mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-08-28 11:56:07 +00:00
* s3tables: add the maintenance configuration APIs Stores the configuration verbatim as the wire shape under a new s3tables.maintenance extended attribute, so Get hands back what Put took and no translation layer can drift from the AWS model. Nothing reads the configuration yet. Put merges a single type into the stored map so configuring compaction does not drop snapshot management, and asserts the attribute's prior value so two concurrent Puts cannot silently clobber each other. * iceberg: apply the maintenance configuration in the worker The worker now reads the per-table and per-bucket maintenance configuration written by the control plane, so the wildcard plugin config is a default rather than the only setting a table can have. Table properties still win by default, since a table declaring its own layout is what every engine honours and the compactor has to agree with whoever writes the files. Clearing table_properties_override makes the maintenance configuration authoritative instead. Status is not part of that contest: a disabled type drops its operations and no property can re-enable them, so the operator's kill switch always holds. Manifest and delete-file rewrites have no AWS equivalent and ride with compaction. Detection reads both attributes from entries it already lists. * s3tables: report maintenance job status The worker records the outcome of each run in its own extended attribute, separate from the configuration so operator and worker writes do not contend, and GetTableMaintenanceJobStatus reads it back. Only the types a run touched are written, so a partial run cannot erase what an earlier one recorded. The reader fills in the rest: Disabled when the configuration switched a type off, Not_Yet_Run otherwise. Status is advisory, so a lost race is logged rather than failing a job whose work already committed. * s3tables: route the maintenance APIs over REST The five actions were only reachable by X-Amz-Target dispatch, which the AWS CLI and SDK do not use for this service. They address the operations by path, so the APIs were unreachable from any official client. * s3tables: fix the table bucket ARN field name GetTableBucketMaintenanceConfiguration emitted tableBucketArn where the wire field is tableBucketARN, as every other response in this package already spells it. Official SDK deserializers ignore the unknown key, so the required field came back unset. * s3tables: carry the compaction strategy through to the worker IcebergCompactionSettings modelled only targetFileSizeMB, so a request naming a strategy was accepted and then dropped on the way to storage. The worker now maps binpack and sort onto its own rewrite strategy and lets auto defer to the worker configuration. z-order is rejected rather than accepted and quietly binpacked. * s3tables: report bucket-level maintenance status GetTableMaintenanceJobStatus read only the table's configuration, so unreferenced file removal — which is configured on the bucket — reported Not_Yet_Run or a stale success after an operator disabled it. The merge helper now lives in this package and the worker shares it. * iceberg: delete orphans only after the non-current window AWS marks a file non-current once it has been unreferenced for unreferencedDays, then deletes it a further nonCurrentDays later. The cutoff was taken from unreferencedDays alone, so a 3/10 configuration hard-deleted on day three and threw away the ten day recovery window. remove_orphans deletes in one step rather than marking, so the cutoff is now the sum of the two. * s3tables: assert every attribute when rewriting an entry UpdateEntry writes the whole entry back from the snapshot the caller read, and its precondition only covers the keys the caller names. Both maintenance writers named one key, so a job status write could revert a maintenance configuration an operator had just disabled, turning an advisory write into a silent re-enable. Both now