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
279 lines
8.5 KiB
Go
279 lines
8.5 KiB
Go
package protocol
|
|
|
|
import (
|
|
"encoding/binary"
|
|
"fmt"
|
|
"net"
|
|
"sync"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/mq/kafka/consumer"
|
|
)
|
|
|
|
// ConsumerProtocolMetadata represents parsed consumer protocol metadata
|
|
type ConsumerProtocolMetadata struct {
|
|
Version int16 // Protocol metadata version
|
|
Topics []string // Subscribed topic names
|
|
UserData []byte // Optional user data
|
|
AssignmentStrategy string // Preferred assignment strategy
|
|
}
|
|
|
|
// ConnectionContext holds connection-specific information for requests
|
|
type ConnectionContext struct {
|
|
RemoteAddr net.Addr // Client's remote address
|
|
LocalAddr net.Addr // Server's local address
|
|
ConnectionID string // Connection identifier
|
|
ClientID string // Kafka client ID from request headers
|
|
ConsumerGroup string // Consumer group (set by JoinGroup)
|
|
MemberID string // Consumer group member ID (set by JoinGroup)
|
|
// Per-connection broker client for isolated gRPC streams
|
|
// Each Kafka connection MUST have its own gRPC streams to avoid interference
|
|
// when multiple consumers or requests are active on different connections
|
|
BrokerClient interface{} // Will be set to *integration.BrokerClient
|
|
|
|
// Persistent partition readers - one goroutine per topic-partition that maintains position
|
|
// and streams forward, eliminating repeated offset lookups and reducing broker CPU load
|
|
partitionReaders sync.Map // map[TopicPartitionKey]*partitionReader
|
|
}
|
|
|
|
// ExtractClientHost extracts the client hostname/IP from connection context
|
|
func ExtractClientHost(connCtx *ConnectionContext) string {
|
|
if connCtx == nil || connCtx.RemoteAddr == nil {
|
|
return "unknown"
|
|
}
|
|
|
|
// Extract host portion from address
|
|
if tcpAddr, ok := connCtx.RemoteAddr.(*net.TCPAddr); ok {
|
|
return tcpAddr.IP.String()
|
|
}
|
|
|
|
// Fallback: parse string representation
|
|
addrStr := connCtx.RemoteAddr.String()
|
|
if host, _, err := net.SplitHostPort(addrStr); err == nil {
|
|
return host
|
|
}
|
|
|
|
// Last resort: return full address
|
|
return addrStr
|
|
}
|
|
|
|
// ParseConsumerProtocolMetadata parses consumer protocol metadata with enhanced error handling
|
|
func ParseConsumerProtocolMetadata(metadata []byte, strategyName string) (*ConsumerProtocolMetadata, error) {
|
|
if len(metadata) < 2 {
|
|
return &ConsumerProtocolMetadata{
|
|
Version: 0,
|
|
Topics: []string{},
|
|
UserData: []byte{},
|
|
AssignmentStrategy: strategyName,
|
|
}, nil
|
|
}
|
|
|
|
result := &ConsumerProtocolMetadata{
|
|
AssignmentStrategy: strategyName,
|
|
}
|
|
|
|
offset := 0
|
|
|
|
// Parse version (2 bytes)
|
|
if len(metadata) < offset+2 {
|
|
return nil, fmt.Errorf("metadata too short for version field")
|
|
}
|
|
result.Version = int16(binary.BigEndian.Uint16(metadata[offset : offset+2]))
|
|
offset += 2
|
|
|
|
// Parse topics array
|
|
if len(metadata) < offset+4 {
|
|
return nil, fmt.Errorf("metadata too short for topics count")
|
|
}
|
|
topicsCount := binary.BigEndian.Uint32(metadata[offset : offset+4])
|
|
offset += 4
|
|
|
|
// Validate topics count (reasonable limit)
|
|
if topicsCount > 10000 {
|
|
return nil, fmt.Errorf("unreasonable topics count: %d", topicsCount)
|
|
}
|
|
|
|
result.Topics = make([]string, 0, topicsCount)
|
|
|
|
for i := uint32(0); i < topicsCount && offset < len(metadata); i++ {
|
|
// Parse topic name length
|
|
if len(metadata) < offset+2 {
|
|
return nil, fmt.Errorf("metadata too short for topic %d name length", i)
|
|
}
|
|
topicNameLength := binary.BigEndian.Uint16(metadata[offset : offset+2])
|
|
offset += 2
|
|
|
|
// Validate topic name length
|
|
if topicNameLength > 1000 {
|
|
return nil, fmt.Errorf("unreasonable topic name length: %d", topicNameLength)
|
|
}
|
|
|
|
if len(metadata) < offset+int(topicNameLength) {
|
|
return nil, fmt.Errorf("metadata too short for topic %d name data", i)
|
|
}
|
|
|
|
topicName := string(metadata[offset : offset+int(topicNameLength)])
|
|
offset += int(topicNameLength)
|
|
|
|
// Validate topic name (basic validation)
|
|
if len(topicName) == 0 {
|
|
continue // Skip empty topic names
|
|
}
|
|
|
|
result.Topics = append(result.Topics, topicName)
|
|
}
|
|
|
|
// Parse user data if remaining bytes exist
|
|
if len(metadata) >= offset+4 {
|
|
userDataLength := binary.BigEndian.Uint32(metadata[offset : offset+4])
|
|
offset += 4
|
|
|
|
// Handle -1 (0xFFFFFFFF) as null/empty user data (Kafka protocol convention)
|
|
if userDataLength == 0xFFFFFFFF {
|
|
result.UserData = []byte{}
|
|
return result, nil
|
|
}
|
|
|
|
