mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-11-07 20:47:46 +01:00
* lance catalog: in-process DescribeTable for trusted callers DescribeTable and DescribeTableInternal resolve a table's location and storage options without the HTTP layer; the internal form runs the lookup through a trusted manager so the caller's catalog grants do not gate a resolution its own permission already authorized. Same code as the Enterprise repository. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011UpvafvK8JpagF94MHWqwK * vector.proto: Table carries its location and storage options The gateway resolves the table it addresses, so the engine can open it without a describe round trip of its own. Both fields are optional; an empty location means the engine looks the table up as before. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011UpvafvK8JpagF94MHWqwK * lance catalog: test the in-process describe Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011UpvafvK8JpagF94MHWqwK * s3vectors: resolve the table before calling the engine The gateway describes the table in process, through the trusted catalog manager, and sends its location and storage options with every engine call. Storage options are vended for the caller's principal, as the Enterprise router does for queries. A catalog failure answers with the code the engine would have given. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011UpvafvK8JpagF94MHWqwK * weed-vector: open a table at the location the gateway sent A request whose table carries a location is opened there, with the storage options the gateway vended over the engine's fallback; the catalog is described only for a table that comes without one, as from an older gateway. dataset::open_at and dataset::drop_at take a description the caller already holds. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011UpvafvK8JpagF94MHWqwK * s3vectors e2e: run the engine without a catalog VECTOR_ENGINE_NO_CATALOG=1 gives the engine an unreachable catalog URL; every CI leg sets it, so the suite proves the gateway resolves each table it sends. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011UpvafvK8JpagF94MHWqwK * lance catalog: an internal describe may write a vector index With credential vending on, the options vended to the engine followed the caller's s3tables grants, which never allow writing the vector namespace, so every write the gateway sent would have run with read-only credentials and reads would have lost their version lease. The engine is that namespace's writer and the caller's vector permission authorized the operation, so an internal describe of a vector table vends write-capable options; other namespaces keep the UpdateTable check. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011UpvafvK8JpagF94MHWqwK * s3: resolve tables for the engine only while the catalog runs With -port.lance=0 the gateway has no catalog to resolve through; the engine then keeps looking tables up itself, as before. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011UpvafvK8JpagF94MHWqwK * lance catalog: a deregistered table describes as NoSuchTable So the gateway answers NotFoundException for it, not InternalFailure. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011UpvafvK8JpagF94MHWqwK * weed-vector: trust a sent location only for a colocated vector index A caller that reaches the engine could otherwise name any storage the engine's credentials cover. A location is taken from the request only when the id names a vector index and the location is its colocated path, which the engine writes already; anything else is described through the catalog as before. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011UpvafvK8JpagF94MHWqwK * weed-vector: scope the read cache by storage endpoint The cache was keyed by bucket and path alone, so the same path reached through another endpoint would have shared entries. Each open wraps the store with the cache scoped to the endpoint its options name. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011UpvafvK8JpagF94MHWqwK * weed-vector: keep a configured endpoint over one a request names A caller that reaches the engine could otherwise send its fallback credentials to an endpoint of the caller's choosing. When the engine's --storage-option names an aws_endpoint, a table whose request names another one is described through the catalog instead. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011UpvafvK8JpagF94MHWqwK * weed-vector: use request options only where credentials cannot leave A request's storage options are taken only when they hold the keys a gateway's describe produces, so a proxy or an endpoint alias cannot route the engine's credentials elsewhere, and an endpoint only when it is the configured one or the engine holds no credentials to send. Anything else sends the table to the catalog. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011UpvafvK8JpagF94MHWqwK * s3vectors e2e: give the engine its endpoint with its credentials Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011UpvafvK8JpagF94MHWqwK * weed-vector: a drop checks the request's options like an open Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011UpvafvK8JpagF94MHWqwK * weed-vector: an unpinned endpoint needs the request to sign for itself Without configured credentials the S3 store still signs with the AWS default chain, so an endpoint from a request is taken only when the request skips signing or brings its own credentials. