seaweedfs/weed/filer/stream.go

package filer

import (
	"bytes"
	"context"
	"fmt"
	"io"
	"math"
	"strings"
	"sync"
	"time"

	"slices"

	"github.com/seaweedfs/seaweedfs/weed/glog"
	"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
	"github.com/seaweedfs/seaweedfs/weed/security"
	"github.com/seaweedfs/seaweedfs/weed/stats"
	"github.com/seaweedfs/seaweedfs/weed/util"
	util_http "github.com/seaweedfs/seaweedfs/weed/util/http"
	"github.com/seaweedfs/seaweedfs/weed/wdclient"
)

var getLookupFileIdBackoffSchedule = []time.Duration{
	150 * time.Millisecond,
	600 * time.Millisecond,
	1800 * time.Millisecond,
}

var (
	jwtSigningReadKey        security.SigningKey
	jwtSigningReadKeyExpires int
	loadJwtConfigOnce        sync.Once
)

func loadJwtConfig() {
	v := util.GetViper()
	jwtSigningReadKey = security.SigningKey(v.GetString("jwt.signing.read.key"))
	jwtSigningReadKeyExpires = v.GetInt("jwt.signing.read.expires_after_seconds")
	if jwtSigningReadKeyExpires == 0 {
		jwtSigningReadKeyExpires = 60
	}
}

// JwtForVolumeServer generates a JWT token for volume server read operations if jwt.signing.read is configured
func JwtForVolumeServer(fileId string) string {
	loadJwtConfigOnce.Do(loadJwtConfig)
	if len(jwtSigningReadKey) == 0 {
		return ""
	}
	return string(security.GenJwtForVolumeServer(jwtSigningReadKey, jwtSigningReadKeyExpires, fileId))
}

func HasData(entry *filer_pb.Entry) bool {

	if len(entry.Content) > 0 {
		return true
	}

	return len(entry.GetChunks()) > 0
}

func IsSameData(a, b *filer_pb.Entry) bool {

	if len(a.Content) > 0 || len(b.Content) > 0 {
		return bytes.Equal(a.Content, b.Content)
	}

	return isSameChunks(a.Chunks, b.Chunks)
}

func isSameChunks(a, b []*filer_pb.FileChunk) bool {
	if len(a) != len(b) {
		return false
	}
	slices.SortFunc(a, func(i, j *filer_pb.FileChunk) int {
		return strings.Compare(i.ETag, j.ETag)
	})
	slices.SortFunc(b, func(i, j *filer_pb.FileChunk) int {
		return strings.Compare(i.ETag, j.ETag)
	})
	for i := 0; i < len(a); i++ {
		if a[i].ETag != b[i].ETag {
			return false
		}
	}
	return true
}

func NewFileReader(filerClient filer_pb.FilerClient, entry *filer_pb.Entry) io.Reader {
	if len(entry.Content) > 0 {
		return bytes.NewReader(entry.Content)
	}
	return NewChunkStreamReader(filerClient, entry.GetChunks())
}

type DoStreamContent func(writer io.Writer) error

func PrepareStreamContent(masterClient wdclient.HasLookupFileIdFunction, jwtFunc VolumeServerJwtFunction, chunks []*filer_pb.FileChunk, offset int64, size int64) (DoStreamContent, error) {
	return PrepareStreamContentWithThrottler(context.Background(), masterClient, jwtFunc, chunks, offset, size, 0)
}

type VolumeServerJwtFunction func(fileId string) string

type CacheInvalidator interface {
	InvalidateCache(fileId string)
}

// urlSlicesEqual checks if two URL slices contain the same URLs (order-independent)
func urlSlicesEqual(a, b []string) bool {
	if len(a) != len(b) {
		return false
	}
	// Create a map to count occurrences in first slice
	counts := make(map[string]int)
	for _, url := range a {
		counts[url]++
	}
	// Verify all URLs in second slice match
	for _, url := range b {
		if counts[url] == 0 {
			return false
		}
		counts[url]--
	}
	return true
}

