Files
seaweedfs/weed/server/webdav_server.go
T
Eliah RusinandChris Lu cfa8afec92 filer: guard FoundationDB 100KB value limit and pack earlier (#11161)
* filer: guard the FoundationDB value size limit, not the transaction limit

An entry's whole chunk list is one FoundationDB value, and FDB caps a value at
100,000 bytes while a transaction may reach 10MB. UpdateEntry checked the
transaction limit, so every entry between the two limits passed the guard and
was rejected by FDB itself with error 2103 (Value length exceeds limit). The
failure surfaced inside the store rather than at the guard, so the S3 layer
dropped the connection and clients saw a network fault instead of an error.

Check the value limit in UpdateEntry and KvPut instead, after gzip and before
the transaction, with an error that names the limit it hit. The removed
transaction-size constant guarded nothing else: DeleteFolderChildren batches by
entry count.

Refs #11158

* filer: fold at 500 chunks in the foundationdb build

Manifest packing is what keeps a large file's entry small, but it only ran once
a flat chunk list reached 10000 chunks. A FoundationDB value stops at 100,000
bytes and an entry's whole chunk list is one value, which at ~100 bytes per
chunk record is about 1000 chunks -- so on FDB the write always failed before
packing could help: a 3.3 GiB PutObject at the default -maxMB=4 was already
past the limit.

FoundationDB support is its own build (`go build -tags foundationdb`, shipped
as its own image), so the batch is a build-time choice and needs no negotiation
at run time. The tagged build folds at 500, every other build keeps 10000 and
is untouched.

500 is not arbitrary: a single fold level leaves (chunks/batch) manifest
pointers plus up to (batch-1) unfolded chunks in the entry, so the reachable
chunk count is highest when the two terms are near equal. For a 100,000-byte
budget that optimum is 500, which holds an entry inside the limit up to
~250,000 chunks -- ~1 TB at -maxMB=4, against ~4 GB before. Larger files need
nested packing, which no batch size substitutes for.

One binary serves every role in that image, so the filer and each client that
folds -- S3, mount, WebDAV, weed shell, filer.copy -- agree on the batch by
construction. A binary built with the tag but pointed at another store folds
earlier than that store requires, costing one manifest blob per 500 chunks and
one read to resolve it.

Fixes #11158

* filer: fold with rollback inside MaybeManifestize, not beside it

A fold that fails midway has already uploaded manifest blobs for its earlier
batches, and returns only the data chunks -- dropping the manifests it had
separated out of the caller's list. Both were wrong in ways that mattered:

  - AppendToEntry assigned that shortened list straight to entry.Chunks and
    created the entry, so an append to an already-folded file whose fold
    failed lost every previously folded chunk. weed mount had the same shape.
  - cleanupChunks logged the error as "not good, but should be ok" and then
    returned it through a named result, failing the whole CreateEntry or
    UpdateEntry, while the blobs it had written stayed behind referenced by
    nothing.

The S3 path was alone in handling this, through a private helper beside
MaybeManifestize. A second entry point next to the one everything else calls
just means the wrong one gets used, so the behaviour moves inside
MaybeManifestize: on failure it returns inputChunks as it received them, and
hands the blobs it saved to a deleteChunks callback. The filer, S3 and
filer.copy pass their existing deleters -- filer.copy already cleans up this
way after a failed upload -- and mount, WebDAV and weed shell pass nil, which
reports the blobs rather than collecting them, as before. Each caller keeps its
own error policy: the filer HTTP PUT path and filer.copy still fail the request,
the rest still continue with the flat list, which is a correct entry.

