mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-09-20 13:30:46 +02:00
* fix(wdclient,volume): compare master leader with ServerAddress.Equals Raft leader is advertised as host:httpPort.grpcPort, but clients dial host:httpPort. Raw string comparison against VolumeLocation.Leader / HeartbeatResponse.Leader therefore never matches, causing the masterclient and the volume server heartbeat loop to continuously "redirect" to the already-connected master, tearing down the stream and reconnecting. Use ServerAddress.Equals, which normalizes the grpc-port suffix. * fix(filer,mq): compare ServerAddress via Equals in two more sites filer bootstrap skip (MaybeBootstrapFromOnePeer) and the broker's local partition assignment check both compared a wire-supplied address string against the local self ServerAddress with raw string equality. Both are vulnerable to the same plain-vs-host:port.grpcPort mismatch as the masterclient/volume heartbeat sites: filer would bootstrap from itself, and the broker would fail to claim a partition it was actually assigned. Route both through ServerAddress.Equals. * fix(master,shell): more ServerAddress comparisons via Equals - raft_server_handlers.go HealthzHandler: s.serverAddr == leader would skip the child-lock check on the real leader when the two carry different plain/grpc-suffix forms, returning 200 OK instead of 423. - master_server.go SetRaftServer leader-change callback: the Leader() == Name() guard for ensureTopologyId could disagree with topology.IsLeader() (which already uses Equals), so leader-only initialization could be skipped after an election. - command_volume_merge.go isReplicaServer: the -target guard compared user-supplied host:port against NewServerAddressFromDataNode(...) with ==, letting an existing replica slip through when topology carries the embedded gRPC port. All routed through pb.ServerAddress.Equals. * fix(mq,cluster): more ServerAddress comparisons via Equals - broker_grpc_lookup.go GetTopicPublishers/GetTopicSubscribers: the partition ownership check gated listing on raw LeaderBroker == BrokerAddress().String(), so listings silently omitted partitions hosted locally when the assignment carried the other host:port / host:port.grpcPort form. - lock_client.go: LockHostMovedTo comparison and the seedFiler fallback guard both used raw string equality against configured filer addresses (which may be plain host:port while LockHostMovedTo comes back suffixed), causing spurious host-change churn and blocking the seed-filer fallback. * fix(mq): more ServerAddress comparisons via Equals - pub_balancer/allocate.go EnsureAssignmentsToActiveBrokers: direct activeBrokers.Get() lookup missed brokers when a persisted assignment carried a different address encoding than the registered broker key, triggering a bogus reassignment on every read/write cycle. Added a findActiveBroker helper that falls back to an Equals-based scan and canonicalizes the assignment in place so later writes are stable. - broker_grpc_lookup.go isLockOwner: used raw string equality between LockOwner() and BrokerAddress().String(), so a lock owner could fail to recognize itself and proxy local lookup/config/admin RPCs away. - pub_client/scheduler.go onEachAssignments: reused publisher jobs only on exact LeaderBroker match, so an encoding flip in lookup results tore down and recreated a stream to the same broker.
155 lines
4.9 KiB
Go
155 lines
4.9 KiB
Go
package pub_balancer
|
|
|
|
import (
|
|
"math/rand/v2"
|
|
"time"
|
|
|
|
cmap "github.com/orcaman/concurrent-map/v2"
|
|
"github.com/seaweedfs/seaweedfs/weed/glog"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/mq_pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/schema_pb"
|
|
)
|
|
|
|
// findActiveBroker looks up a broker in activeBrokers, tolerating address
|
|
// encoding differences (plain host:port vs host:port.grpcPort) by falling
|
|
// back to an Equals-based scan when the direct key lookup misses.