assert the entry's full attribute set, including the target key when absent so a concurrent create also fails the precondition. * s3tables: assert absent attributes when rewriting an entry The precondition covered the attributes present when the writer read the entry, so an attribute created between that read and the write was absent from it. A first-time PutTableMaintenanceConfiguration disabling a type therefore lands, passes the per-key checks, and is then deleted by the stale whole-entry write. Every attribute this package stores is now asserted, absent ones included. The metadata commit and planning index writers rewrite the same entries and had the same exposure, so both use the shared snapshot too. * iceberg: implement the auto compaction strategy auto was accepted, stored and read back, but left the worker on its own default, so a sorted table configured as auto was compacted with binpack. AWS defines auto as sorting tables that declare a sort order and bin-packing the rest. That needs the table metadata, so the choice is made where the rewrite plan is resolved: an unsorted table falls back to binpack rather than failing the way an explicit sort request does. * s3tables: validate the maintenance setting ranges PUT accepted zero, negative and oversized values for every numeric setting. The worker then ignores a non-positive value and saturates an oversized one, so the configuration read back was not the one that ran. AWS bounds all five to 1..2147483647, which is now enforced. The fields are pointers so an explicit zero is distinguishable from an omitted one and can be rejected rather than silently ignored. * s3tables: give every entry writer the same compare-and-swap updateExtendedAttribute asserted the entry's attributes, but the helpers behind the metadata, policy and tag handlers still wrote the whole entry unconditionally. Any of them could land on a stale snapshot and delete a maintenance configuration an operator had just written. They all share one read-modify-write loop now, so the precondition and the bounded retry apply wherever an entry is rewritten. * s3tables: move the maintenance configuration with a renamed table RenameTable carried the metadata, version, policy and tags to the new name but left the maintenance configuration and job status behind. A table with snapshot management disabled came back enabled under its new name, and the stale configuration stayed on the old name where a table created there would inherit it. The decoupled-delete cleanup left the same two attributes behind. * s3tables: accept every AWS partition in ARNs The route regexes and the ARN patterns both hardcoded arn:aws, so valid aws-cn and aws-us-gov ARNs never reached a handler. The router now shares the partition-tolerant prefix with the parser, and a generated ARN uses the partition its region belongs to so it parses back. * s3tables: generate ARNs in the region's partition The handler's own ARN generators still formatted arn:aws directly rather than going through the partition-aware builder, so a China or GovCloud deployment routed the request but then returned a commercial ARN and matched IAM policies against it. The round-trip test missed this because parsing accepts any partition, so it now asserts the prefix the region implies. * s3tables: complete the ARN partition table aws-iso-e, aws-iso-f and aws-eusc were missing, so eu-isoe-*, us-isof-* and eusc-* regions fell through to the commercial partition. * s3tables: do not let a rename swallow a concurrent maintenance write Rename copied the source attributes early and cleared the source at the end, so a Put landing in between missed the copy to the destination and was then deleted by the cleanup. It succeeded and vanished. The cleanup now clears the source only while it still holds exactly what was copied, and returns a conflict otherwise. Put checks the catalog identity inside the same conditional mutation, so it also cannot write to a name that a rename or delete has already soft-deleted.