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011UpvafvK8JpagF94MHWqwK * weed-vector: a trailing slash does not unpin the endpoint, and say so A configured aws_endpoint written with a trailing slash matched nothing the gateway sends, so every table fell back to the catalog in silence. The comparison ignores the slash, and a fallback for a resolved table is logged at debug. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011UpvafvK8JpagF94MHWqwK * weed-vector: resolved by the gateway, or refused The engine no longer has a catalog: --namespace and --filer-signing-key are gone, a request whose table names no location is InvalidArgument, and one whose location is not the index's own or whose storage options the engine's credentials must not be used with is PermissionDenied. A drop removes the colocated path it was given. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011UpvafvK8JpagF94MHWqwK * s3: the catalog resolves vector tables whether or not its port is served newLanceServer builds the Lance catalog for the S3 Vectors API; the listener on -port.lance is optional. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011UpvafvK8JpagF94MHWqwK * s3vectors tests: start the engine without a catalog Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011UpvafvK8JpagF94MHWqwK * s3: the aux listener test builds the catalog before serving it Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011UpvafvK8JpagF94MHWqwK * weed-vector: an unpinned endpoint takes only credentials the request signs with alone Lance fills an option a request leaves out from the engine's environment, under any of object_store's names for it (TOKEN, SESSION_TOKEN, ...), and asks the AWS default chain when the key pair is incomplete. A request that named its own endpoint with only an access key id, or a key pair while the engine's environment held a session token, would have sent the engine's credentials there. Such a request now needs a full key pair, and its own session token whenever the environment would supply one. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * weed-vector: accept --namespace and --filer-signing-key, ignored Both flags shipped in 4.52 and are documented, so dropping them made an existing command line exit at startup with an unexpected-argument error. They are kept hidden and ignored, with a warning. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * s3vectors design: the engine is started without a catalog Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * weed-vector: the trust check takes the environment it reads The options test read the process environment through signs_alone, so a host exporting AWS_SESSION_TOKEN or TOKEN failed it. The caller now passes the variable names in; describe passes the engine's own. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * weed-vector: log both endpoints when a request's options are refused The gateway turns the PermissionDenied into a bare AccessDenied and logs nothing, so a pinned aws_endpoint written in another form than the one the gateway sends (host case, a default port, an IP for a name) failed every call with no trace of which value differed. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * s3: the Lance catalog sets the credential role whether or not Iceberg runs -iceberg.credentialRole reached the S3 server only while the Iceberg listener started, so with -port.iceberg=0 the Lance catalog installed its vendor but vending stayed off, and the vector engine got no credentials for the tables the gateway resolves. Both catalogs now set the role through one helper. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * s3: set the credential role once, before either catalog serves Both catalogs wrote the role as they were built; the second write landed while the first was already serving requests that read it. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011UpvafvK8JpagF94MHWqwK --------- Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
235 lines
8.5 KiB
Go
235 lines
8.5 KiB
Go
package lance
|
|
|
|
import (
|
|
"encoding/json"
|
|
"fmt"
|
|
"io"
|
|
"net/http"
|
|
"strconv"
|
|
"strings"
|
|
|
|
"github.com/gorilla/mux"
|
|
"github.com/seaweedfs/seaweedfs/weed/glog"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/s3api/s3_constants"
|
|
"github.com/seaweedfs/seaweedfs/weed/s3api/s3tables"
|
|
)
|
|
|
|
const defaultPageSize = 1000
|
|
|
|
// execute runs one S3 Tables operation as the request's authenticated caller.
|
|
func (s *Server) execute(r *http.Request, operation string, req, resp interface{}) error {
|
|
identityName := s3_constants.GetIdentityNameFromContext(r)
|
|
return s.filerClient.WithFilerClient(false, func(client filer_pb.SeaweedFilerClient) error {
|
|
return s.tablesManager.Execute(r.Context(), s3tables.NewManagerClient(client), operation, req, resp, identityName)
|
|
})
|
|
}
|
|
|
|
// executeInternal runs one S3 Tables operation through the trusted manager —
|
|
// the caller's catalog grants must not gate an internal resolution that the
|
|
// caller's own vector permission already authorized.
|
|
func (s *Server) executeInternal(r *http.Request, operation string, req, resp interface{}) error {
|
|
return s.filerClient.WithFilerClient(false, func(client filer_pb.SeaweedFilerClient) error {
|
|
return s.internal.Execute(r.Context(), s3tables.NewManagerClient(client), operation, req, resp, "")
|
|
})
|
|
}
|
|
|
|
func bucketARN(bucket string) string {
|
|
arn, _ := s3tables.BuildBucketARN(s3tables.DefaultRegion, s3_constants.AccountAdminId, bucket)
|
|
return arn
|
|
}
|
|
|
|
// maxRequestBody bounds what one call can make the catalog hold. Every request
|
|
// this surface takes is a small JSON envelope; the largest carries a set of
|
|
// properties, not data.
