mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-11-08 21:08:27 +01:00
* s3tables: give a table created without a location its own directory An Iceberg table created without a location kept its files under its name path, so a rename left them where the next table of that name would land. Such a table now gets s3://<bucket>/<namespace>/<name>-<uuid>, stored as the record's warehouseLocation and returned by GetTable; its first commit writes there without moving the root. Records without one keep resolving to their name path, so existing tables need no rewrite. Lance datasets stay at their name path, where Lance clients and the vector engine look for them. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * iceberg: create tables and views in a directory of their own A table or view created without a location took its name path, or a unique one only when that path was already taken. It now always gets <name>-<uuid>, so a later rename never leaves its files under a name another table can take. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * iceberg: load and commit a table at its warehouse location A table created through S3 Tables without a location has no metadata until its first commit; loading or committing it now uses the directory recorded for it, and only a record without one falls back to its name path. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * iceberg: fail a stage-create whose marker is not saved The marker is how the commit finds the location the stage-create handed out. Without it the commit fell back to the name path while the client's files sat under the returned location. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * test: expect tables created without a location in their own directory Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * test: rename a table that keeps its files elsewhere before reusing its name Enterprise keeps the storage marker on a renamed table's files, so the name of a table whose files sit under its name path stays taken there. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * s3tables: remove the table directory when a create backs out Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * iceberg: answer a create that lost the race with the registered table Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * iceberg: answer a view create that lost the race with the registered view Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * iceberg: fail a staged commit whose name another create registered Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * iceberg: remove the directory of a create whose name another table took Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * iceberg: keep the metadata of a staged commit whose name is taken Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * test: write the lakekeeper table's data under its warehouse location Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * iceberg: commit a staged table at the location of its own stage Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * iceberg: never continue another stage when a commit's own marker is gone Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * iceberg: test filer honors exclusive creates and token-guarded deletes 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 iceberg
|
|
|
|
import (
|
|
"bytes"
|
|
"context"
|
|
"encoding/json"
|
|
"errors"
|
|
"io"
|
|
"net/http"
|
|
"net/http/httptest"
|
|
"path"
|
|
"sort"
|
|
"strings"
|
|
"testing"
|
|
|
|
"github.com/apache/iceberg-go"
|
|
"github.com/apache/iceberg-go/table"
|
|
"github.com/apache/iceberg-go/view"
|
|
"github.com/gorilla/mux"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/s3api/s3_constants"
|
|
"github.com/seaweedfs/seaweedfs/weed/s3api/s3tables"
|
|
"google.golang.org/grpc"
|
|
"google.golang.org/grpc/codes"
|
|
"google.golang.org/grpc/status"
|
|
)
|
|
|
|
// memFiler is a minimal in-memory SeaweedFilerClient backing the view handlers
|
|
// end-to-end through the s3tables manager. Only the entry operations the create
|
|
// path touches are implemented; anything else panics so a missing dependency is
|
|
// loud rather than silently passing.
|
|
type memFiler struct {
|
|
filer_pb.SeaweedFilerClient
|
|
entries map[string]*filer_pb.Entry
|
|
// failFileCreate, when set, makes CreateEntry fail for non-directory entries,
|
|
// simulating a metadata-file write error.
|
|
failFileCreate error
|
|
// onLookup, when set, runs at the start of every LookupDirectoryEntry.
