Files
upstream-seaweedfs/weed/mq/kafka/protocol/consumer_coordination.go
upstream-mirror 89f5be005d
Some checks failed
go: build dev binaries / cleanup (push) Successful in 4s
Codespell / Check for spelling errors (push) Failing after 3s
docker: build dev containers / build-rust-binaries (amd64, x86_64-unknown-linux-musl) (push) Failing after 3s
docker: build dev containers / build-dev-containers (push) Has been skipped
docker: build dev containers / build-rust-binaries (arm64, true, aarch64-unknown-linux-musl) (push) Failing after 3s
End to End / FUSE Mount (push) Failing after 2s
EC Integration Tests / EC Integration Tests (push) Failing after 30s
FUSE DLM Integration Tests / FUSE DLM Integration Tests (push) Failing after 3s
FUSE Volume Server Failover Tests / FUSE Volume Server Failover (push) Failing after 3s
FUSE Integration Tests / FUSE Integration Testing (push) Failing after 2s
FUSE P2P Peer Chunk Sharing Integration Tests / FUSE P2P Peer Chunk Sharing (push) Failing after 3s
go: build binary / Go Vet (push) Failing after 2s
go: build binary / Go Vet 32-bit (push) Failing after 3s
go: build binary / Build (push) Failing after 4s
go: build binary / Build cross-platform (freebsd/amd64) (push) Failing after 3s
go: build binary / Build cross-platform (windows/amd64) (push) Failing after 3s
go: build binary / Build cross-platform (darwin/arm64) (push) Failing after 3s
go: build binary / Build cross-platform (windows/arm64) (push) Failing after 3s
go: build binary / Test (push) Failing after 2s
go: build binary / Test 32-bit (push) Failing after 3s
helm: lint and test charts / lint-test (push) Failing after 3s
Java Client Integration Tests / Java Integration Tests (11) (push) Failing after 3s
Java Client Integration Tests / Java Integration Tests (17) (push) Failing after 3s
go: build dev binaries / build_dev_linux_windows (amd64, linux) (push) Failing after 2s
go: build dev binaries / build_dev_linux_windows (amd64, windows) (push) Failing after 3s
go: build dev binaries / build_dev_darwin (amd64, darwin) (push) Has been skipped
go: build dev binaries / build_dev_darwin (arm64, darwin) (push) Has been skipped
Java Client Unit Tests / Java Unit Tests (11) (push) Failing after 3s
Java Client Unit Tests / Java Unit Tests (17) (push) Failing after 2s
Java Client Unit Tests / Java Unit Tests (21) (push) Failing after 3s
Java Client Unit Tests / Java Unit Tests (8) (push) Failing after 3s
Kafka Quick Test (Load Test with Schema Registry) / Kafka Client Load Test (Quick) (push) Failing after 3s
Kafka Gateway Tests / Kafka Unit Tests (unit-tests-1) (push) Failing after 11s
Kafka Gateway Tests / Kafka Integration Tests (Critical) (integration-1) (push) Failing after 3s
Kafka Gateway Tests / Kafka End-to-End Tests (with SMQ) (e2e-1) (push) Failing after 3s
Kafka Gateway Tests / Kafka Consumer Group Tests (Highly Isolated) (consumer-group-1) (push) Failing after 2s
Kafka Gateway Tests / Kafka Client Compatibility (with SMQ) (client-compat-1) (push) Failing after 3s
Kafka Gateway Tests / Kafka SMQ Integration Tests (Full Stack) (smq-integration-1) (push) Failing after 3s
Kafka Gateway Tests / Kafka Protocol Tests (Isolated) (protocol-1) (push) Failing after 3s
KMS Tests / KMS Provider Integration Tests (push) Failing after 2s
KMS Tests / S3 KMS End-to-End Tests (push) Failing after 3s
Master Cold Start Tests / Master Cold Start Tests (push) Failing after 4s
Metadata Subscribe Integration Tests / Metadata Subscribe Integration Tests (push) Failing after 3s
Multi-Master Tests / Multi-Master Failover Tests (push) Failing after 3s
Performance / CPU and Heap Profile (push) Failing after 2s
Performance / S3 Read/Write Benchmark (rust volume) (push) Failing after 3s
pjdfstest POSIX Compliance / pjdfstest (push) Failing after 2s
Plugin Worker Integration Tests / Plugin Worker: erasure_coding (push) Failing after 3s
Plugin Worker Integration Tests / Plugin Worker: vacuum (push) Failing after 3s
Rust Volume Server Tests / Rust Integration Tests (push) Failing after 3s
Rust Volume Server Tests / Go Tests with Rust Volume (grpc - Shard 1) (push) Failing after 2s
Rust Volume Server Tests / Go Tests with Rust Volume (http - Shard 1) (push) Failing after 3s
Rust Volume Server Tests / Go Tests with Rust Volume (grpc - Shard 2) (push) Failing after 3s
Rust Volume Server Tests / Go Tests with Rust Volume (http - Shard 2) (push) Failing after 3s