---------

Co-authored-by: Chris Lu <chris.lu@gmail.com>
2026-09-04 23:12:27 -07:00

672 lines
17 KiB
Go

package weed_server
import (
"context"
"fmt"
"io"
"net/http"
"os"
"path"
"strings"
"time"
"github.com/seaweedfs/seaweedfs/weed/util/version"
"github.com/seaweedfs/seaweedfs/weed/util/buffered_writer"
"golang.org/x/net/webdav"
"google.golang.org/grpc"
"github.com/seaweedfs/seaweedfs/weed/pb"
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
"github.com/seaweedfs/seaweedfs/weed/util"
"github.com/seaweedfs/seaweedfs/weed/util/chunk_cache"
"github.com/seaweedfs/seaweedfs/weed/wdclient"
"github.com/seaweedfs/seaweedfs/weed/filer"
"github.com/seaweedfs/seaweedfs/weed/glog"
"github.com/seaweedfs/seaweedfs/weed/security"
)
type WebDavOption struct {
Filer pb.ServerAddress
FilerRootPath string
DomainName string
BucketsPath string
GrpcDialOption grpc.DialOption
Collection string
Replication string
DiskType string
Uid uint32
Gid uint32
Cipher bool
CacheDir string
CacheSizeMB int64
MaxMB int
}
type WebDavServer struct {
option *WebDavOption
grpcDialOption grpc.DialOption
Handler http.Handler
}
func max(x, y int64) int64 {
if x <= y {
return y
}
return x
}
func NewWebDavServer(option *WebDavOption) (ws *WebDavServer, err error) {
fs, _ := NewWebDavFileSystem(option)
// Fix no set filer.path , accessing "/" returns "//"
if option.FilerRootPath == "/" {
option.FilerRootPath = ""
}
// filer.path non "/" option means we are accessing filer's sub-folders
if option.FilerRootPath != "" {
fs = NewWrappedFs(fs, path.Clean(option.FilerRootPath))
}
ws = &WebDavServer{
option: option,
grpcDialOption: security.LoadClientTLS(util.GetViper(), "grpc.filer"),
Handler: listedEntriesHandler{
next: &webdav.Handler{
FileSystem: fs,
LockSystem: webdav.NewMemLS(),
},
},
}
return ws, nil
}
// adapted from https://github.com/mattn/davfs/blob/master/plugin/mysql/mysql.go
type WebDavFileSystem struct {
option *WebDavOption
chunkCache *chunk_cache.TieredChunkCache
readerCache *filer.ReaderCache
filerClient *wdclient.FilerClient
signature int32
}
type FileInfo struct {
name string
size int64
mode os.FileMode
modifiedTime time.Time
etag string
isDirectory bool
err error
}
func (fi *FileInfo) Name() string { return fi.name }
func (fi *FileInfo) Size() int64 { return fi.size }
func (fi *FileInfo) Mode() os.FileMode { return fi.mode }
func (fi *FileInfo) ModTime() time.Time { return fi.modifiedTime }
func (fi *FileInfo) IsDir() bool { return fi.isDirectory }
func (fi *FileInfo) Sys() interface{} { return nil }
func (fi *FileInfo) ETag(ctx context.Context) (string, error) {
if fi.err != nil {
return "", fi.err
}
if fi.etag == "" {
// nothing hashed this entry; let webdav derive one rather than
// publish an empty DAV:getetag, which is not a valid entity-tag
return "", webdav.ErrNotImplemented
}
return fi.etag, nil
}
type WebDavFile struct {
fs *WebDavFileSystem
name string
isDirectory bool
off int64
entry *filer_pb.Entry
visibleIntervals *filer.IntervalList[*filer.VisibleInterval]
reader io.ReaderAt
bufWriter *buffered_writer.BufferedWriteCloser
ctx context.Context
}
func NewWebDavFileSystem(option *WebDavOption) (webdav.FileSystem, error) {
cacheUniqueId := util.Md5String([]byte("webdav" + string(option.Filer) + version.Version()))[0:8]
