Add KVM provider image cache: fetch base images into host pools on first use

resolveImage maps placement.image to a configured key or URL; imageCache
streams the download through StorageVolUpload with a sha256 tee, writes
a marker volume when the upload is verified, and re-fetches when the
marker is missing or the configured checksum changed. Errors carry
taxonomy sentinels that classify now honours. Adds the in-memory fake
libvirt API used from here on.

Step 3b of docs/plans/2026-09-04-1404-kvm-provider.md.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
This commit is contained in:
2026-09-10 19:13:51 +00:00
co-authored by Claude Fable 5.1
parent 6322184d50
commit 6dba33adf2
6 changed files with 1087 additions and 8 deletions
+14 -7
View File
@@ -9,14 +9,21 @@ import (
"gitea.home.hrajfrisbee.cz/kacerr/egress-proxies-operator/internal/provider"
)
// classify maps a libvirt error onto the provider taxonomy. 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.
// 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
+2
View File
@@ -38,6 +38,8 @@ func TestClassify(t *testing.T) {
{"internal error", lvErr(libvirt.ErrInternalError), provider.ErrTransient},
{"storage vol exists", lvErr(libvirt.ErrStorageVolExist), provider.ErrTransient},
{"wrapped libvirt error", fmt.Errorf("defining: %w", lvErr(libvirt.ErrNoDomain)), provider.ErrNotFound},
{"pre-tagged permanent", fmt.Errorf("%w: image returned HTTP 404", provider.ErrPermanent), provider.ErrPermanent},
{"pre-tagged transient wrapping libvirt not-found", fmt.Errorf("%w: %w", provider.ErrTransient, lvErr(libvirt.ErrNoDomain)), provider.ErrTransient},
{"transport eof", io.EOF, provider.ErrTransient},
{"context cancelled", context.Canceled, provider.ErrTransient},
{"plain error", errors.New("ssh: handshake failed"), provider.ErrTransient},
+408
View File
@@ -0,0 +1,408 @@
package kvm
import (
"bytes"
"encoding/xml"
"fmt"
"io"
"slices"
"sync"
libvirt "github.com/digitalocean/go-libvirt"
)
// fakeAPI is an in-memory libvirtAPI: pools of volumes and a set of
// domains, with per-method error injection. It models just enough libvirt
// semantics for the provider's decisions to be observable — ErrStorageVolExist
// on duplicate create, ErrNoDomain/ErrNoStorageVol on missing lookups,
// ErrOperationInvalid on destroying a stopped domain, and so on.
type fakeAPI struct {
mu sync.Mutex
poolPath string
pools map[string]map[string]*fakeVol
domains map[string]*fakeDomain
calls []string
fail map[string]error
failOnce map[string]error
// uploadHook, when set, sees every StorageVolUpload before the fake
// reads the stream; it can return an error to simulate a broken upload.
uploadHook func(vol string, r io.Reader) error
}
type fakeVol struct {
name string
format string
capacity int64
backing string
data []byte
}
type fakeDomain struct {
name string
xml string
metadata string
running bool
// addrs is what DomainInterfaceAddresses returns per source.
addrs map[uint32][]libvirt.DomainInterface
}
func newFakeAPI(pools ...string) *fakeAPI {
f := &fakeAPI{
poolPath: "/var/lib/libvirt/images",
pools: map[string]map[string]*fakeVol{},
domains: map[string]*fakeDomain{},
fail: map[string]error{},
failOnce: map[string]error{},
}
for _, p := range pools {
f.pools[p] = map[string]*fakeVol{}
}
return f
}
// enter records the call and returns any injected error for method.