Rust Volume Server Tests / Go Tests with Rust Volume (grpc - Shard 3) (push) Failing after 3s
S3 IAM Integration Tests / S3 IAM Distributed Tests (push) Failing after 2s
S3 IAM Integration Tests / S3 IAM Performance Tests (push) Failing after 3s
Performance / Throughput Benchmark (go volume) (push) Failing after 3s
Performance / Throughput Benchmark (rust volume) (push) Failing after 2s
Performance / S3 Read/Write Benchmark (go volume) (push) Failing after 3s
Plugin Worker Integration Tests / Plugin Worker: volume_balance (push) Failing after 3s
PostgreSQL Gateway Tests / PostgreSQL Basic Tests (push) Failing after 3s
Rust Volume Server Tests / Rust Unit Tests (push) Failing after 2s
Rust Volume Server Tests / Go Tests with Rust Volume (http - Shard 3) (push) Failing after 3s
Rust Plugin Worker Tests / Rust Plugin Worker Build and Unit Tests (push) Failing after 3s
rust: build dev volume server binaries / cleanup (push) Successful in 3s
S3 ETag and ACL Tests / S3 ETag + ACL Integration Tests (push) Failing after 3s
S3 IAM Integration Tests / IAM Unit Tests (push) Failing after 3s
S3 IAM Integration Tests / S3 IAM Integration Tests (advanced) (push) Failing after 3s
S3 IAM Integration Tests / S3 IAM Integration Tests (basic) (push) Failing after 2s
S3 IAM Integration Tests / S3 IAM Integration Tests (group) (push) Failing after 3s
S3 IAM Integration Tests / S3 IAM Integration Tests (policy-enforcement) (push) Failing after 2s
S3 IAM Integration Tests / S3 IAM Integration Tests (sts) (push) Failing after 4s
S3 Keycloak Integration Tests / S3 Keycloak Integration Tests (push) Failing after 3s
S3 PyArrow Parquet Tests / PyArrow Parquet Tests (Python 3.11) (push) Failing after 3s
S3 PyArrow Parquet Tests / Go Unit Tests (Implicit Directory) (push) Has been cancelled
S3 PyArrow Parquet Tests / PyArrow Parquet Tests (Python 3.12) (push) Has been cancelled
rust: build dev volume server binaries / build-rust-volume-dev-darwin (darwin-amd64, x86_64-apple-darwin) (push) Has been cancelled
rust: build dev volume server binaries / build-rust-volume-dev-darwin (darwin-arm64, aarch64-apple-darwin) (push) Has been cancelled
rust: build dev volume server binaries / build-rust-volume-dev-linux (linux-amd64, x86_64-unknown-linux-gnu) (push) Has been cancelled
S3 PyArrow Parquet Tests / PyArrow Parquet Tests (Python 3.9) (push) Has been cancelled
S3 Proxy Signature Tests / S3 Proxy Signature Verification Tests (push) Has been cancelled
S3 SDK V2 Route Disambiguation Tests / S3 SDK V2 Routing Tests (push) Has been cancelled
S3 SSE Tests / S3 SSE Integration Tests (quick) (push) Has been cancelled
S3 SSE Tests / S3 SSE Compatibility Test (push) Has been cancelled
S3 SSE Tests / S3 SSE Metadata Persistence Test (push) Has been cancelled
S3 SSE Tests / S3 SSE Copy Operations Test (push) Has been cancelled
S3 SSE Tests / S3 SSE Multipart Upload Test (push) Has been cancelled
S3 SSE Tests / S3 SSE Performance Test (push) Has been cancelled
S3 SSE Tests / S3 Volume Encryption Test (push) Has been cancelled
S3 SSE Tests / S3 SSE Integration Tests (comprehensive) (push) Has been cancelled
Spark Integration Tests / Spark Integration Tests (push) Failing after 2s
Telemetry Integration Tests / telemetry-integration-test (push) Failing after 3s
Volume Server Integration Tests / Volume Server Integration Tests (grpc - Shard 1) (push) Failing after 3s
Volume Server Integration Tests / Volume Server Integration Tests (http - Shard 1) (push) Failing after 3s
Ceph S3 tests / Basic S3 tests (KV store) (push) Has been cancelled
Ceph S3 tests / S3 Versioning & Object Lock tests (push) Has been cancelled
S3 Policy Integration Tests / S3 Policy Unit Tests (push) Failing after 3s
Ceph S3 tests / S3 CORS tests (push) Has been cancelled
Ceph S3 tests / SeaweedFS Custom S3 Copy tests (push) Has been cancelled
Ceph S3 tests / Basic S3 tests (SQL store) (push) Has been cancelled
test s3 over https using aws-cli / awscli-tests (push) Has been cancelled
TLS Rotation Integration Tests / TLS Rotation Integration Tests (push) Has been cancelled
Vacuum Integration Tests / Vacuum Integration Tests (push) Has been cancelled
S3 Policy Integration Tests / S3 Policy Variables Integration Tests (push) Failing after 3s
S3 Policy Integration Tests / S3 Policy Enforcement Integration Tests (advanced-policy) (push) Failing after 3s
