forked from wrenn/wrenn
pptx704
9bf67aa7f7
Replaces the hardcoded CP_HOST_AGENT_ADDR single-agent setup with a DB-driven registration system supporting multiple host agents (BYOC). Key changes: - Host agents register via one-time token, receive a 7-day JWT + 60-day refresh token; heartbeat loop auto-refreshes on 401/403 and pauses all sandboxes if refresh fails - HostClientPool: lazy Connect RPC client cache keyed by host ID, replacing the single static agent client throughout the API and service layers - RoundRobinScheduler: picks an online host for each new sandbox via ListActiveHosts; extensible for future scheduling strategies - HostMonitor (replaces Reconciler): passive heartbeat staleness check marks hosts unreachable and sandboxes missing after 90s; active reconciliation per online host restores missing-but-alive sandboxes and stops orphans - Graceful host delete: returns 409 with affected sandbox list without ?force=true; force-delete destroys sandboxes then evicts pool client - Snapshot delete broadcasts to all online hosts (templates have no host_id) - sandbox.Manager.PauseAll: pauses all running VMs on CP connectivity loss - New migration: host_refresh_tokens table with token rotation (issue-then- revoke ordering to prevent lockout on mid-rotation crash) - New sandbox status 'missing' (reversible, unlike 'stopped') and host status 'unreachable'; both reflected in OpenAPI spec - Fix: refresh token auth failure now returns 401 (was 400 via generic 'invalid' substring match in serviceErrToHTTP)
52 lines
1.5 KiB
Go
52 lines
1.5 KiB
Go
package scheduler
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
"sync/atomic"
|
|
|
|
"git.omukk.dev/wrenn/sandbox/internal/db"
|
|
)
|
|
|
|
// HostScheduler selects a host for a new sandbox. Implementations may use
|
|
// different strategies (round-robin, least-loaded, tag-based, etc.).
|
|
type HostScheduler interface {
|
|
// SelectHost returns a host that can accept a new sandbox.
|
|
// Returns an error if no suitable host is available.
|
|
SelectHost(ctx context.Context) (db.Host, error)
|
|
}
|
|
|
|
// RoundRobinScheduler cycles through online hosts in round-robin order.
|
|
// It re-fetches the host list on every call so that newly registered or
|
|
// recovered hosts are considered immediately.
|
|
type RoundRobinScheduler struct {
|
|
db *db.Queries
|
|
counter atomic.Int64
|
|
}
|
|
|
|
// NewRoundRobinScheduler creates a RoundRobinScheduler backed by the given DB.
|
|
func NewRoundRobinScheduler(queries *db.Queries) *RoundRobinScheduler {
|
|
return &RoundRobinScheduler{db: queries}
|
|
}
|
|
|
|
// SelectHost returns the next online host in round-robin order.
|
|
func (s *RoundRobinScheduler) SelectHost(ctx context.Context) (db.Host, error) {
|
|
hosts, err := s.db.ListActiveHosts(ctx)
|
|
if err != nil {
|
|
return db.Host{}, fmt.Errorf("list hosts: %w", err)
|
|
}
|
|
|
|
var online []db.Host
|
|
for _, h := range hosts {
|
|
if h.Status == "online" && h.Address.Valid && h.Address.String != "" {
|
|
online = append(online, h)
|
|
}
|
|
}
|
|
if len(online) == 0 {
|
|
return db.Host{}, fmt.Errorf("no online hosts available")
|
|
}
|
|
|
|
idx := s.counter.Add(1) - 1
|
|
return online[int(idx%int64(len(online)))], nil
|
|
}
|