func PrepareStreamContentWithThrottler(ctx context.Context, masterClient wdclient.HasLookupFileIdFunction, jwtFunc VolumeServerJwtFunction, chunks []*filer_pb.FileChunk, offset int64, size int64, downloadMaxBytesPs int64) (DoStreamContent, error) {
	glog.V(4).InfofCtx(ctx, "prepare to stream content for chunks: %d", len(chunks))
	chunkViews := ViewFromChunks(ctx, masterClient.GetLookupFileIdFunction(), chunks, offset, size)

	fileId2Url := make(map[string][]string)

	for x := chunkViews.Front(); x != nil; x = x.Next {
		chunkView := x.Value
		var urlStrings []string
		var err error
		for _, backoff := range getLookupFileIdBackoffSchedule {
			if err := ctx.Err(); err != nil {
				return nil, err
			}
			urlStrings, err = masterClient.GetLookupFileIdFunction()(ctx, chunkView.FileId)
			if err == nil && len(urlStrings) > 0 {
				break
			}
			if err := ctx.Err(); err != nil {
				return nil, err
			}
			glog.V(4).InfofCtx(ctx, "waiting for chunk: %s", chunkView.FileId)
			timer := time.NewTimer(backoff)
			select {
			case <-ctx.Done():
				if !timer.Stop() {
					<-timer.C
				}
				return nil, ctx.Err()
			case <-timer.C:
			}
		}
		if err != nil {
			glog.V(1).InfofCtx(ctx, "operation LookupFileId %s failed, err: %v", chunkView.FileId, err)
			return nil, err
		} else if len(urlStrings) == 0 {
			errUrlNotFound := fmt.Errorf("operation LookupFileId %s failed, err: urls not found", chunkView.FileId)
			glog.ErrorCtx(ctx, errUrlNotFound)
			return nil, errUrlNotFound
		}
		fileId2Url[chunkView.FileId] = urlStrings
	}

	return func(writer io.Writer) error {
		downloadThrottler := util.NewWriteThrottler(downloadMaxBytesPs)
		remaining := size
		for x := chunkViews.Front(); x != nil; x = x.Next {
			chunkView := x.Value
			if offset < chunkView.ViewOffset {
				gap := chunkView.ViewOffset - offset
				remaining -= gap
				glog.V(4).InfofCtx(ctx, "zero [%d,%d)", offset, chunkView.ViewOffset)
				err := writeZero(writer, gap)
				if err != nil {
					return fmt.Errorf("write zero [%d,%d)", offset, chunkView.ViewOffset)
				}
				offset = chunkView.ViewOffset
			}
			urlStrings := fileId2Url[chunkView.FileId]
			start := time.Now()
			jwt := jwtFunc(chunkView.FileId)
			written, err := retriedStreamFetchChunkData(ctx, writer, urlStrings, jwt, chunkView.CipherKey, chunkView.IsGzipped, chunkView.IsFullChunk(), chunkView.OffsetInChunk, int(chunkView.ViewSize))

			if err != nil && ctx.Err() != nil {
				return ctx.Err()
			}

			// If read failed, try to invalidate cache and re-lookup
			if err != nil && written == 0 {
				if invalidator, ok := masterClient.(CacheInvalidator); ok {
					glog.V(0).InfofCtx(ctx, "read chunk %s failed, invalidating cache and retrying", chunkView.FileId)
					invalidator.InvalidateCache(chunkView.FileId)

					// Re-lookup
					newUrlStrings, lookupErr := masterClient.GetLookupFileIdFunction()(ctx, chunkView.FileId)
					if lookupErr == nil && len(newUrlStrings) > 0 {
						// Check if new URLs are different from old ones to avoid infinite retry
						if !urlSlicesEqual(urlStrings, newUrlStrings) {
							glog.V(0).InfofCtx(ctx, "retrying read chunk %s with new locations: %v", chunkView.FileId, newUrlStrings)
							_, err = retriedStreamFetchChunkData(ctx, writer, newUrlStrings, jwt, chunkView.CipherKey, chunkView.IsGzipped, chunkView.IsFullChunk(), chunkView.OffsetInChunk, int(chunkView.ViewSize))
							// Update the map so subsequent references use fresh URLs
							if err == nil {
								fileId2Url[chunkView.FileId] = newUrlStrings
							}
						} else {
							glog.V(0).InfofCtx(ctx, "re-lookup returned same locations for chunk %s, skipping retry", chunkView.FileId)
						}
					} else {
						if lookupErr != nil {
							glog.WarningfCtx(ctx, "failed to re-lookup chunk %s after cache invalidation: %v", chunkView.FileId, lookupErr)
						} else {
							glog.WarningfCtx(ctx, "re-lookup for chunk %s returned no locations, skipping retry", chunkView.FileId)
						}
					}
				}
			}