530 lines
20 KiB
Go
530 lines
20 KiB
Go
package s3tables
|
|
|
|
import (
|
|
"encoding/json"
|
|
"errors"
|
|
"fmt"
|
|
"net/http"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
|
|
)
|
|
|
|
// Maintenance types are scoped: AWS configures unreferenced file removal on the
|
|
// table bucket and compaction and snapshot management on the table.
|
|
var (
|
|
bucketMaintenanceTypes = map[string]bool{
|
|
MaintenanceTypeIcebergUnreferencedFileRemoval: true,
|
|
}
|
|
tableMaintenanceTypes = map[string]bool{
|
|
MaintenanceTypeIcebergCompaction: true,
|
|
MaintenanceTypeIcebergSnapshotManagement: true,
|
|
}
|
|
)
|
|
|
|
// handlePutTableBucketMaintenanceConfiguration sets a maintenance configuration on a table bucket
|
|
func (h *S3TablesHandler) handlePutTableBucketMaintenanceConfiguration(w http.ResponseWriter, r *http.Request, filerClient FilerClient) error {
|
|
var req PutTableBucketMaintenanceConfigurationRequest
|
|
if err := h.readRequestBody(r, &req); err != nil {
|
|
h.writeError(w, http.StatusBadRequest, ErrCodeInvalidRequest, err.Error())
|
|
return err
|
|
}
|
|
|
|
if req.TableBucketARN == "" {
|
|
h.writeError(w, http.StatusBadRequest, ErrCodeInvalidRequest, "tableBucketARN is required")
|
|
return fmt.Errorf("tableBucketARN is required")
|
|
}
|
|
|
|
bucketName, err := parseBucketNameFromARN(req.TableBucketARN)
|
|
if err != nil {
|
|
h.writeError(w, http.StatusBadRequest, ErrCodeInvalidRequest, err.Error())
|
|
return err
|
|
}
|
|
|
|
if err := validateMaintenanceValue(req.Type, bucketMaintenanceTypes, req.Value); err != nil {
|
|
h.writeError(w, http.StatusBadRequest, ErrCodeInvalidRequest, err.Error())
|
|
return err
|
|
}
|
|
|
|
if _, err := h.authorizeMaintenanceBucket(r, filerClient, "PutTableBucketMaintenanceConfiguration", bucketName); err != nil {
|
|
h.writeMaintenanceError(w, err, ErrCodeNoSuchBucket, fmt.Sprintf("table bucket %s not found", bucketName))
|
|
return err
|
|
}
|
|
|
|
if err := h.putMaintenanceConfiguration(r, filerClient, GetTableBucketPath(bucketName), req.Type, req.Value); err != nil {
|
|
h.writeMaintenanceError(w, err, ErrCodeNoSuchBucket, fmt.Sprintf("table bucket %s not found", bucketName))
|
|
return err
|
|
}
|
|
|
|
h.writeJSON(w, http.StatusOK, nil)
|
|
return nil
|
|
}
|
|
|
|
// handleGetTableBucketMaintenanceConfiguration gets the maintenance configuration of a table bucket
|
|
func (h *S3TablesHandler) handleGetTableBucketMaintenanceConfiguration(w http.ResponseWriter, r *http.Request, filerClient FilerClient) error {
|
|
var req GetTableBucketMaintenanceConfigurationRequest
|
|
if err := h.readRequestBody(r, &req); err != nil {
|
|
h.writeError(w, http.StatusBadRequest, ErrCodeInvalidRequest, err.Error())
|
|
return err
|
|
}
|
|
|
|
if req.TableBucketARN == "" {
|
|
h.writeError(w, http.StatusBadRequest, ErrCodeInvalidRequest, "tableBucketARN is required")
|
|
return fmt.Errorf("tableBucketARN is required")
|
|
}
|
|
|
|
bucketName, err := parseBucketNameFromARN(req.TableBucketARN)
|
|
if err != nil {
|
|
h.writeError(w, http.StatusBadRequest, ErrCodeInvalidRequest, err.Error())
|
|
return err
|
|
}
|
|
|
|
bucketARN, err := h.authorizeMaintenanceBucket(r, filerClient, "GetTableBucketMaintenanceConfiguration", bucketName)
|
|
if err != nil {
|
|
h.writeMaintenanceError(w, err, ErrCodeNoSuchBucket, fmt.Sprintf("table bucket %s not found", bucketName))
|
|
return err
|
|
}
|
|
|
|
config, err := h.readMaintenanceConfiguration(r, filerClient, GetTableBucketPath(bucketName))
|
|
if err != nil {
|
|
h.writeMaintenanceError(w, err, ErrCodeNoSuchBucket, fmt.Sprintf("table bucket %s not found", bucketName))
|
|
return err
|
|
}
|
|
|
|
h.writeJSON(w, http.StatusOK, &GetTableBucketMaintenanceConfigurationResponse{
|
|
TableBucketARN: bucketARN,
|
|
Configuration: config,
|
|
})
|
|
return nil
|
|
}
|
|
|
|
// handlePutTableMaintenanceConfiguration sets a maintenance configuration on a table
|
|
func (h *S3TablesHandler) handlePutTableMaintenanceConfiguration(w http.ResponseWriter, r *http.Request, filerClient FilerClient) error {