func (f *fakeAPI) enter(method string) error {
f.calls = append(f.calls, method)
if err, ok := f.failOnce[method]; ok {
delete(f.failOnce, method)
return err
}
return f.fail[method]
}
func (f *fakeAPI) callCount(method string) int {
f.mu.Lock()
defer f.mu.Unlock()
n := 0
for _, c := range f.calls {
if c == method {
n++
}
}
return n
}
func (f *fakeAPI) hasCall(method string) bool { return f.callCount(method) > 0 }
func (f *fakeAPI) vol(pool, name string) *fakeVol {
f.mu.Lock()
defer f.mu.Unlock()
return f.pools[pool][name]
}
func (f *fakeAPI) putVol(pool, name, format string, data []byte) {
f.mu.Lock()
defer f.mu.Unlock()
f.pools[pool][name] = &fakeVol{name: name, format: format, capacity: int64(len(data)), data: data}
}
func (f *fakeAPI) volNames(pool string) []string {
f.mu.Lock()
defer f.mu.Unlock()
var out []string
for n := range f.pools[pool] {
out = append(out, n)
}
slices.Sort(out)
return out
}
func (f *fakeAPI) domain(name string) *fakeDomain {
f.mu.Lock()
defer f.mu.Unlock()
return f.domains[name]
}
func (f *fakeAPI) putDomain(d *fakeDomain) {
f.mu.Lock()
defer f.mu.Unlock()
f.domains[d.name] = d
}
func lvError(code libvirt.ErrorNumber, format string, args ...any) error {
return libvirt.Error{Code: uint32(code), Message: fmt.Sprintf(format, args...)}
}
// --- domains ---
func (f *fakeAPI) DomainLookupByName(name string) (libvirt.Domain, error) {
f.mu.Lock()
defer f.mu.Unlock()
if err := f.enter("DomainLookupByName"); err != nil {
return libvirt.Domain{}, err
}
if _, ok := f.domains[name]; !ok {
return libvirt.Domain{}, lvError(libvirt.ErrNoDomain, "Domain not found: no domain with matching name '%s'", name)
}
return libvirt.Domain{Name: name}, nil
}
func (f *fakeAPI) DomainDefineXML(raw string) (libvirt.Domain, error) {
f.mu.Lock()
defer f.mu.Unlock()
if err := f.enter("DomainDefineXML"); err != nil {
return libvirt.Domain{}, err
}
var d domainXML
if err := xml.Unmarshal([]byte(raw), &d); err != nil {
return libvirt.Domain{}, lvError(libvirt.ErrXMLError, "%v", err)
}
meta, err := xml.Marshal(d.Metadata.Instance)
if err != nil {
return libvirt.Domain{}, lvError(libvirt.ErrXMLError, "%v", err)
}
existing := f.domains[d.Name]
nd := &fakeDomain{name: d.Name, xml: raw, metadata: string(meta)}
if existing != nil {
nd.running = existing.running
nd.addrs = existing.addrs
}
f.domains[d.Name] = nd
return libvirt.Domain{Name: d.Name}, nil
}
func (f *fakeAPI) DomainCreate(d libvirt.Domain) error {
f.mu.Lock()
defer f.mu.Unlock()
if err := f.enter("DomainCreate"); err != nil {
return err
}
dom, ok := f.domains[d.Name]
if !ok {
return lvError(libvirt.ErrNoDomain, "no domain %s", d.Name)
}
if dom.running {
return lvError(libvirt.ErrOperationInvalid, "domain is already running")
}
dom.running = true
return nil
}
func (f *fakeAPI) DomainDestroy(d libvirt.Domain) error {
f.mu.Lock()
defer f.mu.Unlock()
if err := f.enter("DomainDestroy"); err != nil {
return err
}
dom, ok := f.domains[d.Name]
if !ok {
return lvError(libvirt.ErrNoDomain, "no domain %s", d.Name)
}
if !dom.running {
return lvError(libvirt.ErrOperationInvalid, "domain is not running")
}
dom.running = false
return nil
}
func (f *fakeAPI) DomainUndefineFlags(d libvirt.Domain, _ libvirt.DomainUndefineFlagsValues) error {
f.mu.Lock()
defer f.mu.Unlock()
if err := f.enter("DomainUndefineFlags"); err != nil {
return err
}
if _, ok := f.domains[d.Name]; !ok {
return lvError(libvirt.ErrNoDomain, "no domain %s", d.Name)
}
delete(f.domains, d.Name)
return nil
}
func (f *fakeAPI) DomainGetState(d libvirt.Domain, _ uint32) (int32, int32, error) {
f.mu.Lock()
defer f.mu.Unlock()
if err := f.enter("DomainGetState"); err != nil {
return 0, 0, err
}
dom, ok := f.domains[d.Name]
if !ok {
return 0, 0, lvError(libvirt.ErrNoDomain, "no domain %s", d.Name)
}
if dom.running {
return int32(libvirt.DomainRunning), 0, nil
}
return int32(libvirt.DomainShutoff), 0, nil
}
func (f *fakeAPI) DomainGetMetadata(d libvirt.Domain, typ int32, uri libvirt.OptString, _ libvirt.DomainModificationImpact) (string, error) {
f.mu.Lock()
defer f.mu.Unlock()
if err := f.enter("DomainGetMetadata"); err != nil {
return "", err
}
dom, ok := f.domains[d.Name]
if !ok {
return "", lvError(libvirt.ErrNoDomain, "no domain %s", d.Name)
}
if typ != int32(libvirt.DomainMetadataElement) || len(uri) != 1 || uri[0] != metadataURI || dom.metadata == "" {
