core/txpool/blobpool, eth/catalyst: place null for missing blob (ethereum#32536)

This pull request fixes a regression, introduced in ethereum#32190

Specifically, in GetBlobsV1 engine API, if any blob is missing, the null
should be placed in
response, unfortunately a behavioral change was introduced in ethereum#32190,
returning an error
instead.

What's more, a more comprehensive test suite is added to cover both
`GetBlobsV1` and
`GetBlobsV2` endpoints.

Author: rjl493456442

core/txpool/blobpool/blobpool.go

@@ -1298,6 +1298,13 @@ func (p *BlobPool) GetMetadata(hash common.Hash) *txpool.TxMetadata {
 }
 
 // GetBlobs returns a number of blobs and proofs for the given versioned hashes.
+// Blobpool must place responses in the order given in the request, using null
+// for any missing blobs.
+//
+// For instance, if the request is [A_versioned_hash, B_versioned_hash,
+// C_versioned_hash] and blobpool has data for blobs A and C, but doesn't have
+// data for B, the response MUST be [A, null, C].
+//
 // This is a utility method for the engine API, enabling consensus clients to
 // retrieve blobs from the pools directly instead of the network.
 func (p *BlobPool) GetBlobs(vhashes []common.Hash, version byte) ([]*kzg4844.Blob, []kzg4844.Commitment, [][]kzg4844.Proof, error) {
@@ -1317,12 +1324,13 @@ func (p *BlobPool) GetBlobs(vhashes []common.Hash, version byte) ([]*kzg4844.Blo
 		if _, ok := filled[vhash]; ok {
 			continue
 		}
-		// Retrieve the corresponding blob tx with the vhash
+		// Retrieve the corresponding blob tx with the vhash, skip blob resolution
+		// if it's not found locally and place the null instead.
 		p.lock.RLock()
 		txID, exists := p.lookup.storeidOfBlob(vhash)
 		p.lock.RUnlock()
 		if !exists {
-			return nil, nil, nil, fmt.Errorf("blob with vhash %x is not found", vhash)
+			continue
 		}
 		data, err := p.store.Get(txID)
 		if err != nil {

core/txpool/blobpool/blobpool_test.go

@@ -24,6 +24,7 @@ import (
 	"fmt"
 	"math"
 	"math/big"
+	"math/rand"
 	"os"
 	"path/filepath"
 	"reflect"
@@ -41,6 +42,7 @@ import (
 	"github.com/ethereum/go-ethereum/core/types"
 	"github.com/ethereum/go-ethereum/crypto"
 	"github.com/ethereum/go-ethereum/crypto/kzg4844"
+	"github.com/ethereum/go-ethereum/internal/testrand"
 	"github.com/ethereum/go-ethereum/params"
 	"github.com/ethereum/go-ethereum/rlp"
 	"github.com/holiman/billy"
@@ -1814,10 +1816,10 @@ func TestGetBlobs(t *testing.T) {
 	}
 
