Files
seaweedfs/weed/s3api/s3api_internal_lifecycle_test.go
T
Chris LuandClaude Opus 5.5 2be4498c04 s3 lifecycle: walker deletes carry the listed identity and must target the latest version (#12452)
* s3 lifecycle: send the listed entry's identity on walker deletes

The daily walker dispatched LifecycleDelete with no ExpectedIdentity, so
the server skipped its compare-and-swap and an object rewritten between
listing and dispatch was deleted. The list adapter now records each
listed entry's identity, computed the same way as on the event path, and
the walker sends it.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* s3 lifecycle: current-version expiration must target the latest version

The walker addresses the latest version of a versioned key by id. A
version file never changes, so its identity still matches after a newer
PUT, and the delete went ahead: a delete marker over the new version with
versioning enabled, or the new null version deleted while suspended.
LifecycleDelete now resolves the key's latest version for
EXPIRATION_DAYS/EXPIRATION_DATE requests that carry a version id and
answers NOOP_RESOLVED (VERSION_NOT_LATEST) when it is a different one.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* s3 lifecycle: check the latest version for unaddressed suspended expirations

With versioning suspended, an expiration without a version id reads the
plain entry, which is the null version but not necessarily the latest:
a newer real version can sit in .versions. The latest-version check now
runs in the expiration branch, by versioning state: for every suspended
request (an unaddressed one addresses the null version) and for enabled
requests that carry a version id.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* s3 lifecycle: test that each version sibling carries its own identity

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 09:39:12 -08:00

471 lines
18 KiB
Go

package s3api
import (
"bytes"
"context"
"net"
"testing"
"time"
"github.com/prometheus/client_golang/prometheus/testutil"
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
"github.com/seaweedfs/seaweedfs/weed/pb/s3_lifecycle_pb"
"github.com/seaweedfs/seaweedfs/weed/s3api/s3_constants"
"github.com/seaweedfs/seaweedfs/weed/s3api/s3lifecycle"
"github.com/seaweedfs/seaweedfs/weed/security"
stats_collect "github.com/seaweedfs/seaweedfs/weed/stats"
"github.com/stretchr/testify/require"
"google.golang.org/grpc/codes"
"google.golang.org/grpc/peer"
"google.golang.org/grpc/status"
"google.golang.org/protobuf/proto"
)
func TestComputeEntryIdentity_BasicFields(t *testing.T) {
entry := &filer_pb.Entry{
Attributes: &filer_pb.FuseAttributes{Mtime: 1700000000, MtimeNs: 123, FileSize: 4096},
Chunks: []*filer_pb.FileChunk{
{FileId: "1,abc"},
{FileId: "1,def"},
},
}
id := computeEntryIdentity(entry)
want := int64(1700000000)*int64(1e9) + int64(123)
if id.MtimeNs != want {
t.Fatalf("MtimeNs want %d, got %d", want, id.MtimeNs)
}
if id.Size != 4096 {
t.Fatalf("Size want 4096, got %d", id.Size)
}
if id.HeadFid != "1,abc" {
t.Fatalf("HeadFid want 1,abc, got %s", id.HeadFid)
}
}
func TestComputeEntryIdentity_NilSafeMissingChunks(t *testing.T) {
if got := computeEntryIdentity(nil); got != nil {
t.Fatalf("nil entry should return nil, got %v", got)
}
id := computeEntryIdentity(&filer_pb.Entry{})
if id == nil {
t.Fatalf("entry with nil Attributes should still produce identity")
}
if id.HeadFid != "" {
t.Fatalf("missing chunks should yield empty HeadFid, got %s", id.HeadFid)
}
}
func TestHashExtended_OrderStable(t *testing.T) {
a := map[string][]byte{"k1": []byte("v1"), "k2": []byte("v2")}
b := map[string][]byte{"k2": []byte("v2"), "k1": []byte("v1")}
if !bytes.Equal(s3lifecycle.HashExtended(a), s3lifecycle.HashExtended(b)) {
t.Fatalf("hash should be insensitive to map iteration order")
}
}
func TestHashExtended_DelimiterCollisionResistant(t *testing.T) {
// Naively concatenated: "k1=v1k2v2" could collide with "k1=v1k" / "2v2".