|
|
var req PutTableMaintenanceConfigurationRequest
|
|
if err := h.readRequestBody(r, &req); err != nil {
|
|
h.writeError(w, http.StatusBadRequest, ErrCodeInvalidRequest, err.Error())
|
|
return err
|
|
}
|
|
|
|
bucketName, namespaceName, tableName, err := h.parseTableTarget(req.TableBucketARN, req.Namespace, req.Name)
|
|
if err != nil {
|
|
h.writeError(w, http.StatusBadRequest, ErrCodeInvalidRequest, err.Error())
|
|
return err
|
|
}
|
|
|
|
if err := validateMaintenanceValue(req.Type, tableMaintenanceTypes, req.Value); err != nil {
|
|
h.writeError(w, http.StatusBadRequest, ErrCodeInvalidRequest, err.Error())
|
|
return err
|
|
}
|
|
|
|
if _, err := h.authorizeMaintenanceTable(r, filerClient, "PutTableMaintenanceConfiguration", bucketName, namespaceName, tableName); err != nil {
|
|
h.writeMaintenanceError(w, err, ErrCodeNoSuchTable, fmt.Sprintf("table %s not found", tableName))
|
|
return err
|
|
}
|
|
|
|
tablePath := GetTablePath(bucketName, namespaceName, tableName)
|
|
if err := h.putMaintenanceConfiguration(r, filerClient, tablePath, req.Type, req.Value); err != nil {
|
|
h.writeMaintenanceError(w, err, ErrCodeNoSuchTable, fmt.Sprintf("table %s not found", tableName))
|
|
return err
|
|
}
|
|
|
|
h.writeJSON(w, http.StatusOK, nil)
|
|
return nil
|
|
}
|
|
|
|
// handleGetTableMaintenanceConfiguration gets the maintenance configuration of a table
|
|
func (h *S3TablesHandler) handleGetTableMaintenanceConfiguration(w http.ResponseWriter, r *http.Request, filerClient FilerClient) error {
|
|
var req GetTableMaintenanceConfigurationRequest
|
|
if err := h.readRequestBody(r, &req); err != nil {
|
|
h.writeError(w, http.StatusBadRequest, ErrCodeInvalidRequest, err.Error())
|
|
return err
|
|
}
|
|
|
|
bucketName, namespaceName, tableName, err := h.parseTableTarget(req.TableBucketARN, req.Namespace, req.Name)
|
|
if err != nil {
|
|
h.writeError(w, http.StatusBadRequest, ErrCodeInvalidRequest, err.Error())
|
|
return err
|
|
}
|
|
|
|
tableARN, err := h.authorizeMaintenanceTable(r, filerClient, "GetTableMaintenanceConfiguration", bucketName, namespaceName, tableName)
|
|
if err != nil {
|
|
h.writeMaintenanceError(w, err, ErrCodeNoSuchTable, fmt.Sprintf("table %s not found", tableName))
|
|
return err
|
|
}
|
|
|
|
tablePath := GetTablePath(bucketName, namespaceName, tableName)
|
|
config, err := h.readMaintenanceConfiguration(r, filerClient, tablePath)
|
|
if err != nil {
|
|
h.writeMaintenanceError(w, err, ErrCodeNoSuchTable, fmt.Sprintf("table %s not found", tableName))
|
|
return err
|
|
}
|
|
|
|
h.writeJSON(w, http.StatusOK, &GetTableMaintenanceConfigurationResponse{
|
|
TableARN: tableARN,
|
|
Namespace: []string{namespaceName},
|
|
Name: tableName,
|
|
Configuration: config,
|
|
})
|
|
return nil
|
|
}
|
|
|
|
// handleGetTableMaintenanceJobStatus reports the outcome of the last maintenance run on a table
|
|
func (h *S3TablesHandler) handleGetTableMaintenanceJobStatus(w http.ResponseWriter, r *http.Request, filerClient FilerClient) error {
|
|
var req GetTableMaintenanceJobStatusRequest
|
|
if err := h.readRequestBody(r, &req); err != nil {
|
|
h.writeError(w, http.StatusBadRequest, ErrCodeInvalidRequest, err.Error())
|
|
return err
|
|
}
|
|
|
|
bucketName, namespaceName, tableName, err := h.parseTableTarget(req.TableBucketARN, req.Namespace, req.Name)
|
|
if err != nil {
|
|
h.writeError(w, http.StatusBadRequest, ErrCodeInvalidRequest, err.Error())
|
|
return err
|
|
}
|
|
|
|
tableARN, err := h.authorizeMaintenanceTable(r, filerClient, "GetTableMaintenanceJobStatus", bucketName, namespaceName, tableName)
|
|
if err != nil {
|
|
h.writeMaintenanceError(w, err, ErrCodeNoSuchTable, fmt.Sprintf("table %s not found", tableName))
|
|
return err
|
|
}
|
|
|
|
tablePath := GetTablePath(bucketName, namespaceName, tableName)
|
|
|
|
// Unreferenced file removal is configured on the bucket, so a bucket-level
|
|
// disable has to show up here as Disabled rather than a stale table status.