|
|
const maxRequestBody = 4 << 20
|
|
|
|
// decodeBody reads an optional JSON request body. Every Lance operation carries
|
|
// one, but the fields that matter are also in the route, so an empty body is
|
|
// not an error.
|
|
func decodeBody(r *http.Request, into interface{}) error {
|
|
body, err := io.ReadAll(io.LimitReader(r.Body, maxRequestBody+1))
|
|
if err != nil {
|
|
return fmt.Errorf("read request body: %w", err)
|
|
}
|
|
if len(body) > maxRequestBody {
|
|
return fmt.Errorf("request body is larger than %d bytes", maxRequestBody)
|
|
}
|
|
if len(strings.TrimSpace(string(body))) == 0 {
|
|
return nil
|
|
}
|
|
if err := json.Unmarshal(body, into); err != nil {
|
|
return fmt.Errorf("invalid request body: %w", err)
|
|
}
|
|
return nil
|
|
}
|
|
|
|
// routeIdentifier parses the {id} route variable, writing the error response
|
|
// itself when the identifier is malformed.
|
|
func routeIdentifier(w http.ResponseWriter, r *http.Request) (identifier, string, bool) {
|
|
delimiter := requestDelimiter(r)
|
|
id, err := parseIdentifier(mux.Vars(r)["id"], delimiter)
|
|
if err != nil {
|
|
writeError(w, r, http.StatusBadRequest, codeInvalidInput, err.Error())
|
|
return nil, delimiter, false
|
|
}
|
|
return id, delimiter, true
|
|
}
|
|
|
|
// checkBodyIdentifier enforces the spec rule that a route and a body naming
|
|
// different objects is a bad request rather than a silent preference.
|
|
func checkBodyIdentifier(w http.ResponseWriter, r *http.Request, id identifier, body []string) bool {
|
|
if id.matchesBody(body) {
|
|
return true
|
|
}
|
|
writeError(w, r, http.StatusBadRequest, codeInvalidInput,
|
|
"the identifier in the request body does not match the one in the route")
|
|
return false
|
|
}
|
|
|
|
func pageSize(r *http.Request) int {
|
|
if raw := r.URL.Query().Get("limit"); raw != "" {
|
|
if parsed, err := strconv.Atoi(raw); err == nil && parsed > 0 {
|
|
return parsed
|
|
}
|
|
}
|
|
return defaultPageSize
|
|
}
|
|
|
|
func boolQuery(r *http.Request, name string) bool {
|
|
value, err := strconv.ParseBool(r.URL.Query().Get(name))
|
|
return err == nil && value
|
|
}
|
|
|
|
// wants resolves a tri-state request flag: the query parameter the REST spec
|
|
// adds, else the body field, else the implementation's own choice.
|
|
func wants(r *http.Request, name string, body *bool) bool {
|
|
if boolQuery(r, name) {
|
|
return true
|
|
}
|
|
return body != nil && *body
|
|
}
|
|
|
|
// tableLocation is where a table's dataset lives when the caller does not name
|
|
// a location. It mirrors the Iceberg catalog's layout so both catalogs put a
|
|
// table of the same name in the same place.
|
|
func tableLocation(bucket string, ns []string, name string) string {
|
|
return fmt.Sprintf("s3://%s/%s/%s", bucket, strings.Join(ns, "."), name)
|
|
}
|
|
|
|
// confineLocation rejects a client-supplied table location that does not resolve
|
|
// inside the caller's own bucket, the way the Iceberg gateway confines the same
|
|
// field. The location feeds TableDataDirFromMetadataLocation, which joins it
|
|
// under /buckets and collapses any "../" segments; an unconfined location lets a
|
|
// marker write escape into another tenant's namespace.
|
|
func confineLocation(bucket, location string) error {
|
|
rest, ok := strings.CutPrefix(location, "s3://")
|
|
if !ok {
|
|
return fmt.Errorf("location must be an s3:// URI")
|
|
}
|
|
name, keys, _ := strings.Cut(rest, "/")
|
|
if name != bucket {
|
|
return fmt.Errorf("location must be within bucket %s", bucket)
|
|
}
|
|
for _, segment := range strings.Split(keys, "/") {
|
|
switch {
|
|
case segment == "." || segment == "..":
|
|
return fmt.Errorf("location must not contain a path traversal segment")
|
|
case strings.ContainsAny(segment, "\\\x00"):
|
|
return fmt.Errorf("location contains an invalid character")
|
|
}
|
|
}
|
|
return nil
|
|
}
|
|
|
|
// storageOptions builds the object_store settings a Lance client needs to reach
|
|
// the dataset. The key names are the aws_-prefixed forms Lance clients pass
|
|
// through to object_store.
