Keep WebP, AVIF and JPEG XL encodes at the limits under 40 seconds (closes #272)

WebP is saved at effort 2 and JPEG XL at effort 4, and an AVIF output of
more than 16,777,216 pixels is refused with 400 before anything is
decoded, as AVIF is already at the lowest effort govips can set. With
one libvips thread, at any quality, 8192x8192 random pixels with an
alpha channel take up to about 23 seconds as WebP and 27 as JPEG XL, and
4096x4096, 8192x2048 or 2048x8192 up to about 34 as AVIF. Resizing with
fit=cover already decodes the input, so the output's dimensions are now
worked out before resizing, in outputDimensions. Reading the input moves
into readInput to keep Process within the linter's limits.

Model: opus-5-5

internal/handlers/image.go

@@ -264,6 +264,14 @@ func (s *Handlers) respondImageError(
 		return
 	}
 
+	if errors.Is(err, imageprocessor.ErrAVIFOutputTooLarge) {
+		s.respondError(w, fmt.Sprintf("size too large for AVIF: the output "+
+			"would be above %d pixels", imageprocessor.MaxAVIFOutputPixels),
+			http.StatusBadRequest)
+
+		return
+	}
+
 	s.respondError(w, "internal error", http.StatusInternalServerError)
 }
 

internal/handlers/imageenc.go

@@ -170,6 +170,10 @@ func (s *Handlers) handleImageError(w http.ResponseWriter, err error) {
 		s.respondError(w, fmt.Sprintf("size too large for the source: the side "+
 			"computed from its proportions is above %d",
 			imageprocessor.MaxOutputDimension), http.StatusBadRequest)
+	case errors.Is(err, imageprocessor.ErrAVIFOutputTooLarge):
+		s.respondError(w, fmt.Sprintf("size too large for AVIF: the output "+
+			"would be above %d pixels", imageprocessor.MaxAVIFOutputPixels),
+			http.StatusBadRequest)
 	default:
 		s.log.Error("image request failed", "error", err)
 		s.respondError(w, "internal error", http.StatusInternalServerError)

internal/imageprocessor/imageprocessor.go

@@ -142,6 +142,19 @@ const MaxOutputDimension = 8192
 // requested size.
 var ErrOutputTooLarge = errors.New("output image dimensions exceed maximum")
 
+// MaxAVIFOutputPixels is the most pixels an AVIF output may have, so that an
+// encode takes at most 40 seconds of the default downstream_timeout of 60
+// seconds; AVIF is already at the lowest effort govips can set (avifEffort).
+// With one thread, as pixad runs libvips, saving 4096x4096, 8192x2048 or
+// 2048x8192 random pixels with an alpha channel takes up to about 34
+// seconds, the slowest at any quality and at 8 or 16 bits per sample, and
+// 5120x4096 at 8 bits already takes about 36.
+const MaxAVIFOutputPixels = 4096 * 4096
+
+// ErrAVIFOutputTooLarge is returned, before anything is decoded, when an AVIF
+// output would have more than MaxAVIFOutputPixels pixels.
+var ErrAVIFOutputTooLarge = errors.New("AVIF output has too many pixels")
+
 // ErrUnsupportedOutputFormat is returned when the requested output format is
 // not supported.
 var ErrUnsupportedOutputFormat = errors.New("unsupported output format")
@@ -210,7 +223,8 @@ func New(params Params) *ImageProcessor {
 // ErrTooManyImages. When ctx has ended once Process has a slot, or before it
 // encodes, it returns ctx's error and gives the slot back. govips gives pixa
 // no way to stop libvips once an encode has begun, so an encode keeps its
-// slot until it finishes.
+// slot until it finishes. An AVIF output of more than MaxAVIFOutputPixels is
+// refused with ErrAVIFOutputTooLarge before anything is decoded.
 func (p *ImageProcessor) Process(
 	ctx context.Context,
 	input io.Reader,
@@ -223,18 +237,9 @@ func (p *ImageProcessor) Process(
 
 	defer release()
 
