distribution/registry/layerupload.go
Stephen J Day 0270bec916 Handle empty blob files more appropriately
Several API tests were added to ensure correct acceptance of zero-size and
empty tar files. This led to several changes in the storage backend around the
guarantees of remote file reading, which backs the layer and layer upload type.

In support of these changes, zero-length and empty checks have been added to
the digest package. These provide a sanity check against upstream tarsum
changes. The fileReader has been modified to be more robust when reading and
seeking on zero-length or non-existent files. The file no longer needs to exist
for the reader to be created. Seeks can now move beyond the end of the file,
causing reads to issue an io.EOF. This eliminates errors during certain race
conditions for reading files which should be detected by stat calls. As a part
of this, a few error types were factored out and the read buffer size was
increased to something more reasonable.

Signed-off-by: Stephen J Day <stephen.day@docker.com>
2015-02-02 13:01:49 -08:00

287 lines
8.8 KiB
Go

package registry
import (
"fmt"
"io"
"net/http"
"net/url"
"os"
"github.com/Sirupsen/logrus"
"github.com/docker/distribution/api/v2"
"github.com/docker/distribution/digest"
"github.com/docker/distribution/storage"
"github.com/gorilla/handlers"
)
// layerUploadDispatcher constructs and returns the layer upload handler for
// the given request context.
func layerUploadDispatcher(ctx *Context, r *http.Request) http.Handler {
luh := &layerUploadHandler{
Context: ctx,
UUID: ctx.vars["uuid"],
}
handler := http.Handler(handlers.MethodHandler{
"POST": http.HandlerFunc(luh.StartLayerUpload),
"GET": http.HandlerFunc(luh.GetUploadStatus),
"HEAD": http.HandlerFunc(luh.GetUploadStatus),
// TODO(stevvooe): Must implement patch support.
// "PATCH": http.HandlerFunc(luh.PutLayerChunk),
"PUT": http.HandlerFunc(luh.PutLayerUploadComplete),
"DELETE": http.HandlerFunc(luh.CancelLayerUpload),
})
if luh.UUID != "" {
luh.log = luh.log.WithField("uuid", luh.UUID)
state, err := hmacKey(ctx.Config.HTTP.Secret).unpackUploadState(r.FormValue("_state"))
if err != nil {
return http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
ctx.log.Infof("error resolving upload: %v", err)
w.WriteHeader(http.StatusBadRequest)
luh.Errors.Push(v2.ErrorCodeBlobUploadInvalid, err)
})
}
luh.State = state
if state.Name != ctx.Repository.Name() {
return http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
ctx.log.Infof("mismatched repository name in upload state: %q != %q", state.Name, luh.Repository.Name())
w.WriteHeader(http.StatusBadRequest)
luh.Errors.Push(v2.ErrorCodeBlobUploadInvalid, err)
})
}
if state.UUID != luh.UUID {
return http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
ctx.log.Infof("mismatched uuid in upload state: %q != %q", state.UUID, luh.UUID)
w.WriteHeader(http.StatusBadRequest)
luh.Errors.Push(v2.ErrorCodeBlobUploadInvalid, err)
})
}
layers := ctx.Repository.Layers()
upload, err := layers.Resume(luh.UUID)
if err != nil {
ctx.log.Errorf("error resolving upload: %v", err)
if err == storage.ErrLayerUploadUnknown {
return http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
w.WriteHeader(http.StatusNotFound)
luh.Errors.Push(v2.ErrorCodeBlobUploadUnknown, err)
})
}
return http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
w.WriteHeader(http.StatusInternalServerError)
luh.Errors.Push(v2.ErrorCodeUnknown, err)
})
}
luh.Upload = upload
if state.Offset > 0 {
// Seek the layer upload to the correct spot if it's non-zero.
// These error conditions should be rare and demonstrate really
// problems. We basically cancel the upload and tell the client to
// start over.
if nn, err := upload.Seek(luh.State.Offset, os.SEEK_SET); err != nil {
defer upload.Close()
ctx.log.Infof("error seeking layer upload: %v", err)
return http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
w.WriteHeader(http.StatusBadRequest)
luh.Errors.Push(v2.ErrorCodeBlobUploadInvalid, err)
upload.Cancel()
})
} else if nn != luh.State.Offset {
defer upload.Close()
ctx.log.Infof("seek to wrong offest: %d != %d", nn, luh.State.Offset)
return http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
w.WriteHeader(http.StatusBadRequest)
luh.Errors.Push(v2.ErrorCodeBlobUploadInvalid, err)
upload.Cancel()
})
}
}
handler = closeResources(handler, luh.Upload)
}
return handler
}
// layerUploadHandler handles the http layer upload process.
type layerUploadHandler struct {
*Context
// UUID identifies the upload instance for the current request.
UUID string
Upload storage.LayerUpload
State layerUploadState
}
// StartLayerUpload begins the layer upload process and allocates a server-
// side upload session.
func (luh *layerUploadHandler) StartLayerUpload(w http.ResponseWriter, r *http.Request) {