cacheDir := path.Join(option.CacheDir, cacheUniqueId)
os.MkdirAll(cacheDir, os.FileMode(0755))
chunkCache := chunk_cache.NewTieredChunkCache(256, cacheDir, option.CacheSizeMB, 1024*1024)
t := &WebDavFileSystem{
option: option,
chunkCache: chunkCache,
signature: util.RandomInt32(),
}
// FilerClient rather than filer.LookupFn: its cache is bounded, which the
// LookupFn doc asks long-running processes to prefer, and it can invalidate
// a volume's locations, so a read that failed against every cached location
// looks the volume up again instead of retrying a server that has moved or
// died.
t.filerClient = wdclient.NewFilerClient([]pb.ServerAddress{option.Filer}, option.GrpcDialOption, "")
t.readerCache = filer.NewReaderCache(32, chunkCache, t.filerClient.GetLookupFileIdFunction(), t.filerClient)
return t, nil
}
var _ = filer_pb.FilerClient(&WebDavFileSystem{})
func (fs *WebDavFileSystem) WithFilerClient(streamingMode bool, fn func(filer_pb.SeaweedFilerClient) error) error {
return pb.WithGrpcClient(context.Background(), streamingMode, fs.signature, func(grpcConnection *grpc.ClientConn) error {
client := filer_pb.NewSeaweedFilerClient(grpcConnection)
return fn(client)
}, fs.option.Filer.ToGrpcAddress(), false, fs.option.GrpcDialOption)
}
func (fs *WebDavFileSystem) AdjustedUrl(location *filer_pb.Location) string {
return location.Url
}
func (fs *WebDavFileSystem) GetDataCenter() string {
return ""
}
func clearName(name string) (string, error) {
slashed := strings.HasSuffix(name, "/")
name = path.Clean(name)
if !strings.HasSuffix(name, "/") && slashed {
name += "/"
}
if !strings.HasPrefix(name, "/") {
return "", os.ErrInvalid
}
return name, nil
}
func (fs *WebDavFileSystem) Mkdir(ctx context.Context, fullDirPath string, perm os.FileMode) error {
glog.V(2).Infof("WebDavFileSystem.Mkdir %v", fullDirPath)
if !strings.HasSuffix(fullDirPath, "/") {
fullDirPath += "/"
}
var err error
if fullDirPath, err = clearName(fullDirPath); err != nil {
return err
}
_, err = fs.stat(ctx, fullDirPath)
if err == nil {
return os.ErrExist
}
return fs.WithFilerClient(false, func(client filer_pb.SeaweedFilerClient) error {
dir, name := util.FullPath(fullDirPath).DirAndName()
request := &filer_pb.CreateEntryRequest{
Directory: dir,
Entry: &filer_pb.Entry{
Name: name,
IsDirectory: true,
Attributes: &filer_pb.FuseAttributes{
Mtime: time.Now().Unix(),
Crtime: time.Now().Unix(),
FileMode: uint32(perm | os.ModeDir),
Uid: fs.option.Uid,
Gid: fs.option.Gid,
},
},
Signatures: []int32{fs.signature},
}
glog.V(1).Infof("mkdir: %v", request)
if err := filer_pb.CreateEntry(context.Background(), client, request); err != nil {
return fmt.Errorf("mkdir %s/%s: %v", dir, name, err)
}
return nil
})
}
func (fs *WebDavFileSystem) OpenFile(ctx context.Context, fullFilePath string, flag int, perm os.FileMode) (webdav.File, error) {
glog.V(2).Infof("WebDavFileSystem.OpenFile %v %x", fullFilePath, flag)
var err error
if fullFilePath, err = clearName(fullFilePath); err != nil {
return nil, err
}
if flag&os.O_CREATE != 0 {
// file should not have / suffix.
if strings.HasSuffix(fullFilePath, "/") {
return nil, os.ErrInvalid
}
_, err = fs.stat(ctx, fullFilePath)
if err == nil {
if flag&os.O_EXCL != 0 {
return nil, os.ErrExist
}
fs.removeAll(ctx, fullFilePath)
}