 	cases := []struct {
-		start   int
-		limit   int
-		version byte
-		expErr  bool
+		start      int
+		limit      int
+		fillRandom bool
+		version    byte
 	}{
 		{
 			start: 0, limit: 6,
@@ -1827,6 +1829,14 @@ func TestGetBlobs(t *testing.T) {
 			start: 0, limit: 6,
 			version: types.BlobSidecarVersion1,
 		},
+		{
+			start: 0, limit: 6, fillRandom: true,
+			version: types.BlobSidecarVersion0,
+		},
+		{
+			start: 0, limit: 6, fillRandom: true,
+			version: types.BlobSidecarVersion1,
+		},
 		{
 			start: 3, limit: 9,
 			version: types.BlobSidecarVersion0,
@@ -1835,6 +1845,14 @@ func TestGetBlobs(t *testing.T) {
 			start: 3, limit: 9,
 			version: types.BlobSidecarVersion1,
 		},
+		{
+			start: 3, limit: 9, fillRandom: true,
+			version: types.BlobSidecarVersion0,
+		},
+		{
+			start: 3, limit: 9, fillRandom: true,
+			version: types.BlobSidecarVersion1,
+		},
 		{
 			start: 3, limit: 15,
 			version: types.BlobSidecarVersion0,
@@ -1843,6 +1861,14 @@ func TestGetBlobs(t *testing.T) {
 			start: 3, limit: 15,
 			version: types.BlobSidecarVersion1,
 		},
+		{
+			start: 3, limit: 15, fillRandom: true,
+			version: types.BlobSidecarVersion0,
+		},
+		{
+			start: 3, limit: 15, fillRandom: true,
+			version: types.BlobSidecarVersion1,
+		},
 		{
 			start: 0, limit: 18,
 			version: types.BlobSidecarVersion0,
@@ -1852,58 +1878,79 @@ func TestGetBlobs(t *testing.T) {
 			version: types.BlobSidecarVersion1,
 		},
 		{
-			start: 18, limit: 20,
+			start: 0, limit: 18, fillRandom: true,
 			version: types.BlobSidecarVersion0,
-			expErr:  true,
+		},
+		{
+			start: 0, limit: 18, fillRandom: true,
+			version: types.BlobSidecarVersion1,
 		},
 	}
 	for i, c := range cases {
-		var vhashes []common.Hash
+		var (
+			vhashes []common.Hash
+			filled  = make(map[int]struct{})
+		)
+		if c.fillRandom {
+			filled[len(vhashes)] = struct{}{}
+			vhashes = append(vhashes, testrand.Hash())
+		}
 		for j := c.start; j < c.limit; j++ {
 			vhashes = append(vhashes, testBlobVHashes[j])
+			if c.fillRandom && rand.Intn(2) == 0 {
+				filled[len(vhashes)] = struct{}{}
+				vhashes = append(vhashes, testrand.Hash())
+			}
+		}
+		if c.fillRandom {
+			filled[len(vhashes)] = struct{}{}
+			vhashes = append(vhashes, testrand.Hash())
 		}
 		blobs, _, proofs, err := pool.GetBlobs(vhashes, c.version)
+		if err != nil {
+			t.Errorf("Unexpected error for case %d, %v", i, err)
+		}
 
-		if c.expErr {
-			if err == nil {
-				t.Errorf("Unexpected return, want error for case %d", i)
+		// Cross validate what we received vs what we wanted
+		length := c.limit - c.start
+		wantLen := length + len(filled)
+		if len(blobs) != wantLen || len(proofs) != wantLen {
+			t.Errorf("retrieved blobs/proofs size mismatch: have %d/%d, want %d", len(blobs), len(proofs), wantLen)
+			continue
+		}
+
+		var unknown int
+		for j := 0; j < len(blobs); j++ {
+			if _, exist := filled[j]; exist {
+				if blobs[j] != nil || proofs[j] != nil {
+					t.Errorf("Unexpected blob and proof, item %d", j)
+				}
+				unknown++
+				continue
 			}
-		} else {
-			if err != nil {
-				t.Errorf("Unexpected error for case %d, %v", i, err)
+			// If an item is missing, but shouldn't, error
+			if blobs[j] == nil || proofs[j] == nil {
+				t.Errorf("tracked blob retrieval failed: item %d, hash %x", j, vhashes[j])
+				continue
 			}
-			// Cross validate what we received vs what we wanted
-			length := c.limit - c.start
-			if len(blobs) != length || len(proofs) != length {
-				t.Errorf("retrieved blobs/proofs size mismatch: have %d/%d, want %d", len(blobs), len(proofs), length)
+			// Item retrieved, make sure the blob matches the expectation
+			if *blobs[j] != *testBlobs[c.start+j-unknown] {
+				t.Errorf("retrieved blob mismatch: item %d, hash %x", j, vhashes[j])
 				continue
 			}
-			for j := 0; j < len(blobs); j++ {
-				// If an item is missing, but shouldn't, error
-				if blobs[j] == nil || proofs[j] == nil {
-					t.Errorf("tracked blob retrieval failed: item %d, hash %x", j, vhashes[j])
-					continue
+			// Item retrieved, make sure the proof matches the expectation
+			if c.version == types.BlobSidecarVersion0 {
+				if proofs[j][0] != testBlobProofs[c.start+j-unknown] {
+					t.Errorf("retrieved proof mismatch: item %d, hash %x", j, vhashes[j])
 				}
-				// Item retrieved, make sure the blob matches the expectation
-				if *blobs[j] != *testBlobs[c.start+j] {
-					t.Errorf("retrieved blob mismatch: item %d, hash %x", j, vhashes[j])
-					continue
-				}
-				// Item retrieved, make sure the proof matches the expectation
-				if c.version == types.BlobSidecarVersion0 {
-					if proofs[j][0] != testBlobProofs[c.start+j] {
-						t.Errorf("retrieved proof mismatch: item %d, hash %x", j, vhashes[j])
-					}
-				} else {
-					want, _ := kzg4844.ComputeCellProofs(blobs[j])
-					if !reflect.DeepEqual(want, proofs[j]) {
-						t.Errorf("retrieved proof mismatch: item %d, hash %x", j, vhashes[j])
-					}
+			} else {
+				want, _ := kzg4844.ComputeCellProofs(blobs[j])
+				if !reflect.DeepEqual(want, proofs[j]) {
+					t.Errorf("retrieved proof mismatch: item %d, hash %x", j, vhashes[j])
 				}
 			}
 		}
 	}
-
 	pool.Close()
 }
 

eth/catalyst/api.go

@@ -458,6 +458,26 @@ func (api *ConsensusAPI) getPayload(payloadID engine.PayloadID, full bool) (*eng
 }
 