|
|
onLookup func(p string)
|
|
}
|
|
|
|
func newMemFiler() *memFiler {
|
|
return &memFiler{entries: map[string]*filer_pb.Entry{}}
|
|
}
|
|
|
|
func (m *memFiler) WithFilerClient(_ bool, fn func(client filer_pb.SeaweedFilerClient) error) error {
|
|
return fn(m)
|
|
}
|
|
|
|
func (m *memFiler) seed(p string, entry *filer_pb.Entry) {
|
|
m.entries[p] = entry
|
|
}
|
|
|
|
func (m *memFiler) LookupDirectoryEntry(_ context.Context, in *filer_pb.LookupDirectoryEntryRequest, _ ...grpc.CallOption) (*filer_pb.LookupDirectoryEntryResponse, error) {
|
|
if hook := m.onLookup; hook != nil {
|
|
hook(path.Join(in.Directory, in.Name))
|
|
}
|
|
entry, ok := m.entries[path.Join(in.Directory, in.Name)]
|
|
if !ok {
|
|
return nil, filer_pb.ErrNotFound
|
|
}
|
|
return &filer_pb.LookupDirectoryEntryResponse{Entry: entry}, nil
|
|
}
|
|
|
|
func (m *memFiler) CreateEntry(_ context.Context, in *filer_pb.CreateEntryRequest, _ ...grpc.CallOption) (*filer_pb.CreateEntryResponse, error) {
|
|
if m.failFileCreate != nil && !in.Entry.IsDirectory {
|
|
return nil, m.failFileCreate
|
|
}
|
|
if _, taken := m.entries[path.Join(in.Directory, in.Entry.Name)]; taken && in.OExcl {
|
|
return &filer_pb.CreateEntryResponse{ErrorCode: filer_pb.FilerError_ENTRY_ALREADY_EXISTS}, nil
|
|
}
|
|
m.entries[path.Join(in.Directory, in.Entry.Name)] = in.Entry
|
|
return &filer_pb.CreateEntryResponse{}, nil
|
|
}
|
|
|
|
func (m *memFiler) DeleteEntry(_ context.Context, in *filer_pb.DeleteEntryRequest, _ ...grpc.CallOption) (*filer_pb.DeleteEntryResponse, error) {
|
|
prefix := path.Join(in.Directory, in.Name)
|
|
if entry, ok := m.entries[prefix]; ok {
|
|
for key, want := range in.ExpectedExtended {
|
|
if string(entry.Extended[key]) != string(want) {
|
|
return nil, status.Errorf(codes.FailedPrecondition, "%s: %s changed", prefix, key)
|
|
}
|
|
}
|
|
}
|
|
for p := range m.entries {
|
|
if p == prefix || strings.HasPrefix(p, prefix+"/") {
|
|
delete(m.entries, p)
|
|
}
|
|
}
|
|
return &filer_pb.DeleteEntryResponse{}, nil
|
|
}
|
|
|
|
func (m *memFiler) UpdateEntry(_ context.Context, in *filer_pb.UpdateEntryRequest, _ ...grpc.CallOption) (*filer_pb.UpdateEntryResponse, error) {
|
|
m.entries[path.Join(in.Directory, in.Entry.Name)] = in.Entry
|
|
return &filer_pb.UpdateEntryResponse{}, nil
|
|
}
|
|
|
|
func (m *memFiler) ListEntries(_ context.Context, in *filer_pb.ListEntriesRequest, _ ...grpc.CallOption) (filer_pb.SeaweedFiler_ListEntriesClient, error) {
|
|
var names []string
|
|
for p := range m.entries {
|
|
if path.Dir(p) != in.Directory {
|
|
continue
|
|
}
|
|
if name := path.Base(p); in.StartFromFileName != "" && (name < in.StartFromFileName || name == in.StartFromFileName && !in.InclusiveStartFrom) {
|
|
continue
|
|
}
|
|
names = append(names, p)
|
|
}
|
|
sort.Strings(names)
|
|
stream := &memListEntries{}
|
|
for _, name := range names {
|
|
if in.Limit > 0 && uint32(len(stream.entries)) >= in.Limit {
|
|
break
|
|
}
|
|
stream.entries = append(stream.entries, m.entries[name])
|
|
}
|
|
return stream, nil
|
|
}
|
|
|
|
type memListEntries struct {
|
|
grpc.ClientStream
|
|
entries []*filer_pb.Entry
|
|
}
|
|
|
|
func (m *memListEntries) Recv() (*filer_pb.ListEntriesResponse, error) {
|
|
if len(m.entries) == 0 {
|
|
return nil, io.EOF
|
|
}
|
|
entry := m.entries[0]
|
|
m.entries = m.entries[1:]
|
|
return &filer_pb.ListEntriesResponse{Entry: entry}, nil
|
|
}
|
|
|
|
func newCreateViewRequest(t *testing.T, namespace, name, sql string) *http.Request {
|
|
t.Helper()
|
|
schema := iceberg.NewSchemaWithIdentifiers(0, nil,
|
|
iceberg.NestedField{ID: 1, Name: "id", Type: iceberg.PrimitiveTypes.Int32, Required: true},
|
|
)
|
|
ver, err := view.NewVersionFromSQL(1, schema.ID, sql, table.Identifier{namespace})
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
body, err := json.Marshal(CreateViewRequest{Name: name, Schema: schema, ViewVersion: ver})
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
r := httptest.NewRequest(http.MethodPost, "/v1/namespaces/"+namespace+"/views", bytes.NewReader(body))
|
|
r = mux.SetURLVars(r, map[string]string{"namespace": namespace})
|
|
r = r.WithContext(s3_constants.SetIdentityNameInContext(r.Context(), s3_constants.AccountAdminId))
|
|
return r
|
|
}
|
|
|
|
// seedNamespace registers a bucket and namespace owned by owner so the s3tables
|
|
// existence and auth-context lookups pass.
