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

package proxmox

import (
	"context"
	"errors"
	"fmt"

	"github.com/go-logr/logr"

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

// lockSuspended is the lock of a VM hibernated to disk: it is not a task in
// progress, and the VM stays that way until someone resumes it.
const lockSuspended = "suspended"

// Get is spec entries 7 to 9: the VMID's resource entry, then its config
// for the name and the mark, then status/current and, for a running VM, the
// guest agent. A running Get makes four calls.
func (p *Provider) Get(ctx context.Context, id string) (*provider.Instance, error) {
	vmid, name, err := parseProviderID(id)
	if err != nil {
		return nil, p.wrapErr("get", id, err)
	}
	log := p.logger(ctx).WithValues("vmid", vmid, "name", name)
	inst, err := p.get(ctx, log, vmid, name)
	if err != nil {
		err = p.wrapErr("get", id, err)
		if errors.Is(err, provider.ErrNotFound) {
			log.V(1).Info("proxmox vm not found", "reason", err.Error())
		}
		return nil, err
	}
	return inst, nil
}

func (p *Provider) get(ctx context.Context, log logr.Logger, vmid int, name string) (*provider.Instance, error) {
	r, ok, err := p.resolve(ctx, vmid)
	if err != nil {
		return nil, err
	}
	if !ok {
		return nil, fmt.Errorf("%w: VM %d is not in the cluster's resources", provider.ErrNotFound, vmid)
	}
	log = log.WithValues("node", r.Node)
	// A mid-clone entry has no name and status unknown, so the lock is
	// checked before anything that would read it as absent or foreign.
	if r.Lock != "" && r.Lock != lockSuspended {
		return nil, transientf("VM %d is locked (%s)", vmid, r.Lock)
	}
	if r.Status == "unknown" {
		return nil, transientf("VM %d has status unknown: its node %s is not answering, or the VM is too new to be reported yet", vmid, r.Node)
	}
	cfg, err := p.api.VMConfig(ctx, r.Node, vmid)
	if err != nil {
		return nil, fmt.Errorf("reading config of VM %d: %w", vmid, err)
	}
	if lock := cfg["lock"]; lock != "" && lock != lockSuspended {
		return nil, transientf("VM %d is locked (%s)", vmid, lock)
	}
	if cfg["name"] != name {
		return nil, fmt.Errorf("%w: VM %d is now named %q: the VMID was reused", provider.ErrNotFound, vmid, cfg["name"])
	}
	mark := parseDescription(cfg["description"])
	if !mark.Managed {
		return nil, fmt.Errorf("%w: VM %d carries no proxy-operator mark", provider.ErrNotFound, vmid)
	}
	inst := &provider.Instance{ID: formatProviderID(vmid, name), UID: mark.UID, CreatedAt: mark.CreatedAt}

	// A hibernated VM is Stopped whatever status/current says; it needs no
	// further call.
	if r.Lock == lockSuspended || cfg["lock"] == lockSuspended {
		inst.State = provider.StateStopped
		log.V(1).Info("proxmox vm fetched", "state", inst.State, "lock", lockSuspended, "uid", inst.UID)
		return inst, nil
	}
	st, err := p.api.VMStatus(ctx, r.Node, vmid)
	if err != nil {
		return nil, fmt.Errorf("reading status of VM %d: %w", vmid, err)
	}
	if guestRunning(st.Status, st.QMPStatus) {
		ip, state, err := p.agentAddress(ctx, log, r.Node, vmid)
		if err != nil {
			return nil, err
		}
		inst.IP = ip
		inst.State = state
	} else {
		inst.State = mapState(st.Status, st.QMPStatus, "")
	}
	log.V(1).Info("proxmox vm fetched", "state", inst.State, "ip", inst.IP, "uid", inst.UID, "status", st.Status, "qmpstatus", st.QMPStatus)
	return inst, nil
}

// agentAddress asks the guest agent of a running VM for its address and
// turns its answers into a state (spec entry 7). Any answer it cannot place
// is Transient, whatever its status: an address read never latches or
// loses a Proxy.
func (p *Provider) agentAddress(ctx context.Context, log logr.Logger, node string, vmid int) (string, provider.InstanceState, error) {
	ifaces, err := p.api.AgentNetworkInterfaces(ctx, node, vmid)
	switch {
	case err == nil:
		ip := firstIPv4(ifaces)
		log.V(2).Info("proxmox guest agent answered", "interfaces", len(ifaces), "ip", ip)
		return ip, mapState("running", "running", ip), nil
	case isAgentNotRunning(err):
		return "", provider.StateProvisioning, nil
	case isAgentNotConfigured(err):
		// agent=1 was removed: this VM can never report an address, so it
		// is replaced by one that can.
		return "", provider.StateStopped, nil
	default:
		// Includes "VM <vmid> is not running": it stopped since the status
		// read, and the next Get sees that directly.
		return "", "", fmt.Errorf("%w: reading the guest agent of VM %d: %w", provider.ErrTransient, vmid, err)
	}
}

// resolve finds a VMID in the cluster's resources. Only QEMU VMs count: a
// container at the VMID means ours is gone.
func (p *Provider) resolve(ctx context.Context, vmid int) (vmResource, bool, error) {
	rs, err := p.api.ClusterResources(ctx)
	if err != nil {
		return vmResource{}, false, fmt.Errorf("listing cluster resources: %w", err)
	}
	for _, r := range rs {
		if r.VMID == vmid && r.Type == "qemu" {
			return r, true, nil
		}
	}
	return vmResource{}, false, nil
}