|
|
bucketConfig, err := h.readMaintenanceConfiguration(r, filerClient, GetTableBucketPath(bucketName))
|
|
if err != nil {
|
|
h.writeMaintenanceError(w, err, ErrCodeNoSuchBucket, fmt.Sprintf("table bucket %s not found", bucketName))
|
|
return err
|
|
}
|
|
tableConfig, err := h.readMaintenanceConfiguration(r, filerClient, tablePath)
|
|
if err != nil {
|
|
h.writeMaintenanceError(w, err, ErrCodeNoSuchTable, fmt.Sprintf("table %s not found", tableName))
|
|
return err
|
|
}
|
|
config := MergeMaintenanceConfiguration(bucketConfig, tableConfig)
|
|
|
|
recorded := MaintenanceJobStatus{}
|
|
err = filerClient.WithFilerClient(false, func(client filer_pb.SeaweedFilerClient) error {
|
|
data, err := h.getExtendedAttribute(r.Context(), client, tablePath, ExtendedKeyMaintenanceStatus)
|
|
if err != nil {
|
|
if errors.Is(err, ErrAttributeNotFound) {
|
|
return nil
|
|
}
|
|
return err
|
|
}
|
|
return json.Unmarshal(data, &recorded)
|
|
})
|
|
if err != nil {
|
|
h.writeMaintenanceError(w, err, ErrCodeNoSuchTable, fmt.Sprintf("table %s not found", tableName))
|
|
return err
|
|
}
|
|
|
|
h.writeJSON(w, http.StatusOK, &GetTableMaintenanceJobStatusResponse{
|
|
TableARN: tableARN,
|
|
Status: buildJobStatusResponse(recorded, config),
|
|
})
|
|
return nil
|
|
}
|
|
|
|
// buildJobStatusResponse reports every job type: what the worker recorded, or
|
|
// Disabled when the configuration switched the type off, or Not_Yet_Run.
|
|
func buildJobStatusResponse(recorded MaintenanceJobStatus, config MaintenanceConfiguration) MaintenanceJobStatus {
|
|
jobTypes := []string{
|
|
MaintenanceTypeIcebergCompaction,
|
|
MaintenanceTypeIcebergSnapshotManagement,
|
|
MaintenanceTypeIcebergUnreferencedFileRemoval,
|
|
}
|
|
|
|
status := make(MaintenanceJobStatus, len(jobTypes))
|
|
for _, jobType := range jobTypes {
|
|
if value, ok := config[jobType]; ok && value != nil && value.Status == MaintenanceStatusDisabled {
|
|
status[jobType] = &MaintenanceJobStatusValue{Status: MaintenanceJobStatusDisabled}
|
|
continue
|
|
}
|
|
if value, ok := recorded[jobType]; ok && value != nil {
|
|
status[jobType] = value
|
|
continue
|
|
}
|
|
status[jobType] = &MaintenanceJobStatusValue{Status: MaintenanceJobStatusNotYetRun}
|
|
}
|
|
return status
|
|
}
|
|
|
|
// putMaintenanceConfiguration merges one maintenance type into the stored
|
|
// configuration, leaving the other types alone. The write checks the catalog
|
|
// identity in the same conditional mutation, so it cannot land on a name a
|
|
// concurrent rename or delete has already soft-deleted.
|
|
func (h *S3TablesHandler) putMaintenanceConfiguration(
|
|
r *http.Request,
|
|
filerClient FilerClient,
|
|
resourcePath, maintenanceType string,
|
|
value *MaintenanceConfigurationValue,
|
|
) error {
|
|
return filerClient.WithFilerClient(false, func(client filer_pb.SeaweedFilerClient) error {
|
|
return h.mutateEntryExtended(r.Context(), client, resourcePath, func(extended map[string][]byte) error {
|
|
if len(extended[ExtendedKeyMetadata]) == 0 {
|
|
return fmt.Errorf("%w: %s", filer_pb.ErrNotFound, resourcePath)
|
|
}
|
|
|
|
config := MaintenanceConfiguration{}
|
|
if current := extended[ExtendedKeyMaintenance]; len(current) > 0 {
|
|
if err := json.Unmarshal(current, &config); err != nil {
|
|
return fmt.Errorf("failed to unmarshal maintenance configuration: %w", err)
|
|
}
|
|
}
|
|
config[maintenanceType] = value
|
|
|
|
data, err := json.Marshal(config)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
extended[ExtendedKeyMaintenance] = data
|
|
return nil
|
|
})
|
|
})
|
|
}
|
|
|
|
// readMaintenanceConfiguration returns the stored configuration, or an empty
|
|
// one when the resource has never been configured.