return "", lvError(libvirt.ErrNoDomainMetadata, "Requested metadata element is not present")
}
return dom.metadata, nil
}
func (f *fakeAPI) DomainInterfaceAddresses(d libvirt.Domain, source uint32, _ uint32) ([]libvirt.DomainInterface, error) {
f.mu.Lock()
defer f.mu.Unlock()
if err := f.enter("DomainInterfaceAddresses"); err != nil {
return nil, err
}
dom, ok := f.domains[d.Name]
if !ok {
return nil, lvError(libvirt.ErrNoDomain, "no domain %s", d.Name)
}
if !dom.running {
return nil, lvError(libvirt.ErrOperationInvalid, "domain is not running")
}
if source == uint32(libvirt.DomainInterfaceAddressesSrcAgent) && dom.addrs[source] == nil {
return nil, lvError(libvirt.ErrAgentUnresponsive, "Guest agent is not responding")
}
return dom.addrs[source], nil
}
func (f *fakeAPI) ConnectListAllDomains(_ int32, _ libvirt.ConnectListAllDomainsFlags) ([]libvirt.Domain, uint32, error) {
f.mu.Lock()
defer f.mu.Unlock()
if err := f.enter("ConnectListAllDomains"); err != nil {
return nil, 0, err
}
names := make([]string, 0, len(f.domains))
for n := range f.domains {
names = append(names, n)
}
slices.Sort(names)
out := make([]libvirt.Domain, 0, len(names))
for _, n := range names {
out = append(out, libvirt.Domain{Name: n})
}
return out, uint32(len(out)), nil
}
// --- storage ---
func (f *fakeAPI) StoragePoolLookupByName(name string) (libvirt.StoragePool, error) {
f.mu.Lock()
defer f.mu.Unlock()
if err := f.enter("StoragePoolLookupByName"); err != nil {
return libvirt.StoragePool{}, err
}
if _, ok := f.pools[name]; !ok {
return libvirt.StoragePool{}, lvError(libvirt.ErrNoStoragePool, "Storage pool not found: no storage pool with matching name '%s'", name)
}
return libvirt.StoragePool{Name: name}, nil
}
func (f *fakeAPI) StoragePoolRefresh(pool libvirt.StoragePool, _ uint32) error {
f.mu.Lock()
defer f.mu.Unlock()
if err := f.enter("StoragePoolRefresh"); err != nil {
return err
}
if _, ok := f.pools[pool.Name]; !ok {
return lvError(libvirt.ErrNoStoragePool, "no pool %s", pool.Name)
}
return nil
}
func (f *fakeAPI) StorageVolLookupByName(pool libvirt.StoragePool, name string) (libvirt.StorageVol, error) {
f.mu.Lock()
defer f.mu.Unlock()
if err := f.enter("StorageVolLookupByName"); err != nil {
return libvirt.StorageVol{}, err
}
if _, ok := f.pools[pool.Name][name]; !ok {
return libvirt.StorageVol{}, lvError(libvirt.ErrNoStorageVol, "Storage volume not found: no storage vol with matching name '%s'", name)
}
return libvirt.StorageVol{Pool: pool.Name, Name: name, Key: f.poolPath + "/" + name}, nil
}
func (f *fakeAPI) StorageVolGetPath(vol libvirt.StorageVol) (string, error) {
f.mu.Lock()
defer f.mu.Unlock()
if err := f.enter("StorageVolGetPath"); err != nil {
return "", err
}
if _, ok := f.pools[vol.Pool][vol.Name]; !ok {
return "", lvError(libvirt.ErrNoStorageVol, "no vol %s", vol.Name)
}
return f.poolPath + "/" + vol.Name, nil
}
func (f *fakeAPI) StorageVolCreateXML(pool libvirt.StoragePool, raw string, _ libvirt.StorageVolCreateFlags) (libvirt.StorageVol, error) {
f.mu.Lock()
defer f.mu.Unlock()
if err := f.enter("StorageVolCreateXML"); err != nil {
return libvirt.StorageVol{}, err
}
vols, ok := f.pools[pool.Name]
if !ok {
return libvirt.StorageVol{}, lvError(libvirt.ErrNoStoragePool, "no pool %s", pool.Name)
}
var v volumeXML
if err := xml.Unmarshal([]byte(raw), &v); err != nil {
return libvirt.StorageVol{}, lvError(libvirt.ErrXMLError, "%v", err)
}
if _, exists := vols[v.Name]; exists {
return libvirt.StorageVol{}, lvError(libvirt.ErrStorageVolExist, "storage volume '%s' exists already", v.Name)
}
fv := &fakeVol{name: v.Name, format: v.Target.Format.Type, capacity: v.Capacity.Value}
if v.BackingStore != nil {
fv.backing = v.BackingStore.Path
}
vols[v.Name] = fv
return libvirt.StorageVol{Pool: pool.Name, Name: v.Name, Key: f.poolPath + "/" + v.Name}, nil
}
func (f *fakeAPI) StorageVolUpload(vol libvirt.StorageVol, r io.Reader, _, _ uint64, _ libvirt.StorageVolUploadFlags) error {
f.mu.Lock()
if err := f.enter("StorageVolUpload"); err != nil {
f.mu.Unlock()
return err
}
fv, ok := f.pools[vol.Pool][vol.Name]
hook := f.uploadHook
f.mu.Unlock()
if !ok {
return lvError(libvirt.ErrNoStorageVol, "no vol %s", vol.Name)
}
if hook != nil {
if err := hook(vol.Name, r); err != nil {
return err
}
}
// Read outside the lock: the stream may be a slow HTTP body.