 // GetBlobsV1 returns a blob from the transaction pool.
+//
+// Specification:
+//
+// Given an array of blob versioned hashes client software MUST respond with an
+// array of BlobAndProofV1 objects with matching versioned hashes, respecting the
+// order of versioned hashes in the input array.
+//
+// Client software MUST place responses in the order given in the request, using
+// null for any missing blobs. For instance:
+//
+// if the request is [A_versioned_hash, B_versioned_hash, C_versioned_hash] and
+// client software has data for blobs A and C, but doesn't have data for B, the
+// response MUST be [A, null, C].
+//
+// Client software MUST support request sizes of at least 128 blob versioned hashes.
+// The client MUST return -38004: Too large request error if the number of requested
+// blobs is too large.
+//
+// Client software MAY return an array of all null entries if syncing or otherwise
+// unable to serve blob pool data.
 func (api *ConsensusAPI) GetBlobsV1(hashes []common.Hash) ([]*engine.BlobAndProofV1, error) {
 	if len(hashes) > 128 {
 		return nil, engine.TooLargeRequest.With(fmt.Errorf("requested blob count too large: %v", len(hashes)))
@@ -468,6 +488,10 @@ func (api *ConsensusAPI) GetBlobsV1(hashes []common.Hash) ([]*engine.BlobAndProo
 	}
 	res := make([]*engine.BlobAndProofV1, len(hashes))
 	for i := 0; i < len(blobs); i++ {
+		// Skip the non-existing blob
+		if blobs[i] == nil {
+			continue
+		}
 		res[i] = &engine.BlobAndProofV1{
 			Blob:  blobs[i][:],
 			Proof: proofs[i][0][:],
@@ -477,6 +501,33 @@ func (api *ConsensusAPI) GetBlobsV1(hashes []common.Hash) ([]*engine.BlobAndProo
 }
 
 // GetBlobsV2 returns a blob from the transaction pool.
+//
+// Specification:
+// Refer to the specification for engine_getBlobsV1 with changes of the following:
+//
+// Given an array of blob versioned hashes client software MUST respond with an
+// array of BlobAndProofV2 objects with matching versioned hashes, respecting
+// the order of versioned hashes in the input array.
+//
+// Client software MUST return null in case of any missing or older version blobs.
+// For instance,
+//
+//   - if the request is [A_versioned_hash, B_versioned_hash, C_versioned_hash] and
+//     client software has data for blobs A and C, but doesn't have data for B, the
+//     response MUST be null.
+//
+//   - if the request is [A_versioned_hash_for_blob_with_blob_proof], the response
+//     MUST be null as well.
+//
+//     Note, geth internally make the conversion from old version to new one, so the
+//     data will be returned normally.
+//
+// Client software MUST support request sizes of at least 128 blob versioned
+// hashes. The client MUST return -38004: Too large request error if the number
+// of requested blobs is too large.
+//
+// Client software MUST return null if syncing or otherwise unable to serve
+// blob pool data.
 func (api *ConsensusAPI) GetBlobsV2(hashes []common.Hash) ([]*engine.BlobAndProofV2, error) {
 	if len(hashes) > 128 {
 		return nil, engine.TooLargeRequest.With(fmt.Errorf("requested blob count too large: %v", len(hashes)))
@@ -498,6 +549,12 @@ func (api *ConsensusAPI) GetBlobsV2(hashes []common.Hash) ([]*engine.BlobAndProo
 	}
 	res := make([]*engine.BlobAndProofV2, len(hashes))
 	for i := 0; i < len(blobs); i++ {
+		// the blob is missing, return null as response. It should
+		// be caught by `AvailableBlobs` though, perhaps data race
+		// occurs between two calls.
+		if blobs[i] == nil {
+			return nil, nil
+		}
 		var cellProofs []hexutil.Bytes
 		for _, proof := range proofs[i] {
 			cellProofs = append(cellProofs, proof[:])