S3 Policy Integration Tests / S3 Policy Enforcement Integration Tests (basic-policy) (push) Failing after 2s
S3 Policy Integration Tests / S3 Policy Enforcement Integration Tests (contextual-policy) (push) Failing after 4s
S3 Policy Integration Tests / Trusted Proxy Detection Tests (push) Failing after 2s
S3 Policy Integration Tests / S3 Policy Shell Integration Tests (push) Failing after 3s
Samba on FUSE Integration / samba-integration (push) Failing after 2s
SFTP Integration Tests / SFTP Integration Testing (push) Failing after 3s
terraform: validate and test modules / fmt, validate, plan-level tests (push) Failing after 3s
terraform: validate and test modules / local cluster smoke test (real weed) (push) Failing after 2s
Volume Server Integration Tests / Volume Server Integration Tests (grpc - Shard 3) (push) Failing after 3s
Volume Server Integration Tests / Volume Server Integration Tests (grpc - Shard 2) (push) Failing after 3s
Volume Server Integration Tests / Volume Server Integration Tests (http - Shard 2) (push) Failing after 2s
Volume Server Integration Tests / Volume Server Integration Tests (http - Shard 3) (push) Failing after 5s
mount: windows conformance / WinFsp conformance (push) Has been cancelled
mount: windows / Mount on Windows (push) Has been cancelled
snapshot of https://github.com/seaweedfs/seaweedfs.git (master, 2026-09-16; blobs > 131072B omitted)
2026-09-16 03:23:42 +05:00

731 lines
22 KiB
Go

package protocol
import (
"encoding/binary"
"fmt"
"time"
"github.com/seaweedfs/seaweedfs/weed/mq/kafka/consumer"
)
// Heartbeat API (key 12) - Consumer group heartbeat
// Consumers send periodic heartbeats to stay in the group and receive rebalancing signals
// HeartbeatRequest represents a Heartbeat request from a Kafka client
type HeartbeatRequest struct {
GroupID string
GenerationID int32
MemberID string
GroupInstanceID string // Optional static membership ID
}
// HeartbeatResponse represents a Heartbeat response to a Kafka client
type HeartbeatResponse struct {
CorrelationID uint32
ErrorCode int16
}
// LeaveGroup API (key 13) - Consumer graceful departure
// Consumers call this when shutting down to trigger immediate rebalancing
// LeaveGroupRequest represents a LeaveGroup request from a Kafka client
type LeaveGroupRequest struct {
GroupID string
MemberID string
GroupInstanceID string // Optional static membership ID
Members []LeaveGroupMember // For newer versions, can leave multiple members
}
// LeaveGroupMember represents a member leaving the group (for batch departures)
type LeaveGroupMember struct {
MemberID string
GroupInstanceID string
Reason string // Optional reason for leaving
}
// LeaveGroupResponse represents a LeaveGroup response to a Kafka client
type LeaveGroupResponse struct {
CorrelationID uint32
ErrorCode int16
Members []LeaveGroupMemberResponse // Per-member responses for newer versions
}
// LeaveGroupMemberResponse represents per-member leave group response
type LeaveGroupMemberResponse struct {
MemberID string
GroupInstanceID string
ErrorCode int16
}
// Error codes specific to consumer coordination are imported from errors.go
func (h *Handler) handleHeartbeat(correlationID uint32, apiVersion uint16, requestBody []byte) ([]byte, error) {
// Parse Heartbeat request
request, err := h.parseHeartbeatRequest(requestBody, apiVersion)
if err != nil {
return h.buildHeartbeatErrorResponseV(correlationID, ErrorCodeInvalidGroupID, apiVersion), nil
}
// Validate request
if request.GroupID == "" || request.MemberID == "" {
return h.buildHeartbeatErrorResponseV(correlationID, ErrorCodeInvalidGroupID, apiVersion), nil
}
// Get consumer group
group := h.groupCoordinator.GetGroup(request.GroupID)
if group == nil {
return h.buildHeartbeatErrorResponseV(correlationID, ErrorCodeInvalidGroupID, apiVersion), nil
}
group.Mu.Lock()
defer group.Mu.Unlock()
// Update group's last activity
group.LastActivity = time.Now()
// Validate member exists
member, exists := group.Members[request.MemberID]
if !exists {
return h.buildHeartbeatErrorResponseV(correlationID, ErrorCodeUnknownMemberID, apiVersion), nil
}
// Validate generation. If the group is rebalancing we want Sarama to rejoin
// (via ErrRebalanceInProgress -> heartbeatLoop cancels session -> newSession)
// rather than tear down on ErrIllegalGeneration, which would exit the caller's
// Consume() entirely since Consume does not internally re-enter on that error.