dir, name := util.FullPath(fullFilePath).DirAndName()
err = fs.WithFilerClient(false, func(client filer_pb.SeaweedFilerClient) error {
if err := filer_pb.CreateEntry(context.Background(), client, &filer_pb.CreateEntryRequest{
Directory: dir,
Entry: &filer_pb.Entry{
Name: name,
IsDirectory: perm&os.ModeDir > 0,
Attributes: &filer_pb.FuseAttributes{
Mtime: 0,
Crtime: time.Now().Unix(),
FileMode: uint32(perm),
Uid: fs.option.Uid,
Gid: fs.option.Gid,
TtlSec: 0,
},
},
Signatures: []int32{fs.signature},
}); err != nil {
return fmt.Errorf("create %s: %v", fullFilePath, err)
}
return nil
})
if err != nil {
return nil, err
}
return &WebDavFile{
fs: fs,
name: fullFilePath,
isDirectory: false,
bufWriter: buffered_writer.NewBufferedWriteCloser(fs.option.MaxMB * 1024 * 1024),
ctx: ctx,
}, nil
}
fi, err := fs.stat(ctx, fullFilePath)
if err != nil {
if err == os.ErrNotExist {
return nil, err
}
return &WebDavFile{fs: fs, ctx: ctx}, nil
}
if !strings.HasSuffix(fullFilePath, "/") && fi.IsDir() {
fullFilePath += "/"
}
return &WebDavFile{
fs: fs,
name: fullFilePath,
isDirectory: false,
bufWriter: buffered_writer.NewBufferedWriteCloser(fs.option.MaxMB * 1024 * 1024),
ctx: ctx,
}, nil
}
func (fs *WebDavFileSystem) removeAll(ctx context.Context, fullFilePath string) error {
var err error
if fullFilePath, err = clearName(fullFilePath); err != nil {
return err
}
dir, name := util.FullPath(fullFilePath).DirAndName()
return filer_pb.Remove(context.Background(), fs, dir, name, true, false, false, false, []int32{fs.signature})
}
func (fs *WebDavFileSystem) RemoveAll(ctx context.Context, name string) error {
glog.V(2).Infof("WebDavFileSystem.RemoveAll %v", name)
return fs.removeAll(ctx, name)
}
func (fs *WebDavFileSystem) Rename(ctx context.Context, oldName, newName string) error {
glog.V(2).Infof("WebDavFileSystem.Rename %v to %v", oldName, newName)
var err error
if oldName, err = clearName(oldName); err != nil {
return err
}
if newName, err = clearName(newName); err != nil {
return err
}
of, err := fs.stat(ctx, oldName)
if err != nil {
return os.ErrExist
}
if of.IsDir() {
if strings.HasSuffix(oldName, "/") {
oldName = strings.TrimRight(oldName, "/")
}
if strings.HasSuffix(newName, "/") {
newName = strings.TrimRight(newName, "/")
}
}
_, err = fs.stat(ctx, newName)
if err == nil {
return os.ErrExist
}
oldDir, oldBaseName := util.FullPath(oldName).DirAndName()
newDir, newBaseName := util.FullPath(newName).DirAndName()
return fs.WithFilerClient(false, func(client filer_pb.SeaweedFilerClient) error {
request := &filer_pb.AtomicRenameEntryRequest{
OldDirectory: oldDir,
OldName: oldBaseName,
NewDirectory: newDir,
NewName: newBaseName,
}
_, err := client.AtomicRenameEntry(ctx, request)
if err != nil {
return fmt.Errorf("renaming %s/%s => %s/%s: %v", oldDir, oldBaseName, newDir, newBaseName, err)
}
return nil
})
}
func (fs *WebDavFileSystem) stat(ctx context.Context, fullFilePath string) (os.FileInfo, error) {
var err error
if fullFilePath, err = clearName(fullFilePath); err != nil {
return nil, err
}
fullpath := util.FullPath(fullFilePath)
if listedFi := listedEntriesFrom(ctx).get(string(fullpath)); listedFi != nil {
return listedFi, nil
}
entry, _, _, err := filer_pb.GetEntry(ctx, fs, fullpath)
if err != nil {
if err == filer_pb.ErrNotFound {
