kacerr/egress-proxies-operator
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

kvm2: apply the milestone review

Browse Source 
Shorter start wait with immediate verdicts for dead or paused domains,
ListByTag without state or address RPCs, Timeout for an expired check
round, no adoption of unmarked domains, reference-counted keyed locks,
dead options removed, HEAD fallback on any non-2xx.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
This commit is contained in:
kacerr
2026-09-16 21:19:50 +00:00
co-authored by Claude Fable 5.1
parent fcbf8ddc91
commit 2510842396
21 changed files with 586 additions and 254 deletions
Download Patch File Download Diff File Expand all files Collapse all files
internal/provider/kvm2/image.go
+15 -22
View File
@@ -66,24 +66,15 @@ func resolveImage(cfg provider.KVMConfig, image string) (imageSource, error) {
}
// lockImage takes the per-(host, volume) lock of spec entry 19, or gives up
// with ctx. The lock is a one-slot channel rather than a mutex so a caller
// whose ctx ends while another caller's download runs returns promptly
// (contract §1.5) instead of waiting out a 20-minute transfer.
// with ctx: a caller whose ctx ends while another caller's download runs
// returns promptly (contract §1.5) instead of waiting out a 20-minute
// transfer.
func (p *Provider) lockImage(ctx context.Context, hostName, volume string) (func(), error) {
key := hostName + "/" + volume
p.imageMu.Lock()
sem, ok := p.imageLocks[key]
if !ok {
sem = make(chan struct{}, 1)
p.imageLocks[key] = sem
}
p.imageMu.Unlock()
select {
case sem <- struct{}{}:
return func() { <-sem }, nil
case <-ctx.Done():
return nil, fmt.Errorf("%w: waiting for image %s on host %s: %w", provider.ErrTransient, volume, hostName, ctx.Err())
release, err := p.imageLocks.acquire(ctx, hostName+"/"+volume)
if err != nil {
return nil, fmt.Errorf("%w: waiting for image %s on host %s: %w", provider.ErrTransient, volume, hostName, err)
}
return release, nil
}
// ensureImage makes the base image present and complete in the host's pool
@@ -208,7 +199,7 @@ func deleteVolumeIfPresent(ctx context.Context, be backend, pool libvirt.Storage
// finding no marker, and removing it now frees the space at once.
func (p *Provider) fetchImage(ctx context.Context, host provider.KVMHost, pool libvirt.StoragePool, be backend, src imageSource) (libvirt.StorageVol, error) {
name := src.volumeName()
ctx, cancel := context.WithTimeout(ctx, p.budgets.transfer)
ctx, cancel := context.WithTimeout(ctx, defaultBudgets.transfer)
defer cancel()
ctx, span := tracing.StartSpan(ctx, tracing.Tracer(p.tracing...), "kvm2.download",
trace.WithSpanKind(trace.SpanKindClient),
@@ -337,7 +328,7 @@ func (c *countingReader) state() (int64, error) {
// budget bounds it on its own. Failure is logged, not returned: the next
// attempt finds the volume without a marker and deletes it then.
func (p *Provider) discardVolume(ctx context.Context, log logr.Logger, be backend, pool libvirt.StoragePool, name string) {
ctx, cancel := context.WithTimeout(context.WithoutCancel(ctx), p.budgets.rpc)
ctx, cancel := context.WithTimeout(context.WithoutCancel(ctx), defaultBudgets.rpc)
defer cancel()
if err := deleteVolumeIfPresent(ctx, be, pool, name); err != nil {
log.V(1).Info("incomplete base volume left behind; the next attempt removes it", "error", err.Error())
@@ -421,8 +412,10 @@ func urlHost(rawURL string) string {
// imageSizeIfUncached returns the image's Content-Length when the base is
// not cached on the host, and 0 when the marker is present, for the quota
// precheck of spec entry 13. It never downloads: HEAD first, and a GET whose
// body is closed at once when the server does not allow HEAD. A marker is
// taken at face value here; ensureImage decides whether it still matches.
// body is closed at once when HEAD answers anything but 2xx, since servers
// refuse HEAD with 405, 403 or 501 alike; the GET's status is what gets
// classified. A marker is taken at face value here; ensureImage decides
// whether it still matches.
func (p *Provider) imageSizeIfUncached(ctx context.Context, be backend, pool libvirt.StoragePool, src imageSource) (int64, error) {
_, err := be.StorageVolLookupByName(ctx, pool, src.markerName())
switch {
@@ -431,14 +424,14 @@ func (p *Provider) imageSizeIfUncached(ctx context.Context, be backend, pool lib
case !hasCode(err, libvirt.ErrNoStorageVol):
return 0, fmt.Errorf("looking up marker %s: %w", src.markerName(), err)
}
ctx, cancel := context.WithTimeout(ctx, p.budgets.rpc)
ctx, cancel := context.WithTimeout(ctx, defaultBudgets.rpc)
defer cancel()
resp, err := p.do(ctx, http.MethodHead, src.URL)
if err != nil {
return 0, err
}
_ = resp.Body.Close()
if resp.StatusCode == http.StatusMethodNotAllowed {
if resp.StatusCode < 200 || resp.StatusCode >= 300 {
if resp, err = p.do(ctx, http.MethodGet, src.URL); err != nil {
return 0, err
}