// Length-prefix encoding must keep them apart.
a := map[string][]byte{"k1": []byte("v1"), "k2": []byte("v2")}
b := map[string][]byte{"k1": []byte("v1k2v2")}
if bytes.Equal(s3lifecycle.HashExtended(a), s3lifecycle.HashExtended(b)) {
t.Fatalf("delimiter-forged Extended payloads must not collide")
}
}
func TestHashExtended_NilEqualsEmpty(t *testing.T) {
if got := s3lifecycle.HashExtended(nil); len(got) != 0 {
t.Fatalf("nil should produce zero-length hash, got %d bytes", len(got))
}
if got := s3lifecycle.HashExtended(map[string][]byte{}); len(got) != 0 {
t.Fatalf("empty map should produce zero-length hash, got %d bytes", len(got))
}
}
func TestIdentityMatches_NilWantTreatedAsMatch(t *testing.T) {
// Bootstrap callers that don't yet have an identity to CAS against
// pass nil expected_identity; the server treats this as "no CAS".
live := &s3_lifecycle_pb.EntryIdentity{MtimeNs: 1, Size: 2}
if !identityMatches(live, nil) {
t.Fatalf("nil want should match")
}
}
func TestIdentityMatches_NilLiveDoesNotMatch(t *testing.T) {
if identityMatches(nil, &s3_lifecycle_pb.EntryIdentity{MtimeNs: 1}) {
t.Fatalf("nil live should not match a populated want")
}
}
func TestIdentityMatches_AllFieldsCompared(t *testing.T) {
base := &s3_lifecycle_pb.EntryIdentity{MtimeNs: 100, Size: 2048, HeadFid: "1,abc", ExtendedHash: []byte{0x01, 0x02}}
cases := []struct {
name string
live *s3_lifecycle_pb.EntryIdentity
want bool
}{
{"identical", &s3_lifecycle_pb.EntryIdentity{MtimeNs: 100, Size: 2048, HeadFid: "1,abc", ExtendedHash: []byte{0x01, 0x02}}, true},
{"mtime-drift", &s3_lifecycle_pb.EntryIdentity{MtimeNs: 101, Size: 2048, HeadFid: "1,abc", ExtendedHash: []byte{0x01, 0x02}}, false},
{"size-drift", &s3_lifecycle_pb.EntryIdentity{MtimeNs: 100, Size: 2049, HeadFid: "1,abc", ExtendedHash: []byte{0x01, 0x02}}, false},
{"fid-drift", &s3_lifecycle_pb.EntryIdentity{MtimeNs: 100, Size: 2048, HeadFid: "1,xyz", ExtendedHash: []byte{0x01, 0x02}}, false},
{"extended-drift", &s3_lifecycle_pb.EntryIdentity{MtimeNs: 100, Size: 2048, HeadFid: "1,abc", ExtendedHash: []byte{0x03, 0x04}}, false},
}
for _, c := range cases {
t.Run(c.name, func(t *testing.T) {
if got := identityMatches(c.live, base); got != c.want {
t.Fatalf("want %v, got %v", c.want, got)
}
})
}
}
func TestLifecycleDelete_RejectsEmptyRequest(t *testing.T) {
s := &S3ApiServer{}
resp, err := s.LifecycleDelete(s3LocalPeerCtx(), &s3_lifecycle_pb.LifecycleDeleteRequest{})
if err != nil {
t.Fatalf("unexpected gRPC error: %v", err)
}
if resp.Outcome != s3_lifecycle_pb.LifecycleDeleteOutcome_BLOCKED {
t.Fatalf("empty request should be BLOCKED, got %v", resp.Outcome)
}
}
func TestLifecycleAbortMPU_RejectsTraversalUploadIDs(t *testing.T) {
// "." and ".." pass the no-slash check but resolve to the bucket
// root via util.JoinPath; they must be rejected before any rm call.
