fix(gitea): improve retry logic precision for net.OpError
PR Ready Gate / clear-labels (pull_request) Successful in 2s
CI / test (pull_request) Successful in 17s
CI / review (anthropic--claude-4.6-sonnet, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 46s
CI / review (gpt-5, security, SECURITY_REVIEW.md, SECURITY_REVIEW_TOKEN) (pull_request) Successful in 1m11s
CI / review (gpt-5, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 1m23s
PR Ready Gate / clear-labels (pull_request) Successful in 2s
CI / test (pull_request) Successful in 17s
CI / review (anthropic--claude-4.6-sonnet, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 46s
CI / review (gpt-5, security, SECURITY_REVIEW.md, SECURITY_REVIEW_TOKEN) (pull_request) Successful in 1m11s
CI / review (gpt-5, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 1m23s
Address review feedback on isTemporaryNetError being too broad: 1. RetryBackoff field: Added doc comment clarifying it must be configured before the first request (addresses concurrency concern). 2. isTemporaryNetError: Now inspects the underlying syscall error instead of treating all net.OpError as retriable. Only retries on: - ECONNREFUSED (connection refused) - ECONNRESET (connection reset) - ENETUNREACH (network unreachable) - EHOSTUNREACH (host unreachable) - ETIMEDOUT (connection timed out) Permanent errors like EACCES, EPERM are no longer retried. 3. DNS errors: Changed from Temporary() to IsTimeout, since "no such host" is permanent and shouldn't be retried. 4. Empty backoff slice: Added comment explaining that retry without delay is intentional when caller explicitly configures it. Addresses MINOR findings from sonnet-review-bot and gpt-review-bot.
This commit is contained in:
+44
-9
@@ -15,6 +15,7 @@ import (
|
||||
"net/http"
|
||||
"net/url"
|
||||
"strings"
|
||||
"syscall"
|
||||
"time"
|
||||
)
|
||||
|
||||
@@ -56,6 +57,9 @@ type Client struct {
|
||||
// RetryBackoff defines the delays between retry attempts.
|
||||
// RetryBackoff[i] is the delay before attempt i+1 (after attempt i fails).
|
||||
// If nil, defaults to {1s, 2s}. Set to shorter durations in tests.
|
||||
//
|
||||
// This field must be configured before the first request is made.
|
||||
// Modifying it while requests are in flight is not safe.
|
||||
RetryBackoff []time.Duration
|
||||
}
|
||||
|
||||
@@ -223,25 +227,25 @@ func (c *Client) PostReview(ctx context.Context, owner, repo string, number int,
|
||||
}
|
||||
|
||||
// isTemporaryNetError reports whether err is a temporary network error worth retrying.
|
||||
// This includes connection refused, DNS failures, and timeouts that aren't context-based.
|
||||
// This includes connection refused, network unreachable, connection reset, and DNS
|
||||
// timeouts. It explicitly excludes permanent errors like permission denied or
|
||||
// "no such host" DNS failures.
|
||||
func isTemporaryNetError(err error) bool {
|
||||
if err == nil {
|
||||
return false
|
||||
}
|
||||
|
||||
// Check for common retriable error patterns in the error chain.
|
||||
// Check OpError first since it embeds net.Error, and we want to catch
|
||||
// connection refused, network unreachable, etc. as retriable.
|
||||
// Check for OpError and inspect the underlying syscall error.
|
||||
// Not all OpErrors are transient — permission denied, for example, is permanent.
|
||||
var opErr *net.OpError
|
||||
if errors.As(err, &opErr) {
|
||||
// Connection refused, network unreachable, etc. are typically transient
|
||||
return true
|
||||
return isRetriableSyscallError(opErr.Err)
|
||||
}
|
||||
|
||||
// DNS errors are often transient
|
||||
// DNS errors: only retry on timeout, not on "no such host" which is permanent.
|
||||
var dnsErr *net.DNSError
|
||||
if errors.As(err, &dnsErr) {
|
||||
return dnsErr.Temporary()
|
||||
return dnsErr.IsTimeout
|
||||
}
|
||||
|
||||
// Check for net.Error with Timeout() (Temporary is deprecated)
|
||||
@@ -253,6 +257,35 @@ func isTemporaryNetError(err error) bool {
|
||||
return false
|
||||
}
|
||||
|
||||
// isRetriableSyscallError reports whether the underlying error from a net.OpError
|
||||
// is a transient syscall error worth retrying.
|
||||
func isRetriableSyscallError(err error) bool {
|
||||
if err == nil {
|
||||
return false
|
||||
}
|
||||
|
||||
// Check for syscall.Errno directly or wrapped
|
||||
var errno syscall.Errno
|
||||
if errors.As(err, &errno) {
|
||||
switch errno {
|
||||
case syscall.ECONNREFUSED, // connection refused — server not listening
|
||||
syscall.ECONNRESET, // connection reset by peer
|
||||
syscall.ENETUNREACH, // network unreachable
|
||||
syscall.EHOSTUNREACH, // host unreachable
|
||||
syscall.ETIMEDOUT: // connection timed out
|
||||
return true
|
||||
default:
|
||||
// EACCES, EPERM, etc. are permanent — don't retry
|
||||
return false
|
||||
}
|
||||
}
|
||||
|
||||
// If we can't identify the specific syscall error, be conservative and retry.
|
||||
// This handles wrapped errors or platform-specific error types.
|
||||
// The retry count is limited, so erring on the side of retrying is safe.
|
||||
return true
|
||||
}
|
||||
|
||||
// doGet performs an HTTP GET request with retry on 5xx errors and temporary
|
||||
// network errors. Retries up to 3 times with exponential backoff (1s, 2s delays
|
||||
// by default; configurable via Client.RetryBackoff for testing).
|
||||
@@ -272,7 +305,9 @@ func (c *Client) doGet(ctx context.Context, reqURL string) ([]byte, error) {
|
||||
var lastErr error
|
||||
for attempt := 0; attempt < maxAttempts; attempt++ {
|
||||
if attempt > 0 {
|
||||
// Determine delay: use backoff slice if available, otherwise no delay
|
||||
// Determine delay: use backoff slice if available, otherwise retry immediately.
|
||||
// An empty RetryBackoff slice means "retry without delay" — this is intentional
|
||||
// as the caller explicitly configured no delays.
|
||||
var delay time.Duration
|
||||
if attempt-1 < len(backoff) {
|
||||
delay = backoff[attempt-1]
|
||||
|
||||
Reference in New Issue
Block a user