mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-11-16 08:45:22 +01:00
* s3api: create a multipart upload's directory on the object's owner filer CreateMultipartUpload wrote .uploads/<id> to the gateway's own filer while the upload's completion commits on the object's write owner. With independent filer stores, a part or completion reaching another gateway before peer metadata replication caught up could not see the upload. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * s3api: look up a multipart upload on the object's owner filer UploadPart, UploadPartCopy, ListParts, CompleteMultipartUpload, AbortMultipartUpload and the bucket policy SSE lookup read .uploads/<id> from the gateway's own filer, so a request on another gateway shortly after CreateMultipartUpload answered NoSuchUpload until replication caught up. Read it preferring the object's write owner, like object reads. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * s3api: write multipart parts to the upload's owner filer UploadPart and UploadPartCopy stored part entries on the gateway's own filer, so ListParts and CompleteMultipartUpload on another gateway could miss a part that replication had not delivered yet. Store them next to the upload directory on the object's write owner. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * s3api: list and clean up a multipart upload on its owner filer ListParts, CompleteMultipartUpload and AbortMultipartUpload listed and removed part entries on the gateway's own filer. Do it where the upload and its parts now live, so completion sees every part and cleanup does not miss entries replication has not delivered yet. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * s3api: test a multipart upload against a lagging gateway filer Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * s3api: check the upload's owner before freeing a failed part's chunks A part write that the owner stored but answered with an error went to recovery with no object, so the owner was never among the filers checked. When the owner is outside the gateway's filer list, the others' not-found answers freed chunks the stored part still references. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * s3api: list an upload's parts on the prior owner after a ring change The upload record lookup already falls back to the key's prior owner while a ring change is in its cooling-off window, but the part listing read only the new owner. ListParts then reported no parts for an open upload. Fall back the same way when the new owner has nothing yet. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * s3api: find the upload record on the prior owner past a bare directory A part routed to a new owner that has not received the upload yet makes that filer create .uploads/<id> without the upload's key. The post-write check then read it as an aborted upload and removed the part. While the ring change is in its cooling-off window, a record on the prior owner now wins over such a directory. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * s3api: merge the prior owner's parts into an upload listing During a ring change's cooling-off window the new owner may have received only some of an upload's parts. Listing returned the new owner's parts alone once it had any, so ListParts dropped the rest and a completion naming them failed with InvalidPart. Both owners' pages are now merged, the owner's entry winning a shared name, and cut to the page limit. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * s3api: fail an upload listing the prior owner could not answer When the new owner has none of an upload's parts yet and the prior owner's listing fails, the parts may all be on the prior owner. That listing read as empty, so CompleteMultipartUpload answered NoSuchUpload for an upload that still exists; it now returns the error. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * s3api: fail an upload lookup the prior owner could not answer During a ring change's cooling-off window an upload the new owner has not received yet, or holds only as a bare directory, read as NoSuchUpload when the prior owner's lookup failed. That failure is now returned, so the client sees a retryable error instead of an upload that is gone. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
292 lines
10 KiB
Go
292 lines
10 KiB
Go
package s3api
|
|
|
|
import (
|
|
"bytes"
|
|
"errors"
|
|
"net/http"
|
|
"net/http/httptest"
|
|
"strings"
|
|
"testing"
|
|
"time"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/s3_pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/s3api/s3_constants"
|
|
"github.com/seaweedfs/seaweedfs/weed/s3api/s3err"
|
|
"github.com/seaweedfs/seaweedfs/weed/s3api/s3tables"
|
|
)
|
|
|
|
// Issue 11647: Bucket default encryption (SSE-S3) must be applied when
|
|
// -s3.encryptVolumeData (s3a.cipher) is enabled, matching explicit SSE headers.
|
|
func TestPutObjectAppliesBucketDefaultEncryptionWithVolumeCipher(t *testing.T) {
|
|
// Configure test key manager with a super key for SSE-S3 encryption.
|
|
km := GetSSES3KeyManager()
|
|
oldSuperKey := km.superKey
|
|
km.superKey = make([]byte, 32)
|
|
for i := range km.superKey {
|
|
km.superKey[i] = byte(i + 1)
|
|
}
|
|
t.Cleanup(func() {
|
|
km.superKey = oldSuperKey
|
|
})
|
|
|
|
testCases := []struct {
|
|
name string
|
|
enableCipher bool
|
|
}{
|
|
{
|
|
name: "volume encryption enabled (s3a.cipher=true)",
|
|
enableCipher: true,
|
|
},
|
|
{
|
|
name: "volume encryption disabled (s3a.cipher=false)",
|
|
enableCipher: false,
|
|
},
|
|
}
|
|
|
|
for _, tc := range testCases {
|
|
t.Run(tc.name, func(t *testing.T) {
|
|
volume := startFakeVolumeServer(t)
|
|
filerImpl := &ambiguousPutFiler{
|
|
volume: volume,
|
|
entries: map[string]*filer_pb.Entry{},
|
|
apply: true,
|
|
}
|
|
s3a := newPutTestServer(t, startFakeFiler(t, filerImpl))
|
|
s3a.cipher = tc.enableCipher
|
|
|
|
// Configure bucket "b" with default AES256 (SSE-S3) encryption.