s := &S3ApiServer{}
cases := []string{
"",
".uploads",
".uploads/",
".uploads/.",
".uploads/..",
".uploads/u1/extra",
}
for _, path := range cases {
t.Run(path, func(t *testing.T) {
resp, err := s.LifecycleDelete(s3LocalPeerCtx(), &s3_lifecycle_pb.LifecycleDeleteRequest{
Bucket: "bk",
ObjectPath: path,
ActionKind: s3_lifecycle_pb.ActionKind_ABORT_MPU,
})
if err != nil {
t.Fatalf("unexpected gRPC error: %v", err)
}
if resp.Outcome != s3_lifecycle_pb.LifecycleDeleteOutcome_BLOCKED {
t.Fatalf("path %q: outcome=%v reason=%q, want BLOCKED",
path, resp.Outcome, resp.Reason)
}
})
}
}
func TestLifecycleDispatch_AbortMPUAfterFetchIsBlocked(t *testing.T) {
// LifecycleDelete routes ABORT_MPU to lifecycleAbortMPU before
// getObjectEntry; reaching lifecycleDispatch with ABORT_MPU means
// some caller bypassed that route. Defensive BLOCKED so a
// regression there can't accidentally rm a real object via the
// expiration paths.
s := &S3ApiServer{}
resp, err := s.lifecycleDispatch(nil, &s3_lifecycle_pb.LifecycleDeleteRequest{
Bucket: "bk",
ObjectPath: "k",
ActionKind: s3_lifecycle_pb.ActionKind_ABORT_MPU,
}, &filer_pb.Entry{Attributes: &filer_pb.FuseAttributes{}})
if err != nil {
t.Fatalf("unexpected gRPC error: %v", err)
}
if resp.Outcome != s3_lifecycle_pb.LifecycleDeleteOutcome_BLOCKED {
t.Fatalf("ABORT_MPU at dispatch should be BLOCKED, got %v reason=%q", resp.Outcome, resp.Reason)
}
if !contains(resp.Reason, "ABORT_MPU dispatched after fetch") {
t.Fatalf("reason should name the route bypass, got %q", resp.Reason)
}
}
func TestLifecycleDispatch_UnknownActionKindIsBlocked(t *testing.T) {
// An ActionKind value the proto doesn't define yet must produce a
// FATAL outcome rather than fall through to a default delete path.
s := &S3ApiServer{}
const bogus = s3_lifecycle_pb.ActionKind(999)
resp, err := s.lifecycleDispatch(nil, &s3_lifecycle_pb.LifecycleDeleteRequest{
Bucket: "bk",
ObjectPath: "k",
ActionKind: bogus,
}, &filer_pb.Entry{Attributes: &filer_pb.FuseAttributes{}})
if err != nil {
t.Fatalf("unexpected gRPC error: %v", err)
}
if resp.Outcome != s3_lifecycle_pb.LifecycleDeleteOutcome_BLOCKED {
t.Fatalf("unknown action kind should be BLOCKED, got %v reason=%q", resp.Outcome, resp.Reason)
}
if !contains(resp.Reason, "unknown action_kind") {
t.Fatalf("reason should name the unknown kind, got %q", resp.Reason)
}
}
func TestLifecycleDispatch_NoncurrentRequiresVersionID(t *testing.T) {
// Noncurrent / EXPIRED_DELETE_MARKER target a specific version; an
// empty version_id is a writer-side bug and must be rejected before
// any filer call. This pinning keeps the early-return in place so
// a refactor doesn't accidentally let the empty-version_id path
// reach deleteSpecificObjectVersion.
s := &S3ApiServer{}
for _, kind := range []s3_lifecycle_pb.ActionKind{
s3_lifecycle_pb.ActionKind_NONCURRENT_DAYS,
s3_lifecycle_pb.ActionKind_NEWER_NONCURRENT,
s3_lifecycle_pb.ActionKind_EXPIRED_DELETE_MARKER,
} {
t.Run(kind.String(), func(t *testing.T) {
resp, err := s.lifecycleDispatch(nil, &s3_lifecycle_pb.LifecycleDeleteRequest{
Bucket: "bk",
ObjectPath: "k",
ActionKind: kind,
// VersionId intentionally empty
}, &filer_pb.Entry{Attributes: &filer_pb.FuseAttributes{}})
if err != nil {
t.Fatalf("unexpected gRPC error: %v", err)
}
if resp.Outcome != s3_lifecycle_pb.LifecycleDeleteOutcome_BLOCKED {
t.Fatalf("kind %v with empty version_id should be BLOCKED, got %v reason=%q",
kind, resp.Outcome, resp.Reason)
}
if !contains(resp.Reason, "version_id required") {
t.Fatalf("reason should name the missing version_id, got %q", resp.Reason)
}
})
}
}
// contains is a tiny helper so the tests above don't pull in strings
// just for a substring check.
