banger/internal/daemon/tap_pool.go
Thales Maciel 59e48e830b
daemon: split owner daemon from root helper
Move the supported systemd path to two services: an owner-user bangerd for
orchestration and a narrow root helper for bridge/tap, NAT/resolver, dm/loop,
and Firecracker ownership. This removes repeated sudo from daily vm and image
flows without leaving the general daemon running as root.

Add install metadata, system install/status/restart/uninstall commands, and a
system-owned runtime layout. Keep user SSH/config material in the owner home,
lock file_sync to the owner home, and move daemon known_hosts handling out of
the old root-owned control path.

Route privileged lifecycle steps through typed privilegedOps calls, harden the
two systemd units, and rewrite smoke plus docs around the supported service
model.

Verified with make build, make test, make lint, and make smoke on the
supported systemd host path.
2026-04-26 12:43:17 -03:00

129 lines
3 KiB
Go

package daemon
import (
"context"
"fmt"
"strconv"
"strings"
"sync"
)
const tapPoolPrefix = "tap-pool-"
// tapPool owns the idle TAP interface cache plus the monotonic index used to
// name new pool entries. All access goes through mu.
type tapPool struct {
mu sync.Mutex
entries []string
next int
}
// initializeTapPool seeds the monotonic pool index from the set of
// tap names already in use by running/stopped VMs, so newly warmed
// pool entries don't collide with existing ones. Callers (Daemon.Open)
// enumerate used taps from the handle cache and pass them in.
func (n *HostNetwork) initializeTapPool(usedTaps []string) {
if n.config.TapPoolSize <= 0 {
return
}
next := 0
for _, tapName := range usedTaps {
if index, ok := parseTapPoolIndex(tapName); ok && index >= next {
next = index + 1
}
}
n.tapPool.mu.Lock()
n.tapPool.next = next
n.tapPool.mu.Unlock()
}
func (n *HostNetwork) ensureTapPool(ctx context.Context) {
if n.config.TapPoolSize <= 0 {
return
}
for {
select {
case <-ctx.Done():
return
case <-n.closing:
return
default:
}
n.tapPool.mu.Lock()
if len(n.tapPool.entries) >= n.config.TapPoolSize {
n.tapPool.mu.Unlock()
return
}
tapName := fmt.Sprintf("%s%d", tapPoolPrefix, n.tapPool.next)
n.tapPool.next++
n.tapPool.mu.Unlock()
if err := n.createTap(ctx, tapName); err != nil {
if n.logger != nil {
n.logger.Warn("tap pool warmup failed", "tap_device", tapName, "error", err.Error())
}
return
}
n.tapPool.mu.Lock()
n.tapPool.entries = append(n.tapPool.entries, tapName)
n.tapPool.mu.Unlock()
if n.logger != nil {
n.logger.Debug("tap added to idle pool", "tap_device", tapName)
}
}
}
func (n *HostNetwork) acquireTap(ctx context.Context, fallbackName string) (string, error) {
n.tapPool.mu.Lock()
if count := len(n.tapPool.entries); count > 0 {
tapName := n.tapPool.entries[count-1]
n.tapPool.entries = n.tapPool.entries[:count-1]
n.tapPool.mu.Unlock()
return tapName, nil
}
n.tapPool.mu.Unlock()
if err := n.createTap(ctx, fallbackName); err != nil {
return "", err
}
return fallbackName, nil
}
func (n *HostNetwork) releaseTap(ctx context.Context, tapName string) error {
tapName = strings.TrimSpace(tapName)
if tapName == "" {
return nil
}
if isTapPoolName(tapName) {
n.tapPool.mu.Lock()
if len(n.tapPool.entries) < n.config.TapPoolSize {
n.tapPool.entries = append(n.tapPool.entries, tapName)
n.tapPool.mu.Unlock()
return nil
}
n.tapPool.mu.Unlock()
}
err := n.privOps().DeleteTap(ctx, tapName)
if err == nil {
go n.ensureTapPool(context.Background())
}
return err
}
func isTapPoolName(tapName string) bool {
return strings.HasPrefix(strings.TrimSpace(tapName), tapPoolPrefix)
}
func parseTapPoolIndex(tapName string) (int, bool) {
if !isTapPoolName(tapName) {
return 0, false
}
value, err := strconv.Atoi(strings.TrimPrefix(strings.TrimSpace(tapName), tapPoolPrefix))
if err != nil {
return 0, false
}
return value, true
}