feat: bump badger to v4

go.mod

@@ -4,7 +4,7 @@ go 1.23.0
 
 require (
 	github.com/cespare/xxhash/v2 v2.3.0
-	github.com/dgraph-io/badger/v2 v2.2007.4
+	github.com/dgraph-io/badger/v4 v4.3.1
 	github.com/dustin/go-humanize v1.0.1
 	github.com/elastic/apm-aggregation v1.1.0
 	github.com/elastic/apm-data v1.13.1
@@ -60,13 +60,11 @@ require (
 require (
 	github.com/DataDog/zstd v1.4.5 // indirect
 	github.com/Microsoft/go-winio v0.6.2 // indirect
-	github.com/OneOfOne/xxhash v1.2.8 // indirect
 	github.com/Shopify/sarama v1.38.1 // indirect
 	github.com/apache/thrift v0.20.0 // indirect
 	github.com/armon/go-radix v1.0.0 // indirect
 	github.com/axiomhq/hyperloglog v0.2.0 // indirect
 	github.com/beorn7/perks v1.0.1 // indirect
-	github.com/cespare/xxhash v1.1.0 // indirect
 	github.com/cockroachdb/errors v1.11.3 // indirect
 	github.com/cockroachdb/fifo v0.0.0-20240606204812-0bbfbd93a7ce // indirect
 	github.com/cockroachdb/logtags v0.0.0-20230118201751-21c54148d20b // indirect
@@ -75,8 +73,7 @@ require (
 	github.com/cockroachdb/tokenbucket v0.0.0-20230807174530-cc333fc44b06 // indirect
 	github.com/containerd/errdefs v0.1.0 // indirect
 	github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc // indirect
-	github.com/dgraph-io/ristretto v0.1.1 // indirect
-	github.com/dgryski/go-farm v0.0.0-20200201041132-a6ae2369ad13 // indirect
+	github.com/dgraph-io/ristretto v1.0.0 // indirect
 	github.com/dgryski/go-metro v0.0.0-20180109044635-280f6062b5bc // indirect
 	github.com/dlclark/regexp2 v1.8.1 // indirect
 	github.com/docker/distribution v2.8.3+incompatible // indirect
@@ -100,10 +97,11 @@ require (
 	github.com/go-ole/go-ole v1.2.6 // indirect
 	github.com/gofrs/uuid/v5 v5.2.0 // indirect
 	github.com/gogo/googleapis v1.4.1 // indirect
-	github.com/golang/glog v1.2.2 // indirect
+	github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da // indirect
 	github.com/golang/protobuf v1.5.4 // indirect
 	github.com/golang/snappy v0.0.4 // indirect
 	github.com/gomodule/redigo v1.8.9 // indirect
+	github.com/google/flatbuffers v24.3.25+incompatible // indirect
 	github.com/google/uuid v1.6.0 // indirect
 	github.com/h2non/filetype v1.1.3 // indirect
 	github.com/hashicorp/go-uuid v1.0.3 // indirect
@@ -116,7 +114,7 @@ require (
 	github.com/jcmturner/rpc/v2 v2.0.3 // indirect
 	github.com/joeshaw/multierror v0.0.0-20140124173710-69b34d4ec901 // indirect
 	github.com/json-iterator/go v1.1.12 // indirect
-	github.com/klauspost/compress v1.17.9 // indirect
+	github.com/klauspost/compress v1.17.10 // indirect
 	github.com/kr/pretty v0.3.1 // indirect
 	github.com/kr/text v0.2.0 // indirect
 	github.com/lufia/plan9stats v0.0.0-20220913051719-115f729f3c8c // indirect
@@ -149,6 +147,7 @@ require (
 	github.com/yusufpapurcu/wmi v1.2.4 // indirect
 	go.elastic.co/apm/module/apmzap/v2 v2.6.0 // indirect
 	go.elastic.co/ecszap v1.0.2 // indirect
+	go.opencensus.io v0.24.0 // indirect
 	go.opentelemetry.io/collector/semconv v0.109.0 // indirect
 	go.opentelemetry.io/otel/sdk v1.30.0 // indirect
 	go.opentelemetry.io/otel/trace v1.30.0 // indirect

x-pack/apm-server/main.go

@@ -10,8 +10,9 @@ import (
 	"fmt"
 	"os"
 	"sync"
+	"time"
 