data, err := io.ReadAll(r)
if err != nil {
return fmt.Errorf("reading upload stream: %w", err)
}
f.mu.Lock()
defer f.mu.Unlock()
fv.data = data
return nil
}
func (f *fakeAPI) StorageVolDownload(vol libvirt.StorageVol, w io.Writer, _, _ uint64, _ libvirt.StorageVolDownloadFlags) error {
f.mu.Lock()
defer f.mu.Unlock()
if err := f.enter("StorageVolDownload"); err != nil {
return err
}
fv, ok := f.pools[vol.Pool][vol.Name]
if !ok {
return lvError(libvirt.ErrNoStorageVol, "no vol %s", vol.Name)
}
_, err := io.Copy(w, bytes.NewReader(fv.data))
return err
}
func (f *fakeAPI) StorageVolDelete(vol libvirt.StorageVol, _ libvirt.StorageVolDeleteFlags) error {
f.mu.Lock()
defer f.mu.Unlock()
if err := f.enter("StorageVolDelete"); err != nil {
return err
}
if _, ok := f.pools[vol.Pool][vol.Name]; !ok {
return lvError(libvirt.ErrNoStorageVol, "no vol %s", vol.Name)
}
delete(f.pools[vol.Pool], vol.Name)
return nil
}
+232
View File
@@ -0,0 +1,232 @@
package kvm
import (
"bytes"
"context"
"crypto/sha256"
"encoding/hex"
"fmt"
"io"
"net/http"
"net/url"
"strings"
"sync"
"time"
libvirt "github.com/digitalocean/go-libvirt"
"github.com/go-logr/logr"
"gitea.home.hrajfrisbee.cz/kacerr/egress-proxies-operator/internal/provider"
)
// imageSource is a resolved placement.image: either an entry from the
// provider's images map (Key set) or a URL given directly.
type imageSource struct {
Key string
URL string
SHA256 string
Format string
}
// resolveImage maps placement.image to a source. Anything that is neither a
// configured key nor an http(s) URL is a spec error the reconciler should
// surface, not retry.
func resolveImage(cfg provider.KVMConfig, image string) (imageSource, error) {
if img, ok := cfg.Images[image]; ok {
return imageSource{Key: image, URL: img.URL, SHA256: img.SHA256, Format: img.Format}, nil
}
u, err := url.Parse(image)
if err == nil && (u.Scheme == "http" || u.Scheme == "https") && u.Host != "" {
return imageSource{URL: image, Format: formatQcow2}, nil
}
return imageSource{}, fmt.Errorf("%w: placement.image %q is neither a key in kvm.images nor an http(s) URL",
provider.ErrPermanent, image)
}
// volumeName is the cached base image's name in the pool: readable for
// configured keys, a URL hash for ad-hoc URLs.
func (s imageSource) volumeName() string {
if s.Key != "" {
return "base-" + s.Key + "." + s.Format
}
sum := sha256.Sum256([]byte(s.URL))
return "base-" + hex.EncodeToString(sum[:8]) + "." + s.Format
}
// markerName is the sidecar volume holding the sha256 of the verified
// upload. Its presence is what says "the base volume is complete".
func (s imageSource) markerName() string {
return s.volumeName() + ".sha256"
}
// imageCache fetches base images into a host's pool on first use. It keeps
// no state about what is cached — the pool is the source of truth, checked
// on every call — only a per-(host, image) lock so concurrent Creates for
// the same image on the same host result in one download.
type imageCache struct {
http *http.Client
mu sync.Mutex
locks map[string]*sync.Mutex
}
func newImageCache(client *http.Client) *imageCache {
if client == nil {
client = http.DefaultClient
}
return &imageCache{http: client, locks: make(map[string]*sync.Mutex)}
}
func (c *imageCache) lockFor(key string) *sync.Mutex {
c.mu.Lock()
defer c.mu.Unlock()
m, ok := c.locks[key]
if !ok {
m = &sync.Mutex{}
c.locks[key] = m
}
return m
}
// ensure makes src present in pool and returns the base volume's path on
// the host. The image is downloaded synchronously through the libvirt
// stream when the pool does not already hold a verified copy.
func (c *imageCache) ensure(ctx context.Context, log logr.Logger, api libvirtAPI, hostName string, pool libvirt.StoragePool, src imageSource) (string, error) {
m := c.lockFor(hostName + "/" + src.volumeName())
m.Lock()
defer m.Unlock()
base, ready, err := c.lookup(api, pool, src)
if err != nil {
return "", err
}
if ready {
log.V(1).Info("base image already cached", "host", hostName, "volume", src.volumeName())
return api.StorageVolGetPath(base)
}
if err := deleteIfExists(api, pool, src.markerName()); err != nil {
return "", err
}
if err := deleteIfExists(api, pool, src.volumeName()); err != nil {
return "", err
}
base, err = c.fetch(ctx, log, api, hostName, pool, src)
if err != nil {
return "", err
}
return api.StorageVolGetPath(base)
}
// lookup reports whether the pool holds a complete, verified base volume:
// the volume and its marker both exist and, when a checksum is configured,
// the marker records that checksum.