-	// Read input with a size limit to prevent unbounded memory consumption.
-	// We read at most maxInputBytes+1 so we can detect if the input exceeds
-	// the limit without consuming additional memory.
-	limited := io.LimitReader(input, p.maxInputBytes+1)
-
-	data, err := io.ReadAll(limited)
+	data, err := p.readInput(input)
 	if err != nil {
-		return nil, fmt.Errorf("failed to read input: %w", err)
-	}
-
-	if int64(len(data)) > p.maxInputBytes {
-		return nil, ErrInputDataTooLarge
+		return nil, err
 	}
 
 	// govips picks the libvips loader from the input's first bytes with
@@ -277,20 +282,28 @@ func (p *ImageProcessor) Process(
 		return nil, err
 	}
 
-	// Resize if needed
-	if targetWidth != origWidth || targetHeight != origHeight {
-		err := p.resize(img, targetWidth, targetHeight, req.FitMode)
-		if err != nil {
-			return nil, fmt.Errorf("failed to resize: %w", err)
-		}
-	}
-
 	// orig is the source's own format; encode refuses an empty format
 	outputFormat := req.Format
 	if outputFormat == FormatOriginal {
 		outputFormat = sourceFormat
 	}
 
+	// Determine output dimensions; too large ones are refused before
+	// resizing, which with FitCover already decodes the input
+	outputWidth, outputHeight, err := outputDimensions(origWidth, origHeight,
+		targetWidth, targetHeight, req.FitMode, outputFormat)
+	if err != nil {
+		return nil, err
+	}
+
+	// Resize if needed
+	if targetWidth != origWidth || targetHeight != origHeight {
+		err := p.resize(img, outputWidth, outputHeight, req.FitMode)
+		if err != nil {
+			return nil, fmt.Errorf("failed to resize: %w", err)
+		}
+	}
+
 	// Encode to target format
 	output, err := p.encode(ctx, img, outputFormat, req.Quality)
 	if err != nil {
@@ -443,6 +456,23 @@ func (p *ImageProcessor) acquireSlot(ctx context.Context) (func(), error) {
 	return release, nil
 }
 
+// readInput reads input with a size limit to prevent unbounded memory
+// consumption, refusing more than maxInputBytes with ErrInputDataTooLarge. It
+// reads at most maxInputBytes+1 so it can detect if the input exceeds the
+// limit without consuming additional memory.
+func (p *ImageProcessor) readInput(input io.Reader) ([]byte, error) {
+	data, err := io.ReadAll(io.LimitReader(input, p.maxInputBytes+1))
+	if err != nil {
+		return nil, fmt.Errorf("failed to read input: %w", err)
+	}
+
+	if int64(len(data)) > p.maxInputBytes {
+		return nil, ErrInputDataTooLarge
+	}
+
+	return data, nil
+}
+
 // detectFormat returns the format string for a govips image type.
 func (p *ImageProcessor) detectFormat(imageType vips.ImageType) string {
 	switch imageType {
@@ -467,9 +497,61 @@ func (p *ImageProcessor) detectFormat(imageType vips.ImageType) string {
 	}
 }
 