-	"github.com/dgraph-io/badger/v2"
+	"github.com/dgraph-io/badger/v4"
 	"github.com/gofrs/uuid"
 	"golang.org/x/sync/errgroup"
 
@@ -33,7 +34,8 @@ import (
 )
 
 const (
-	tailSamplingStorageDir = "tail_sampling"
+	oldTailSamplingStorageDir = "tail_sampling"
+	tailSamplingStorageDir    = "tail_sampling_v4"
 )
 
 var (
@@ -117,6 +119,24 @@ func newTailSamplingProcessor(args beater.ServerParams) (*sampling.Processor, er
 		return nil, fmt.Errorf("failed to create Elasticsearch client for tail-sampling: %w", err)
 	}
 
+	oldStorageDir := paths.Resolve(paths.Data, oldTailSamplingStorageDir)
+	if entries, err := os.ReadDir(oldStorageDir); err == nil {
+		var newest time.Time
+		for _, de := range entries {
+			if i, err := de.Info(); err == nil {
+				if t := i.ModTime(); t.After(newest) {
+					newest = t
+				}
+			}
+		}
+
+		if newest.IsZero() || time.Since(newest) > tailSamplingConfig.TTL {
+			if err := os.RemoveAll(oldStorageDir); err != nil {
+				args.Logger.Warnf("failed to remove old tail sampling storage dir: %v", err)
+			}
+		}
+	}
+
 	storageDir := paths.Resolve(paths.Data, tailSamplingStorageDir)
 	badgerDB, err = getBadgerDB(storageDir)
 	if err != nil {

x-pack/apm-server/main_test.go

@@ -8,6 +8,7 @@ package main
 
 import (
 	"context"
+	"os"
 	"testing"
 
 	"github.com/pkg/errors"
@@ -67,3 +68,24 @@ func TestMonitoring(t *testing.T) {
 		assert.NotEqual(t, monitoring.MakeFlatSnapshot(), tailSamplingMonitoringSnapshot)
 	}
 }
+
+func TestSamplingOldDir(t *testing.T) {
+	home := t.TempDir()
+	err := paths.InitPaths(&paths.Path{Home: home})
+	require.NoError(t, err)
+
+	oldDir := paths.Resolve(paths.Data, oldTailSamplingStorageDir)
+	os.Mkdir(oldDir, 0600)
+
+	cfg := config.DefaultConfig()
+	cfg.Sampling.Tail.Policies = []config.TailSamplingPolicy{{SampleRate: 0.1}}
+	_, err = newTailSamplingProcessor(beater.ServerParams{
+		Config:                 cfg,
+		NewElasticsearchClient: elasticsearch.NewClient,
+		BatchProcessor:         modelpb.ProcessBatchFunc(func(context.Context, *modelpb.Batch) error { return nil }),
+		Namespace:              "default",
+	})
+	require.NoError(t, err)
+
+	require.NoDirExists(t, oldDir)
+}

x-pack/apm-server/sampling/config.go

@@ -7,7 +7,7 @@ package sampling
 import (
 	"time"
 
-	"github.com/dgraph-io/badger/v2"
+	"github.com/dgraph-io/badger/v4"
 	"github.com/pkg/errors"
 
 	"github.com/elastic/apm-data/model/modelpb"

x-pack/apm-server/sampling/config_test.go

@@ -7,7 +7,7 @@ package sampling_test
 import (
 	"testing"
 