func (c *imageCache) lookup(api libvirtAPI, pool libvirt.StoragePool, src imageSource) (libvirt.StorageVol, bool, error) {
base, err := api.StorageVolLookupByName(pool, src.volumeName())
if hasCode(err, libvirt.ErrNoStorageVol) {
return libvirt.StorageVol{}, false, nil
}
if err != nil {
return libvirt.StorageVol{}, false, fmt.Errorf("looking up base volume: %w", err)
}
marker, err := api.StorageVolLookupByName(pool, src.markerName())
if hasCode(err, libvirt.ErrNoStorageVol) {
return base, false, nil
}
if err != nil {
return libvirt.StorageVol{}, false, fmt.Errorf("looking up image marker: %w", err)
}
if src.SHA256 == "" {
return base, true, nil
}
var buf bytes.Buffer
if err := api.StorageVolDownload(marker, &buf, 0, 0, 0); err != nil {
return libvirt.StorageVol{}, false, fmt.Errorf("reading image marker: %w", err)
}
return base, strings.EqualFold(strings.TrimSpace(buf.String()), src.SHA256), nil
}
// fetch streams the image from its URL straight into a new base volume,
// hashing on the way, then writes the marker. Nothing is buffered in the
// operator beyond the HTTP body's read buffer.
func (c *imageCache) fetch(ctx context.Context, log logr.Logger, api libvirtAPI, hostName string, pool libvirt.StoragePool, src imageSource) (libvirt.StorageVol, error) {
req, err := http.NewRequestWithContext(ctx, http.MethodGet, src.URL, nil)
if err != nil {
return libvirt.StorageVol{}, fmt.Errorf("%w: building image request: %v", provider.ErrPermanent, err)
}
resp, err := c.http.Do(req)
if err != nil {
return libvirt.StorageVol{}, fmt.Errorf("%w: fetching image %s: %v", provider.ErrTransient, src.URL, err)
}
defer resp.Body.Close()
switch {
case resp.StatusCode >= 200 && resp.StatusCode < 300:
case resp.StatusCode >= 400 && resp.StatusCode < 500:
return libvirt.StorageVol{}, fmt.Errorf("%w: image %s returned HTTP %d", provider.ErrPermanent, src.URL, resp.StatusCode)
default:
return libvirt.StorageVol{}, fmt.Errorf("%w: image %s returned HTTP %d", provider.ErrTransient, src.URL, resp.StatusCode)
}
if resp.ContentLength < 0 {
return libvirt.StorageVol{}, fmt.Errorf("%w: image %s has no Content-Length; the base volume needs a known size", provider.ErrPermanent, src.URL)
}
log.Info("fetching base image into host pool",
"host", hostName, "pool", pool.Name, "volume", src.volumeName(),
"url", src.URL, "bytes", resp.ContentLength)
start := time.Now()
baseXML, err := buildVolumeXML(volumeSpec{Name: src.volumeName(), SizeBytes: resp.ContentLength, Format: src.Format})
if err != nil {
return libvirt.StorageVol{}, err
}
base, err := api.StorageVolCreateXML(pool, baseXML, 0)
if err != nil {
return libvirt.StorageVol{}, fmt.Errorf("creating base volume: %w", err)
}
hasher := sha256.New()
if err := api.StorageVolUpload(base, io.TeeReader(resp.Body, hasher), 0, 0, 0); err != nil {
_ = api.StorageVolDelete(base, 0)
return libvirt.StorageVol{}, fmt.Errorf("uploading image to base volume: %w", err)
}
digest := hex.EncodeToString(hasher.Sum(nil))
if src.SHA256 != "" && !strings.EqualFold(digest, src.SHA256) {
_ = api.StorageVolDelete(base, 0)
return libvirt.StorageVol{}, fmt.Errorf("%w: image %s sha256 is %s, config expects %s",
provider.ErrPermanent, src.URL, digest, src.SHA256)
}
// libvirt sized the volume from Content-Length; a refresh makes it
// re-read the real virtual size from the uploaded qcow2 header.
if err := api.StoragePoolRefresh(pool, 0); err != nil {
return libvirt.StorageVol{}, fmt.Errorf("refreshing pool after upload: %w", err)
}
markerXML, err := buildVolumeXML(rawVolume(src.markerName(), int64(len(digest))))
if err != nil {
return libvirt.StorageVol{}, err
}
marker, err := api.StorageVolCreateXML(pool, markerXML, 0)
if err != nil {
return libvirt.StorageVol{}, fmt.Errorf("creating image marker: %w", err)
}
if err := api.StorageVolUpload(marker, strings.NewReader(digest), 0, 0, 0); err != nil {
_ = api.StorageVolDelete(marker, 0)
return libvirt.StorageVol{}, fmt.Errorf("writing image marker: %w", err)
}
log.Info("base image cached",
"host", hostName, "volume", src.volumeName(), "sha256", digest,
"bytes", resp.ContentLength, "duration", time.Since(start).Round(time.Second))
return base, nil
}
func deleteIfExists(api libvirtAPI, pool libvirt.StoragePool, name string) error {
vol, err := api.StorageVolLookupByName(pool, name)
if hasCode(err, libvirt.ErrNoStorageVol) {
return nil
}
if err != nil {
return fmt.Errorf("looking up volume %s: %w", name, err)
}
if err := api.StorageVolDelete(vol, 0); err != nil && !hasCode(err, libvirt.ErrNoStorageVol) {
return fmt.Errorf("deleting volume %s: %w", name, err)
}
return nil
}
+385
View File
@@ -0,0 +1,385 @@
package kvm
import (
"bytes"
"context"
"crypto/sha256"
"encoding/hex"
"errors"
"io"
"net/http"
"net/http/httptest"
"strconv"
"strings"
"sync"
"sync/atomic"
"testing"
"time"
"github.com/go-logr/logr"
"gitea.home.hrajfrisbee.cz/kacerr/egress-proxies-operator/internal/provider"
)
var testImage = bytes.Repeat([]byte("QFI\xfb fake qcow2 payload "), 1024)
func testImageSHA() string {
sum := sha256.Sum256(testImage)
return hex.EncodeToString(sum[:])
}
// imageServer serves testImage and counts hits. Status overrides the
// response, noLength forces chunked encoding (no Content-Length), delay
// slows each response so concurrent callers overlap.