|
|
func (h *S3TablesHandler) readMaintenanceConfiguration(r *http.Request, filerClient FilerClient, resourcePath string) (MaintenanceConfiguration, error) {
|
|
config := MaintenanceConfiguration{}
|
|
|
|
err := filerClient.WithFilerClient(false, func(client filer_pb.SeaweedFilerClient) error {
|
|
data, err := h.getExtendedAttribute(r.Context(), client, resourcePath, ExtendedKeyMaintenance)
|
|
if err != nil {
|
|
if errors.Is(err, ErrAttributeNotFound) {
|
|
return nil
|
|
}
|
|
return err
|
|
}
|
|
return json.Unmarshal(data, &config)
|
|
})
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
return config, nil
|
|
}
|
|
|
|
// parseTableTarget validates the bucket/namespace/table triple every
|
|
// table-scoped maintenance request carries.
|
|
func (h *S3TablesHandler) parseTableTarget(tableBucketARN string, namespace []string, name string) (bucketName, namespaceName, tableName string, err error) {
|
|
if tableBucketARN == "" || len(namespace) == 0 || name == "" {
|
|
return "", "", "", fmt.Errorf("tableBucketARN, namespace, and name are required")
|
|
}
|
|
if namespaceName, err = validateNamespace(namespace); err != nil {
|
|
return "", "", "", err
|
|
}
|
|
if bucketName, err = parseBucketNameFromARN(tableBucketARN); err != nil {
|
|
return "", "", "", err
|
|
}
|
|
if tableName, err = validateTableName(name); err != nil {
|
|
return "", "", "", err
|
|
}
|
|
return bucketName, namespaceName, tableName, nil
|
|
}
|
|
|
|
// authorizeMaintenanceBucket checks the caller may perform operation on the
|
|
// table bucket, returning the bucket ARN.
|
|
func (h *S3TablesHandler) authorizeMaintenanceBucket(r *http.Request, filerClient FilerClient, operation, bucketName string) (string, error) {
|
|
bucketPath := GetTableBucketPath(bucketName)
|
|
|
|
var bucketMetadata tableBucketMetadata
|
|
var bucketPolicy string
|
|
err := filerClient.WithFilerClient(false, func(client filer_pb.SeaweedFilerClient) error {
|
|
data, err := h.getExtendedAttribute(r.Context(), client, bucketPath, ExtendedKeyMetadata)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
if err := json.Unmarshal(data, &bucketMetadata); err != nil {
|
|
return fmt.Errorf("failed to unmarshal bucket metadata: %w", err)
|
|
}
|
|
bucketPolicy, err = h.readBucketPolicy(r, client, bucketPath)
|
|
return err
|
|
})
|
|
if err != nil {
|
|
return "", err
|
|
}
|
|
|
|
bucketARN := h.generateTableBucketARN(bucketMetadata.OwnerAccountID, bucketName)
|
|
principal := h.getAccountID(r)
|
|
if !CheckPermissionWithContext(operation, principal, bucketMetadata.OwnerAccountID, bucketPolicy, bucketARN, &PolicyContext{
|
|
TableBucketName: bucketName,
|
|
IdentityActions: getIdentityActions(r),
|
|
DefaultAllow: h.defaultAllowFor(r),
|
|
}) {
|
|
return "", NewAuthError(operation, principal, "not authorized to "+operation)
|
|
}
|
|
|
|
return bucketARN, nil
|
|
}
|
|
|
|
// authorizeMaintenanceTable checks the caller may perform operation on the
|
|
// table, returning the table ARN.