if request.GenerationID != group.Generation {
switch group.State {
case consumer.GroupStatePreparingRebalance, consumer.GroupStateCompletingRebalance:
return h.buildHeartbeatErrorResponseV(correlationID, ErrorCodeRebalanceInProgress, apiVersion), nil
default:
return h.buildHeartbeatErrorResponseV(correlationID, ErrorCodeIllegalGeneration, apiVersion), nil
}
}
// Update member's last heartbeat
member.LastHeartbeat = time.Now()
// Check if rebalancing is in progress
var errorCode int16 = ErrorCodeNone
switch group.State {
case consumer.GroupStatePreparingRebalance, consumer.GroupStateCompletingRebalance:
// Signal the consumer that rebalancing is happening
errorCode = ErrorCodeRebalanceInProgress
case consumer.GroupStateDead:
errorCode = ErrorCodeInvalidGroupID
case consumer.GroupStateEmpty:
// This shouldn't happen if member exists, but handle gracefully
errorCode = ErrorCodeUnknownMemberID
case consumer.GroupStateStable:
// Normal case - heartbeat accepted
errorCode = ErrorCodeNone
}
// Build successful response
response := HeartbeatResponse{
CorrelationID: correlationID,
ErrorCode: errorCode,
}
return h.buildHeartbeatResponseV(response, apiVersion), nil
}
func (h *Handler) handleLeaveGroup(correlationID uint32, apiVersion uint16, requestBody []byte) ([]byte, error) {
// Parse LeaveGroup request
request, err := h.parseLeaveGroupRequest(requestBody, apiVersion)
if err != nil {
return h.buildLeaveGroupErrorResponse(correlationID, ErrorCodeInvalidGroupID, apiVersion), nil
}
// Validate request - v3+ carries member IDs inside the Members array
if request.GroupID == "" {
return h.buildLeaveGroupErrorResponse(correlationID, ErrorCodeInvalidGroupID, apiVersion), nil
}
if request.MemberID == "" && len(request.Members) == 0 {
return h.buildLeaveGroupErrorResponse(correlationID, ErrorCodeInvalidGroupID, apiVersion), nil
}
// Get consumer group
group := h.groupCoordinator.GetGroup(request.GroupID)
if group == nil {
return h.buildLeaveGroupErrorResponse(correlationID, ErrorCodeInvalidGroupID, apiVersion), nil
}
group.Mu.Lock()
defer group.Mu.Unlock()
// Update group's last activity
group.LastActivity = time.Now()
// Normalize to a list of leaving members. v0-v2 carry a single MemberID at
// the top level; v3+ carry an array. parseLeaveGroupRequest already copies
// Members[0] to MemberID for back-compat, but the full list must be honored
// so batch departures (KIP-345) don't leave stale phantoms in the group.
