Files
seaweedfs/weed/server/filer_server_handlers.go
T
Chris LuandClaude Opus 5.5 fcfca3fee3 s3, filer: bound the wait for an upload slot (#12559)
* util: add WaitUntil, a cond wait bounded by a context and a timeout

The caller holds the cond lock. Cancellation and the timeout wake the
waiter through a broadcast taken under the same lock, so no wakeup is lost.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* s3: bound the wait for an upload slot

A PUT that arrived while the concurrent upload limits were exhausted waited
on the condition variable with no bound. The handler reads nothing from the
body while it waits, so a client that gave up and reset its connection went
unnoticed: the socket and goroutine stayed pinned until a slot freed, and a
stalled volume server grew the gateway's fd count by one per aborted PUT.

The wait now ends on InflightUploadDataTimeout with 503 SlowDown, which S3
SDKs retry, and on request cancellation. An admitted upload takes its slot
under the lock, and a finished upload broadcasts, so freed bytes admit every
waiter that fits instead of one.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* filer: bound the wait for an upload slot

The filer's PUT/POST upload limits queued requests the same unbounded way.
Reuse the bounded wait: reject with 429 after InflightUploadDataTimeout, as
the volume server does, and stop on request cancellation.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* command: add -inflightUploadDataTimeout for the S3 gateway and the filer

weed s3 -inflightUploadDataTimeout, weed filer -inflightUploadDataTimeout and
-s3.inflightUploadDataTimeout, weed server and weed mini
-filer.inflightUploadDataTimeout and -s3.inflightUploadDataTimeout. The
default of 60s matches the volume server's flag of the same name; 0 keeps
the old unbounded wait.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* s3: reject a queued upload without reading its body

WriteErrorResponse drains the request body before answering. Behind the
stats recorder the drain has no read deadline, and reading the body sends an
Expect: 100-continue client the go-ahead to upload what is about to be
discarded. Answer the rejection with an empty-body copy of the request so
the drain is skipped; net/http closes the connection when a large unread
body remains.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* s3, filer: release an upload slot under the cond lock

A waiter checks the counters under the cond lock and then waits. A release
that decremented and broadcast without the lock could land between the two,
so the waiter slept with a slot free until the next release or its timeout.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* s3, filer: close the HTTP/1 connection when rejecting a queued upload

net/http reads up to 256 KiB of an unread request body before sending a
keep-alive reply, so a client that stalls its body held back the 503 or
429 until the connection idle timeout. Connection: close skips that read.
HTTP/2 is left alone: there it would shut down the whole connection.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 10:17:18 -08:00