|
|
func seedNamespace(fc *memFiler, bucket, namespace, owner string) {
|
|
fc.seed(s3tables.GetTableBucketPath(bucket), &filer_pb.Entry{Name: bucket, IsDirectory: true})
|
|
meta, _ := json.Marshal(map[string]any{"namespace": []string{namespace}, "ownerAccountId": owner})
|
|
fc.seed(s3tables.GetNamespacePath(bucket, namespace), &filer_pb.Entry{
|
|
Name: namespace,
|
|
IsDirectory: true,
|
|
Extended: map[string][]byte{s3tables.ExtendedKeyMetadata: meta},
|
|
})
|
|
}
|
|
|
|
func TestCreateViewMissingNamespaceReturns404(t *testing.T) {
|
|
fc := newMemFiler()
|
|
s := NewServer(fc, nil)
|
|
|
|
w := httptest.NewRecorder()
|
|
s.handleCreateView(w, newCreateViewRequest(t, "ns", "v", "SELECT 1"))
|
|
|
|
if w.Code != http.StatusNotFound {
|
|
t.Fatalf("status = %d, want %d (body: %s)", w.Code, http.StatusNotFound, w.Body.String())
|
|
}
|
|
var errResp ErrorResponse
|
|
if err := json.Unmarshal(w.Body.Bytes(), &errResp); err != nil {
|
|
t.Fatalf("unmarshal error body: %v", err)
|
|
}
|
|
if errResp.Error.Type != "NoSuchNamespaceException" {
|
|
t.Fatalf("error type = %q, want NoSuchNamespaceException", errResp.Error.Type)
|
|
}
|
|
}
|
|
|
|
func TestCreateViewTagsEntryAsView(t *testing.T) {
|
|
const bucket = "warehouse"
|
|
fc := newMemFiler()
|
|
seedNamespace(fc, bucket, "ns", s3_constants.AccountAdminId)
|
|
s := NewServer(fc, nil)
|
|
|
|
w := httptest.NewRecorder()
|
|
s.handleCreateView(w, newCreateViewRequest(t, "ns", "v", "SELECT 1"))
|
|
if w.Code != http.StatusOK {
|
|
t.Fatalf("create status = %d, want 200 (body: %s)", w.Code, w.Body.String())
|
|
}
|
|
|
|
entry, ok := fc.entries[s3tables.GetTablePath(bucket, "ns", "v")]
|
|
if !ok {
|
|
t.Fatalf("view entry not created")
|
|
}
|
|
if got := string(entry.Extended[s3tables.ExtendedKeyEntryType]); got != s3tables.EntryTypeView {
|
|
t.Fatalf("entryType = %q, want %q", got, s3tables.EntryTypeView)
|
|
}
|
|
if _, ok := entry.Extended[s3tables.ExtendedKeyMetadata]; !ok {
|
|
t.Fatalf("view entry missing metadata attribute")
|
|
}
|
|
}
|
|
|
|
func TestCreateViewDuplicateDoesNotClobberMetadata(t *testing.T) {
|
|
const bucket = "warehouse"
|
|
fc := newMemFiler()
|
|
seedNamespace(fc, bucket, "ns", s3_constants.AccountAdminId)
|
|
s := NewServer(fc, nil)
|
|
|
|
w := httptest.NewRecorder()
|
|
s.handleCreateView(w, newCreateViewRequest(t, "ns", "v", "SELECT 1"))
|
|
if w.Code != http.StatusOK {
|
|
t.Fatalf("first create status = %d, want 200 (body: %s)", w.Code, w.Body.String())
|
|
}
|
|
|
|
var created struct {
|
|
MetadataLocation string `json:"metadata-location"`
|
|
}
|
|
if err := json.Unmarshal(w.Body.Bytes(), &created); err != nil {
|
|
t.Fatalf("decode create response: %v", err)
|
|
}
|
|
if !strings.HasPrefix(created.MetadataLocation, "s3://"+bucket+"/ns/v-") {
|
|
t.Fatalf("metadata-location = %q, want one under a directory of the view's own", created.MetadataLocation)
|
|
}
|
|
metadataKey := path.Join(s3tables.TablesPath, strings.TrimPrefix(created.MetadataLocation, "s3://"))
|
|
first, ok := fc.entries[metadataKey]
|
|
if !ok {
|
|
t.Fatalf("metadata file not written at %s", metadataKey)
|
|
}
|
|
original := append([]byte(nil), first.Content...)