leavingMembers := request.Members
if len(leavingMembers) == 0 {
leavingMembers = []LeaveGroupMember{{
MemberID: request.MemberID,
GroupInstanceID: request.GroupInstanceID,
}}
}
memberResponses := make([]LeaveGroupMemberResponse, 0, len(leavingMembers))
removedAny := false
leaderLeft := false
for _, leaving := range leavingMembers {
member, exists := group.Members[leaving.MemberID]
if !exists {
memberResponses = append(memberResponses, LeaveGroupMemberResponse{
MemberID: leaving.MemberID,
GroupInstanceID: leaving.GroupInstanceID,
ErrorCode: ErrorCodeUnknownMemberID,
})
continue
}
if h.groupCoordinator.IsStaticMember(member) {
if leaving.GroupInstanceID != "" && *member.GroupInstanceID != leaving.GroupInstanceID {
memberResponses = append(memberResponses, LeaveGroupMemberResponse{
MemberID: leaving.MemberID,
GroupInstanceID: leaving.GroupInstanceID,
ErrorCode: ErrorCodeFencedInstanceID,
})
continue
}
h.groupCoordinator.UnregisterStaticMemberLocked(group, *member.GroupInstanceID)
}
if group.Leader == leaving.MemberID {
leaderLeft = true
}
delete(group.Members, leaving.MemberID)
removedAny = true
memberResponses = append(memberResponses, LeaveGroupMemberResponse{
MemberID: leaving.MemberID,
GroupInstanceID: leaving.GroupInstanceID,
ErrorCode: ErrorCodeNone,
})
}
if removedAny {
// One group-state transition applied after processing all departures.
if len(group.Members) == 0 {
group.State = consumer.GroupStateEmpty
group.Generation++
group.Leader = ""
} else {
group.State = consumer.GroupStatePreparingRebalance
group.Generation++
if leaderLeft {
for memberID := range group.Members {
group.Leader = memberID
break
}
}
for _, m := range group.Members {
m.State = consumer.MemberStatePending
}
}
h.updateGroupSubscriptionFromMembers(group)
}
response := LeaveGroupResponse{
CorrelationID: correlationID,
ErrorCode: ErrorCodeNone,
Members: memberResponses,
}
return h.buildLeaveGroupResponse(response, apiVersion), nil
}
func (h *Handler) parseHeartbeatRequest(data []byte, apiVersion uint16) (*HeartbeatRequest, error) {
if len(data) < 8 {
return nil, fmt.Errorf("request too short")
}
offset := 0
isFlexible := IsFlexibleVersion(12, apiVersion) // Heartbeat API key = 12
// ADMINCLIENT COMPATIBILITY FIX: Parse top-level tagged fields at the beginning for flexible versions
if isFlexible {
_, consumed, err := DecodeTaggedFields(data[offset:])
if err == nil {
offset += consumed
}
}
// Parse GroupID
var groupID string
if isFlexible {
// FLEXIBLE V4+ FIX: GroupID is a compact string
groupIDBytes, consumed := parseCompactString(data[offset:])
if consumed == 0 {
return nil, fmt.Errorf("invalid group ID compact string")
}
if groupIDBytes != nil {
groupID = string(groupIDBytes)
}
offset += consumed
} else {
// Non-flexible parsing (v0-v3)
groupIDLength := int(binary.BigEndian.Uint16(data[offset:]))
offset += 2
if offset+groupIDLength > len(data) {
return nil, fmt.Errorf("invalid group ID length")
}
groupID = string(data[offset : offset+groupIDLength])
offset += groupIDLength
}
// Generation ID (4 bytes) - always fixed-length
if offset+4 > len(data) {
return nil, fmt.Errorf("missing generation ID")
}
generationID := int32(binary.BigEndian.Uint32(data[offset:]))
offset += 4
// Parse MemberID
var memberID string
if isFlexible {
// FLEXIBLE V4+ FIX: MemberID is a compact string
memberIDBytes, consumed := parseCompactString(data[offset:])
if consumed == 0 {
return nil, fmt.Errorf("invalid member ID compact string")
}
if memberIDBytes != nil {
memberID = string(memberIDBytes)
}
offset += consumed
} else {
// Non-flexible parsing (v0-v3)
if offset+2 > len(data) {
return nil, fmt.Errorf("missing member ID length")
}
memberIDLength := int(binary.BigEndian.Uint16(data[offset:]))
offset += 2
if offset+memberIDLength > len(data) {
return nil, fmt.Errorf("invalid member ID length")
}
memberID = string(data[offset : offset+memberIDLength])
offset += memberIDLength
}
// Parse GroupInstanceID (nullable string) - for Heartbeat v1+
var groupInstanceID string
if apiVersion >= 1 {
if isFlexible {
// FLEXIBLE V4+ FIX: GroupInstanceID is a compact nullable string
groupInstanceIDBytes, consumed := parseCompactString(data[offset:])
if consumed == 0 && len(data) > offset && data[offset] == 0x00 {
groupInstanceID = "" // null
offset += 1
} else {
if groupInstanceIDBytes != nil {
groupInstanceID = string(groupInstanceIDBytes)
}
offset += consumed
}
} else {
// Non-flexible v1-v3: regular nullable string
if offset+2 <= len(data) {
instanceIDLength := int16(binary.BigEndian.Uint16(data[offset:]))
offset += 2
if instanceIDLength == -1 {
groupInstanceID = "" // null string