|
|
s3a.bucketConfigCache = NewBucketConfigCache(time.Minute)
|
|
s3a.bucketConfigCache.Set("b", &BucketConfig{
|
|
Name: "b",
|
|
Encryption: &s3_pb.EncryptionConfiguration{
|
|
SseAlgorithm: "AES256",
|
|
},
|
|
})
|
|
|
|
// PUT request without explicit SSE headers.
|
|
r := httptest.NewRequest(http.MethodPut, "/b/plain.txt", nil)
|
|
filePath := "/buckets/b/plain.txt"
|
|
etag, code, sseMeta := s3a.putToFiler(r, filePath, strings.NewReader("hello seaweedfs"), "b", "plain.txt", 1, 0, nil, false, "")
|
|
if code != s3err.ErrNone {
|
|
t.Fatalf("putToFiler returned error code %v, want %v", code, s3err.ErrNone)
|
|
}
|
|
if etag == "" {
|
|
t.Fatal("expected non-empty etag")
|
|
}
|
|
|
|
// Verify returned SSE response metadata.
|
|
if sseMeta.SSEType != s3_constants.SSETypeS3 {
|
|
t.Fatalf("expected SSE response metadata type %s, got %s", s3_constants.SSETypeS3, sseMeta.SSEType)
|
|
}
|
|
|
|
// Verify entry saved on the filer.
|
|
entry, ok := filerImpl.entries[filePath]
|
|
if !ok {
|
|
t.Fatalf("entry not found on filer at %s", filePath)
|
|
}
|
|
|
|
sseHeaderVal, hasSSE := entry.Extended[s3_constants.AmzServerSideEncryption]
|
|
if !hasSSE || !bytes.Equal(sseHeaderVal, []byte("AES256")) {
|
|
t.Fatalf("expected entry to have %s=AES256, got hasSSE=%v val=%s", s3_constants.AmzServerSideEncryption, hasSSE, string(sseHeaderVal))
|
|
}
|
|
|
|
if len(entry.Extended[s3_constants.SeaweedFSSSES3Key]) == 0 {
|
|
t.Fatal("expected entry to have stored SSE-S3 key metadata")
|
|
}
|
|
|
|
if len(entry.Chunks) == 0 {
|
|
t.Fatal("expected entry to have at least one chunk")
|
|
}
|
|
|
|
for i, chunk := range entry.Chunks {
|
|
if chunk.SseType != filer_pb.SSEType_SSE_S3 {
|
|
t.Errorf("chunk %d: expected SseType SSE_S3, got %v", i, chunk.SseType)
|
|
}
|
|
if len(chunk.SseMetadata) == 0 {
|
|
t.Errorf("chunk %d: expected non-empty SseMetadata", i)
|
|
}
|
|
if tc.enableCipher && len(chunk.CipherKey) == 0 {
|
|
t.Errorf("chunk %d: expected volume CipherKey when s3a.cipher is true", i)
|
|
}
|
|
if !tc.enableCipher && len(chunk.CipherKey) != 0 {
|
|
t.Errorf("chunk %d: expected empty volume CipherKey when s3a.cipher is false", i)
|
|
}
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
// A part staged under .uploads must not pick up a bucket default encryption
|
|
// change: the upload's encryption is fixed at CreateMultipartUpload, so a part
|
|
// written after PutBucketEncryption would otherwise mix plaintext and
|
|
// ciphertext parts and the completed object would fail to decrypt.
