0,0 +1,115 @@
|
||||
package daemon
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
ec2v1 "github.com/mulgadc/spinifex/contracts/ec2/v1"
|
||||
"github.com/mulgadc/spinifex/internal/testkit"
|
||||
awserrors "github.com/mulgadc/spinifex/spinifex/foundation/aws/errors"
|
||||
"github.com/nats-io/nats.go"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// newCapabilityTestDaemon builds a daemon serving its real subscription table
|
||||
// with node as its configured node ID.
|
||||
func newCapabilityTestDaemon(t *testing.T, node string) (*nats.Conn, *nats.Conn) {
|
||||
t.Helper()
|
||||
ns, nc, _ := testutil.StartTestJetStream(t)
|
||||
|
||||
d := newSubscribeTestDaemon(t, nc, "", "")
|
||||
d.node = node
|
||||
require.NoError(t, d.subscribeAll())
|
||||
require.NoError(t, nc.Flush())
|
||||
|
||||
caller, err := nats.Connect(ns.ClientURL())
|
||||
require.NoError(t, err)
|
||||
t.Cleanup(caller.Close)
|
||||
return nc, caller
|
||||
}
|
||||
|
||||
func capabilityRequest(t *testing.T, nc *nats.Conn, node string) *nats.Msg {
|
||||
t.Helper()
|
||||
data, err := json.Marshal(ec2v1.AccountSettingsSealCapabilityRequest{Node: node, CorrelationRef: "req-1"})
|
||||
require.NoError(t, err)
|
||||
reply, err := nc.Request(ec2v1.AccountSettingsSealCapabilitySubject(node), data, 5*time.Second)
|
||||
require.NoError(t, err)
|
||||
return reply
|
||||
}
|
||||
|
||||
// The responder answers its own node with version 1, the configured node and
|
||||
// no KV access (no settings service is wired into the test daemon at all).
|
||||
func TestAccountSettingsSealCapabilityAnswersOwnNode(t *testing.T) {
|
||||
_, caller := newCapabilityTestDaemon(t, "node-1")
|
||||
|
||||
raw := capabilityRequest(t, caller, "node-1")
|
||||
assert.Equal(t, "node-1", raw.Header.Get("X-Node-ID"))
|
||||
|
||||
var reply ec2v1.AccountSettingsSealCapabilityReply
|
||||
require.NoError(t, json.Unmarshal(raw.Data, &reply))
|
||||
assert.Equal(t, "node-1", reply.Node)
|
||||
assert.Equal(t, ec2v1.AccountSettingsSealCapabilityVersion, reply.CapabilityVersion)
|
||||
assert.Equal(t, "req-1", reply.CorrelationRef)
|
||||
}
|
||||
|
||||
// A request naming a node other than this daemon's own is refused, not
|
||||
// answered as if it were this node.
|
||||
func TestAccountSettingsSealCapabilityRefusesOtherNode(t *testing.T) {
|
||||
_, caller := newCapabilityTestDaemon(t, "node-1")
|
||||
|
||||
data, err := json.Marshal(ec2v1.AccountSettingsSealCapabilityRequest{Node: "node-2"})
|
||||
require.NoError(t, err)
|
||||
raw, err := caller.Request(ec2v1.AccountSettingsSealCapabilitySubject("node-1"), data, 5*time.Second)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, awserrors.ErrorInvalidParameterValue, replyErrCode(t, raw.Data))
|
||||
}
|
||||
|
||||
// The subject is per node with no queue group, so two daemons configured
|
||||
// with the same node ID both answer a request addressed to that node.
