banger/internal/daemon/vm_create_ops.go
Thales Maciel 30f0c0b54a
Manage image artifacts and show VM create progress
Stop relying on ad hoc rootfs handling by adding image promotion, managed work-seed fingerprint metadata, and lazy self-healing for older managed images after the first create.

Rebuild guest images with baked SSH access, a guest NIC bootstrap, and default opencode services, and add the staged Void kernel/initramfs/modules workflow so void-exp uses a matching Void boot stack.

Replace the opaque blocking vm.create RPC with a begin/status flow that prints live stages in the CLI while still waiting for vsock health and opencode on guest port 4096.

Validate with GOCACHE=/tmp/banger-gocache go test ./... and live void-exp create/delete smoke runs.
2026-03-21 14:48:01 -03:00

205 lines
4.4 KiB
Go

package daemon
import (
"context"
"fmt"
"strings"
"sync"
"time"
"banger/internal/api"
"banger/internal/model"
)
type vmCreateProgressKey struct{}
type vmCreateOperationState struct {
mu sync.Mutex
cancel context.CancelFunc
op api.VMCreateOperation
}
func newVMCreateOperationState() (*vmCreateOperationState, error) {
id, err := model.NewID()
if err != nil {
return nil, err
}
now := model.Now()
return &vmCreateOperationState{
op: api.VMCreateOperation{
ID: id,
Stage: "queued",
Detail: "waiting to start",
StartedAt: now,
UpdatedAt: now,
},
}, nil
}
func withVMCreateProgress(ctx context.Context, op *vmCreateOperationState) context.Context {
if op == nil {
return ctx
}
return context.WithValue(ctx, vmCreateProgressKey{}, op)
}
func vmCreateProgressFromContext(ctx context.Context) *vmCreateOperationState {
if ctx == nil {
return nil
}
op, _ := ctx.Value(vmCreateProgressKey{}).(*vmCreateOperationState)
return op
}
func vmCreateStage(ctx context.Context, stage, detail string) {
if op := vmCreateProgressFromContext(ctx); op != nil {
op.stage(stage, detail)
}
}
func vmCreateBindVM(ctx context.Context, vm model.VMRecord) {
if op := vmCreateProgressFromContext(ctx); op != nil {
op.bindVM(vm)
}
}
func (op *vmCreateOperationState) setCancel(cancel context.CancelFunc) {
op.mu.Lock()
defer op.mu.Unlock()
op.cancel = cancel
}
func (op *vmCreateOperationState) bindVM(vm model.VMRecord) {
op.mu.Lock()
defer op.mu.Unlock()
op.op.VMID = vm.ID
op.op.VMName = vm.Name
}
func (op *vmCreateOperationState) stage(stage, detail string) {
op.mu.Lock()
defer op.mu.Unlock()
stage = strings.TrimSpace(stage)
detail = strings.TrimSpace(detail)
if stage == "" {
stage = op.op.Stage
}
if stage == op.op.Stage && detail == op.op.Detail {
return
}
op.op.Stage = stage
op.op.Detail = detail
op.op.UpdatedAt = model.Now()
}
func (op *vmCreateOperationState) done(vm model.VMRecord) {
op.mu.Lock()
defer op.mu.Unlock()
vmCopy := vm
op.op.VMID = vm.ID
op.op.VMName = vm.Name
op.op.Stage = "ready"
op.op.Detail = "vm is ready"
op.op.Done = true
op.op.Success = true
op.op.Error = ""
op.op.VM = &vmCopy
op.op.UpdatedAt = model.Now()
}
func (op *vmCreateOperationState) fail(err error) {
op.mu.Lock()
defer op.mu.Unlock()
op.op.Done = true
op.op.Success = false
if err != nil {
op.op.Error = err.Error()
}
if strings.TrimSpace(op.op.Detail) == "" {
op.op.Detail = "vm create failed"
}
op.op.UpdatedAt = model.Now()
}
func (op *vmCreateOperationState) snapshot() api.VMCreateOperation {
op.mu.Lock()
defer op.mu.Unlock()
snapshot := op.op
if snapshot.VM != nil {
vmCopy := *snapshot.VM
snapshot.VM = &vmCopy
}
return snapshot
}
func (op *vmCreateOperationState) cancelOperation() {
op.mu.Lock()
cancel := op.cancel
op.mu.Unlock()
if cancel != nil {
cancel()
}
}
func (d *Daemon) BeginVMCreate(_ context.Context, params api.VMCreateParams) (api.VMCreateOperation, error) {
op, err := newVMCreateOperationState()
if err != nil {
return api.VMCreateOperation{}, err
}
createCtx, cancel := context.WithCancel(context.Background())
op.setCancel(cancel)
d.createOpsMu.Lock()
if d.createOps == nil {
d.createOps = map[string]*vmCreateOperationState{}
}
d.createOps[op.op.ID] = op
d.createOpsMu.Unlock()
go d.runVMCreateOperation(withVMCreateProgress(createCtx, op), op, params)
return op.snapshot(), nil
}
func (d *Daemon) runVMCreateOperation(ctx context.Context, op *vmCreateOperationState, params api.VMCreateParams) {
vm, err := d.CreateVM(ctx, params)
if err != nil {
op.fail(err)
return
}
op.done(vm)
}
func (d *Daemon) VMCreateStatus(_ context.Context, id string) (api.VMCreateOperation, error) {
d.createOpsMu.Lock()
op, ok := d.createOps[strings.TrimSpace(id)]
d.createOpsMu.Unlock()
if !ok {
return api.VMCreateOperation{}, fmt.Errorf("vm create operation not found: %s", id)
}
return op.snapshot(), nil
}
func (d *Daemon) CancelVMCreate(_ context.Context, id string) error {
d.createOpsMu.Lock()
op, ok := d.createOps[strings.TrimSpace(id)]
d.createOpsMu.Unlock()
if !ok {
return fmt.Errorf("vm create operation not found: %s", id)
}
op.cancelOperation()
return nil
}
func (d *Daemon) pruneVMCreateOperations(olderThan time.Time) {
d.createOpsMu.Lock()
defer d.createOpsMu.Unlock()
for id, op := range d.createOps {
snapshot := op.snapshot()
if !snapshot.Done {
continue
}
if snapshot.UpdatedAt.Before(olderThan) {
delete(d.createOps, id)
}
}
}