|
|
func (s *Server) storageOptions(r *http.Request, bucket, location string, vend bool, canWrite func() bool) (map[string]string, error) {
|
|
options := map[string]string{}
|
|
if s.s3Endpoint != "" {
|
|
options["aws_endpoint"] = s.s3Endpoint
|
|
if strings.HasPrefix(s.s3Endpoint, "http://") {
|
|
// object_store refuses a plaintext endpoint unless told to allow it,
|
|
// and the resulting failure reads like a credential problem.
|
|
options["allow_http"] = "true"
|
|
}
|
|
}
|
|
if s.s3Region != "" {
|
|
options["aws_region"] = s.s3Region
|
|
}
|
|
if !s.authEnabled() {
|
|
// The S3 port takes unsigned requests, and a client with no
|
|
// credentials of its own would otherwise fail looking for some.
|
|
options["aws_skip_signature"] = "true"
|
|
}
|
|
|
|
if !vend || s.credentialVendor == nil {
|
|
return options, nil
|
|
}
|
|
|
|
principal := s3_constants.GetIdentityNameFromContext(r)
|
|
credentials, err := s.credentialVendor.VendTableCredentials(r.Context(), principal, bucket, locationPrefix(location), canWrite == nil || !canWrite())
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
if credentials == nil {
|
|
return options, nil
|
|
}
|
|
options["aws_access_key_id"] = credentials.AccessKeyID
|
|
options["aws_secret_access_key"] = credentials.SecretAccessKey
|
|
if credentials.SessionToken != "" {
|
|
options["aws_session_token"] = credentials.SessionToken
|
|
}
|
|
if !credentials.Expiration.IsZero() {
|
|
options["expires_at_millis"] = strconv.FormatInt(credentials.Expiration.UnixMilli(), 10)
|
|
}
|
|
return options, nil
|
|
}
|
|
|
|
// mayUpdateTable reports whether the caller may commit to the table the
|
|
// credentials would cover, the same gate the Iceberg catalog applies so a
|
|
// read-only caller never gets write-capable storage_options.
|
|
func (s *Server) mayUpdateTable(r *http.Request, bucket string, ns []string, name string) bool {
|
|
if !s.mayWriteNamespace(r, bucket, ns) {
|
|
return false
|
|
}
|
|
req := &s3tables.UpdateTableRequest{
|
|
TableBucketARN: bucketARN(bucket),
|
|
Namespace: ns,
|
|
Name: name,
|
|
}
|
|
identityName := s3_constants.GetIdentityNameFromContext(r)
|
|
err := s.filerClient.WithFilerClient(false, func(client filer_pb.SeaweedFilerClient) error {
|
|
return s.tablesManager.AuthorizeUpdateTable(r.Context(), s3tables.NewManagerClient(client), req, identityName)
|
|
})
|
|
if err != nil {
|
|
glog.V(1).Infof("lance: UpdateTable check for %s/%s failed, vending read-only: %v", bucket, name, err)
|
|
}
|
|
return err == nil
|
|
}
|
|
|
|
// mayWriteNamespace keeps the vector namespace of a vector bucket out of reach
|
|
// of s3tables grants: its index data is written only by trusted callers, and
|
|
// the vector bucket policy gates everyone else through S3 Vectors.
|
|
func (s *Server) mayWriteNamespace(r *http.Request, bucket string, ns []string) bool {
|
|
if isTrustedCaller(r.Context()) {
|
|
return true
|
|
}
|
|
err := s.tablesManager.CheckVectorNamespaceWrite(r.Context(), s.filerClient, bucket, ns)
|
|
if err != nil {
|
|
glog.V(1).Infof("lance: %s/%s is read-only to this caller: %v", bucket, strings.Join(ns, "."), err)
|
|
}
|
|
return err == nil
|
|
}
|
|
|
|
// locationPrefix strips the s3://bucket/ part of a location, leaving the key
|
|
// prefix a credential is scoped to.
|
|
func locationPrefix(location string) string {
|
|
trimmed := strings.TrimPrefix(location, "s3://")
|
|
if _, prefix, found := strings.Cut(trimmed, "/"); found {
|
|
return prefix
|
|
}
|
|
return ""
|
|
}
|