Files
wehub-resource-sync 498b235461
Build and test / Build and test AMD64 Ubuntu 22.04 (push) Failing after 0s
Publish Builder / amazonlinux2023 (push) Failing after 1s
Build and test / UT for Go (push) Has been skipped
Publish KRTE Images / KRTE (push) Failing after 1s
Build and test / Integration Test (push) Has been skipped
Build and test / Upload Code Coverage (push) Has been skipped
Publish Builder / rockylinux9 (push) Failing after 1s
Publish Builder / ubuntu22.04 (push) Failing after 0s
Publish Builder / ubuntu24.04 (push) Failing after 0s
Publish Gpu Builder / publish-gpu-builder (push) Failing after 1s
Publish Test Images / PyTest (push) Failing after 0s
Build and test / UT for Cpp (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 12:31:17 +08:00

175 lines
5.2 KiB
Go

package pulsar
import (
"context"
"time"
"github.com/apache/pulsar-client-go/pulsar"
"github.com/cenkalti/backoff/v4"
"github.com/cockroachdb/errors"
"golang.org/x/time/rate"
"github.com/milvus-io/milvus/pkg/v3/mlog"
"github.com/milvus-io/milvus/pkg/v3/proto/streamingpb"
"github.com/milvus-io/milvus/pkg/v3/streaming/util/message"
"github.com/milvus-io/milvus/pkg/v3/streaming/util/types"
"github.com/milvus-io/milvus/pkg/v3/streaming/walimpls"
"github.com/milvus-io/milvus/pkg/v3/streaming/walimpls/helper"
"github.com/milvus-io/milvus/pkg/v3/util/syncutil"
)
var _ walimpls.WALImpls = (*walImpl)(nil)
type walImpl struct {
*helper.WALHelper
c pulsar.Client
p *syncutil.Future[pulsar.Producer]
notifier *syncutil.AsyncTaskNotifier[struct{}]
backlogClearHelper *backlogClearHelper
tenant tenant
}
// initProducerAtBackground initializes the producer at background.
func (w *walImpl) initProducerAtBackground() {
if w.Channel().AccessMode != types.AccessModeRW {
w.notifier.Finish(struct{}{})
return
}
defer w.notifier.Finish(struct{}{})
backoff := backoff.NewExponentialBackOff()
backoff.InitialInterval = 10 * time.Millisecond
backoff.MaxInterval = 10 * time.Second
backoff.MaxElapsedTime = 0
backoff.Reset()
for {
if err := w.initProducer(); err == nil {
return
}
select {
case <-time.After(backoff.NextBackOff()):
continue
case <-w.notifier.Context().Done():
return
}
}
}
// initProducer initializes the producer.
func (w *walImpl) initProducer() error {
topic := w.tenant.MustGetFullTopicName(w.Channel().Name)
p, err := w.c.CreateProducer(pulsar.ProducerOptions{
Topic: topic,
// TODO: current go pulsar client does not support fencing, we should enable it after go pulsar client supports it.
// ProducerAccessMode: pulsar.ProducerAccessModeExclusiveWithFencing,
})
if err != nil {
w.Log().Warn(context.TODO(), "create producer failed", mlog.Err(err))
return err
}
w.Log().Info(context.TODO(), "pulsar create producer done")
w.p.Set(p)
return nil
}
func (w *walImpl) WALName() message.WALName {
return message.WALNamePulsar
}
func (w *walImpl) Append(ctx context.Context, msg message.MutableMessage) (message.MessageID, error) {
if w.Channel().AccessMode != types.AccessModeRW {
panic("write on a wal that is not in read-write mode")
}
p, err := w.p.GetWithContext(ctx)
if err != nil {
return nil, errors.Wrap(err, "get producer from future")
}
pb := msg.IntoMessageProto()
id, err := p.Send(ctx, &pulsar.ProducerMessage{
Payload: pb.Payload,
Properties: pb.Properties,
})
// Observe the append traffic even if the message is not sent successfully.
// Because if the write is failed, the message may be already written to the pulsar topic.
w.backlogClearHelper.ObserveAppend(msg.EstimateSize())
if err != nil {
w.Log().RatedWarn(ctx, rate.Limit(1), "send message to pulsar failed", mlog.Err(err))
return nil, err
}
return pulsarID{id}, nil
}
func (w *walImpl) Read(ctx context.Context, opt walimpls.ReadOption) (s walimpls.ScannerImpls, err error) {
topic := w.tenant.MustGetFullTopicName(w.Channel().Name)
ch := make(chan pulsar.ReaderMessage, 1)
readerOpt := pulsar.ReaderOptions{
Topic: topic,
Name: opt.Name,
MessageChannel: ch,
ReceiverQueueSize: opt.ReadAheadBufferSize,
}
switch t := opt.DeliverPolicy.GetPolicy().(type) {
case *streamingpb.DeliverPolicy_All:
readerOpt.StartMessageID = pulsar.EarliestMessageID()
case *streamingpb.DeliverPolicy_Latest:
readerOpt.StartMessageID = pulsar.LatestMessageID()
case *streamingpb.DeliverPolicy_StartFrom:
id, err := unmarshalMessageID(t.StartFrom.GetId())
if err != nil {
return nil, err
}
readerOpt.StartMessageID = id
readerOpt.StartMessageIDInclusive = true
case *streamingpb.DeliverPolicy_StartAfter:
id, err := unmarshalMessageID(t.StartAfter.GetId())
if err != nil {
return nil, err
}
readerOpt.StartMessageID = id
readerOpt.StartMessageIDInclusive = false
}
reader, err := w.c.CreateReader(readerOpt)
if err != nil {
return nil, err
}
return newScanner(opt.Name, reader), nil
}
func (w *walImpl) Truncate(ctx context.Context, id message.MessageID) error {
if w.Channel().AccessMode != types.AccessModeRW {
panic("truncate on a wal that is not in read-write mode")
}
if w.backlogClearHelper != nil {
// The backlogClearHelper is always non-nil currently, so we can determine the truncate position
return nil
}
topic := w.tenant.MustGetFullTopicName(w.Channel().Name)
cursor, err := w.c.Subscribe(pulsar.ConsumerOptions{
Topic: topic,
SubscriptionName: truncateCursorSubscriptionName,
Type: pulsar.Exclusive,
MaxPendingChunkedMessage: 1, // We cannot set it to 0, because the 0 means 100.
ReceiverQueueSize: 1, // We cannot set it to 0, because the 0 means 1000.
StartMessageIDInclusive: true,
})
if err != nil {
return err
}
defer cursor.Close()
return cursor.Seek(id.(pulsarID).PulsarID())
}
func (w *walImpl) Close() {
w.notifier.Cancel()
w.notifier.BlockUntilFinish()
// close producer if it is initialized
if w.p.Ready() {
w.p.Get().Close()
}
if w.backlogClearHelper != nil {
w.backlogClearHelper.Close()
}
}