First phase of splitting the daemon god-struct into focused services with explicit ownership. HostNetwork now owns everything host-networking: the TAP interface pool (initializeTapPool / ensureTapPool / acquireTap / releaseTap / createTap), bridge + socket dir setup, firecracker process primitives (find/resolve/kill/wait/ensureSocketAccess/sendCtrlAltDel), DM snapshot lifecycle, NAT rule enforcement, guest DNS server lifecycle + routing setup, and the vsock-agent readiness probe. That's 7 files whose receivers flipped from *Daemon to *HostNetwork, plus a new host_network.go that declares the struct, its hostNetworkDeps, and the factored firecracker + DNS helpers that used to live in vm.go. Daemon gives up the tapPool and vmDNS fields entirely; they're now HostNetwork's business. Construction goes through newHostNetwork in Daemon.Open with an explicit dependency bag (runner, logger, config, layout, closing). A lazy-init hostNet() helper on Daemon supports test literals that don't wire net explicitly — production always populates it eagerly. Signature tightenings where the old receiver reached into VM-service state: - ensureNAT(ctx, vm, enable) → ensureNAT(ctx, guestIP, tap, enable). Callers resolve tap from the handle cache themselves. - initializeTapPool(ctx) → initializeTapPool(usedTaps []string). Daemon.Open enumerates VMs, collects taps from handles, hands the slice in. rebuildDNS stays on *Daemon as the orchestrator — it filters by vm-alive (a VMService concern handles will move to in phase 4) then calls HostNetwork.replaceDNS with the already-filtered map. Capability hooks continue to take *Daemon; they now use it as a facade to reach services (d.net.ensureNAT, d.hostNet().*). Planned CapabilityHost interface extraction is orthogonal, left for later. Tests: dns_routing_test.go + fastpath_test.go + nat_test.go + snapshot_test.go + open_close_test.go were touched to construct HostNetwork literals where they exercise its methods directly, or route through d.hostNet() where they exercise the Daemon entry points. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
129 lines
3 KiB
Go
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.runner.RunSudo(ctx, "ip", "link", "del", 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
|
|
}
|