Merge pull request #101 from metabarcoding/push-klzowrsmmnyv

Dynamic Batch Flushing and Build Improvements

.github/workflows/release.yml

@@ -16,7 +16,7 @@ jobs:
       - name: Setup Go
         uses: actions/setup-go@v5
         with:
-          go-version: "1.23"
+          go-version: "1.26"
       - name: Checkout obitools4 project
         uses: actions/checkout@v4
       - name: Run tests
@@ -54,7 +54,7 @@ jobs:
       - name: Setup Go
         uses: actions/setup-go@v5
         with:
-          go-version: "1.23"
+          go-version: "1.26"
 
       - name: Extract version from tag
         id: get_version
@@ -62,12 +62,6 @@ jobs:
           TAG=${GITHUB_REF#refs/tags/Release_}
           echo "version=$TAG" >> $GITHUB_OUTPUT
 
-      - name: Install build tools (Linux)
-        if: runner.os == 'Linux'
-        run: |
-          sudo apt-get update -q
-          sudo apt-get install -y musl-tools zlib1g-dev
-
       - name: Install build tools (macOS)
         if: runner.os == 'macOS'
         run: |
@@ -75,20 +69,30 @@ jobs:
           xcode-select --install 2>/dev/null || true
           xcode-select -p
 
-      - name: Build binaries
+      - name: Build binaries (Linux)
+        if: runner.os == 'Linux'
+        env:
+          VERSION: ${{ steps.get_version.outputs.version }}
+        run: |
+          docker run --rm \
+            -v "$(pwd):/src" \
+            -w /src \
+            -e VERSION="${VERSION}" \
+            golang:1.26-alpine \
+            sh -c "apk add --no-cache gcc musl-dev zlib-dev zlib-static make && \
+                   make LDFLAGS='-linkmode=external -extldflags=-static' obitools"
+          mkdir -p artifacts
+          tar -czf artifacts/obitools4_${VERSION}_${{ matrix.output_name }}.tar.gz -C build .
+
+      - name: Build binaries (macOS)
+        if: runner.os == 'macOS'
         env:
           GOOS: ${{ matrix.goos }}
           GOARCH: ${{ matrix.goarch }}
           VERSION: ${{ steps.get_version.outputs.version }}
-          CC: ${{ matrix.goos == 'linux' && 'musl-gcc' || '' }}
         run: |
-          if [ "$GOOS" = "linux" ]; then
-            make LDFLAGS='-linkmode=external -extldflags=-static' obitools
-          else
-            make obitools
-          fi
+          make obitools
           mkdir -p artifacts
-          # Create a single tar.gz with all binaries for this platform
           tar -czf artifacts/obitools4_${VERSION}_${{ matrix.output_name }}.tar.gz -C build .
 
       - name: Upload artifacts

go.work.sum

@@ -52,6 +52,7 @@ golang.org/x/image v0.6.0/go.mod h1:MXLdDR43H7cDJq5GEGXEVeeNhPgi+YYEQ2pC1byI1x0=
 golang.org/x/mod v0.13.0 h1:I/DsJXRlw/8l/0c24sM9yb0T4z9liZTduXvdAWYiysY=
 golang.org/x/mod v0.13.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
 golang.org/x/mod v0.14.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
+golang.org/x/net v0.38.0/go.mod h1:ivrbrMbzFq5J41QOQh0siUuly180yBYtLp+CKbEaFx8=
 golang.org/x/net v0.52.0/go.mod h1:R1MAz7uMZxVMualyPXb+VaqGSa3LIaUqk0eEt3w36Sw=
 golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4 h1:uVc8UZUe6tr40fFVnUP5Oj+veunVezqYl9z7DYw9xzw=
 golang.org/x/text v0.13.0 h1:ablQoSUd0tRdKxZewP80B+BaqeKJuVhuRxj/dkrun3k=

pkg/obiiter/distribute.go

@@ -57,34 +57,21 @@ func (dist *IDistribute) Classifier() *obiseq.BioSequenceClassifier {
 }
 