402 lines
13 KiB
Go

package weed_server
import (
"context"
"errors"
"fmt"
"net/http"
"path"
"strconv"
"strings"
"sync/atomic"
"time"
"github.com/seaweedfs/seaweedfs/weed/filer"
"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/util/version"
)
func (fs *FilerServer) filerHandler(w http.ResponseWriter, r *http.Request) {
start := time.Now()
inFlightGauge := stats.FilerInFlightRequestsGauge.WithLabelValues(r.Method)
inFlightGauge.Inc()
defer inFlightGauge.Dec()
statusRecorder := stats.NewStatusResponseWriter(w)
w = statusRecorder
origin := r.Header.Get("Origin")
if origin != "" {
if fs.option.AllowedOrigins == nil || len(fs.option.AllowedOrigins) == 0 || fs.option.AllowedOrigins[0] == "*" {
origin = "*"
} else {
originFound := false
for _, allowedOrigin := range fs.option.AllowedOrigins {
if origin == allowedOrigin {
originFound = true
}
}
if !originFound {
writeJsonError(w, r, http.StatusForbidden, errors.New("origin not allowed"))
return
}
}
w.Header().Set("Access-Control-Allow-Origin", origin)
w.Header().Set("Access-Control-Expose-Headers", "*")
w.Header().Set("Access-Control-Allow-Headers", "*")
w.Header().Set("Access-Control-Allow-Credentials", "true")
w.Header().Set("Access-Control-Allow-Methods", "PUT, POST, GET, DELETE, OPTIONS")
}
if r.Method == http.MethodOptions {
OptionsHandler(w, r, false)
return
}
requestMethod := r.Method
defer func(method *string) {
stats.FilerRequestCounter.WithLabelValues(*method, strconv.Itoa(statusRecorder.Status)).Inc()
stats.FilerRequestHistogram.WithLabelValues(*method).Observe(time.Since(start).Seconds())
}(&requestMethod)
isReadHttpCall := r.Method == http.MethodGet || r.Method == http.MethodHead
if !fs.maybeCheckJwtAuthorization(r, !isReadHttpCall) {
writeJsonError(w, r, http.StatusUnauthorized, errors.New("wrong jwt"))
return
}
// proxy to volume servers, after the gate: this is the one port operators
// expose, and the branch reaches any needle in the cluster by file id.
if r.URL.Path == "/" {
if fileId := r.URL.Query().Get(util_http.ProxyChunkIdParam); fileId != "" {
fs.proxyToVolumeServer(w, r, fileId)
stats.FilerHandlerCounter.WithLabelValues(stats.ChunkProxy).Inc()
// Name the deferred observation after the proxy rather than
// observing a second time, which would count the request twice.
requestMethod = stats.ChunkProxy
return
}
}
w.Header().Set("Server", "SeaweedFS "+version.VERSION)
switch r.Method {
case http.MethodGet, http.MethodHead:
fs.GetOrHeadHandler(w, r)
case http.MethodDelete:
if _, ok := r.URL.Query()["tagging"]; ok {
fs.DeleteTaggingHandler(w, r)
} else {
fs.DeleteHandler(w, r)
}
case http.MethodPost, http.MethodPut:
// wait until in flight data is less than the limit
contentLength := getContentLength(r)
if !fs.waitForUploadSlot(w, r, contentLength) {
return
}
defer func() {
fs.inFlightDataLimitCond.L.Lock()
defer fs.inFlightDataLimitCond.L.Unlock()
// Decrement counters
newUploads := atomic.AddInt64(&fs.inFlightUploads, -1)
newSize := atomic.AddInt64(&fs.inFlightDataSize, -contentLength)
// Update metrics
stats.FilerInFlightUploadCountGauge.Set(float64(newUploads))
stats.FilerInFlightUploadBytesGauge.Set(float64(newSize))
fs.inFlightDataLimitCond.Broadcast()
}()
if r.Method == http.MethodPut {
if _, ok := r.URL.Query()["tagging"]; ok {
fs.PutTaggingHandler(w, r)
} else {
fs.PostHandler(w, r, contentLength)
}
} else { // method == "POST"
fs.PostHandler(w, r, contentLength)
}
default:
requestMethod = "INVALID"
w.WriteHeader(http.StatusMethodNotAllowed)
}
}
func (fs *FilerServer) waitForUploadSlot(w http.ResponseWriter, r *http.Request, contentLength int64) bool {
fs.inFlightDataLimitCond.L.Lock()
err := util.WaitUntil(r.Context(), fs.inFlightDataLimitCond, fs.option.InflightUploadDataTimeout, func() bool {
inFlightDataSize := atomic.LoadInt64(&fs.inFlightDataSize)
if fs.option.ConcurrentUploadLimit != 0 && inFlightDataSize > fs.option.ConcurrentUploadLimit {
glog.V(4).Infof("wait because inflight data %d > %d", inFlightDataSize, fs.option.ConcurrentUploadLimit)
return false
}
inFlightUploads := atomic.LoadInt64(&fs.inFlightUploads)
if fs.option.ConcurrentFileUploadLimit != 0 && inFlightUploads >= fs.option.ConcurrentFileUploadLimit {