|
|
func TestPutObjectPartSkipsBucketDefaultEncryption(t *testing.T) {
|
|
volume := startFakeVolumeServer(t)
|
|
filerImpl := &ambiguousPutFiler{
|
|
volume: volume,
|
|
entries: map[string]*filer_pb.Entry{},
|
|
apply: true,
|
|
}
|
|
s3a := newPutTestServer(t, startFakeFiler(t, filerImpl))
|
|
s3a.bucketConfigCache = NewBucketConfigCache(time.Minute)
|
|
s3a.bucketConfigCache.Set("b", &BucketConfig{
|
|
Name: "b",
|
|
Encryption: &s3_pb.EncryptionConfiguration{
|
|
SseAlgorithm: "AES256",
|
|
},
|
|
})
|
|
|
|
filePath := "/buckets/b/.uploads/up1/0002_deadbeef.part"
|
|
r := withMultipartPart(httptest.NewRequest(http.MethodPut, "/b/o?partNumber=2&uploadId=up1", nil), s3a.uploadFiler("b", "o"))
|
|
etag, code, sseMeta := s3a.putToFiler(r, filePath, strings.NewReader("part data"), "b", "", 2, 0, nil, false, "")
|
|
if code != s3err.ErrNone {
|
|
t.Fatalf("putToFiler = %v, want %v", code, s3err.ErrNone)
|
|
}
|
|
if etag == "" {
|
|
t.Fatal("expected non-empty etag")
|
|
}
|
|
if sseMeta.SSEType != "" {
|
|
t.Fatalf("part unexpectedly encrypted, SSEType=%s", sseMeta.SSEType)
|
|
}
|
|
|
|
entry, ok := filerImpl.entries[filePath]
|
|
if !ok {
|
|
t.Fatalf("entry not found on filer at %s", filePath)
|
|
}
|
|
if _, has := entry.Extended[s3_constants.AmzServerSideEncryption]; has {
|
|
t.Fatal("part entry carries SSE attributes from bucket default encryption")
|
|
}
|
|
for i, chunk := range entry.Chunks {
|
|
if chunk.SseType != filer_pb.SSEType_NONE {
|
|
t.Errorf("chunk %d: expected SseType NONE, got %v", i, chunk.SseType)
|
|
}
|
|
}
|
|
}
|
|
|
|
// An ordinary PutObject whose key happens to look like a staged part path
|
|
// (.uploads/...part) is still a top-level object write and must get the
|
|
// bucket's default encryption; only calls explicitly marked as part writes
|
|
// skip it.
|
|
func TestPutObjectUnderUploadsFolderKeepsBucketDefaultEncryption(t *testing.T) {
|
|
km := GetSSES3KeyManager()
|
|
oldSuperKey := km.superKey
|
|
km.superKey = make([]byte, 32)
|
|
for i := range km.superKey {
|
|
km.superKey[i] = byte(i + 1)
|
|
}
|
|
t.Cleanup(func() {
|
|
km.superKey = oldSuperKey
|
|
})
|
|
|
|
volume := startFakeVolumeServer(t)
|
|
filerImpl := &ambiguousPutFiler{
|
|
volume: volume,
|
|
entries: map[string]*filer_pb.Entry{},
|
|
apply: true,
|
|
}
|
|
s3a := newPutTestServer(t, startFakeFiler(t, filerImpl))
|
|
s3a.bucketConfigCache = NewBucketConfigCache(time.Minute)
|
|
s3a.bucketConfigCache.Set("b", &BucketConfig{
|
|
Name: "b",
|
|
Encryption: &s3_pb.EncryptionConfiguration{
|
|
SseAlgorithm: "AES256",
|
|
},
|
|
})
|
|
|
|
filePath := "/buckets/b/.uploads/notes.part"
|
|
r := httptest.NewRequest(http.MethodPut, "/b/.uploads/notes.part", nil)
|
|
etag, code, sseMeta := s3a.putToFiler(r, filePath, strings.NewReader("ordinary object body"), "b", ".uploads/notes.part", 1, 0, nil, false, "")
|
|
if code != s3err.ErrNone {
|
|
t.Fatalf("putToFiler = %v, want %v", code, s3err.ErrNone)
|
|
}
|
|
if etag == "" {
|
|
t.Fatal("expected non-empty etag")
|
|
}
|
|
if sseMeta.SSEType != s3_constants.SSETypeS3 {
|
|
t.Fatalf("expected SSE response metadata type %s, got %s", s3_constants.SSETypeS3, sseMeta.SSEType)
|
|
}
|
|
|
|
entry, ok := filerImpl.entries[filePath]
|
|
if !ok {
|
|
t.Fatalf("entry not found on filer at %s", filePath)
|
|
}
|
|
if !bytes.Equal(entry.Extended[s3_constants.AmzServerSideEncryption], []byte("AES256")) {
|
|
t.Fatal("expected object entry to keep bucket default AES256 encryption")
|
|
}
|
|
for i, chunk := range entry.Chunks {
|
|
if chunk.SseType != filer_pb.SSEType_SSE_S3 {
|
|
t.Errorf("chunk %d: expected SseType SSE_S3, got %v", i, chunk.SseType)
|
|
}
|
|
}
|
|
}
|
|
|
|
// A vector bucket is a LANCE table bucket; the AES256 its record declares is
|
|
// the bucket's default encryption. An ICEBERG bucket's declaration is not
|
|
// applied, because its catalog reads client manifests straight from the filer.
