Files
egress-proxies-operator/internal/provider/kvm/errors.go
T
kacerrandClaude Fable 5.1 f50d30e58e Trace every libvirt call in the KVM provider at V(1), visible in the integration test
A tracingAPI decorator wraps the 17-method libvirt seam and logs one
"libvirt call" line per RPC after it returns: method, the identifiers it
was given, curated results, duration, and on failure the error with its
libvirt code, name and message. At V(2) the same line carries the domain
and volume XML, metadata and addresses; upload bodies are never logged.
The pool applies it in call() when V(1) is enabled and logs connect,
dial-failure and drop events, taking the caller's logger explicitly like
every other helper in the package.

The integration test installs a testr logger at KVM_TEST_LOG_LEVEL
(default 1) so the trace interleaves with t.Log output, which also ends
the "log.SetLogger(...) was never called" warning. Docs gained a Logging
section and the test env var; the KVM provider execution log records run
4 (guest hang at GRUB) that prompted this.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-10 19:13:51 +00:00

84 lines
2.9 KiB
Go

package kvm
import (
"errors"
libvirt "github.com/digitalocean/go-libvirt"
"github.com/go-logr/logr"
"gitea.home.hrajfrisbee.cz/kacerr/egress-proxies-operator/internal/provider"
)
// classify maps an error onto the provider taxonomy. Errors the package
// already tagged with a sentinel (image download failures, placement
// errors) keep their class. For libvirt errors: missing domain or volume →
// NotFound; anything the host will keep rejecting (bad XML, unsupported
// config, denied access, missing pool) → Permanent; every other libvirt
// code, plus SSH/transport failures and cancellation, → Transient, because
// retrying is safer than latching Failed on an error nobody taught this
// function to recognise. libvirt exposes no quota signal, so nothing maps
// to QuotaExceeded.
func classify(err error) error {
for _, class := range []error{provider.ErrNotFound, provider.ErrQuotaExceeded, provider.ErrPermanent, provider.ErrTransient} {
if errors.Is(err, class) {
return class
}
}
var lerr libvirt.Error
if !errors.As(err, &lerr) {
return provider.ErrTransient
}
switch libvirt.ErrorNumber(lerr.Code) {
case libvirt.ErrNoDomain, libvirt.ErrNoStorageVol:
return provider.ErrNotFound
case libvirt.ErrNoStoragePool,
libvirt.ErrXMLError, libvirt.ErrXMLDetail, libvirt.ErrXMLInvalidSchema,
libvirt.ErrConfigUnsupported, libvirt.ErrNoSupport,
libvirt.ErrOperationUnsupported, libvirt.ErrArgumentUnsupported,
libvirt.ErrInvalidArg,
libvirt.ErrAuthFailed, libvirt.ErrAccessDenied, libvirt.ErrOperationDenied:
return provider.ErrPermanent
default:
return provider.ErrTransient
}
}
// isLibvirtError reports whether err came back from the libvirt daemon (as
// opposed to the SSH or RPC transport), which is what decides whether the
// cached connection is still trustworthy.
func isLibvirtError(err error) bool {
var lerr libvirt.Error
return errors.As(err, &lerr)
}
func hasCode(err error, code libvirt.ErrorNumber) bool {
var lerr libvirt.Error
return errors.As(err, &lerr) && libvirt.ErrorNumber(lerr.Code) == code
}
// logAPIError records the raw libvirt code and message at V(1); classify
// collapses them onto the coarser taxonomy, so this is the only place the
// original detail survives.
func logAPIError(log logr.Logger, op string, err error) {
if !log.V(1).Enabled() {
return
}
kv := append([]any{"op", op, "error", err.Error()}, libvirtErrorFields(err)...)
log.V(1).Info("libvirt call failed", kv...)
}
// libvirtErrorFields renders a daemon-reported error as log key/values:
// the numeric code, its constant name (ErrNoDomain, ...) and the daemon's
// message. Nil for transport and other non-libvirt errors.
func libvirtErrorFields(err error) []any {
var lerr libvirt.Error
if !errors.As(err, &lerr) {
return nil
}
return []any{
"libvirtCode", lerr.Code,
"libvirtCodeName", libvirt.ErrorNumber(lerr.Code).String(),
"libvirtMessage", lerr.Message,
}
}