// Validate user data length
|
|
if userDataLength > 100000 { // 100KB limit
|
|
return nil, fmt.Errorf("unreasonable user data length: %d", userDataLength)
|
|
}
|
|
|
|
if len(metadata) >= offset+int(userDataLength) {
|
|
result.UserData = make([]byte, userDataLength)
|
|
copy(result.UserData, metadata[offset:offset+int(userDataLength)])
|
|
}
|
|
}
|
|
|
|
return result, nil
|
|
}
|
|
|
|
// ValidateAssignmentStrategy checks if an assignment strategy is supported
|
|
func ValidateAssignmentStrategy(strategy string) bool {
|
|
supportedStrategies := map[string]bool{
|
|
consumer.ProtocolNameRange: true,
|
|
consumer.ProtocolNameRoundRobin: true,
|
|
consumer.ProtocolNameSticky: true,
|
|
consumer.ProtocolNameCooperativeSticky: true, // Incremental cooperative rebalancing (Kafka 2.4+)
|
|
}
|
|
|
|
return supportedStrategies[strategy]
|
|
}
|
|
|
|
// ExtractTopicsFromMetadata extracts topic list from protocol metadata with fallback
|
|
func ExtractTopicsFromMetadata(protocols []GroupProtocol, fallbackTopics []string) []string {
|
|
for _, protocol := range protocols {
|
|
if ValidateAssignmentStrategy(protocol.Name) {
|
|
parsed, err := ParseConsumerProtocolMetadata(protocol.Metadata, protocol.Name)
|
|
if err != nil {
|
|
continue
|
|
}
|
|
|
|
if len(parsed.Topics) > 0 {
|
|
return parsed.Topics
|
|
}
|
|
}
|
|
}
|
|
|
|
// Fallback to provided topics or empty list
|
|
if len(fallbackTopics) > 0 {
|
|
return fallbackTopics
|
|
}
|
|
|
|
// Return empty slice if no topics found - consumer may be using pattern subscription
|
|
return []string{}
|
|
}
|
|
|
|
// SelectBestProtocol chooses the best assignment protocol from available options
|
|
func SelectBestProtocol(protocols []GroupProtocol, groupProtocols []string) string {
|
|
// Priority order: sticky > roundrobin > range
|
|
protocolPriority := []string{consumer.ProtocolNameSticky, consumer.ProtocolNameRoundRobin, consumer.ProtocolNameRange}
|
|
|
|
// Find supported protocols in client's list
|
|
clientProtocols := make(map[string]bool)
|
|
for _, protocol := range protocols {
|
|
if ValidateAssignmentStrategy(protocol.Name) {
|
|
clientProtocols[protocol.Name] = true
|
|
}
|
|
}
|
|
|
|
// Find supported protocols in group's list
|
|
groupProtocolSet := make(map[string]bool)
|
|
for _, protocol := range groupProtocols {
|
|
groupProtocolSet[protocol] = true
|
|
}
|
|
|
|
// Select highest priority protocol that both client and group support
|
|
for _, preferred := range protocolPriority {
|
|
if clientProtocols[preferred] && (len(groupProtocols) == 0 || groupProtocolSet[preferred]) {
|
|
return preferred
|
|
}
|
|
}
|
|
|
|
// If group has existing protocols, find a protocol supported by both client and group
|
|
if len(groupProtocols) > 0 {
|
|
// Try to find a protocol that both client and group support
|
|
for _, preferred := range protocolPriority {
|
|
if clientProtocols[preferred] && groupProtocolSet[preferred] {
|
|
return preferred
|
|
}
|
|
}
|
|
|
|
// No common protocol found - handle special fallback case
|
|
// If client supports nothing we validate, but group supports "range", use "range"
|
|
if len(clientProtocols) == 0 && groupProtocolSet[consumer.ProtocolNameRange] {
|
|
return consumer.ProtocolNameRange
|
|
}
|
|
|
|
// Return empty string to indicate no compatible protocol found
|
|
return ""
|
|
}
|
|
|
|
// Fallback to first supported protocol from client (only when group has no existing protocols)
|
|
for _, protocol := range protocols {
|
|
if ValidateAssignmentStrategy(protocol.Name) {
|
|
return protocol.Name
|
|
}
|
|
}
|
|
|
|
// Last resort
|
|
return consumer.ProtocolNameRange
|
|
}
|
|
|
|
// ProtocolMetadataDebugInfo returns debug information about protocol metadata
|
|
type ProtocolMetadataDebugInfo struct {
|
|
Strategy string
|
|
Version int16
|
|
TopicCount int
|
|
Topics []string
|
|
UserDataSize int
|
|
ParsedOK bool
|
|
ParseError string
|
|
}
|
|
|
|
// AnalyzeProtocolMetadata provides detailed debug information about protocol metadata
|
|
func AnalyzeProtocolMetadata(protocols []GroupProtocol) []ProtocolMetadataDebugInfo {
|
|
result := make([]ProtocolMetadataDebugInfo, 0, len(protocols))
|
|
|
|
for _, protocol := range protocols {
|
|
info := ProtocolMetadataDebugInfo{
|
|
Strategy: protocol.Name,
|
|
}
|
|
|
|
parsed, err := ParseConsumerProtocolMetadata(protocol.Metadata, protocol.Name)
|
|
if err != nil {
|
|
info.ParsedOK = false
|
|
info.ParseError = err.Error()
|
|
} else {
|
|
info.ParsedOK = true
|
|
info.Version = parsed.Version
|
|
info.TopicCount = len(parsed.Topics)
|
|
info.Topics = parsed.Topics
|
|
info.UserDataSize = len(parsed.UserData)
|
|
}
|
|
|
|
result = append(result, info)
|
|
}
|
|
|
|
return result
|
|
}
|