type imageServer struct {
*httptest.Server
hits atomic.Int32
status int
noLength bool
delay time.Duration
body []byte
}
func newImageServer(t *testing.T) *imageServer {
t.Helper()
s := &imageServer{status: http.StatusOK, body: testImage}
s.Server = httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
s.hits.Add(1)
time.Sleep(s.delay)
if s.status != http.StatusOK {
w.WriteHeader(s.status)
return
}
// Bodies larger than the server's write buffer would otherwise go
// out chunked without a Content-Length, unlike real image mirrors.
if s.noLength {
w.(http.Flusher).Flush()
} else {
w.Header().Set("Content-Length", strconv.Itoa(len(s.body)))
}
_, _ = w.Write(s.body)
}))
t.Cleanup(s.Close)
return s
}
func testSource(srv *imageServer, sha string) imageSource {
return imageSource{Key: "debian-13", URL: srv.URL + "/debian.qcow2", SHA256: sha, Format: formatQcow2}
}
func ensureTest(t *testing.T, api *fakeAPI, src imageSource) (string, error) {
t.Helper()
c := newImageCache(nil)
pool, err := api.StoragePoolLookupByName("default")
if err != nil {
t.Fatal(err)
}
return c.ensure(context.Background(), logr.Discard(), api, "nas1", pool, src)
}
func TestResolveImage(t *testing.T) {
t.Parallel()
cfg := withDefaults(provider.KVMConfig{Images: map[string]provider.KVMImage{
"debian-13": {URL: "https://cloud.debian.org/d.qcow2", SHA256: "abc"},
}})
tests := []struct {
name string
image string
want imageSource
wantErr bool
}{
{"configured key", "debian-13", imageSource{Key: "debian-13", URL: "https://cloud.debian.org/d.qcow2", SHA256: "abc", Format: "qcow2"}, false},
{"direct https url", "https://x.example/img.qcow2", imageSource{URL: "https://x.example/img.qcow2", Format: "qcow2"}, false},
{"direct http url", "http://mirror/img.qcow2", imageSource{URL: "http://mirror/img.qcow2", Format: "qcow2"}, false},
{"unknown key", "ubuntu", imageSource{}, true},
{"file url", "file:///tmp/x.qcow2", imageSource{}, true},
{"empty", "", imageSource{}, true},
}
for _, tc := range tests {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
got, err := resolveImage(cfg, tc.image)
if tc.wantErr {
if !errors.Is(err, provider.ErrPermanent) {
t.Fatalf("resolveImage(%q) error = %v, want ErrPermanent", tc.image, err)
}
return
}
if err != nil {
t.Fatalf("resolveImage(%q) error = %v", tc.image, err)
}
if got != tc.want {
t.Errorf("resolveImage(%q) = %+v, want %+v", tc.image, got, tc.want)
}
})
}
}
func TestImageSource_volumeNames(t *testing.T) {
t.Parallel()
keyed := imageSource{Key: "debian-13", URL: "https://a/b.qcow2", Format: "qcow2"}
if keyed.volumeName() != "base-debian-13.qcow2" || keyed.markerName() != "base-debian-13.qcow2.sha256" {
t.Errorf("keyed names = %s / %s", keyed.volumeName(), keyed.markerName())
}
direct := imageSource{URL: "https://a/b.qcow2", Format: "qcow2"}
name := direct.volumeName()
if !strings.HasPrefix(name, "base-") || !strings.HasSuffix(name, ".qcow2") || len(name) != len("base-")+16+len(".qcow2") {
t.Errorf("direct-url name = %q, want base-<16 hex>.qcow2", name)
}
other := imageSource{URL: "https://a/c.qcow2", Format: "qcow2"}
if other.volumeName() == name {
t.Error("different URLs produced the same volume name")
}
}
func TestImageCache_ensure_freshFetch(t *testing.T) {
t.Parallel()
srv := newImageServer(t)
api := newFakeAPI("default")
path, err := ensureTest(t, api, testSource(srv, testImageSHA()))
if err != nil {
t.Fatalf("ensure() error = %v", err)
}
if path != "/var/lib/libvirt/images/base-debian-13.qcow2" {
t.Errorf("path = %q", path)
}
base := api.vol("default", "base-debian-13.qcow2")
if base == nil || !bytes.Equal(base.data, testImage) {
t.Fatalf("base volume missing or content differs")
}
if base.format != "qcow2" || base.capacity != int64(len(testImage)) {
t.Errorf("base volume format/capacity = %s/%d, want qcow2/%d", base.format, base.capacity, len(testImage))
}
marker := api.vol("default", "base-debian-13.qcow2.sha256")
