mirror of
https://gitea.com/gitea/runner.git
synced 2026-08-27 22:37:46 +00:00
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:
@@ -17,7 +17,7 @@ import (
|
||||
"gitea.dev/actionslib/runner/v1/runnerv1connect"
|
||||
)
|
||||
|
||||
func getHTTPClient(endpoint string, insecure bool) *http.Client {
|
||||
func getHTTPClient(endpoint string, insecure bool, timeout time.Duration) *http.Client {
|
||||
transport := &http.Transport{
|
||||
Proxy: http.ProxyFromEnvironment,
|
||||
MaxIdleConns: 10,
|
||||
@@ -29,11 +29,13 @@ func getHTTPClient(endpoint string, insecure bool) *http.Client {
|
||||
InsecureSkipVerify: true,
|
||||
}
|
||||
}
|
||||
return &http.Client{Transport: transport}
|
||||
return &http.Client{Transport: transport, Timeout: timeout}
|
||||
}
|
||||
|
||||
// New returns a new runner client.
|
||||
func New(endpoint string, insecure bool, uuid, token string, opts ...connect.ClientOption) *HTTPClient {
|
||||
// New returns a new runner client. timeout bounds every RPC: without it a
|
||||
// stalled connection parks the reporter for the whole job context, so logs and
|
||||
// heartbeats stop together and the task is reaped as a zombie.
|
||||
func New(endpoint string, insecure bool, uuid, token string, timeout time.Duration, opts ...connect.ClientOption) *HTTPClient {
|
||||
baseURL := strings.TrimRight(endpoint, "/") + "/api/actions"
|
||||
|
||||
opts = append(opts, connect.WithInterceptors(connect.UnaryInterceptorFunc(func(next connect.UnaryFunc) connect.UnaryFunc {
|
||||
@@ -49,7 +51,7 @@ func New(endpoint string, insecure bool, uuid, token string, opts ...connect.Cli
|
||||
}
|
||||
})))
|
||||
|
||||
httpClient := getHTTPClient(endpoint, insecure)
|
||||
httpClient := getHTTPClient(endpoint, insecure, timeout)
|
||||
return &HTTPClient{
|
||||
PingServiceClient: pingv1connect.NewPingServiceClient(
|
||||
httpClient,
|
||||
|
||||
Reference in New Issue
Block a user