-	"github.com/dgraph-io/badger/v2"
+	"github.com/dgraph-io/badger/v4"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 

x-pack/apm-server/sampling/eventstorage/badger.go

@@ -5,7 +5,7 @@
 package eventstorage
 
 import (
-	"github.com/dgraph-io/badger/v2"
+	"github.com/dgraph-io/badger/v4"
 
 	"github.com/elastic/apm-server/internal/logs"
 	"github.com/elastic/elastic-agent-libs/logp"
@@ -34,11 +34,10 @@ func OpenBadger(storageDir string, valueLogFileSize int64) (*badger.DB, error) {
 	const tableLimit = 4
 	badgerOpts := badger.DefaultOptions(storageDir).
 		WithLogger(&LogpAdaptor{Logger: logger}).
-		WithTruncate(true).                          // Truncate unreadable files which cannot be read.
 		WithNumMemtables(tableLimit).                // in-memory tables.
 		WithNumLevelZeroTables(tableLimit).          // L0 tables.
 		WithNumLevelZeroTablesStall(tableLimit * 3). // Maintain the default 1-to-3 ratio before stalling.
-		WithMaxTableSize(int64(16 << 20)).           // Max LSM table or file size.
+		WithBaseTableSize(int64(16 << 20)).          // Max LSM table or file size.
 		WithValueLogFileSize(valueLogFileSize)       // vlog file size.
 
 	return badger.Open(badgerOpts)

x-pack/apm-server/sampling/eventstorage/storage.go

@@ -11,7 +11,7 @@ import (
 	"sync/atomic"
 	"time"
 
-	"github.com/dgraph-io/badger/v2"
+	"github.com/dgraph-io/badger/v4"
 
 	"github.com/elastic/apm-data/model/modelpb"
 )

x-pack/apm-server/sampling/eventstorage/storage_test.go

@@ -8,7 +8,7 @@ import (
 	"testing"
 	"time"
 
-	"github.com/dgraph-io/badger/v2"
+	"github.com/dgraph-io/badger/v4"
 	"github.com/gofrs/uuid"
 	"github.com/google/go-cmp/cmp"
 	"github.com/google/go-cmp/cmp/cmpopts"

x-pack/apm-server/sampling/eventstorage/storage_whitebox_test.go

@@ -8,7 +8,7 @@ import (
 	"testing"
 	"time"
 
-	"github.com/dgraph-io/badger/v2"
+	"github.com/dgraph-io/badger/v4"
 	"github.com/gofrs/uuid"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"

x-pack/apm-server/sampling/processor.go

@@ -14,7 +14,7 @@ import (
 	"sync/atomic"
 	"time"
 
-	"github.com/dgraph-io/badger/v2"
+	"github.com/dgraph-io/badger/v4"
 	"github.com/pkg/errors"
 	"golang.org/x/sync/errgroup"
 

x-pack/apm-server/sampling/processor_test.go

@@ -597,12 +597,6 @@ func TestStorageGC(t *testing.T) {
 	config.TTL = 10 * time.Millisecond
 	config.FlushInterval = 10 * time.Millisecond
 
-	// Create a new badger DB with smaller value log files so we can test GC.
-	config.DB.Close()
-	badgerDB, err := eventstorage.OpenBadger(config.StorageDir, 1024*1024)
-	require.NoError(t, err)
-	t.Cleanup(func() { badgerDB.Close() })
-	config.DB = badgerDB
 	config.Storage = eventstorage.
 		New(config.DB, eventstorage.ProtobufCodec{}).
 		NewShardedReadWriter()
@@ -622,6 +616,8 @@ func TestStorageGC(t *testing.T) {
 				Span: &modelpb.Span{
 					Type: "type",
 					Id:   traceID,
+					// inflate the size of the span so the entry is written to the vlog
+					Name: strings.Repeat("foo", 1024*1024),
 				},
 			}}
 			err := processor.ProcessBatch(context.Background(), &batch)