|
|
func TestPutObjectAppliesTableBucketDeclaredEncryption(t *testing.T) {
|
|
km := GetSSES3KeyManager()
|
|
oldSuperKey := km.superKey
|
|
km.superKey = make([]byte, 32)
|
|
for i := range km.superKey {
|
|
km.superKey[i] = byte(i + 1)
|
|
}
|
|
t.Cleanup(func() {
|
|
km.superKey = oldSuperKey
|
|
})
|
|
|
|
volume := startFakeVolumeServer(t)
|
|
filerImpl := &ambiguousPutFiler{
|
|
volume: volume,
|
|
entries: map[string]*filer_pb.Entry{},
|
|
apply: true,
|
|
}
|
|
s3a := newPutTestServer(t, startFakeFiler(t, filerImpl))
|
|
s3a.bucketConfigCache = NewBucketConfigCache(time.Minute)
|
|
for bucket, format := range map[string]string{"lance": s3tables.FormatLance, "ice": s3tables.FormatIceberg} {
|
|
s3a.bucketConfigCache.Set(bucket, s3a.newBucketConfigFromEntry(bucket, &filer_pb.Entry{
|
|
Name: bucket,
|
|
Extended: map[string][]byte{
|
|
s3tables.ExtendedKeyTableBucket: []byte("true"),
|
|
s3tables.ExtendedKeyMetadata: []byte(`{"name":"` + bucket + `","format":"` + format +
|
|
`","encryptionConfiguration":{"sseAlgorithm":"AES256"}}`),
|
|
},
|
|
}))
|
|
}
|
|
|
|
cfg, err := s3a.GetBucketEncryptionConfig("lance")
|
|
if err != nil || cfg.SseAlgorithm != EncryptionTypeAES256 {
|
|
t.Fatalf("GetBucketEncryptionConfig(lance) = %v, %v; want AES256", cfg, err)
|
|
}
|
|
if metadata, err := s3a.GetBucketMetadata("lance"); err != nil || metadata.Encryption != nil {
|
|
t.Fatalf("declared encryption leaked into the stored bucket metadata: %v, %v", metadata, err)
|
|
}
|
|
if _, err := s3a.GetBucketEncryptionConfig("ice"); !errors.Is(err, ErrNoEncryptionConfig) {
|
|
t.Fatalf("GetBucketEncryptionConfig(ice) error = %v, want ErrNoEncryptionConfig", err)
|
|
}
|
|
if code := s3a.removeEncryptionConfiguration("lance"); code != s3err.ErrMethodNotAllowed {
|
|
t.Fatalf("DeleteBucketEncryption(lance) = %v, want MethodNotAllowed for a declared encryption", code)
|
|
}
|
|
if code := s3a.removeEncryptionConfiguration("ice"); code != s3err.ErrNoSuchBucketEncryptionConfiguration {
|
|
t.Fatalf("DeleteBucketEncryption(ice) = %v, want NoSuchBucketEncryptionConfiguration", code)
|
|
}
|
|
|
|
for bucket, want := range map[string]filer_pb.SSEType{"lance": filer_pb.SSEType_SSE_S3, "ice": filer_pb.SSEType_NONE} {
|
|
filePath := "/buckets/" + bucket + "/vector/idx/data/0.lance"
|
|
r := httptest.NewRequest(http.MethodPut, "/"+bucket+"/vector/idx/data/0.lance", nil)
|
|
_, code, _ := s3a.putToFiler(r, filePath, strings.NewReader("lance data file"), bucket, "vector/idx/data/0.lance", 1, 0, nil, false, "")
|
|
if code != s3err.ErrNone {
|
|
t.Fatalf("putToFiler(%s) = %v, want %v", bucket, code, s3err.ErrNone)
|
|
}
|
|
entry := filerImpl.entries[filePath]
|
|
if entry == nil || len(entry.Chunks) == 0 {
|
|
t.Fatalf("no entry with chunks at %s", filePath)
|
|
}
|
|
for i, chunk := range entry.Chunks {
|
|
if chunk.SseType != want {
|
|
t.Errorf("%s chunk %d: SseType %v, want %v", bucket, i, chunk.SseType, want)
|
|
}
|
|
}
|
|
}
|
|
}
|