func contains(haystack, needle string) bool {
if len(needle) == 0 {
return true
}
for i := 0; i+len(needle) <= len(haystack); i++ {
if haystack[i:i+len(needle)] == needle {
return true
}
}
return false
}
func TestEntryUsesMetadataOnlyDelete(t *testing.T) {
cases := []struct {
name string
entry *filer_pb.Entry
want bool
}{
{
name: "nil entry",
entry: nil,
want: false,
},
{
name: "nil attributes",
entry: &filer_pb.Entry{},
want: false,
},
{
name: "TtlSec=0 (no per-write stamp)",
entry: &filer_pb.Entry{Attributes: &filer_pb.FuseAttributes{TtlSec: 0}},
want: false,
},
{
name: "TtlSec>0 (PR 9377 stamped a fast-path TTL)",
entry: &filer_pb.Entry{Attributes: &filer_pb.FuseAttributes{TtlSec: 86400}},
want: true,
},
{
name: "TtlSec<0 should not happen but must not flip the path on",
entry: &filer_pb.Entry{Attributes: &filer_pb.FuseAttributes{TtlSec: -1}},
want: false,
},
}
for _, c := range cases {
t.Run(c.name, func(t *testing.T) {
if got := entryUsesMetadataOnlyDelete(c.entry); got != c.want {
t.Fatalf("want %v, got %v", c.want, got)
}
})
}
}
func TestRecordMetadataOnlyIf_OnlyFiresWhenOn(t *testing.T) {
// Counter must increment exactly once per (bucket, hex(rule_hash))
// when on=true, and not at all when on=false. Other lifecycle paths
// in the same suite share the global counter — use distinct bucket
// names per test so series don't bleed.
c := stats_collect.S3LifecycleMetadataOnlyCounter
bucket := "bk-counter-on"
hash := []byte{0xde, 0xad, 0xbe, 0xef, 0x01, 0x02, 0x03, 0x04}
hexHash := "deadbeef01020304"
before := testutil.ToFloat64(c.WithLabelValues(bucket, hexHash))
recordMetadataOnlyIf(true, &s3_lifecycle_pb.LifecycleDeleteRequest{
Bucket: bucket,
RuleHash: hash,
})
if got := testutil.ToFloat64(c.WithLabelValues(bucket, hexHash)); got != before+1 {
t.Fatalf("on=true should bump by 1; before=%v after=%v", before, got)
}
beforeOff := testutil.ToFloat64(c.WithLabelValues("bk-counter-off", hexHash))
recordMetadataOnlyIf(false, &s3_lifecycle_pb.LifecycleDeleteRequest{
Bucket: "bk-counter-off",
RuleHash: hash,
})
if got := testutil.ToFloat64(c.WithLabelValues("bk-counter-off", hexHash)); got != beforeOff {
t.Fatalf("on=false should not bump; before=%v after=%v", beforeOff, got)
}
}
func TestRecordMetadataOnlyIf_NilRequestSafe(t *testing.T) {
// A nil req is a defensive no-op; never panic on the prometheus
// label call which would otherwise dereference req.Bucket.
recordMetadataOnlyIf(true, nil)
}
func TestRecordMetadataOnlyIf_EmptyRuleHashCollapsesToEmptyLabel(t *testing.T) {
// Bootstrap or test paths may not stamp a rule hash; the label
// must end up as an empty string rather than panicking on
// hex.EncodeToString(nil).