|
||||
func TestAccountSettingsSealCapabilityHasNoQueueGroup(t *testing.T) {
|
||||
_, nc, _ := testutil.StartTestJetStream(t)
|
||||
|
||||
first := newSubscribeTestDaemon(t, nc, "", "")
|
||||
first.node = "node-1"
|
||||
require.NoError(t, first.subscribeAll())
|
||||
|
||||
second := newSubscribeTestDaemon(t, nc, "", "")
|
||||
second.node = "node-1"
|
||||
require.NoError(t, second.subscribeAll())
|
||||
require.NoError(t, nc.Flush())
|
||||
|
||||
sub, err := nc.SubscribeSync(nats.NewInbox())
|
||||
require.NoError(t, err)
|
||||
t.Cleanup(func() { _ = sub.Unsubscribe() })
|
||||
|
||||
data, err := json.Marshal(ec2v1.AccountSettingsSealCapabilityRequest{Node: "node-1"})
|
||||
require.NoError(t, err)
|
||||
msg := nats.NewMsg(ec2v1.AccountSettingsSealCapabilitySubject("node-1"))
|
||||
msg.Data = data
|
||||
msg.Reply = sub.Subject
|
||||
require.NoError(t, nc.PublishMsg(msg))
|
||||
require.NoError(t, nc.Flush())
|
||||
|
||||
seen := 0
|
||||
for {
|
||||
_, err := sub.NextMsg(300 * time.Millisecond)
|
||||
if err != nil {
|
||||
break
|
||||
}
|
||||
seen++
|
||||
}
|
||||
assert.Equal(t, 2, seen)
|
||||
}
|
||||
|
||||
// A wildcard node ID must not become a wildcard subscription: built unchecked,
|
||||
// "node-*" would answer probes addressed to node-1 on node-1's behalf.
|
||||
func TestAccountSettingsSealCapabilityNotServedForInvalidNodeID(t *testing.T) {
|
||||
_, caller := newCapabilityTestDaemon(t, "node-*")
|
||||
|
||||
data, err := json.Marshal(ec2v1.AccountSettingsSealCapabilityRequest{Node: "node-1"})
|
||||
require.NoError(t, err)
|
||||
_, err = caller.Request(ec2v1.AccountSettingsSealCapabilitySubject("node-1"), data, time.Second)
|
||||
require.ErrorIs(t, err, nats.ErrNoResponders)
|
||||
}
|
||||
@@ -0,0 +1,68 @@
|
||||
package account
|
||||
|
||||
//test:in-package — pins what AccountSettingsSealCapabilityVersion 1 asserts:
|
||||
// nothing in this package writes the settings KV except through the
|
||||
// revision-guarded helpers.
|
||||
|
||||
import (
|
||||
"go/ast"
|
||||
"go/parser"
|
||||
"go/token"
|
||||
"io/fs"
|
||||
"path/filepath"
|
||||
"runtime"
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
func accountPackageDir(t *testing.T) string {
|
||||
t.Helper()
|
||||
_, file, _, ok := runtime.Caller(0)
|
||||
if !ok {
|
||||
t.Fatal("cannot locate test source")
|
||||
}
|
||||
return filepath.Dir(file)
|
||||
}
|
||||
|
||||
// The capability daemons report as version 1 is a claim about every writer in
|
||||
// the binary, not just the responder: no non-test file in this package may
|
||||
// call Put or PutString, which bypass the revision-guarded mutate/seal paths.