-// resize resizes the image according to the fit mode. With FitOutside one
-// side can come out larger than requested; when it would be above
-// MaxOutputDimension, resize returns ErrOutputTooLarge without resizing.
+// outputDimensions returns the dimensions resize gives an image of imgWidth x
+// imgHeight for the target dimensions and fit mode, without resizing it, and
+// refuses an output too large for format. With FitOutside one side can come
+// out larger than the target; when it would be above MaxOutputDimension,
+// outputDimensions returns ErrOutputTooLarge. An AVIF output of more than
+// MaxAVIFOutputPixels is ErrAVIFOutputTooLarge.
+func outputDimensions(
+	imgWidth, imgHeight, width, height int, fit FitMode, format Format,
+) (int, int, error) {
+	scaleW := float64(width) / float64(imgWidth)
+	scaleH := float64(height) / float64(imgHeight)
+	outputWidth, outputHeight := width, height
+
+	switch fit {
+	case FitCover, FitFill, "":
+		// Cover crops, and fill stretches, to exactly the target dimensions
+
+	case FitContain:
+		// Fit within the target dimensions, maintaining aspect ratio
+		scale := min(scaleW, scaleH)
+		outputWidth = int(float64(imgWidth) * scale)
+		outputHeight = int(float64(imgHeight) * scale)
+
+	case FitInside:
+		// Same as contain, but only shrink
+		scale := min(scaleW, scaleH, 1)
+		outputWidth = int(float64(imgWidth) * scale)
+		outputHeight = int(float64(imgHeight) * scale)
+
+	case FitOutside:
+		// The smallest dimension fits, the other may exceed the target
+		scale := max(scaleW, scaleH)
+		outputWidth = int(float64(imgWidth) * scale)
+		outputHeight = int(float64(imgHeight) * scale)
+
+	default:
+		return 0, 0, fmt.Errorf("%w: %s", ErrInvalidFitMode, fit)
+	}
+
+	// The side FitOutside scales past the target is held to the maximum too
+	if max(outputWidth, outputHeight) > MaxOutputDimension {
+		return 0, 0, fmt.Errorf("%w: %dx%d is above %d", ErrOutputTooLarge,
+			outputWidth, outputHeight, MaxOutputDimension)
+	}
+
+	if format == FormatAVIF && outputWidth*outputHeight > MaxAVIFOutputPixels {
+		return 0, 0, fmt.Errorf("%w: %dx%d is above %d pixels",
+			ErrAVIFOutputTooLarge, outputWidth, outputHeight, MaxAVIFOutputPixels)
+	}
+
+	return outputWidth, outputHeight, nil
+}
+
+// resize resizes the image to width x height, the dimensions
+// outputDimensions gives for the fit mode.
 func (p *ImageProcessor) resize(
 	img *vips.ImageRef, width, height int, fit FitMode,
 ) error {
@@ -478,52 +560,20 @@ func (p *ImageProcessor) resize(
 		// Resize and crop to fill exact dimensions (default)
 		return img.Thumbnail(width, height, vips.InterestingCentre)
 
-	case FitContain:
-		// Resize to fit within dimensions, maintaining aspect ratio
-		imgW, imgH := img.Width(), img.Height()
-		scaleW := float64(width) / float64(imgW)
-		scaleH := float64(height) / float64(imgH)
-		scale := min(scaleW, scaleH)
-		newW := int(float64(imgW) * scale)
-		newH := int(float64(imgH) * scale)
-
-		return img.Thumbnail(newW, newH, vips.InterestingNone)
-
 	case FitFill:
 		// Resize to exact dimensions (may distort)
 		return img.ThumbnailWithSize(width, height, vips.InterestingNone, vips.SizeForce)
 
 	case FitInside:
-		// Same as contain, but only shrink
-		if img.Width() <= width && img.Height() <= height {
-			return nil // Already fits
+		// outputDimensions keeps the dimensions of an image that already fits
+		if img.Width() == width && img.Height() == height {
+			return nil
 		}
 
-		imgW, imgH := img.Width(), img.Height()
-		scaleW := float64(width) / float64(imgW)
-		scaleH := float64(height) / float64(imgH)
-		scale := min(scaleW, scaleH)
-		newW := int(float64(imgW) * scale)
-		newH := int(float64(imgH) * scale)
+		return img.Thumbnail(width, height, vips.InterestingNone)
 
-		return img.Thumbnail(newW, newH, vips.InterestingNone)
-
-	case FitOutside:
-		// Resize so smallest dimension fits, may exceed target on other dimension
-		imgW, imgH := img.Width(), img.Height()
-		scaleW := float64(width) / float64(imgW)
-		scaleH := float64(height) / float64(imgH)
-		scale := max(scaleW, scaleH)
-		newW := int(float64(imgW) * scale)
-		newH := int(float64(imgH) * scale)
-
-		// The dimension that exceeds the target is held to the maximum too
-		if newW > MaxOutputDimension || newH > MaxOutputDimension {
-			return fmt.Errorf("%w: %dx%d is above %d", ErrOutputTooLarge,
-				newW, newH, MaxOutputDimension)
-		}
-
-		return img.Thumbnail(newW, newH, vips.InterestingNone)
+	case FitContain, FitOutside:
+		return img.Thumbnail(width, height, vips.InterestingNone)
 
 	default:
 		return fmt.Errorf("%w: %s", ErrInvalidFitMode, fit)
@@ -627,11 +677,16 @@ func exportGIF(img *vips.ImageRef) ([]byte, error) {
 	return output, err
 }
 