c := stats_collect.S3LifecycleMetadataOnlyCounter
bucket := "bk-counter-emptyhash"
before := testutil.ToFloat64(c.WithLabelValues(bucket, ""))
recordMetadataOnlyIf(true, &s3_lifecycle_pb.LifecycleDeleteRequest{Bucket: bucket})
if got := testutil.ToFloat64(c.WithLabelValues(bucket, "")); got != before+1 {
t.Fatalf("nil rule_hash should produce empty-label series; before=%v after=%v", before, got)
}
}
func TestLifecycleDelete_RequiresAdminAuth(t *testing.T) {
s := newTestS3IamCacheServer(t, testS3IamCacheSigningKey)
_, err := s.LifecycleDelete(context.Background(), &s3_lifecycle_pb.LifecycleDeleteRequest{
Bucket: "victim", ObjectPath: "important.dat",
ActionKind: s3_lifecycle_pb.ActionKind_EXPIRATION_DAYS,
})
if got, want := status.Code(err), codes.Unauthenticated; got != want {
t.Fatalf("LifecycleDelete without token: got code %v, want %v (err=%v)", got, want, err)
}
bad := security.GenJwtForFilerAdmin(security.SigningKey("a-different-key"), 60)
_, err = s.LifecycleDelete(s3IamCacheBearerCtx(string(bad)), &s3_lifecycle_pb.LifecycleDeleteRequest{
Bucket: "victim", ObjectPath: "important.dat",
ActionKind: s3_lifecycle_pb.ActionKind_EXPIRATION_DAYS,
})
if got, want := status.Code(err), codes.Unauthenticated; got != want {
t.Fatalf("LifecycleDelete with mis-signed token: got code %v, want %v (err=%v)", got, want, err)
}
}
func TestLifecycleDelete_NoSigningKey_LocalPeerOnly(t *testing.T) {
s := newTestS3IamCacheServer(t, "")
_, err := s.LifecycleDelete(context.Background(), &s3_lifecycle_pb.LifecycleDeleteRequest{})
if got, want := status.Code(err), codes.Unauthenticated; got != want {
t.Fatalf("LifecycleDelete with no peer info: got code %v, want %v (err=%v)", got, want, err)
}
remoteCtx := peer.NewContext(context.Background(),
&peer.Peer{Addr: &net.TCPAddr{IP: net.ParseIP("203.0.113.7"), Port: 11111}})
_, err = s.LifecycleDelete(remoteCtx, &s3_lifecycle_pb.LifecycleDeleteRequest{})
if got, want := status.Code(err), codes.Unauthenticated; got != want {
t.Fatalf("LifecycleDelete from remote peer: got code %v, want %v (err=%v)", got, want, err)
}
localCtx := peer.NewContext(context.Background(),
&peer.Peer{Addr: &net.TCPAddr{IP: net.ParseIP("127.0.0.1"), Port: 11111}})
resp, err := s.LifecycleDelete(localCtx, &s3_lifecycle_pb.LifecycleDeleteRequest{})
if err != nil {
t.Fatalf("LifecycleDelete from loopback without signing key: unexpected error %v", err)
}
if resp == nil || resp.Outcome != s3_lifecycle_pb.LifecycleDeleteOutcome_BLOCKED {
t.Fatalf("expected BLOCKED for empty request without signing key, got %v", resp)
}
}
func TestLifecycleDelete_CurrentExpirationRequiresLatestVersion(t *testing.T) {
listed := &filer_pb.Entry{
Name: "v_old",
Attributes: &filer_pb.FuseAttributes{Mtime: 1_700_000_000, FileSize: 3},
Chunks: []*filer_pb.FileChunk{{FileId: "3,01637037d6", Size: 3}},
Extended: map[string][]byte{s3_constants.ExtVersionIdKey: []byte("old")},
}
newer := &filer_pb.Entry{
Name: "v_new",
Attributes: &filer_pb.FuseAttributes{Mtime: 1_700_000_100, FileSize: 5},
Chunks: []*filer_pb.FileChunk{{FileId: "3,02637037d6", Size: 5}},