|
||||
func TestAccountSettingsWritesAreRevisionGuarded(t *testing.T) {
|
||||
root := accountPackageDir(t)
|
||||
fset := token.NewFileSet()
|
||||
scanned := 0
|
||||
|
||||
err := filepath.WalkDir(root, func(path string, d fs.DirEntry, err error) error {
|
||||
if err != nil || d.IsDir() || !strings.HasSuffix(path, ".go") || strings.HasSuffix(path, "_test.go") {
|
||||
return err
|
||||
}
|
||||
f, perr := parser.ParseFile(fset, path, nil, 0)
|
||||
if perr != nil {
|
||||
return perr
|
||||
}
|
||||
scanned++
|
||||
|
||||
ast.Inspect(f, func(n ast.Node) bool {
|
||||
call, ok := n.(*ast.CallExpr)
|
||||
if !ok {
|
||||
return true
|
||||
}
|
||||
sel, ok := call.Fun.(*ast.SelectorExpr)
|
||||
if !ok {
|
||||
return true
|
||||
}
|
||||
if sel.Sel.Name == "Put" || sel.Sel.Name == "PutString" {
|
||||
t.Errorf("%s: unconditional %s call bypasses the revision-guarded settings write; use mutateSettings or SealAccount's CAS loop instead",
|
||||
fset.Position(call.Pos()), sel.Sel.Name)
|
||||
}
|
||||
return true
|
||||
})
|
||||
return nil
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if scanned == 0 {
|
||||
t.Fatalf("scanned no Go files under %s; the invariant would pass vacuously", root)
|
||||
}
|
||||
}
|
||||
@@ -3,7 +3,6 @@ package instance
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"fmt"
|
||||
"github.com/mulgadc/spinifex/spinifex/foundation/messaging/nats"
|
||||
"log/slog"
|
||||
@@ -101,10 +100,10 @@ func DescribeInstanceTypes(ctx context.Context, input *ec2.DescribeInstanceTypes
|
||||
|
||||
if missing := missingInstanceTypes(finalInstanceTypes, input.InstanceTypes); len(missing) > 0 {
|
||||
if !proveAbsence || !everyNodeAnswered(nodeIDs, answered, sum) {
|
||||
return nil, errors.Join(
|
||||
return nil, awserrors.WithRetryAfter(
|
||||
awserrors.Errorf(awserrors.ErrorServiceUnavailable,
|
||||
"cannot confirm instance type(s) %s: describe fan-out did not complete", strings.Join(missing, ", ")),
|
||||
awserrors.RetryAfter(awserrors.ErrorServiceUnavailable, describeIncompleteRetryAfter),
|
||||
describeIncompleteRetryAfter,
|
||||
)
|
||||
}
|
||||
return nil, awserrors.Errorf(awserrors.ErrorInvalidInstanceType,
|
||||
|
||||
@@ -126,10 +126,10 @@ func DescribeInstancesChecked(ctx context.Context, input *ec2.DescribeInstancesI
|
||||
// An incomplete sweep cannot prove absence, so a missing id is
|
||||
// unresolved, not gone. NotFound would be a false negative and an
|
||||
// empty success would look identical to a real one, so return 503.
|
||||
return nil, errors.Join(
|
||||
return nil, awserrors.WithRetryAfter(
|
||||
awserrors.Errorf(awserrors.ErrorServiceUnavailable,
|
||||
"cannot confirm status of instance(s) %s: describe fan-out did not complete", strings.Join(missing, ", ")),
|
||||
awserrors.RetryAfter(awserrors.ErrorServiceUnavailable, describeIncompleteRetryAfter),
|
||||
describeIncompleteRetryAfter,
|
||||
)
|
||||
}
|
||||
}
|
||||
@@ -198,10 +198,10 @@ func DescribeAccountInstancesComplete(ctx context.Context, natsConn *nats.Conn,
|
||||
}
|
||||
|
||||
func incompleteListingError() error {
|
||||
return errors.Join(
|
||||
return awserrors.WithRetryAfter(
|
||||
awserrors.Errorf(awserrors.ErrorServiceUnavailable,
|
||||
"cannot list instances: not every node and instance store answered"),
|
||||
awserrors.RetryAfter(awserrors.ErrorServiceUnavailable, describeIncompleteRetryAfter),
|
||||
describeIncompleteRetryAfter,
|
||||
)
|
||||
}
|
||||
|
||||
|
||||
@@ -658,13 +658,22 @@ func HasDependencies(kind, id string) error {
|
||||
// retryableError wraps a registered code with a suggested Retry-After
|
||||
// duration, for a 503 that a client can expect to clear on its own within a
|
||||
// bounded window (e.g. a warm-up race) rather than an open-ended outage.
|
||||
// Error() returns only the code, so code resolution is unaffected.
|
||||
// Error() returns only the code, or the wrapped error's text, so code
|
||||
// resolution is unaffected.