} else if instanceIDLength >= 0 && offset+int(instanceIDLength) <= len(data) {
groupInstanceID = string(data[offset : offset+int(instanceIDLength)])
offset += int(instanceIDLength)
}
}
}
}
// Parse request-level tagged fields (v4+)
if isFlexible {
if offset < len(data) {
_, consumed, err := DecodeTaggedFields(data[offset:])
if err == nil {
offset += consumed
}
}
}
return &HeartbeatRequest{
GroupID: groupID,
GenerationID: generationID,
MemberID: memberID,
GroupInstanceID: groupInstanceID,
}, nil
}
func (h *Handler) parseLeaveGroupRequest(data []byte, apiVersion uint16) (*LeaveGroupRequest, error) {
if len(data) < 4 {
return nil, fmt.Errorf("request too short")
}
offset := 0
isFlexible := IsFlexibleVersion(uint16(APIKeyLeaveGroup), apiVersion)
if isFlexible {
// Skip top-level tagged fields
_, consumed, err := DecodeTaggedFields(data[offset:])
if err != nil {
return nil, fmt.Errorf("LeaveGroup v%d: top-level tagged fields: %w", apiVersion, err)
}
offset += consumed
}
// GroupID
var groupID string
if isFlexible {
bytes, consumed := parseCompactString(data[offset:])
if consumed == 0 {
return nil, fmt.Errorf("LeaveGroup v%d: invalid group ID compact string", apiVersion)
}
if bytes != nil {
groupID = string(bytes)
}
offset += consumed
} else {
if offset+2 > len(data) {
return nil, fmt.Errorf("missing group ID length")
}
groupIDLength := int(binary.BigEndian.Uint16(data[offset:]))
offset += 2
if offset+groupIDLength > len(data) {
return nil, fmt.Errorf("invalid group ID length")
}
groupID = string(data[offset : offset+groupIDLength])
offset += groupIDLength
}
req := &LeaveGroupRequest{
GroupID: groupID,
Members: []LeaveGroupMember{},
}
// v0-v2: top-level MemberID (string). v3+: Members array.
if apiVersion <= 2 {
if offset+2 > len(data) {
return nil, fmt.Errorf("missing member ID length")
}
memberIDLength := int(binary.BigEndian.Uint16(data[offset:]))
offset += 2
if offset+memberIDLength > len(data) {
return nil, fmt.Errorf("invalid member ID length")
}
req.MemberID = string(data[offset : offset+memberIDLength])
offset += memberIDLength
return req, nil
}
// v3+: Members array [{MemberID, GroupInstanceID[, Reason]}]
var membersCount int
if isFlexible {
compactLen, consumed, err := DecodeCompactArrayLength(data[offset:])
if err != nil {
return nil, fmt.Errorf("LeaveGroup v%d: invalid members compact array: %w", apiVersion, err)
}
membersCount = int(compactLen)
offset += consumed
} else {
if offset+4 > len(data) {
return nil, fmt.Errorf("missing members array length")
}
membersCount = int(int32(binary.BigEndian.Uint32(data[offset:])))
offset += 4
}
if membersCount < 0 || membersCount > 100000 {
return nil, fmt.Errorf("unreasonable members count: %d", membersCount)
}
for i := 0; i < membersCount; i++ {
var m LeaveGroupMember
// MemberID
if isFlexible {
bytes, consumed := parseCompactString(data[offset:])
if consumed == 0 {
return nil, fmt.Errorf("LeaveGroup v%d: invalid members[%d].member_id", apiVersion, i)
}
if bytes != nil {
m.MemberID = string(bytes)
}
offset += consumed
} else {
if offset+2 > len(data) {
return nil, fmt.Errorf("members[%d]: missing member_id length", i)
}
ml := int(binary.BigEndian.Uint16(data[offset:]))
offset += 2
if offset+ml > len(data) {
return nil, fmt.Errorf("members[%d]: invalid member_id length", i)
}
m.MemberID = string(data[offset : offset+ml])
offset += ml
}
// GroupInstanceID (nullable)
if isFlexible {
bytes, consumed := parseCompactString(data[offset:])
if consumed == 0 {
return nil, fmt.Errorf("LeaveGroup v%d: invalid members[%d].group_instance_id", apiVersion, i)
}
if bytes != nil {
m.GroupInstanceID = string(bytes)
}
offset += consumed
} else {
if offset+2 > len(data) {
return nil, fmt.Errorf("members[%d]: missing group_instance_id length", i)
}
gil := int16(binary.BigEndian.Uint16(data[offset:]))
offset += 2
if gil >= 0 {
if offset+int(gil) > len(data) {
return nil, fmt.Errorf("members[%d]: invalid group_instance_id length", i)
}
m.GroupInstanceID = string(data[offset : offset+int(gil)])
offset += int(gil)
}
}
// v5+: Reason (compact nullable string, flexible only)
if apiVersion >= 5 && isFlexible {
bytes, consumed := parseCompactString(data[offset:])
if consumed > 0 {
if bytes != nil {
m.Reason = string(bytes)
}
offset += consumed
}
}
// Per-member tagged fields
if isFlexible {
_, consumed, err := DecodeTaggedFields(data[offset:])
if err != nil {
return nil, fmt.Errorf("LeaveGroup v%d: members[%d] tagged fields: %w", apiVersion, i, err)
}
offset += consumed
}
req.Members = append(req.Members, m)
}
// Back-compat convenience: expose the first member as top-level MemberID so
// handler code that pre-dates Members support keeps working.