			offset += int64(chunkView.ViewSize)
			remaining -= int64(chunkView.ViewSize)
			stats.FilerRequestHistogram.WithLabelValues("chunkDownload").Observe(time.Since(start).Seconds())
			if err != nil {
				stats.FilerHandlerCounter.WithLabelValues("chunkDownloadError").Inc()
				return fmt.Errorf("read chunk: %w", err)
			}
			stats.FilerHandlerCounter.WithLabelValues("chunkDownload").Inc()
			downloadThrottler.MaybeSlowdown(int64(chunkView.ViewSize))
		}
		if remaining > 0 {
			glog.V(4).InfofCtx(ctx, "zero [%d,%d)", offset, offset+remaining)
			err := writeZero(writer, remaining)
			if err != nil {
				return fmt.Errorf("write zero [%d,%d)", offset, offset+remaining)
			}
		}

		return nil
	}, nil
}

// PrepareStreamContentWithPrefetch is like PrepareStreamContentWithThrottler but uses
// concurrent chunk prefetching to overlap network I/O. When prefetchAhead > 1, fetch
// goroutines establish HTTP connections to volume servers ahead of time, streaming data
// through io.Pipe with minimal memory overhead.
//
// prefetchAhead controls the number of chunks fetched concurrently:
//   - 0 or 1: falls back to sequential fetching (same as PrepareStreamContentWithThrottler)
//   - 2+: uses pipe-based prefetch pipeline with that many concurrent fetches
func PrepareStreamContentWithPrefetch(ctx context.Context, masterClient wdclient.HasLookupFileIdFunction, jwtFunc VolumeServerJwtFunction, chunks []*filer_pb.FileChunk, offset int64, size int64, downloadMaxBytesPs int64, prefetchAhead int) (DoStreamContent, error) {
	if prefetchAhead <= 1 {
		return PrepareStreamContentWithThrottler(ctx, masterClient, jwtFunc, chunks, offset, size, downloadMaxBytesPs)
	}

	glog.V(4).InfofCtx(ctx, "prepare to stream content with prefetch=%d for chunks: %d", prefetchAhead, len(chunks))
	chunkViews := ViewFromChunks(ctx, masterClient.GetLookupFileIdFunction(), chunks, offset, size)

	fileId2Url := make(map[string][]string)

	for x := chunkViews.Front(); x != nil; x = x.Next {
		chunkView := x.Value
		var urlStrings []string
		var err error
		for _, backoff := range getLookupFileIdBackoffSchedule {
			if err := ctx.Err(); err != nil {
				return nil, err
			}
			urlStrings, err = masterClient.GetLookupFileIdFunction()(ctx, chunkView.FileId)
			if err == nil && len(urlStrings) > 0 {
				break
			}
			if err := ctx.Err(); err != nil {
				return nil, err
			}
			glog.V(4).InfofCtx(ctx, "waiting for chunk: %s", chunkView.FileId)
			timer := time.NewTimer(backoff)
			select {
			case <-ctx.Done():
				if !timer.Stop() {
					<-timer.C
				}
				return nil, ctx.Err()
			case <-timer.C:
			}
		}
		if err != nil {
			glog.V(1).InfofCtx(ctx, "operation LookupFileId %s failed, err: %v", chunkView.FileId, err)
			return nil, err
		} else if len(urlStrings) == 0 {
			errUrlNotFound := fmt.Errorf("operation LookupFileId %s failed, err: urls not found", chunkView.FileId)
			glog.ErrorCtx(ctx, errUrlNotFound)
			return nil, errUrlNotFound
		}
		fileId2Url[chunkView.FileId] = urlStrings
	}

	return func(writer io.Writer) error {
		return streamChunksPrefetched(ctx, writer, chunkViews, fileId2Url, jwtFunc, masterClient, offset, size, downloadMaxBytesPs, prefetchAhead)
	}, nil
}

func StreamContent(masterClient wdclient.HasLookupFileIdFunction, writer io.Writer, chunks []*filer_pb.FileChunk, offset int64, size int64) error {
	streamFn, err := PrepareStreamContent(masterClient, JwtForVolumeServer, chunks, offset, size)
	if err != nil {
		return err
	}
	return streamFn(writer)
}