 // Distribute organizes the biosequences from the iterator into batches
-// based on the provided classifier and batch sizes. It returns an
-// IDistribute instance that manages the distribution of the sequences.
+// based on the provided classifier. It returns an IDistribute instance
+// that manages the distribution of the sequences.
 //
-// Parameters:
-//   - class: A pointer to a BioSequenceClassifier used to classify
-//     the biosequences during distribution.
-//   - sizes: Optional integer values specifying the batch size. If
-//     no sizes are provided, a default batch size of 5000 is used.
-//
-// Returns:
-// An IDistribute instance that contains the outputs of the
-// classified biosequences, a channel for new data notifications,
-// and the classifier used for distribution. The method operates
-// asynchronously, processing the sequences in separate goroutines.
-// It ensures that the outputs are closed and cleaned up once
-// processing is complete.
-func (iterator IBioSequence) Distribute(class *obiseq.BioSequenceClassifier, sizes ...int) IDistribute {
-	batchsize := obidefault.BatchSize()
+// Batches are flushed when either BatchSizeMax() sequences or BatchMem()
+// bytes are accumulated per key, mirroring the RebatchBySize strategy.
+func (iterator IBioSequence) Distribute(class *obiseq.BioSequenceClassifier) IDistribute {
+	maxCount := obidefault.BatchSizeMax()
+	maxBytes := obidefault.BatchMem()
 
 	outputs := make(map[int]IBioSequence, 100)
 	slices := make(map[int]*obiseq.BioSequenceSlice, 100)
+	bufBytes := make(map[int]int, 100)
 	orders := make(map[int]int, 100)
 	news := make(chan int)
 
-	if len(sizes) > 0 {
-		batchsize = sizes[0]
-	}
-
 	jobDone := sync.WaitGroup{}
 	lock := sync.Mutex{}
 
@@ -115,6 +102,7 @@ func (iterator IBioSequence) Distribute(class *obiseq.BioSequenceClassifier, siz
 					slice = &s
 					slices[key] = slice
 					orders[key] = 0
+					bufBytes[key] = 0
 
 					lock.Lock()
 					outputs[key] = MakeIBioSequence()
@@ -123,14 +111,20 @@ func (iterator IBioSequence) Distribute(class *obiseq.BioSequenceClassifier, siz
 					news <- key
 				}
 
-				*slice = append(*slice, s)
-
-				if len(*slice) == batchsize {
+				sz := s.MemorySize()
+				countFull := maxCount > 0 && len(*slice) >= maxCount
+				memFull := maxBytes > 0 && bufBytes[key]+sz > maxBytes && len(*slice) > 0
+				if countFull || memFull {
 					outputs[key].Push(MakeBioSequenceBatch(source, orders[key], *slice))
 					orders[key]++
 					s := obiseq.MakeBioSequenceSlice()
 					slices[key] = &s
+					slice = &s
+					bufBytes[key] = 0
 				}
+
+				*slice = append(*slice, s)
+				bufBytes[key] += sz
 			}
 		}
 

pkg/obilua/obiseqslice.go

@@ -31,7 +31,8 @@ func obiseqslice2Lua(interpreter *lua.LState,
 }
 
 func newObiSeqSlice(luaState *lua.LState) int {
-	seqslice := obiseq.NewBioSequenceSlice()
+	capacity := luaState.OptInt(1, 0)
+	seqslice := obiseq.NewBioSequenceSlice(capacity)
 	luaState.Push(obiseqslice2Lua(luaState, seqslice))
 	return 1
 }

pkg/obioptions/version.go

@@ -3,7 +3,7 @@ package obioptions
 // Version is automatically updated by the Makefile from version.txt
 // The patch number (third digit) is incremented on each push to the repository
 
-var _Version = "Release 4.4.24"
+var _Version = "Release 4.4.29"
 
 // Version returns the version of the obitools package.
 //

pkg/obiseq/worker.go

@@ -104,11 +104,11 @@ func SeqToSliceWorker(worker SeqWorker,
 			for _, s := range input {
 				r, err := worker(s)
 				if err == nil {
+					if i+len(r) > cap(output) {
+						output = slices.Grow(output[:i], len(r))
+						output = output[:cap(output)]
+					}
 					for _, rs := range r {
-						if i == len(output) {
-							output = slices.Grow(output, cap(output))
-							output = output[:cap(output)]
-						}
 						output[i] = rs
 						i++
 					}

pkg/obitools/obidistribute/distribute.go

@@ -46,8 +46,7 @@ func CLIDistributeSequence(sequences obiiter.IBioSequence) {
 		formater = obiformats.WriteSequencesToFile
 	}
 
-	dispatcher := sequences.Distribute(CLISequenceClassifier(),
-		obidefault.BatchSize())
+	dispatcher := sequences.Distribute(CLISequenceClassifier())
 
 	obiformats.WriterDispatcher(CLIFileNamePattern(),
 		dispatcher, formater, opts...,

version.txt

@@ -1 +1 @@
-4.4.24
+4.4.29