return nil, os.ErrNotExist
}
return &FileInfo{err: err}, nil
}
if entry == nil {
return nil, os.ErrNotExist
}
return toFileInfo(fullpath, entry), nil
}
func toFileInfo(fullpath util.FullPath, entry *filer_pb.Entry) *FileInfo {
// Name is what WebDAV publishes as DAV:displayname; clients that build a
// child URL from it reach nothing when it carries the whole path.
fp := util.FullPath(listedEntryKey(string(fullpath)))
fi := &FileInfo{
size: int64(filer.FileSize(entry)),
name: fp.Name(),
mode: os.FileMode(entry.Attributes.FileMode),
modifiedTime: time.Unix(entry.Attributes.Mtime, 0),
etag: filer.ETag(entry),
isDirectory: entry.IsDirectory,
}
if fp == "/" {
fi.modifiedTime = time.Now()
fi.isDirectory = true
}
return fi
}
func (fs *WebDavFileSystem) Stat(ctx context.Context, name string) (os.FileInfo, error) {
glog.V(2).Infof("WebDavFileSystem.Stat %v", name)
return fs.stat(ctx, name)
}
func (f *WebDavFile) saveDataAsChunk(reader io.Reader, name string, offset int64, tsNs int64, _ uint64) (chunk *filer_pb.FileChunk, err error) {
// Delegate to the shared filer-gateway helper so WebDAV, NFS, and
// any future filer-backed protocols go through one implementation of
// AssignVolume + volume-server upload.
chunk, err = filer.SaveGatewayDataAsChunk(filer.GatewayChunkUploadRequest{
FilerClient: f.fs,
Reader: reader,
FullPath: name,
Filename: f.name,
Offset: offset,
TsNs: tsNs,
Collection: f.fs.option.Collection,
Replication: f.fs.option.Replication,
DiskType: f.fs.option.DiskType,
Cipher: f.fs.option.Cipher,
})
if err != nil {
glog.V(0).Infof("upload data %v: %v", f.name, err)
return nil, err
}
return chunk, nil
}
func (f *WebDavFile) Write(buf []byte) (int, error) {
glog.V(2).Infof("WebDavFileSystem.Write %v", f.name)
fullPath := util.FullPath(f.name)
dir, _ := fullPath.DirAndName()
var getErr error
ctx := context.Background()
if f.entry == nil {
f.entry, _, _, getErr = filer_pb.GetEntry(context.Background(), f.fs, fullPath)
}
if f.entry == nil {
return 0, getErr
}
if getErr != nil {
return 0, getErr
}
if f.bufWriter.FlushFunc == nil {
f.bufWriter.FlushFunc = func(data []byte, offset int64) (flushErr error) {
var chunk *filer_pb.FileChunk
chunk, flushErr = f.saveDataAsChunk(util.NewBytesReader(data), f.name, offset, time.Now().UnixNano(), uint64(len(data)))
if flushErr != nil {
if f.entry.Attributes.Mtime == 0 {
if err := f.fs.removeAll(ctx, f.name); err != nil {
glog.Errorf("bufWriter.Flush remove file error: %+v", f.name)
}
}
return fmt.Errorf("%s upload result: %v", f.name, flushErr)
}
f.entry.Content = nil
f.entry.Chunks = append(f.entry.GetChunks(), chunk)
return flushErr
}
f.bufWriter.CloseFunc = func() error {
// no chunk deleter here: a failed fold reports the blobs it saved
manifestedChunks, manifestErr := filer.MaybeManifestize(f.saveDataAsChunk, nil, f.entry.GetChunks())
if manifestErr != nil {
// not good, but should be ok
glog.V(0).Infof("file %s close MaybeManifestize: %v", f.name, manifestErr)
} else {
f.entry.Chunks = manifestedChunks
}
flushErr := f.fs.WithFilerClient(false, func(client filer_pb.SeaweedFilerClient) error {
f.entry.Attributes.Mtime = time.Now().Unix()
request := &filer_pb.UpdateEntryRequest{
Directory: dir,
Entry: f.entry,
Signatures: []int32{f.fs.signature},
}
if _, err := client.UpdateEntry(ctx, request); err != nil {