layers := luh.Repository.Layers()
upload, err := layers.Upload()
if err != nil {
w.WriteHeader(http.StatusInternalServerError) // Error conditions here?
luh.Errors.Push(v2.ErrorCodeUnknown, err)
return
}
luh.Upload = upload
defer luh.Upload.Close()
if err := luh.layerUploadResponse(w, r); err != nil {
w.WriteHeader(http.StatusInternalServerError) // Error conditions here?
luh.Errors.Push(v2.ErrorCodeUnknown, err)
return
}
w.WriteHeader(http.StatusAccepted)
}
// GetUploadStatus returns the status of a given upload, identified by uuid.
func (luh *layerUploadHandler) GetUploadStatus(w http.ResponseWriter, r *http.Request) {
if luh.Upload == nil {
w.WriteHeader(http.StatusNotFound)
luh.Errors.Push(v2.ErrorCodeBlobUploadUnknown)
return
}
if err := luh.layerUploadResponse(w, r); err != nil {
w.WriteHeader(http.StatusInternalServerError) // Error conditions here?
luh.Errors.Push(v2.ErrorCodeUnknown, err)
return
}
w.WriteHeader(http.StatusNoContent)
}
// PutLayerUploadComplete takes the final request of a layer upload. The final
// chunk may include all the layer data, the final chunk of layer data or no
// layer data. Any data provided is received and verified. If successful, the
// layer is linked into the blob store and 201 Created is returned with the
// canonical url of the layer.
func (luh *layerUploadHandler) PutLayerUploadComplete(w http.ResponseWriter, r *http.Request) {
if luh.Upload == nil {
w.WriteHeader(http.StatusNotFound)
luh.Errors.Push(v2.ErrorCodeBlobUploadUnknown)
return
}
dgstStr := r.FormValue("digest") // TODO(stevvooe): Support multiple digest parameters!
if dgstStr == "" {
// no digest? return error, but allow retry.
w.WriteHeader(http.StatusNotFound)
luh.Errors.Push(v2.ErrorCodeDigestInvalid, "digest missing")
return
}
dgst, err := digest.ParseDigest(dgstStr)
if err != nil {
// no digest? return error, but allow retry.
w.WriteHeader(http.StatusNotFound)
luh.Errors.Push(v2.ErrorCodeDigestInvalid, "digest parsing failed")
return
}
// TODO(stevvooe): Check the incoming range header here, per the
// specification. LayerUpload should be seeked (sought?) to that position.
// Read in the final chunk, if any.
io.Copy(luh.Upload, r.Body)
layer, err := luh.Upload.Finish(dgst)
if err != nil {
switch err := err.(type) {
case storage.ErrLayerInvalidDigest:
w.WriteHeader(http.StatusBadRequest)
luh.Errors.Push(v2.ErrorCodeDigestInvalid, err)
default:
luh.log.Errorf("unknown error completing upload: %#v", err)
w.WriteHeader(http.StatusInternalServerError)
luh.Errors.Push(v2.ErrorCodeUnknown, err)
}
// Clean up the backend layer data if there was an error.
if err := luh.Upload.Cancel(); err != nil {
// If the cleanup fails, all we can do is observe and report.
luh.log.Errorf("error canceling upload after error: %v", err)
}
return
}
// Build our canonical layer url
layerURL, err := luh.urlBuilder.BuildBlobURL(layer.Name(), layer.Digest())
if err != nil {
luh.Errors.Push(v2.ErrorCodeUnknown, err)
w.WriteHeader(http.StatusInternalServerError)
return
}
w.Header().Set("Location", layerURL)
w.Header().Set("Content-Length", "0")
w.WriteHeader(http.StatusCreated)
}
// CancelLayerUpload cancels an in-progress upload of a layer.
func (luh *layerUploadHandler) CancelLayerUpload(w http.ResponseWriter, r *http.Request) {
if luh.Upload == nil {
w.WriteHeader(http.StatusNotFound)
luh.Errors.Push(v2.ErrorCodeBlobUploadUnknown)
return
}
if err := luh.Upload.Cancel(); err != nil {
luh.log.Errorf("error encountered canceling upload: %v", err)
w.WriteHeader(http.StatusInternalServerError)
luh.Errors.PushErr(err)
}
w.WriteHeader(http.StatusNoContent)
}
// layerUploadResponse provides a standard request for uploading layers and
// chunk responses. This sets the correct headers but the response status is
// left to the caller.
func (luh *layerUploadHandler) layerUploadResponse(w http.ResponseWriter, r *http.Request) error {
offset, err := luh.Upload.Seek(0, os.SEEK_CUR)
if err != nil {
luh.log.Errorf("unable get current offset of layer upload: %v", err)
return err
}
// TODO(stevvooe): Need a better way to manage the upload state automatically.
luh.State.Name = luh.Repository.Name()
luh.State.UUID = luh.Upload.UUID()
luh.State.Offset = offset
luh.State.StartedAt = luh.Upload.StartedAt()
token, err := hmacKey(luh.Config.HTTP.Secret).packUploadState(luh.State)
if err != nil {
logrus.Infof("error building upload state token: %s", err)
return err
}
uploadURL, err := luh.urlBuilder.BuildBlobUploadChunkURL(
luh.Upload.Name(), luh.Upload.UUID(),
url.Values{
"_state": []string{token},
})
if err != nil {
logrus.Infof("error building upload url: %s", err)
return err
}
w.Header().Set("Location", uploadURL)
w.Header().Set("Content-Length", "0")
w.Header().Set("Range", fmt.Sprintf("0-%d", luh.State.Offset))
return nil
}