Extended: map[string][]byte{s3_constants.ExtVersionIdKey: []byte("new")},
}
versionsDir := func(latestId string) *filer_pb.Entry {
d := &filer_pb.Entry{Name: "obj" + s3_constants.VersionsFolder, IsDirectory: true, Attributes: &filer_pb.FuseAttributes{}}
if latestId != "" {
d.Extended = map[string][]byte{
s3_constants.ExtLatestVersionIdKey: []byte(latestId),
s3_constants.ExtLatestVersionFileNameKey: []byte("v_" + latestId),
}
}
return d
}
nullOverwrite := &filer_pb.Entry{
Name: "obj",
Attributes: &filer_pb.FuseAttributes{Mtime: 1_700_000_200, FileSize: 7},
Chunks: []*filer_pb.FileChunk{{FileId: "3,03637037d6", Size: 7}},
Extended: map[string][]byte{s3_constants.ExtVersionIdKey: []byte("null")},
}
cases := []struct {
name string
versioning string
versionId string
listed *filer_pb.Entry
entries map[string]*filer_pb.Entry
outcome s3_lifecycle_pb.LifecycleDeleteOutcome
}{
{"newer version", s3_constants.VersioningEnabled, "old", listed, map[string]*filer_pb.Entry{
"/buckets/b/obj.versions": versionsDir("new"),
"/buckets/b/obj.versions/v_old": listed,
"/buckets/b/obj.versions/v_new": newer,
}, s3_lifecycle_pb.LifecycleDeleteOutcome_NOOP_RESOLVED},
{"null version written while suspended", s3_constants.VersioningSuspended, "old", listed, map[string]*filer_pb.Entry{
"/buckets/b/obj": nullOverwrite,
"/buckets/b/obj.versions": versionsDir(""),
"/buckets/b/obj.versions/v_old": listed,
}, s3_lifecycle_pb.LifecycleDeleteOutcome_NOOP_RESOLVED},
{"unaddressed null behind a newer version while suspended", s3_constants.VersioningSuspended, "", nullOverwrite, map[string]*filer_pb.Entry{
"/buckets/b/obj": nullOverwrite,
"/buckets/b/obj.versions": versionsDir("new"),
"/buckets/b/obj.versions/v_new": newer,
}, s3_lifecycle_pb.LifecycleDeleteOutcome_NOOP_RESOLVED},
{"still latest", s3_constants.VersioningEnabled, "old", listed, map[string]*filer_pb.Entry{
"/buckets/b/obj.versions": versionsDir("old"),
"/buckets/b/obj.versions/v_old": listed,
}, s3_lifecycle_pb.LifecycleDeleteOutcome_DONE},
}
for _, kind := range []s3_lifecycle_pb.ActionKind{s3_lifecycle_pb.ActionKind_EXPIRATION_DAYS, s3_lifecycle_pb.ActionKind_EXPIRATION_DATE} {
for _, c := range cases {
t.Run(kind.String()+"/"+c.name, func(t *testing.T) {
entries := map[string]*filer_pb.Entry{}
for k, v := range c.entries {
entries[k] = proto.Clone(v).(*filer_pb.Entry)
}
fake := &ambiguousPutFiler{entries: entries, apply: true}
s3a := newPutTestServer(t, startFakeFiler(t, fake))
s3a.bucketConfigCache = NewBucketConfigCache(time.Minute)
s3a.bucketConfigCache.Set("b", &BucketConfig{Name: "b", Versioning: c.versioning})
resp, err := s3a.LifecycleDelete(s3LocalPeerCtx(), &s3_lifecycle_pb.LifecycleDeleteRequest{
Bucket: "b",
ObjectPath: "obj",
VersionId: c.versionId,
ActionKind: kind,
ExpectedIdentity: computeEntryIdentity(c.listed),
})
require.NoError(t, err)
require.Equal(t, c.outcome, resp.Outcome, resp.Reason)
if c.outcome == s3_lifecycle_pb.LifecycleDeleteOutcome_NOOP_RESOLVED {
require.Equal(t, "VERSION_NOT_LATEST", resp.Reason)
require.Zero(t, fake.txnCount, "no delete marker or delete may be written")
require.Len(t, fake.entries, len(c.entries))
}
})
}
}
}