glog.V(4).Infof("wait because inflight uploads %d >= %d", inFlightUploads, fs.option.ConcurrentFileUploadLimit)
return false
}
return true
})
if err == nil {
// Increment counters
newUploads := atomic.AddInt64(&fs.inFlightUploads, 1)
newSize := atomic.AddInt64(&fs.inFlightDataSize, contentLength)
// Update metrics
stats.FilerInFlightUploadCountGauge.Set(float64(newUploads))
stats.FilerInFlightUploadBytesGauge.Set(float64(newSize))
}
fs.inFlightDataLimitCond.L.Unlock()
if err == nil {
return true
}
// Closing an HTTP/1 connection stops net/http from reading the unread
// body before the reply.
if r.ProtoMajor == 1 {
w.Header().Set("Connection", "close")
}
if r.Context().Err() != nil {
glog.V(1).Infof("upload from %s cancelled while waiting for an upload slot: %v", r.RemoteAddr, err)
writeJsonError(w, r, util.HttpStatusCancelled, r.Context().Err())
return false
}
err = fmt.Errorf("reject because no upload slot freed within %v", fs.option.InflightUploadDataTimeout)
glog.V(1).Infof("too many requests from %s: %v", r.RemoteAddr, err)
writeJsonError(w, r, http.StatusTooManyRequests, err)
return false
}
func (fs *FilerServer) readonlyFilerHandler(w http.ResponseWriter, r *http.Request) {
start := time.Now()
statusRecorder := stats.NewStatusResponseWriter(w)
w = statusRecorder
glog.V(4).Infof("Request: %s %s", r.Method, r.URL.Path)
origin := r.Header.Get("Origin")
if origin != "" {
if fs.option.AllowedOrigins == nil || len(fs.option.AllowedOrigins) == 0 || fs.option.AllowedOrigins[0] == "*" {
origin = "*"
} else {
originFound := false
for _, allowedOrigin := range fs.option.AllowedOrigins {
if origin == allowedOrigin {
originFound = true
}
}
if !originFound {
writeJsonError(w, r, http.StatusForbidden, errors.New("origin not allowed"))
return
}
}
w.Header().Set("Access-Control-Allow-Origin", origin)
w.Header().Set("Access-Control-Allow-Headers", "OPTIONS, GET, HEAD")
w.Header().Set("Access-Control-Allow-Credentials", "true")
}
requestMethod := r.Method
defer func(method *string) {
stats.FilerRequestCounter.WithLabelValues(*method, strconv.Itoa(statusRecorder.Status)).Inc()
stats.FilerRequestHistogram.WithLabelValues(*method).Observe(time.Since(start).Seconds())
}(&requestMethod)
// We handle OPTIONS first because it never should be authenticated
if r.Method == http.MethodOptions {
OptionsHandler(w, r, true)
return
}
if !fs.maybeCheckJwtAuthorization(r, false) {
writeJsonError(w, r, http.StatusUnauthorized, errors.New("wrong jwt"))
return
}
w.Header().Set("Server", "SeaweedFS "+version.VERSION)
switch r.Method {
case http.MethodGet, http.MethodHead:
fs.GetOrHeadHandler(w, r.WithContext(context.WithValue(r.Context(), readOnlyListingKey{}, true)))
default:
requestMethod = "INVALID"
w.WriteHeader(http.StatusMethodNotAllowed)
}
}
func OptionsHandler(w http.ResponseWriter, r *http.Request, isReadOnly bool) {
if isReadOnly {
w.Header().Set("Access-Control-Allow-Methods", "GET, OPTIONS")
} else {
w.Header().Set("Access-Control-Allow-Methods", "PUT, POST, GET, DELETE, OPTIONS")
w.Header().Set("Access-Control-Expose-Headers", "*")
}
w.Header().Set("Access-Control-Allow-Headers", "*")
w.Header().Set("Access-Control-Allow-Credentials", "true")
}
// maybeCheckJwtAuthorization returns true if access should be granted, false if it should be denied
func (fs *FilerServer) maybeCheckJwtAuthorization(r *http.Request, isWrite bool) bool {
return fs.checkJwtAuthorization(r, isWrite, jwtScopedRequestPaths(r))
}
// checkJwtAuthorization verifies the request carries a valid filer JWT for the
// requested access level and, for prefix-restricted tokens, that every path in
// scopedPaths falls within AllowedPrefixes.
func (fs *FilerServer) checkJwtAuthorization(r *http.Request, isWrite bool, scopedPaths []string) bool {
claims, ok := fs.authenticateFilerJwt(r, isWrite)
if !ok {
return false
}
return authorizeFilerJwtPaths(r, claims, scopedPaths)
}
// authenticateFilerJwt verifies the JWT signature and method claims. A nil claims
// with ok true means authentication is disabled for this access level. Splitting
// authentication from path authorization lets a handler load an indirect resource
// (the TUS session target) only after the caller's credential is verified.