if req.MemberID == "" && len(req.Members) > 0 {
req.MemberID = req.Members[0].MemberID
req.GroupInstanceID = req.Members[0].GroupInstanceID
}
return req, nil
}
func (h *Handler) buildHeartbeatResponseV(response HeartbeatResponse, apiVersion uint16) []byte {
isFlexible := IsFlexibleVersion(12, apiVersion) // Heartbeat API key = 12
result := make([]byte, 0, 16)
// NOTE: Correlation ID is handled by writeResponseWithCorrelationID
// Do NOT include it in the response body
if isFlexible {
// FLEXIBLE V4+ FORMAT
// NOTE: Response header tagged fields are handled by writeResponseWithHeader
// Do NOT include them in the response body
// Throttle time (4 bytes, 0 = no throttling) - comes first in flexible format
result = append(result, 0, 0, 0, 0)
// Error code (2 bytes)
errorCodeBytes := make([]byte, 2)
binary.BigEndian.PutUint16(errorCodeBytes, uint16(response.ErrorCode))
result = append(result, errorCodeBytes...)
// Response body tagged fields (varint: 0x00 = empty)
result = append(result, 0x00)
} else if apiVersion >= 1 {
// NON-FLEXIBLE V1-V3 FORMAT: throttle_time_ms BEFORE error_code
// CRITICAL FIX: Kafka protocol specifies throttle_time_ms comes FIRST in v1+
// Throttle time (4 bytes, 0 = no throttling) - comes first in v1-v3
result = append(result, 0, 0, 0, 0)
// Error code (2 bytes)
errorCodeBytes := make([]byte, 2)
binary.BigEndian.PutUint16(errorCodeBytes, uint16(response.ErrorCode))
result = append(result, errorCodeBytes...)
} else {
// V0 FORMAT: Only error_code, NO throttle_time_ms
// Error code (2 bytes)
errorCodeBytes := make([]byte, 2)
binary.BigEndian.PutUint16(errorCodeBytes, uint16(response.ErrorCode))
result = append(result, errorCodeBytes...)
}
return result
}
func (h *Handler) buildLeaveGroupResponse(response LeaveGroupResponse, apiVersion uint16) []byte {
// LeaveGroup v0 only includes correlation_id and error_code (no throttle_time_ms, no members)
if apiVersion == 0 {
return h.buildLeaveGroupV0Response(response)
}
// v4+ uses flexible encoding (compact strings/arrays + tagged fields).
if IsFlexibleVersion(uint16(APIKeyLeaveGroup), apiVersion) {
return h.buildLeaveGroupFlexibleResponse(response)
}
// v1-v3 use the full non-flexible response format.
return h.buildLeaveGroupFullResponse(response)
}
// buildLeaveGroupFlexibleResponse encodes a LeaveGroup response for v4+ clients,
// which negotiate flexible versions. Fields:
//
// throttle_time_ms (int32)
// error_code (int16)
// members (compact_array of {member_id: compact_string,
// group_instance_id: compact_nullable_string,
// error_code: int16, _tagged_fields})
// _tagged_fields
func (h *Handler) buildLeaveGroupFlexibleResponse(response LeaveGroupResponse) []byte {
estimatedSize := 16
for _, m := range response.Members {
estimatedSize += len(m.MemberID) + len(m.GroupInstanceID) + 10
}
result := make([]byte, 0, estimatedSize)
// throttle_time_ms
result = append(result, 0, 0, 0, 0)
// error_code
errorCodeBytes := make([]byte, 2)
binary.BigEndian.PutUint16(errorCodeBytes, uint16(response.ErrorCode))
result = append(result, errorCodeBytes...)