|
||||
type retryableError struct {
|
||||
code string
|
||||
err error
|
||||
retryAfter time.Duration
|
||||
}
|
||||
|
||||
func (e *retryableError) Error() string { return e.code }
|
||||
func (e *retryableError) Error() string {
|
||||
if e.err != nil {
|
||||
return e.err.Error()
|
||||
}
|
||||
return e.code
|
||||
}
|
||||
|
||||
func (e *retryableError) Unwrap() error { return e.err }
|
||||
|
||||
// RetryAfter wraps code (a registered ErrorLookup key) with a suggested
|
||||
// Retry-After duration for ErrorHandler to surface as a response header.
|
||||
@@ -672,6 +681,13 @@ func RetryAfter(code string, d time.Duration) error {
|
||||
return &retryableError{code: code, retryAfter: d}
|
||||
}
|
||||
|
||||
// WithRetryAfter attaches a suggested Retry-After duration to err without
|
||||
// changing its text, unlike joining err with RetryAfter, which appends the
|
||||
// bare code on a second line.
|
||||
func WithRetryAfter(err error, d time.Duration) error {
|
||||
return &retryableError{err: err, retryAfter: d}
|
||||
}
|
||||
|
||||
// ResolveRetryAfter returns the Retry-After duration attached to err via
|
||||
// RetryAfter, if any, walking the same unwrap tree ResolveErrorDetail does.
|
||||
func ResolveRetryAfter(err error) (time.Duration, bool) {
|
||||
|
||||
@@ -176,6 +176,24 @@ func TestResolveRetryAfter_WrappedAndResolvable(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// WithRetryAfter keeps the coded error's text and message while still
|
||||
// carrying the hint: a joined RetryAfter would log the code twice.
|
||||
func TestWithRetryAfter_KeepsTextAndResolves(t *testing.T) {
|
||||
inner := Errorf(ErrorServiceUnavailable, "probe incomplete")
|
||||
err := WithRetryAfter(inner, 5*time.Second)
|
||||
|
||||
if err.Error() != inner.Error() {
|
||||
t.Fatalf("Error() = %q, want %q", err.Error(), inner.Error())
|
||||
}
|
||||
if d, ok := ResolveRetryAfter(fmt.Errorf("wrapped: %w", err)); !ok || d != 5*time.Second {
|
||||
t.Fatalf("ResolveRetryAfter() = (%v, %v), want (5s, true)", d, ok)
|
||||
}
|
||||
code, msg, ok := ResolveErrorDetail(err)
|
||||
if !ok || code != ErrorServiceUnavailable || msg != "probe incomplete" {
|
||||
t.Fatalf("ResolveErrorDetail() = (%q, %q, %v), want (%q, %q, true)", code, msg, ok, ErrorServiceUnavailable, "probe incomplete")
|
||||
}
|
||||
}
|
||||
|
||||
// TestResolveRetryAfter_PlainErrorNotFound is the compatibility case: an
|
||||
// ordinary errors.New(code) -- the overwhelming majority of call sites --
|
||||
// carries no Retry-After hint.
|
||||
|
||||
@@ -12,6 +12,7 @@ import (
|
||||
"time"
|
||||
|
||||
"github.com/aws/aws-sdk-go/service/s3"
|
||||
ec2v1 "github.com/mulgadc/spinifex/contracts/ec2/v1"
|
||||
"github.com/mulgadc/spinifex/internal/testkit"
|
||||
"github.com/mulgadc/spinifex/spinifex/accountteardown"
|
||||
"github.com/mulgadc/spinifex/spinifex/foundation/aws/errors"
|
||||
@@ -31,6 +32,10 @@ const deleteClientToken = "8b9c1d2e3f4a5b6c7d8e9f0a1b2c3d4e"
|
||||
// to keep step with the reapers NewClusterEngine wires.