func (fs *FilerServer) authenticateFilerJwt(r *http.Request, isWrite bool) (*security.SeaweedFilerClaims, bool) {
var signingKey security.SigningKey
if isWrite {
signingKey = fs.filerGuard.SigningKey()
} else {
signingKey = fs.filerGuard.ReadSigningKey()
}
if len(signingKey) == 0 {
return nil, true
}
tokenStr := security.GetJwt(r)
if tokenStr == "" {
glog.V(1).Infof("missing jwt from %s", r.RemoteAddr)
return nil, false
}
token, err := security.DecodeJwt(signingKey, tokenStr, &security.SeaweedFilerClaims{})
if err != nil {
glog.V(1).Infof("jwt verification error from %s: %v", r.RemoteAddr, err)
return nil, false
}
if !token.Valid {
glog.V(1).Infof("jwt invalid from %s: %v", r.RemoteAddr, tokenStr)
return nil, false
}
claims, ok := token.Claims.(*security.SeaweedFilerClaims)
if !ok {
glog.V(1).Infof("jwt claims not of type *SeaweedFilerClaims from %s", r.RemoteAddr)
return nil, false
}
if claims.SessionId != "" {
glog.V(1).Infof("jwt is an STS session token, not a filer credential, from %s", r.RemoteAddr)
return nil, false
}
if len(claims.AllowedMethods) > 0 {
hasMethod := false
for _, method := range claims.AllowedMethods {
if method == r.Method {
hasMethod = true
break
}
}
if !hasMethod {
glog.V(1).Infof("jwt method not allowed from %s: %v", r.RemoteAddr, r.Method)
return nil, false
}
}
return claims, true
}
// authorizeFilerJwtPaths checks the resource scope after authentication. A
// prefix-restricted token must name at least one resource path; an empty list
// fails closed, so a caller that cannot resolve its target never falls open.
func authorizeFilerJwtPaths(r *http.Request, claims *security.SeaweedFilerClaims, scopedPaths []string) bool {
if claims == nil || len(claims.AllowedPrefixes) == 0 {
return true
}
if len(scopedPaths) == 0 {
glog.V(1).Infof("jwt resource path missing from %s", r.RemoteAddr)
return false
}
for _, p := range scopedPaths {
if !anyComponentPrefixMatches(claims.AllowedPrefixes, p) {
glog.V(1).Infof("jwt path not allowed from %s: %v", r.RemoteAddr, p)
return false
}
}
return true
}
// jwtScopedRequestPaths returns every filer path a request touches that must be
// covered by the JWT AllowedPrefixes: the write target (r.URL.Path), the
// directory a zip extract writes under, and any copy/move source named by the
// cp.from / mv.from query parameters.
func jwtScopedRequestPaths(r *http.Request) []string {
paths := []string{r.URL.Path}
if (r.Method == http.MethodPost || r.Method == http.MethodPut) && isExtractZip(r) {
paths = append(paths, extractZipRoot(r)+"/")
}
if query := r.URL.Query(); query.Has("cp.from") || query.Has("mv.from") {
if from := query.Get("cp.from"); from != "" {
paths = append(paths, from)
}
if from := query.Get("mv.from"); from != "" {
paths = append(paths, from)
}
}
return paths
}
// anyComponentPrefixMatches reports whether p is within any of the prefixes.
func anyComponentPrefixMatches(prefixes []string, p string) bool {
for _, prefix := range prefixes {
if pathHasComponentPrefix(p, prefix) {
return true
}
}
return false
}
// pathHasComponentPrefix reports whether reqPath is contained within the
// directory subtree denoted by prefix, treating both as "/"-separated
// path components. Both inputs are normalised with path.Clean to neutralise
// "." and ".." segments and collapse duplicate slashes. A prefix of "/"
// matches any path.
func pathHasComponentPrefix(reqPath, prefix string) bool {
if prefix == "" {
return false
}
cleanedPath := path.Clean(reqPath)
if cleanedPath == "." {
cleanedPath = "/"
}
cleanedPrefix := path.Clean(prefix)
if cleanedPrefix == "." {
cleanedPrefix = "/"
}
if cleanedPrefix == "/" {
return true
}
if cleanedPath == cleanedPrefix {
return true
}
return strings.HasPrefix(cleanedPath, cleanedPrefix+"/")
}
func (fs *FilerServer) filerHealthzHandler(w http.ResponseWriter, r *http.Request) {
w.Header().Set("Server", "SeaweedFS "+version.VERSION)
if _, err := fs.filer.Store.FindEntry(context.Background(), filer.TopicsDir); err != nil && err != filer_pb.ErrNotFound {
glog.Warningf("filerHealthzHandler FindEntry: %+v", err)
w.WriteHeader(http.StatusServiceUnavailable)
} else {
w.WriteHeader(http.StatusOK)
}
}