|
|
func findActiveBroker(activeBrokers cmap.ConcurrentMap[string, *BrokerStats], addr string) (string, bool) {
|
|
if addr == "" {
|
|
return "", false
|
|
}
|
|
if _, found := activeBrokers.Get(addr); found {
|
|
return addr, true
|
|
}
|
|
target := pb.ServerAddress(addr)
|
|
for item := range activeBrokers.IterBuffered() {
|
|
if pb.ServerAddress(item.Key).Equals(target) {
|
|
return item.Key, true
|
|
}
|
|
}
|
|
return "", false
|
|
}
|
|
|
|
func AllocateTopicPartitions(brokers cmap.ConcurrentMap[string, *BrokerStats], partitionCount int32) (assignments []*mq_pb.BrokerPartitionAssignment) {
|
|
// divide the ring into partitions
|
|
now := time.Now().UnixNano()
|
|
rangeSize := MaxPartitionCount / partitionCount
|
|
for i := int32(0); i < partitionCount; i++ {
|
|
assignment := &mq_pb.BrokerPartitionAssignment{
|
|
Partition: &schema_pb.Partition{
|
|
RingSize: MaxPartitionCount,
|
|
RangeStart: int32(i * rangeSize),
|
|
RangeStop: int32((i + 1) * rangeSize),
|
|
UnixTimeNs: now,
|
|
},
|
|
}
|
|
if i == partitionCount-1 {
|
|
assignment.Partition.RangeStop = MaxPartitionCount
|
|
}
|
|
assignments = append(assignments, assignment)
|
|
}
|
|
|
|
EnsureAssignmentsToActiveBrokers(brokers, 1, assignments)
|
|
|
|
glog.V(0).Infof("allocate topic partitions %d: %v", len(assignments), assignments)
|
|
return
|
|
}
|
|
|
|
// randomly pick n brokers, which may contain duplicates
|
|
// TODO pick brokers based on the broker stats
|
|
func pickBrokers(brokers cmap.ConcurrentMap[string, *BrokerStats], count int32) []string {
|
|
candidates := make([]string, 0, brokers.Count())
|
|
for brokerStatsItem := range brokers.IterBuffered() {
|
|
candidates = append(candidates, brokerStatsItem.Key)
|
|
}
|
|
pickedBrokers := make([]string, 0, count)
|
|
for i := int32(0); i < count; i++ {
|
|
p := rand.IntN(len(candidates))
|
|
pickedBrokers = append(pickedBrokers, candidates[p])
|
|
}
|
|
return pickedBrokers
|
|
}
|
|
|
|
// reservoir sampling select N brokers from the active brokers, with exclusion of the excluded broker
|
|
func pickBrokersExcluded(brokers []string, count int, excludedLeadBroker string, excludedBroker string) []string {
|
|
pickedBrokers := make([]string, 0, count)
|
|
for i, broker := range brokers {
|
|
if broker == excludedBroker {
|
|
continue
|
|
}
|
|
if len(pickedBrokers) < count {
|
|
pickedBrokers = append(pickedBrokers, broker)
|
|
} else {
|
|
j := rand.IntN(i + 1)
|
|
if j < count {
|
|
pickedBrokers[j] = broker
|
|
}
|
|
}
|
|
}
|
|
|
|
// shuffle the picked brokers
|
|
count = len(pickedBrokers)
|
|
for i := 0; i < count; i++ {
|
|
j := rand.IntN(count)
|
|
pickedBrokers[i], pickedBrokers[j] = pickedBrokers[j], pickedBrokers[i]
|
|
}
|
|
|
|
return pickedBrokers
|
|
}
|
|
|
|
// EnsureAssignmentsToActiveBrokers ensures the assignments are assigned to active brokers
|
|
func EnsureAssignmentsToActiveBrokers(activeBrokers cmap.ConcurrentMap[string, *BrokerStats], followerCount int, assignments []*mq_pb.BrokerPartitionAssignment) (hasChanges bool) {
|
|
glog.V(4).Infof("EnsureAssignmentsToActiveBrokers: activeBrokers: %v, followerCount: %d, assignments: %v", activeBrokers.Count(), followerCount, assignments)
|
|
|
|
candidates := make([]string, 0, activeBrokers.Count())
|
|
for brokerStatsItem := range activeBrokers.IterBuffered() {
|
|
candidates = append(candidates, brokerStatsItem.Key)
|
|
}
|
|
|
|
for _, assignment := range assignments {
|
|
// count how many brokers are needed
|
|
count := 0
|
|
if assignment.LeaderBroker == "" {
|
|
count++
|
|
} else if canonical, found := findActiveBroker(activeBrokers, assignment.LeaderBroker); !found {
|
|
assignment.LeaderBroker = ""
|
|
count++
|
|
} else if canonical != assignment.LeaderBroker {
|
|
assignment.LeaderBroker = canonical
|
|
hasChanges = true
|
|
}
|
|
if assignment.FollowerBroker == "" {
|
|
count++
|
|
} else if canonical, found := findActiveBroker(activeBrokers, assignment.FollowerBroker); !found {
|
|
assignment.FollowerBroker = ""
|
|
count++
|
|
} else if canonical != assignment.FollowerBroker {
|
|
assignment.FollowerBroker = canonical
|
|
hasChanges = true
|
|
}
|
|
|
|
if count > 0 {
|
|
pickedBrokers := pickBrokersExcluded(candidates, count, assignment.LeaderBroker, assignment.FollowerBroker)
|
|
i := 0
|
|
if assignment.LeaderBroker == "" {
|
|
if i < len(pickedBrokers) {
|
|
assignment.LeaderBroker = pickedBrokers[i]
|
|
i++
|
|
hasChanges = true
|
|
}
|
|
}
|
|
if assignment.FollowerBroker == "" {
|
|
if i < len(pickedBrokers) {
|
|
assignment.FollowerBroker = pickedBrokers[i]
|
|
i++
|
|
hasChanges = true
|
|
}
|
|
}
|
|
}
|
|
|
|
}
|
|
|
|
glog.V(4).Infof("EnsureAssignmentsToActiveBrokers: activeBrokers: %v, followerCount: %d, assignments: %v hasChanges: %v", activeBrokers.Count(), followerCount, assignments, hasChanges)
|
|
return
|
|
}
|