-// webpEffort is libvips' default WebP effort, from 0 (fastest) to 6.
-const webpEffort = 4
+// webpEffort is the WebP effort, from 0 (fastest) to 6. It is below libvips'
+// default of 4 so that an encode takes at most 40 seconds of the default
+// downstream_timeout of 60 seconds. With one thread, as pixad runs libvips,
+// saving an 8192x8192 image of random pixels with an alpha channel takes up
+// to about 23 seconds at 2, and up to about 16 without one, at any quality;
+// with an alpha channel, 3 takes about 50 seconds and 4 about 61.
+const webpEffort = 2
 
-// exportWebP encodes img as lossy WebP at quality and libvips' default
-// effort, without metadata.
+// exportWebP encodes img as lossy WebP at quality and webpEffort, without
+// metadata.
 func exportWebP(img *vips.ImageRef, quality int) ([]byte, error) {
 	output, _, err := img.ExportWebp(&vips.WebpExportParams{
 		StripMetadata:   true,
@@ -643,12 +698,13 @@ func exportWebP(img *vips.ImageRef, quality int) ([]byte, error) {
 }
 
 // avifEffort is the AVIF effort, from 0 (fastest) to 9; 1 is the lowest
-// govips can set. With one thread, as pixad runs libvips, 1 takes about 51
-// seconds to save an 8192x8192 RGB image of random pixels, and about 110
-// with an alpha channel, the worst case, against the default
-// downstream_timeout of 60 seconds. On an image of milder noise, which 1
-// saves in about 12 seconds, 2 takes nearly a minute and libvips' default,
-// 4, takes minutes.
+// govips can set. With one thread, as pixad runs libvips, 1 takes about 52
+// seconds to save an 8192x8192 RGB image of random pixels at quality 85,
+// and about 96 with an alpha channel, against the default
+// downstream_timeout of 60 seconds, so an AVIF output is held to
+// MaxAVIFOutputPixels. On an image of milder noise, which 1 saves in about
+// 12 seconds, 2 takes nearly a minute and libvips' default, 4, takes
+// minutes.
 const avifEffort = 1
 
 // avifBitdepth is the AVIF bit depth, 8 bits per sample for every image.
@@ -675,10 +731,18 @@ func exportAVIF(img *vips.ImageRef, quality int) ([]byte, error) {
 // JPEG that names none.
 const jxlResolution = 72 / 25.4
 
-// exportJXL encodes img as JPEG XL at quality, with libvips' default effort
-// and without metadata. govips sends libvips a distance, the JPEG XL
-// encoder's own measure of quality, along with the quality, and libvips then
-// uses the distance alone, so the quality is also given as a distance.
+// jxlEffort is the JPEG XL effort, from 1 (fastest) to 9. It is below
+// libvips' default of 7 so that an encode takes at most 40 seconds of the
+// default downstream_timeout of 60 seconds. With one thread, as pixad runs
+// libvips, saving an 8192x8192 image of random pixels with an alpha channel
+// takes up to about 27 seconds at 4, and up to about 13 without one, at any
+// quality; with an alpha channel, 5 takes about 43 seconds and 7 about 81.
+const jxlEffort = 4
+
+// exportJXL encodes img as JPEG XL at quality and jxlEffort, without
+// metadata. govips sends libvips a distance, the JPEG XL encoder's own
+// measure of quality, along with the quality, and libvips then uses the
+// distance alone, so the quality is also given as a distance.
 func exportJXL(img *vips.ImageRef, quality int) ([]byte, error) {
 	// libvips converts a CMYK image to sRGB before it saves WebP, AVIF or
 	// PNG, but cannot save one as JPEG XL. encode has already converted
@@ -717,6 +781,7 @@ func exportJXL(img *vips.ImageRef, quality int) ([]byte, error) {
 	params := vips.NewJxlExportParams()
 	params.Quality = quality
 	params.Distance = jxlDistance(quality)
+	params.Effort = jxlEffort
 
 	output, _, err := toSave.ExportJxl(params)
 	if err != nil {