perf(actions): cache successful runner token verification (#39934)

Every Actions runner RPC (`FetchTask` polling, `UpdateTask`,
`UpdateLog`, ...) goes through the `withRunner` interceptor, which
verifies the runner token with PBKDF2 (`auth_model.HashToken`, ~2 ms).
In a 60s CPU profile of a production instance with many runners, this
accounted for ~49% of all CPU samples.

- Cache successful verifications in a dedicated LRU of up to 10000
runners, keyed by the stored salt and hash and holding only a SHA-256
digest of the token. A hit costs ~100 ns.
- The runner is still loaded from the DB on every RPC and failures are
never cached, so deleted runners and wrong tokens never pass.
- The shared `auth_model.TokenCache` is not used because its default 20
entries miss on every poll once more runners poll in turn.

---------

Co-authored-by: silverwind <me@silverwind.io>
This commit is contained in:
Lunny Xiaoandsilverwind authored and GitHub committed 2026-10-23 03:59:11 +00:00
1 parent 6624d96689
commit 5129ad5439
2 files changed
+45 -1

No files matched your search

+19 -1
View File
@@ -5,6 +5,7 @@ package runner
import (
"context"
"crypto/sha256"
"errors"
"strings"
"time"
@@ -17,6 +18,7 @@ import (
"gitea.dev/modules/util"
"connectrpc.com/connect/v2"
lru "github.com/hashicorp/golang-lru/v2"
"google.golang.org/grpc/codes"
"google.golang.org/grpc/status"
)
@@ -26,6 +28,10 @@ const (
tokenHeaderKey = protocol.TokenHeader
)
type runnerTokenHash struct{ salt, hash string }
var verifiedRunnerTokens, _ = lru.New[runnerTokenHash, [sha256.Size]byte](10000) // not auth_model.TokenCache, whose small default size thrashes once more runners poll in turn
// withErrorMessages sends plain errors to runners as CodeUnknown with their message, like connect v1 did.
func withErrorMessages(next connect.ServerFunc) connect.ServerFunc {
return func(ctx context.Context, spec connect.Spec, stream connect.ServerStream) error {
@@ -57,7 +63,7 @@ func withRunner(next connect.ServerFunc) connect.ServerFunc {
}
return status.Error(codes.Internal, err.Error())
}
if !util.CryptoConstTimeEqual(runner.TokenHash, auth_model.HashToken(token, runner.TokenSalt)) {
if !verifyRunnerToken(runner, token) {
return errUnregisteredRunner
}
@@ -88,6 +94,18 @@ func withRunner(next connect.ServerFunc) connect.ServerFunc {
}
}
func verifyRunnerToken(runner *actions_model.ActionRunner, token string) bool {
key, digest := runnerTokenHash{runner.TokenSalt, runner.TokenHash}, sha256.Sum256([]byte(token))
if cached, ok := verifiedRunnerTokens.Get(key); ok && util.CryptoConstTimeEqual(cached[:], digest[:]) {
return true
}
if !util.CryptoConstTimeEqual(runner.TokenHash, auth_model.HashToken(token, runner.TokenSalt)) {
return false
}
verifiedRunnerTokens.Add(key, digest)
return true
}
func getMethodName(spec connect.Spec) string {
splits := strings.Split(spec.Procedure, "/")
if len(splits) > 0 {
@@ -0,0 +1,26 @@
// Copyright 2026 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package runner
import (
"crypto/sha256"
"testing"
actions_model "gitea.dev/models/actions"
auth_model "gitea.dev/models/auth"
"github.com/stretchr/testify/assert"
)
func TestVerifyRunnerToken(t *testing.T) {
verifiedRunnerTokens.Purge()
runner := &actions_model.ActionRunner{TokenSalt: "salt", TokenHash: auth_model.HashToken("token", "salt")}
assert.True(t, verifyRunnerToken(runner, "token"))
assert.True(t, verifyRunnerToken(runner, "token"))
assert.False(t, verifyRunnerToken(runner, "wrong"))
other := &actions_model.ActionRunner{TokenSalt: "salt", TokenHash: auth_model.HashToken("other", "salt")}
assert.False(t, verifyRunnerToken(other, "token"))
assert.Equal(t, [][sha256.Size]byte{sha256.Sum256([]byte("token"))}, verifiedRunnerTokens.Values())
}