fix: bound blocking calls and stop failing silently (#1174)

Jobs occasionally go silent ([example](https://gitea.com/gitea/runner/actions/runs/805045/jobs/1055123)) mid-run and Gitea reaped them after `ZOMBIE_TASK_TIMEOUT`, with no error in the log. This contains a number of related fixes, all with full test coverage:

1. Bound every RPC to Gitea with a timeout, a stalled report otherwise parked logs and heartbeats for the whole job.
2. Cap `runner.fetch_timeout` at that ceiling.
3. Let only the daemon loop close its own channel, the race panicked the process.
4. Stop the job on any terminal server result, not just `RESULT_CANCELLED`.
5. Report that result instead of relabelling it as cancelled.
6. Log reporting failures once at each end of an outage instead of discarding them.
7. Clamp the acknowledged log index, a too-large ack panicked on a slice bound.
8. Stop reading server health from a `FetchTask` deadline, it marked the runner healthy and reset the error backoff on a timeout.
9. Return an error from the Docker version probe instead of a `logrus` panic.
10. Pass the context to go-git's fetch and pull.
11. Fail the clone when a refresh dies on a cancelled context.
12. Set `terminationGracePeriodSeconds` in the Kubernetes examples.

Also contains a deprecation fix for goreleaser.

Reviewed-on: https://gitea.com/gitea/runner/pulls/1174
Reviewed-by: bircni <bircni@icloud.com>
Co-authored-by: silverwind <me@silverwind.io>
This commit is contained in:
silverwind
2026-08-19 11:13:21 +00:00
committed by silverwind
parent 3f70822458
commit bc8161c673
21 changed files with 422 additions and 63 deletions
+7 -5
View File
@@ -8,6 +8,7 @@ import (
"net/http/httptest"
"strings"
"testing"
"time"
"connectrpc.com/connect"
pingv1 "gitea.dev/actionslib/ping/v1"
@@ -17,7 +18,8 @@ import (
func TestGetHTTPClientUsesProxyFromEnvironment(t *testing.T) {
t.Setenv("HTTP_PROXY", "http://proxy.example.com:8080")
client := getHTTPClient("http://gitea.example.com", false)
client := getHTTPClient("http://gitea.example.com", false, time.Minute)
require.Equal(t, time.Minute, client.Timeout)
transport, ok := client.Transport.(*http.Transport)
require.True(t, ok)
@@ -32,7 +34,7 @@ func TestGetHTTPClientUsesProxyFromEnvironment(t *testing.T) {
func TestGetHTTPClientInsecureTLS(t *testing.T) {
// insecure only takes effect for https endpoints
httpsInsecure := getHTTPClient("https://gitea.example.com", true)
httpsInsecure := getHTTPClient("https://gitea.example.com", true, time.Minute)
transport, ok := httpsInsecure.Transport.(*http.Transport)
require.True(t, ok)
require.NotNil(t, transport.TLSClientConfig)
@@ -47,7 +49,7 @@ func TestGetHTTPClientInsecureTLS(t *testing.T) {
{"http insecure ignored", "http://gitea.example.com", true},
} {
t.Run(tc.name, func(t *testing.T) {
c := getHTTPClient(tc.endpoint, tc.insecure)
c := getHTTPClient(tc.endpoint, tc.insecure, time.Minute)
tr, ok := c.Transport.(*http.Transport)
require.True(t, ok)
require.Nil(t, tr.TLSClientConfig)
@@ -66,7 +68,7 @@ func TestNewSetsBaseURLAndHeaders(t *testing.T) {
defer server.Close()
// trailing slash must be trimmed before "/api/actions" is appended
c := New(server.URL+"/", false, "the-uuid", "the-token")
c := New(server.URL+"/", false, "the-uuid", "the-token", time.Minute)
// Address returns the endpoint as supplied (untrimmed)
require.Equal(t, server.URL+"/", c.Address())
require.False(t, c.Insecure())
@@ -87,7 +89,7 @@ func TestNewOmitsEmptyHeaders(t *testing.T) {
}))
defer server.Close()
c := New(server.URL, false, "", "")
c := New(server.URL, false, "", "", time.Minute)
_, _ = c.Ping(t.Context(), connect.NewRequest(&pingv1.PingRequest{Data: "hi"}))
require.Empty(t, gotHeaders.Get(UUIDHeader))