improve docs; add DagstoreRecoverShard.

api/api_storage.go

@@ -171,10 +171,32 @@ type StorageMiner interface {
 	// DAG store. Only available on nodes running the markets subsystem.
 	DagstoreListShards(ctx context.Context) ([]DagstoreShardInfo, error) //perm:read
 
-	// DagstoreInitializeShard initializes an uninitialized shard by acquiring
-	// it and releasing it as soon as it's ready.
+	// DagstoreInitializeShard initializes an uninitialized shard.
+	//
+	// Initialization consists of fetching the shard's data (deal payload) from
+	// the storage subsystem, generating an index, and persisting the index
+	// to facilitate later retrievals, and/or to publish to external sources.
+	//
+	// This operation is intended to complement the initial migration. The
+	// migration registers a shard for every unique piece CID, with lazy
+	// initialization. Thus, shards are not initialized immediately to avoid
+	// IO activity competing with proving. Instead, shard are initialized
+	// when first accessed. This method forces the initialization of a shard by
+	// accessing it and immediately releasing it. This is useful to warm up the
+	// cache to facilitate subsequent retrievals, and to generate the indexes
+	// to publish them externally.
+	//
+	// This operation fails if the shard is not in ShardStateNew state.
+	// It blocks until initialization finishes.
 	DagstoreInitializeShard(ctx context.Context, key string) error //perm:write
 
+	// DagstoreRecoverShard attempts to recover a failed shard.
+	//
+	// This operation fails if the shard is not in ShardStateErrored state.
+	// It blocks until recovery finishes. If recovery failed, it returns the
+	// error.
+	DagstoreRecoverShard(ctx context.Context, key string) error //perm:write
+
 	// DagstoreGC runs garbage collection on the DAG store.
 	DagstoreGC(ctx context.Context) ([]DagstoreGCResult, error) //perm:admin
 

api/proxy_gen.go

@@ -609,6 +609,8 @@ type StorageMinerStruct struct {
 
 		DagstoreListShards func(p0 context.Context) ([]DagstoreShardInfo, error) `perm:"read"`
 
+		DagstoreRecoverShard func(p0 context.Context, p1 string) error `perm:"write"`
+
 		DealsConsiderOfflineRetrievalDeals func(p0 context.Context) (bool, error) `perm:"admin"`
 
 		DealsConsiderOfflineStorageDeals func(p0 context.Context) (bool, error) `perm:"admin"`
@@ -3608,6 +3610,17 @@ func (s *StorageMinerStub) DagstoreListShards(p0 context.Context) ([]DagstoreSha
 	return *new([]DagstoreShardInfo), ErrNotSupported
 }
 
+func (s *StorageMinerStruct) DagstoreRecoverShard(p0 context.Context, p1 string) error {
+	if s.Internal.DagstoreRecoverShard == nil {
+		return ErrNotSupported
+	}
+	return s.Internal.DagstoreRecoverShard(p0, p1)
+}
+
+func (s *StorageMinerStub) DagstoreRecoverShard(p0 context.Context, p1 string) error {
+	return ErrNotSupported
+}
+
 func (s *StorageMinerStruct) DealsConsiderOfflineRetrievalDeals(p0 context.Context) (bool, error) {
 	if s.Internal.DealsConsiderOfflineRetrievalDeals == nil {
 		return false, ErrNotSupported

documentation/en/api-v0-methods-miner.md

@@ -22,6 +22,7 @@
   * [DagstoreGC](#DagstoreGC)
   * [DagstoreInitializeShard](#DagstoreInitializeShard)
   * [DagstoreListShards](#DagstoreListShards)
+  * [DagstoreRecoverShard](#DagstoreRecoverShard)
 * [Deals](#Deals)
   * [DealsConsiderOfflineRetrievalDeals](#DealsConsiderOfflineRetrievalDeals)
   * [DealsConsiderOfflineStorageDeals](#DealsConsiderOfflineStorageDeals)
@@ -363,8 +364,23 @@ Inputs: `null`
 Response: `null`
 
 ### DagstoreInitializeShard
-DagstoreInitializeShard initializes an uninitialized shard by acquiring
-it and releasing it as soon as it's ready.
+DagstoreInitializeShard initializes an uninitialized shard.
+
+Initialization consists of fetching the shard's data (deal payload) from
+the storage subsystem, generating an index, and persisting the index
+to facilitate later retrievals, and/or to publish to external sources.
+
+This operation is intended to complement the initial migration. The
+migration registers a shard for every unique piece CID, with lazy
+initialization. Thus, shards are not initialized immediately to avoid
+IO activity competing with proving. Instead, shard are initialized
+when first accessed. This method forces the initialization of a shard by
+accessing it and immediately releasing it. This is useful to warm up the
+cache to facilitate subsequent retrievals, and to generate the indexes
+to publish them externally.
+
+This operation fails if the shard is not in ShardStateNew state.
+It blocks until initialization finishes.
 
 
 Perms: write
@@ -389,6 +405,25 @@ Inputs: `null`
 
 Response: `null`
 
+### DagstoreRecoverShard
+DagstoreRecoverShard attempts to recover a failed shard.
+
+This operation fails if the shard is not in ShardStateErrored state.
+It blocks until recovery finishes. If recovery failed, it returns the
+error.
+
+
+Perms: write
+
+Inputs:
+```json
+[
+  "string value"
+]
+```
+
+Response: `{}`
+
 ## Deals
 
 

node/impl/storminer.go

@@ -616,6 +616,36 @@ func (sm *StorageMinerAPI) DagstoreInitializeShard(ctx context.Context, key stri
 	return nil
 }
 
+func (sm *StorageMinerAPI) DagstoreRecoverShard(ctx context.Context, key string) error {
+	if sm.DAGStore == nil {
+		return fmt.Errorf("dagstore not available on this node")
+	}
+
+	k := shard.KeyFromString(key)
+
+	info, err := sm.DAGStore.GetShardInfo(k)
+	if err != nil {
+		return fmt.Errorf("failed to get shard info: %w", err)
+	}
+	if st := info.ShardState; st != dagstore.ShardStateErrored {
+		return fmt.Errorf("cannot recover shard; expected state ShardStateErrored, was: %s", st.String())
+	}
+
+	ch := make(chan dagstore.ShardResult, 1)
+	if err = sm.DAGStore.RecoverShard(ctx, k, ch, dagstore.RecoverOpts{}); err != nil {
+		return fmt.Errorf("failed to recover shard: %w", err)
+	}
+
+	var res dagstore.ShardResult
+	select {
+	case res = <-ch:
+	case <-ctx.Done():
+		return ctx.Err()
+	}
+
+	return res.Error
+}
+
 func (sm *StorageMinerAPI) DagstoreGC(ctx context.Context) ([]api.DagstoreGCResult, error) {
 	if sm.DAGStore == nil {
 		return nil, fmt.Errorf("dagstore not available on this node")