if marker == nil || string(marker.data) != testImageSHA() {
t.Fatalf("marker missing or wrong: %+v", marker)
}
if !api.hasCall("StoragePoolRefresh") {
t.Error("pool was not refreshed after the upload")
}
if srv.hits.Load() != 1 {
t.Errorf("http hits = %d, want 1", srv.hits.Load())
}
}
func TestImageCache_ensure_noChecksumConfigured(t *testing.T) {
t.Parallel()
srv := newImageServer(t)
api := newFakeAPI("default")
if _, err := ensureTest(t, api, testSource(srv, "")); err != nil {
t.Fatalf("ensure() error = %v", err)
}
if marker := api.vol("default", "base-debian-13.qcow2.sha256"); marker == nil || string(marker.data) != testImageSHA() {
t.Errorf("marker should still record the computed digest, got %+v", marker)
}
// Second call: ready without a checksum to compare, so no marker read.
if _, err := ensureTest(t, api, testSource(srv, "")); err != nil {
t.Fatalf("second ensure() error = %v", err)
}
if srv.hits.Load() != 1 {
t.Errorf("http hits = %d, want 1", srv.hits.Load())
}
}
func TestImageCache_ensure_alreadyCached(t *testing.T) {
t.Parallel()
srv := newImageServer(t)
api := newFakeAPI("default")
api.putVol("default", "base-debian-13.qcow2", "qcow2", testImage)
api.putVol("default", "base-debian-13.qcow2.sha256", "raw", []byte(testImageSHA()))
path, err := ensureTest(t, api, testSource(srv, testImageSHA()))
if err != nil {
t.Fatalf("ensure() error = %v", err)
}
if path != "/var/lib/libvirt/images/base-debian-13.qcow2" {
t.Errorf("path = %q", path)
}
if srv.hits.Load() != 0 {
t.Errorf("http hits = %d, want 0 for a cached image", srv.hits.Load())
}
if api.hasCall("StorageVolCreateXML") || api.hasCall("StorageVolDelete") {
t.Errorf("cached image was touched: calls = %v", api.calls)
}
}
func TestImageCache_ensure_markerMissingRedownloads(t *testing.T) {
t.Parallel()
srv := newImageServer(t)
api := newFakeAPI("default")
api.putVol("default", "base-debian-13.qcow2", "qcow2", []byte("half an image"))
if _, err := ensureTest(t, api, testSource(srv, testImageSHA())); err != nil {
t.Fatalf("ensure() error = %v", err)
}
if srv.hits.Load() != 1 {
t.Errorf("http hits = %d, want 1: a base without its marker is a partial upload", srv.hits.Load())
}
if base := api.vol("default", "base-debian-13.qcow2"); base == nil || !bytes.Equal(base.data, testImage) {
t.Error("partial base volume was not replaced")
}
}
func TestImageCache_ensure_checksumChangedRedownloads(t *testing.T) {
t.Parallel()
srv := newImageServer(t)
api := newFakeAPI("default")
api.putVol("default", "base-debian-13.qcow2", "qcow2", []byte("an older release"))
api.putVol("default", "base-debian-13.qcow2.sha256", "raw", []byte(strings.Repeat("0", 64)))
if _, err := ensureTest(t, api, testSource(srv, testImageSHA())); err != nil {
t.Fatalf("ensure() error = %v", err)
}
if srv.hits.Load() != 1 {
t.Errorf("http hits = %d, want 1 after the configured checksum changed", srv.hits.Load())
}
if marker := api.vol("default", "base-debian-13.qcow2.sha256"); marker == nil || string(marker.data) != testImageSHA() {
t.Errorf("marker not updated: %+v", marker)
}
}
func TestImageCache_ensure_checksumMismatchIsPermanent(t *testing.T) {
t.Parallel()
srv := newImageServer(t)
api := newFakeAPI("default")
_, err := ensureTest(t, api, testSource(srv, strings.Repeat("a", 64)))
if !errors.Is(err, provider.ErrPermanent) {
t.Fatalf("ensure() error = %v, want ErrPermanent", err)
}
if names := api.volNames("default"); len(names) != 0 {
t.Errorf("volumes left behind after a checksum mismatch: %v", names)
}
}
func TestImageCache_ensure_httpErrors(t *testing.T) {
t.Parallel()
tests := []struct {
name string
status int
want error
}{
{"404 is permanent", http.StatusNotFound, provider.ErrPermanent},
{"403 is permanent", http.StatusForbidden, provider.ErrPermanent},
{"503 is transient", http.StatusServiceUnavailable, provider.ErrTransient},
{"500 is transient", http.StatusInternalServerError, provider.ErrTransient},
}