|
|
|
|
// Re-create the same view with different SQL: the existence pre-check must
|
|
// short-circuit so the persisted v1.metadata.json stays byte-for-byte intact.
|
|
w = httptest.NewRecorder()
|
|
s.handleCreateView(w, newCreateViewRequest(t, "ns", "v", "SELECT 2"))
|
|
if w.Code != http.StatusOK {
|
|
t.Fatalf("duplicate create status = %d, want 200 (body: %s)", w.Code, w.Body.String())
|
|
}
|
|
if got := fc.entries[metadataKey].Content; !bytes.Equal(got, original) {
|
|
t.Fatalf("duplicate create clobbered stored metadata:\n got %s\nwant %s", got, original)
|
|
}
|
|
}
|
|
|
|
// A view create that loses the race for its name answers with the view the
|
|
// catalog registered and writes no metadata of its own.
|
|
func TestCreateViewThatLosesTheRaceReturnsTheRegisteredView(t *testing.T) {
|
|
const bucket = "warehouse"
|
|
fc := newMemFiler()
|
|
seedNamespace(fc, bucket, "ns", s3_constants.AccountAdminId)
|
|
s := NewServer(fc, nil)
|
|
first := httptest.NewRecorder()
|
|
raceAtSecondLookup(fc, s3tables.GetTablePath(bucket, "ns", "v"), func() {
|
|
s.handleCreateView(first, newCreateViewRequest(t, "ns", "v", "SELECT 1"))
|
|
})
|
|
second := httptest.NewRecorder()
|
|
s.handleCreateView(second, newCreateViewRequest(t, "ns", "v", "SELECT 2"))
|
|
|
|
won, lost := decodeCreated(t, first), decodeCreated(t, second)
|
|
if lost != won {
|
|
t.Errorf("losing create answered %+v, want the registered view %+v", lost, won)
|
|
}
|
|
for p, entry := range fc.entries {
|
|
if !entry.IsDirectory && strings.HasSuffix(p, ".metadata.json") && p != path.Join(s3tables.TablesPath, strings.TrimPrefix(won.MetadataLocation, "s3://")) {
|
|
t.Errorf("losing create wrote %s", p)
|
|
}
|
|
}
|
|
}
|
|
|
|
func TestCreateViewRollsBackEntryWhenMetadataWriteFails(t *testing.T) {
|
|
const bucket = "warehouse"
|
|
fc := newMemFiler()
|
|
seedNamespace(fc, bucket, "ns", s3_constants.AccountAdminId)
|
|
fc.failFileCreate = errors.New("disk full")
|
|
s := NewServer(fc, nil)
|
|
|
|
w := httptest.NewRecorder()
|
|
s.handleCreateView(w, newCreateViewRequest(t, "ns", "v", "SELECT 1"))
|
|
if w.Code != http.StatusInternalServerError {
|
|
t.Fatalf("status = %d, want %d (body: %s)", w.Code, http.StatusInternalServerError, w.Body.String())
|
|
}
|
|
|
|
// The registered view must be rolled back so it doesn't linger pointing at
|
|
// metadata that was never written.
|
|
if _, ok := fc.entries[s3tables.GetTablePath(bucket, "ns", "v")]; ok {
|
|
t.Fatalf("view entry left behind after metadata write failure")
|
|
}
|
|
}
|