// ----------------  ReadAllReader ----------------------------------

func writeZero(w io.Writer, size int64) (err error) {
	zeroPadding := make([]byte, 1024)
	var written int
	for size > 0 {
		if size > 1024 {
			written, err = w.Write(zeroPadding)
		} else {
			written, err = w.Write(zeroPadding[:size])
		}
		size -= int64(written)
		if err != nil {
			return
		}
	}
	return
}

// ----------------  ChunkStreamReader ----------------------------------
type ChunkStreamReader struct {
	head         *Interval[*ChunkView]
	chunkView    *Interval[*ChunkView]
	totalSize    int64
	logicOffset  int64
	buffer       []byte
	bufferOffset int64
	bufferLock   sync.Mutex
	chunk        string
	lookupFileId wdclient.LookupFileIdFunctionType
}

var _ = io.ReadSeeker(&ChunkStreamReader{})
var _ = io.ReaderAt(&ChunkStreamReader{})
var _ = io.Closer(&ChunkStreamReader{})

func doNewChunkStreamReader(ctx context.Context, lookupFileIdFn wdclient.LookupFileIdFunctionType, chunks []*filer_pb.FileChunk) *ChunkStreamReader {

	chunkViews := ViewFromChunks(ctx, lookupFileIdFn, chunks, 0, math.MaxInt64)

	var totalSize int64
	for x := chunkViews.Front(); x != nil; x = x.Next {
		chunk := x.Value
		totalSize += int64(chunk.ViewSize)
	}

	return &ChunkStreamReader{
		head:         chunkViews.Front(),
		chunkView:    chunkViews.Front(),
		lookupFileId: lookupFileIdFn,
		totalSize:    totalSize,
	}
}

func NewChunkStreamReaderFromFiler(ctx context.Context, masterClient *wdclient.MasterClient, chunks []*filer_pb.FileChunk) *ChunkStreamReader {

	lookupFileIdFn := func(ctx context.Context, fileId string) (targetUrl []string, err error) {
		return masterClient.LookupFileId(ctx, fileId)
	}

	return doNewChunkStreamReader(ctx, lookupFileIdFn, chunks)
}

// NewChunkStreamReaderFromLookup creates a ChunkStreamReader from a lookup function.
// Used by clients that already have a LookupFileIdFunctionType (e.g., from FilerSource).
func NewChunkStreamReaderFromLookup(ctx context.Context, lookupFn wdclient.LookupFileIdFunctionType, chunks []*filer_pb.FileChunk) *ChunkStreamReader {
	return doNewChunkStreamReader(ctx, lookupFn, chunks)
}

func NewChunkStreamReader(filerClient filer_pb.FilerClient, chunks []*filer_pb.FileChunk) *ChunkStreamReader {

	lookupFileIdFn := LookupFn(filerClient)

	return doNewChunkStreamReader(context.Background(), lookupFileIdFn, chunks)
}

func (c *ChunkStreamReader) ReadAt(p []byte, off int64) (n int, err error) {
	c.bufferLock.Lock()
	defer c.bufferLock.Unlock()
	if err = c.prepareBufferFor(off); err != nil {
		return
	}
	c.logicOffset = off
	return c.doRead(p)
}

func (c *ChunkStreamReader) Read(p []byte) (n int, err error) {
	c.bufferLock.Lock()
	defer c.bufferLock.Unlock()
	return c.doRead(p)
}

func (c *ChunkStreamReader) doRead(p []byte) (n int, err error) {
	// fmt.Printf("do read [%d,%d) at %s[%d,%d)\n", c.logicOffset, c.logicOffset+int64(len(p)), c.chunk, c.bufferOffset, c.bufferOffset+int64(len(c.buffer)))
	for n < len(p) {
		// println("read", c.logicOffset)
		if err = c.prepareBufferFor(c.logicOffset); err != nil {
			return
		}
		t := copy(p[n:], c.buffer[c.logicOffset-c.bufferOffset:])
		n += t
		c.logicOffset += int64(t)
	}
	return
}