return fmt.Errorf("update %s: %v", f.name, err)
}
return nil
})
return flushErr
}
}
written, err := f.bufWriter.Write(buf)
if err == nil {
f.entry.Attributes.FileSize = uint64(max(f.off+int64(written), int64(f.entry.Attributes.FileSize)))
glog.V(3).Infof("WebDavFileSystem.Write %v: written [%d,%d)", f.name, f.off, f.off+int64(len(buf)))
f.off += int64(written)
}
return written, err
}
func (f *WebDavFile) Close() error {
glog.V(2).Infof("WebDavFileSystem.Close %v", f.name)
if f.bufWriter == nil {
return nil
}
err := f.bufWriter.Close()
if f.entry != nil {
f.entry = nil
f.visibleIntervals = nil
}
return err
}
func (f *WebDavFile) Read(p []byte) (readSize int, err error) {
glog.V(2).Infof("WebDavFileSystem.Read %v", f.name)
if f.entry == nil {
f.entry, _, _, err = filer_pb.GetEntry(context.Background(), f.fs, util.FullPath(f.name))
}
if f.entry == nil {
return 0, err
}
if err != nil {
return 0, err
}
fileSize := int64(filer.FileSize(f.entry))
if fileSize == 0 {
return 0, io.EOF
}
if f.visibleIntervals == nil {
f.visibleIntervals, _ = filer.NonOverlappingVisibleIntervals(f.ctx, f.fs.filerClient.GetLookupFileIdFunction(), f.entry.GetChunks(), 0, fileSize)
f.reader = nil
}
if f.reader == nil {
chunkViews := filer.ViewFromVisibleIntervals(f.visibleIntervals, 0, fileSize)
f.reader = filer.NewChunkReaderAtFromClient(f.ctx, f.fs.readerCache, chunkViews, fileSize, filer.DefaultPrefetchCount)
}
readSize, err = f.reader.ReadAt(p, f.off)
glog.V(3).Infof("WebDavFileSystem.Read %v: [%d,%d)", f.name, f.off, f.off+int64(readSize))
f.off += int64(readSize)
if err != nil && err != io.EOF {
glog.Errorf("file read %s: %v", f.name, err)
}
return
}
func (f *WebDavFile) Readdir(count int) (ret []os.FileInfo, err error) {
glog.V(2).Infof("WebDavFileSystem.Readdir %v count %d", f.name, count)
dir, _ := util.FullPath(f.name).DirAndName()
ctx := f.requestContext()
listed := listedEntriesFrom(ctx)
err = filer_pb.ReadDirAllEntries(ctx, f.fs, util.FullPath(dir), "", func(entry *filer_pb.Entry, isLast bool) error {
childPath := util.NewFullPath(dir, entry.Name)
fi := toFileInfo(childPath, entry)
glog.V(4).Infof("entry: %v", fi.name)
listed.put(string(childPath), fi)
ret = append(ret, fi)
return nil
})
if err != nil {
return nil, err
}
old := f.off
if old >= int64(len(ret)) {
if count > 0 {
return nil, io.EOF
}
return nil, nil
}
if count > 0 {
f.off += int64(count)
if f.off > int64(len(ret)) {
f.off = int64(len(ret))
}
} else {
f.off = int64(len(ret))
old = 0
}
return ret[old:f.off], nil
}
func (f *WebDavFile) Seek(offset int64, whence int) (int64, error) {
glog.V(2).Infof("WebDavFile.Seek %v %v %v", f.name, offset, whence)
ctx := f.requestContext()
var err error
switch whence {
case io.SeekStart:
f.off = 0
case io.SeekEnd:
if fi, err := f.fs.stat(ctx, f.name); err != nil {
return 0, err
} else {
f.off = fi.Size()
}
}
f.off += offset
return f.off, err
}
func (f *WebDavFile) Stat() (os.FileInfo, error) {
glog.V(2).Infof("WebDavFile.Stat %v", f.name)
return f.fs.stat(f.requestContext(), f.name)
}
// the context of the request that opened the file, or a bare one for files
// opened outside a request
func (f *WebDavFile) requestContext() context.Context {
if f.ctx != nil {
return f.ctx
}
return context.Background()
}