|
|
func (h *S3TablesHandler) authorizeMaintenanceTable(r *http.Request, filerClient FilerClient, operation, bucketName, namespaceName, tableName string) (string, error) {
|
|
tablePath := GetTablePath(bucketName, namespaceName, tableName)
|
|
bucketPath := GetTableBucketPath(bucketName)
|
|
|
|
var metadata tableMetadataInternal
|
|
var bucketPolicy string
|
|
err := filerClient.WithFilerClient(false, func(client filer_pb.SeaweedFilerClient) error {
|
|
data, err := h.getExtendedAttribute(r.Context(), client, tablePath, ExtendedKeyMetadata)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
if err := json.Unmarshal(data, &metadata); err != nil {
|
|
return fmt.Errorf("failed to unmarshal table metadata: %w", err)
|
|
}
|
|
bucketPolicy, err = h.readBucketPolicy(r, client, bucketPath)
|
|
return err
|
|
})
|
|
if err != nil {
|
|
return "", err
|
|
}
|
|
|
|
tableARN := h.generateTableARN(metadata.OwnerAccountID, bucketName, namespaceName+"/"+tableName)
|
|
principal := h.getAccountID(r)
|
|
if !CheckPermissionWithContext(operation, principal, metadata.OwnerAccountID, bucketPolicy, tableARN, &PolicyContext{
|
|
TableBucketName: bucketName,
|
|
Namespace: namespaceName,
|
|
TableName: tableName,
|
|
IdentityActions: getIdentityActions(r),
|
|
DefaultAllow: h.defaultAllowFor(r),
|
|
}) {
|
|
return "", NewAuthError(operation, principal, "not authorized to "+operation)
|
|
}
|
|
|
|
return tableARN, nil
|
|
}
|
|
|
|
// readBucketPolicy returns the bucket policy, or an empty string when the
|
|
// bucket has none.
|
|
func (h *S3TablesHandler) readBucketPolicy(r *http.Request, client filer_pb.SeaweedFilerClient, bucketPath string) (string, error) {
|
|
data, err := h.getExtendedAttribute(r.Context(), client, bucketPath, ExtendedKeyPolicy)
|
|
if err != nil {
|
|
if errors.Is(err, ErrAttributeNotFound) {
|
|
return "", nil
|
|
}
|
|
return "", fmt.Errorf("failed to read bucket policy: %w", err)
|
|
}
|
|
return string(data), nil
|
|
}
|
|
|
|
// writeMaintenanceError maps the shared failure modes of the maintenance
|
|
// handlers onto responses.
|
|
func (h *S3TablesHandler) writeMaintenanceError(w http.ResponseWriter, err error, notFoundCode, notFoundMessage string) {
|
|
switch {
|
|
case errors.Is(err, filer_pb.ErrNotFound):
|
|
h.writeError(w, http.StatusNotFound, notFoundCode, notFoundMessage)
|
|
case isAuthError(err):
|
|
h.writeError(w, http.StatusForbidden, ErrCodeAccessDenied, err.Error())
|
|
case errors.Is(err, ErrConcurrentUpdate):
|
|
h.writeError(w, http.StatusConflict, ErrCodeConflict, "maintenance configuration changed concurrently, retry the request")
|
|
default:
|
|
h.writeError(w, http.StatusInternalServerError, ErrCodeInternalError, err.Error())
|
|
}
|
|
}
|
|
|
|
// validateMaintenanceValue rejects a type that does not belong to the scope and
|
|
// settings that do not name that same type.