for _, tc := range tests {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
srv := newImageServer(t)
srv.status = tc.status
api := newFakeAPI("default")
_, err := ensureTest(t, api, testSource(srv, ""))
if !errors.Is(err, tc.want) {
t.Fatalf("ensure() error = %v, want %v", err, tc.want)
}
if names := api.volNames("default"); len(names) != 0 {
t.Errorf("volumes created despite HTTP %d: %v", tc.status, names)
}
})
}
}
func TestImageCache_ensure_noContentLengthIsPermanent(t *testing.T) {
t.Parallel()
srv := newImageServer(t)
srv.noLength = true
api := newFakeAPI("default")
_, err := ensureTest(t, api, testSource(srv, ""))
if !errors.Is(err, provider.ErrPermanent) || !strings.Contains(err.Error(), "Content-Length") {
t.Fatalf("ensure() error = %v, want ErrPermanent about Content-Length", err)
}
}
func TestImageCache_ensure_uploadFailureCleansUp(t *testing.T) {
t.Parallel()
srv := newImageServer(t)
api := newFakeAPI("default")
api.uploadHook = func(_ string, r io.Reader) error {
_, _ = io.CopyN(io.Discard, r, 100)
return io.ErrUnexpectedEOF
}
_, err := ensureTest(t, api, testSource(srv, testImageSHA()))
if !errors.Is(err, provider.ErrTransient) && classify(err) != provider.ErrTransient {
t.Fatalf("ensure() error = %v, want a transient failure", err)
}
if names := api.volNames("default"); len(names) != 0 {
t.Errorf("volumes left behind after a failed upload: %v", names)
}
// Next attempt starts clean and succeeds.
api.uploadHook = nil
if _, err := ensureTest(t, api, testSource(srv, testImageSHA())); err != nil {
t.Fatalf("retry ensure() error = %v", err)
}
}
func TestImageCache_ensure_missingPoolIsPermanent(t *testing.T) {
t.Parallel()
srv := newImageServer(t)
api := newFakeAPI("default")
c := newImageCache(nil)
pool, _ := api.StoragePoolLookupByName("default")
delete(api.pools, "default")
_, err := c.ensure(context.Background(), logr.Discard(), api, "nas1", pool, testSource(srv, ""))
if classify(err) != provider.ErrPermanent {
t.Fatalf("ensure() error = %v, want one classifying as Permanent", err)
}
}
func TestImageCache_ensure_concurrentCallersDownloadOnce(t *testing.T) {
t.Parallel()
srv := newImageServer(t)
srv.delay = 50 * time.Millisecond
api := newFakeAPI("default")
c := newImageCache(nil)
pool, _ := api.StoragePoolLookupByName("default")
src := testSource(srv, testImageSHA())
var wg sync.WaitGroup
paths := make([]string, 4)
errs := make([]error, 4)
for i := range 4 {
wg.Go(func() {
paths[i], errs[i] = c.ensure(context.Background(), logr.Discard(), api, "nas1", pool, src)
})
}
wg.Wait()
for i := range 4 {
if errs[i] != nil || paths[i] != "/var/lib/libvirt/images/base-debian-13.qcow2" {
t.Errorf("caller %d: path=%q err=%v", i, paths[i], errs[i])
}
}
if srv.hits.Load() != 1 {
t.Errorf("http hits = %d, want 1 for four concurrent callers", srv.hits.Load())
}
}
func TestImageCache_ensure_differentHostsFetchIndependently(t *testing.T) {
t.Parallel()
srv := newImageServer(t)
c := newImageCache(nil)
src := testSource(srv, "")
for _, host := range []string{"nas1", "lab2"} {
api := newFakeAPI("default")
pool, _ := api.StoragePoolLookupByName("default")
if _, err := c.ensure(context.Background(), logr.Discard(), api, host, pool, src); err != nil {
t.Fatalf("ensure(%s) error = %v", host, err)
}
}
if srv.hits.Load() != 2 {
t.Errorf("http hits = %d, want one per host", srv.hits.Load())
}
}
func TestImageCache_ensure_cancelledContextIsTransient(t *testing.T) {
t.Parallel()
srv := newImageServer(t)
api := newFakeAPI("default")
c := newImageCache(nil)
pool, _ := api.StoragePoolLookupByName("default")
ctx, cancel := context.WithCancel(context.Background())
cancel()
_, err := c.ensure(ctx, logr.Discard(), api, "nas1", pool, testSource(srv, ""))
if classify(err) != provider.ErrTransient {
t.Fatalf("ensure() error = %v, want transient", err)
}
if names := api.volNames("default"); len(names) != 0 {
t.Errorf("volumes created despite cancelled context: %v", names)
}
}