func (c *ChunkStreamReader) isBufferEmpty() bool {
	return len(c.buffer) <= int(c.logicOffset-c.bufferOffset)
}

func (c *ChunkStreamReader) Seek(offset int64, whence int) (int64, error) {
	c.bufferLock.Lock()
	defer c.bufferLock.Unlock()

	var err error
	switch whence {
	case io.SeekStart:
	case io.SeekCurrent:
		offset += c.logicOffset
	case io.SeekEnd:
		offset = c.totalSize + offset
	}
	if offset > c.totalSize {
		err = io.ErrUnexpectedEOF
	} else {
		c.logicOffset = offset
	}

	return offset, err

}

func insideChunk(offset int64, chunk *ChunkView) bool {
	return chunk.ViewOffset <= offset && offset < chunk.ViewOffset+int64(chunk.ViewSize)
}

func (c *ChunkStreamReader) prepareBufferFor(offset int64) (err error) {
	// stay in the same chunk
	if c.bufferOffset <= offset && offset < c.bufferOffset+int64(len(c.buffer)) {
		return nil
	}
	// glog.V(2).Infof("c.chunkView: %v buffer:[%d,%d) offset:%d totalSize:%d", c.chunkView, c.bufferOffset, c.bufferOffset+int64(len(c.buffer)), offset, c.totalSize)

	// find a possible chunk view
	p := c.chunkView
	for p != nil {
		chunk := p.Value
		// glog.V(2).Infof("prepareBufferFor check chunk:[%d,%d)", chunk.ViewOffset, chunk.ViewOffset+int64(chunk.ViewSize))
		if insideChunk(offset, chunk) {
			if c.isBufferEmpty() || c.bufferOffset != chunk.ViewOffset {
				c.chunkView = p
				return c.fetchChunkToBuffer(chunk)
			}
		}
		if offset < c.bufferOffset {
			p = p.Prev
		} else {
			p = p.Next
		}
	}

	return io.EOF
}

func (c *ChunkStreamReader) fetchChunkToBuffer(chunkView *ChunkView) error {
	urlStrings, err := c.lookupFileId(context.Background(), chunkView.FileId)
	if err != nil {
		glog.V(1).Infof("operation LookupFileId %s failed, err: %v", chunkView.FileId, err)
		return err
	}
	var buffer bytes.Buffer
	// pre-size to the known chunk size; avoids bytes.Buffer's doubling regrowth
	buffer.Grow(int(chunkView.ViewSize))
	var shouldRetry bool
	jwt := JwtForVolumeServer(chunkView.FileId)
	for _, urlString := range urlStrings {
		shouldRetry, err = util_http.ReadUrlAsStream(context.Background(), util_http.AppendQueryParameter(urlString, "readDeleted", "true"), jwt, chunkView.CipherKey, chunkView.IsGzipped, chunkView.IsFullChunk(), chunkView.OffsetInChunk, int(chunkView.ViewSize), func(data []byte) {
			buffer.Write(data)
		})
		if !shouldRetry {
			break
		}
		if err != nil {
			glog.V(1).Infof("read %s failed, err: %v", chunkView.FileId, err)
			buffer.Reset()
		} else {
			break
		}
	}
	if err != nil {
		return err
	}
	c.buffer = buffer.Bytes()
	c.bufferOffset = chunkView.ViewOffset
	c.chunk = chunkView.FileId

	// glog.V(0).Infof("fetched %s [%d,%d)", chunkView.FileId, chunkView.ViewOffset, chunkView.ViewOffset+int64(chunkView.ViewSize))

	return nil
}

func (c *ChunkStreamReader) Close() error {
	c.bufferLock.Lock()
	defer c.bufferLock.Unlock()
	c.buffer = nil
	c.head = nil
	c.chunkView = nil
	return nil
}

func VolumeId(fileId string) string {
	lastCommaIndex := strings.LastIndex(fileId, ",")
	if lastCommaIndex > 0 {
		return fileId[:lastCommaIndex]
	}
	return fileId
}