|
|
func validateMaintenanceValue(maintenanceType string, allowed map[string]bool, value *MaintenanceConfigurationValue) error {
|
|
if maintenanceType == "" {
|
|
return fmt.Errorf("type is required")
|
|
}
|
|
if !allowed[maintenanceType] {
|
|
return fmt.Errorf("unsupported maintenance type %q", maintenanceType)
|
|
}
|
|
if value == nil {
|
|
return fmt.Errorf("value is required")
|
|
}
|
|
|
|
switch value.Status {
|
|
case MaintenanceStatusEnabled, MaintenanceStatusDisabled:
|
|
case "":
|
|
return fmt.Errorf("value.status is required")
|
|
default:
|
|
return fmt.Errorf("invalid value.status %q, expected %q or %q", value.Status, MaintenanceStatusEnabled, MaintenanceStatusDisabled)
|
|
}
|
|
|
|
if value.Settings != nil && !settingsMatchType(maintenanceType, value.Settings) {
|
|
return fmt.Errorf("value.settings must only contain %s", maintenanceType)
|
|
}
|
|
return validateMaintenanceSettings(value.Settings)
|
|
}
|
|
|
|
// AWS bounds every maintenance setting to a positive 32-bit value. Accepting
|
|
// anything else would store a number the worker then ignores or saturates, so
|
|
// the configuration read back would not be the one that runs.
|
|
const (
|
|
maintenanceSettingMin int64 = 1
|
|
maintenanceSettingMax int64 = 2147483647
|
|
)
|
|
|
|
func validateMaintenanceSettings(settings *MaintenanceSettings) error {
|
|
if settings == nil {
|
|
return nil
|
|
}
|
|
|
|
if c := settings.IcebergCompaction; c != nil {
|
|
if err := validateCompactionStrategy(c.Strategy); err != nil {
|
|
return err
|
|
}
|
|
if err := validateMaintenanceSetting("targetFileSizeMB", c.TargetFileSizeMB); err != nil {
|
|
return err
|
|
}
|
|
}
|
|
if m := settings.IcebergSnapshotManagement; m != nil {
|
|
if err := validateMaintenanceSetting("minSnapshotsToKeep", m.MinSnapshotsToKeep); err != nil {
|
|
return err
|
|
}
|
|
if err := validateMaintenanceSetting("maxSnapshotAgeHours", m.MaxSnapshotAgeHours); err != nil {
|
|
return err
|
|
}
|
|
}
|
|
if u := settings.IcebergUnreferencedFileRemoval; u != nil {
|
|
if err := validateMaintenanceSetting("unreferencedDays", u.UnreferencedDays); err != nil {
|
|
return err
|
|
}
|
|
if err := validateMaintenanceSetting("nonCurrentDays", u.NonCurrentDays); err != nil {
|
|
return err
|
|
}
|
|
}
|
|
return nil
|
|
}
|
|
|
|
func validateMaintenanceSetting(name string, value *int64) error {
|
|
if value == nil {
|
|
return nil
|
|
}
|
|
if *value < maintenanceSettingMin || *value > maintenanceSettingMax {
|
|
return fmt.Errorf("%s must be between %d and %d, got %d", name, maintenanceSettingMin, maintenanceSettingMax, *value)
|
|
}
|
|
return nil
|
|
}
|
|
|
|
// validateCompactionStrategy rejects a strategy the maintenance worker cannot
|
|
// carry out, rather than accepting it and quietly compacting some other way.
|
|
func validateCompactionStrategy(strategy string) error {
|
|
switch strategy {
|
|
case "", CompactionStrategyAuto, CompactionStrategyBinpack, CompactionStrategySort:
|
|
return nil
|
|
case CompactionStrategyZOrder:
|
|
return fmt.Errorf("compaction strategy %q is not supported", strategy)
|
|
default:
|
|
return fmt.Errorf("invalid compaction strategy %q, expected one of %q, %q, %q",
|
|
strategy, CompactionStrategyAuto, CompactionStrategyBinpack, CompactionStrategySort)
|
|
}
|
|
}
|
|
|
|
func settingsMatchType(maintenanceType string, settings *MaintenanceSettings) bool {
|
|
switch maintenanceType {
|
|
case MaintenanceTypeIcebergCompaction:
|
|
return settings.IcebergSnapshotManagement == nil && settings.IcebergUnreferencedFileRemoval == nil
|
|
case MaintenanceTypeIcebergSnapshotManagement:
|
|
return settings.IcebergCompaction == nil && settings.IcebergUnreferencedFileRemoval == nil
|
|
case MaintenanceTypeIcebergUnreferencedFileRemoval:
|
|
return settings.IcebergCompaction == nil && settings.IcebergSnapshotManagement == nil
|
|
}
|
|
return false
|
|
}
|