// members: compact array
result = append(result, CompactArrayLength(uint32(len(response.Members)))...)
for _, m := range response.Members {
// member_id: compact string
result = append(result, CompactStringLength(len(m.MemberID))...)
result = append(result, []byte(m.MemberID)...)
// group_instance_id: compact nullable string
if m.GroupInstanceID == "" {
result = append(result, 0) // null
} else {
result = append(result, CompactStringLength(len(m.GroupInstanceID))...)
result = append(result, []byte(m.GroupInstanceID)...)
}
// member error_code
memberErrorBytes := make([]byte, 2)
binary.BigEndian.PutUint16(memberErrorBytes, uint16(m.ErrorCode))
result = append(result, memberErrorBytes...)
// per-member _tagged_fields (empty)
result = append(result, 0)
}
// response-level _tagged_fields (empty)
result = append(result, 0)
return result
}
func (h *Handler) buildLeaveGroupV0Response(response LeaveGroupResponse) []byte {
result := make([]byte, 0, 6)
// NOTE: Correlation ID is handled by writeResponseWithCorrelationID
// Do NOT include it in the response body
// Error code (2 bytes) - that's it for v0!
errorCodeBytes := make([]byte, 2)
binary.BigEndian.PutUint16(errorCodeBytes, uint16(response.ErrorCode))
result = append(result, errorCodeBytes...)
return result
}
func (h *Handler) buildLeaveGroupFullResponse(response LeaveGroupResponse) []byte {
estimatedSize := 16
for _, member := range response.Members {
estimatedSize += len(member.MemberID) + len(member.GroupInstanceID) + 8
}
result := make([]byte, 0, estimatedSize)
// NOTE: Correlation ID is handled by writeResponseWithCorrelationID
// Do NOT include it in the response body
// For LeaveGroup v1+, throttle_time_ms comes first (4 bytes)
result = append(result, 0, 0, 0, 0)
// Error code (2 bytes)
errorCodeBytes := make([]byte, 2)
binary.BigEndian.PutUint16(errorCodeBytes, uint16(response.ErrorCode))
result = append(result, errorCodeBytes...)
// Members array length (4 bytes)
membersLengthBytes := make([]byte, 4)
binary.BigEndian.PutUint32(membersLengthBytes, uint32(len(response.Members)))
result = append(result, membersLengthBytes...)
// Members
for _, member := range response.Members {
// Member ID length (2 bytes)
memberIDLength := make([]byte, 2)
binary.BigEndian.PutUint16(memberIDLength, uint16(len(member.MemberID)))
result = append(result, memberIDLength...)
// Member ID
result = append(result, []byte(member.MemberID)...)
// Group instance ID length (2 bytes)
instanceIDLength := make([]byte, 2)
binary.BigEndian.PutUint16(instanceIDLength, uint16(len(member.GroupInstanceID)))
result = append(result, instanceIDLength...)
// Group instance ID
if len(member.GroupInstanceID) > 0 {
result = append(result, []byte(member.GroupInstanceID)...)
}
// Error code (2 bytes)
memberErrorBytes := make([]byte, 2)
binary.BigEndian.PutUint16(memberErrorBytes, uint16(member.ErrorCode))
result = append(result, memberErrorBytes...)
}
return result
}
func (h *Handler) buildHeartbeatErrorResponseV(correlationID uint32, errorCode int16, apiVersion uint16) []byte {
response := HeartbeatResponse{
CorrelationID: correlationID,
ErrorCode: errorCode,
}
return h.buildHeartbeatResponseV(response, apiVersion)
}
func (h *Handler) buildLeaveGroupErrorResponse(correlationID uint32, errorCode int16, apiVersion uint16) []byte {
response := LeaveGroupResponse{
CorrelationID: correlationID,
ErrorCode: errorCode,
Members: []LeaveGroupMemberResponse{},
}
return h.buildLeaveGroupResponse(response, apiVersion)
}
func (h *Handler) updateGroupSubscriptionFromMembers(group *consumer.ConsumerGroup) {
// Update group's subscribed topics from remaining members
group.SubscribedTopics = make(map[string]bool)
for _, member := range group.Members {
for _, topic := range member.Subscription {
group.SubscribedTopics[topic] = true
}
}
}