|
||||
var teardownSubjects = []string{"ec2.>", "ecs.>", "eks.>", "rds.>", "elbv2.>", "acm.>", "bedrock.>"}
|
||||
|
||||
// sealCapabilitySubjectPrefix matches every per-node seal-capability subject,
|
||||
// which the generic ec2.> stub below must not also answer.
|
||||
const sealCapabilitySubjectPrefix = "ec2.v1.AccountSettingsSealCapability."
|
||||
|
||||
// newDeleteAccountGateway wires a gateway against a real IAM service and
|
||||
// embedded JetStream, with a stub cluster answering the subjects the reapers
|
||||
// drive. The tenant has no resources, so every stage drains empty and the test
|
||||
@@ -46,8 +51,12 @@ func newDeleteAccountGateway(t *testing.T) *GatewayConfig {
|
||||
|
||||
for _, subject := range teardownSubjects {
|
||||
// Replies carry a node ID: the instance inventory only counts a frame
|
||||
// it can attribute to a configured node.
|
||||
// it can attribute to a configured node. The seal subjects have their
|
||||
// own responders below, which a second reply here would race.
|
||||
sub, err := nc.Subscribe(subject, func(msg *nats.Msg) {
|
||||
if msg.Subject == ec2v1.SealAccountSettingsSubject || strings.HasPrefix(msg.Subject, sealCapabilitySubjectPrefix) {
|
||||
return
|
||||
}
|
||||
reply := nats.NewMsg(msg.Reply)
|
||||
reply.Data = []byte(`{}`)
|
||||
reply.Header.Set(natsmsg.NodeIDHeader, "node-1")
|
||||
@@ -56,6 +65,38 @@ func newDeleteAccountGateway(t *testing.T) *GatewayConfig {
|
||||
require.NoError(t, err)
|
||||
t.Cleanup(func() { _ = sub.Unsubscribe() })
|
||||
}
|
||||
|
||||
// The seal reaper needs a real sealed disposition and revision, and every
|
||||
// configured node answering capability version 1, or it never finalises:
|
||||
// the generic `{}` stub above is neither.
|
||||
sealSub, err := nc.Subscribe(ec2v1.SealAccountSettingsSubject, func(msg *nats.Msg) {
|
||||
var req ec2v1.SealAccountSettingsRequest
|
||||
if json.Unmarshal(msg.Data, &req) != nil {
|
||||
return
|
||||
}
|
||||
data, _ := json.Marshal(ec2v1.SealAccountSettingsReply{
|
||||
AccountID: req.AccountID, CorrelationRef: req.CorrelationRef,
|
||||
Disposition: ec2v1.AccountSettingsDispositionSealed, Revision: 1,
|
||||
})
|
||||
reply := nats.NewMsg(msg.Reply)
|
||||
reply.Data = data
|
||||
reply.Header.Set(natsmsg.NodeIDHeader, "node-1")
|
||||
_ = msg.RespondMsg(reply)
|
||||
})
|
||||
require.NoError(t, err)
|
||||
t.Cleanup(func() { _ = sealSub.Unsubscribe() })
|
||||
|
||||
for _, node := range []string{"node-1"} {
|
||||
capSub, err := nc.Subscribe(ec2v1.AccountSettingsSealCapabilitySubject(node), func(msg *nats.Msg) {
|
||||
data, _ := json.Marshal(ec2v1.AccountSettingsSealCapabilityReply{Node: node, CapabilityVersion: ec2v1.AccountSettingsSealCapabilityVersion})
|
||||
reply := nats.NewMsg(msg.Reply)
|
||||
reply.Data = data
|
||||
reply.Header.Set(natsmsg.NodeIDHeader, node)
|
||||
_ = msg.RespondMsg(reply)
|
||||
})
|
||||
require.NoError(t, err)
|
||||
t.Cleanup(func() { _ = capSub.Unsubscribe() })
|
||||
}
|
||||
require.NoError(t, nc.Flush())
|
||||
|
||||
return &GatewayConfig{
|
||||
|
||||
Reference in New Issue
Block a user