egress-proxies-operator/internal/provider/kvm2/get.go

package kvm2

import (
	"context"
	"errors"
	"fmt"

	"github.com/digitalocean/go-libvirt"
	"github.com/go-logr/logr"

	"gitea.home.hrajfrisbee.cz/kacerr/egress-proxies-operator/internal/provider"
)

// Get is spec entries 7 to 9: look the domain up by name, read the mark
// back, then state and address. Only ErrNoDomain becomes NotFound; every
// other failure is classified, never guessed.
func (p *Provider) Get(ctx context.Context, providerID string) (*provider.Instance, error) {
	hostName, name, err := parseProviderID(providerID)
	if err != nil {
		return nil, provider.Wrap(provider.ErrPermanent, "get", p.name, providerID, err)
	}
	host, err := p.host(hostName)
	if err != nil {
		return nil, p.wrapErr("get", providerID, err)
	}
	log := p.logger(ctx).WithValues("host", host.Name, "name", name)
	be, err := p.hosts.get(ctx, host)
	if err != nil {
		logAPIError(log, "get", err)
		return nil, p.wrapErr("get", providerID, err)
	}
	inst, err := get(ctx, log, be, host.Name, name)
	if err != nil {
		if hasCode(err, libvirt.ErrNoDomain) {
			log.V(1).Info("kvm2 domain not found")
		} else {
			logAPIError(log, "get", err)
		}
		return nil, p.wrapErr("get", providerID, err)
	}
	log.V(1).Info("kvm2 domain fetched", "state", inst.State, "ip", inst.IP, "uid", inst.UID)
	return inst, nil
}

// get builds the Instance from the domain's metadata, its state and, for an
// active domain, its discovered address.
func get(ctx context.Context, log logr.Logger, be backend, hostName, name string) (*provider.Instance, error) {
	dom, err := be.DomainLookupByName(ctx, name)
	if err != nil {
		return nil, fmt.Errorf("looking up domain %s: %w", name, err)
	}
	meta, err := readMetadata(ctx, be, dom)
	if err != nil {
		return nil, err
	}
	state, _, err := be.DomainGetState(ctx, dom, 0)
	if err != nil {
		return nil, fmt.Errorf("reading state of domain %s: %w", dom.Name, err)
	}
	s := libvirt.DomainState(state)
	var ip string
	if isActive(s) {
		if ip, err = address(ctx, log, be, dom); err != nil {
			return nil, err
		}
	}
	return &provider.Instance{
		ID:        formatProviderID(hostName, dom.Name),
		IP:        ip,
		State:     mapState(s, ip),
		UID:       meta.UID,
		CreatedAt: meta.createdAt(),
	}, nil
}

// readMetadata returns the kvm2 mark of a domain, or the zero value (not
// managed, empty UID) when the domain carries none. A mark that does not
// parse is Permanent, from parseInstanceMetadata.
func readMetadata(ctx context.Context, be backend, dom libvirt.Domain) (instanceMetadata, error) {
	raw, err := be.DomainGetMetadata(ctx, dom, int32(libvirt.DomainMetadataElement), libvirt.OptString{metadataURI}, libvirt.DomainAffectCurrent)
	if hasCode(err, libvirt.ErrNoDomainMetadata) {
		return instanceMetadata{}, nil
	}
	if err != nil {
		return instanceMetadata{}, fmt.Errorf("reading metadata of domain %s: %w", dom.Name, err)
	}
	return parseInstanceMetadata(raw)
}

// addressSources is the discovery order of spec entry 7: the guest agent
// answers where the host's ARP table never sees guest traffic.
var addressSources = []struct {
	name string
	src  libvirt.DomainInterfaceAddressesSource
}{
	{"agent", libvirt.DomainInterfaceAddressesSrcAgent},
	{"arp", libvirt.DomainInterfaceAddressesSrcArp},
}

// address returns the first usable IPv4 from the first source that yields
// one, or "" for "no address yet". One source failing is normal and is
// skipped: a booting VM has no agent yet, while the host's ARP table
// simply reports nothing, since it never sees traffic addressed
// elsewhere. A connection already gone, and every source failing, are
// errors instead — otherwise a link some other reconcile killed reads as
// a running VM that lost its address, and the controller clears its IP
// and the health engine drops its accumulated state.
func address(ctx context.Context, log logr.Logger, be backend, dom libvirt.Domain) (string, error) {
	errs := make([]error, 0, len(addressSources))
	for _, s := range addressSources {
		ifaces, err := be.DomainInterfaceAddresses(ctx, dom, uint32(s.src), 0)
		if err != nil {
			if isDead(be) || errors.Is(err, context.Canceled) || errors.Is(err, context.DeadlineExceeded) {
				return "", fmt.Errorf("reading addresses of domain %s from the %s source: %w", dom.Name, s.name, err)
			}
			log.V(2).Info("no addresses from source", "source", s.name, "error", err.Error())
			errs = append(errs, fmt.Errorf("%s source: %w", s.name, err))
			continue
		}
		if ip := firstIPv4(ifaces); ip != "" {
			return ip, nil
		}
	}
	// Transient explicitly: classify would otherwise pick a libvirt code
	// out of the joined error, and ErrInvalidArg, ErrAccessDenied and
	// ErrNoSupport are Permanent, which would latch a running proxy as
	// Failed over an address read.
	if len(errs) == len(addressSources) {
		return "", fmt.Errorf("%w: reading addresses of domain %s: every source failed: %w",
			provider.ErrTransient, dom.Name, errors.Join(errs...))
	}
	return "", nil
}