mirror of
https://tangled.org/evan.jarrett.net/at-container-registry
synced 2026-09-23 02:34:17 +00:00
The scanner shared the hold's 1 GB host and thrashed it twice: 11 hours on 2026-09-12 and again on the 13th (644 MiB resident plus 1.9 GB of swap, 504 on every repo page). It is memory-bound, not CPU-bound, so it now gets a dedicated STARTER-2xCPU-4GB server: own state entry, own plan flag (pinned name, shape match if UpCloud renames the tier again, picker last), own cloud-init, firewall, `update scanner`, `ssh scanner`, status, backup and teardown. Its config reaches the hold over the private network and its unit sets MemorySwapMax=0 so an overshoot is an OOM kill and a restart, not a wedged host. The hold's cloud-init and update paths no longer carry it. Three defects the first provision run exposed, all fixed here: - Frontend HTTP/2 defaulted to on and was reconciled onto the LB every run. Re-enabling it on the 12th stranded the appview<->hold connections for 25 minutes. Default is now off and reconciled off, with a guard test. - The TLS step requested Let's Encrypt bundles for every registry domain, re-adding the .cr ones that were removed when those moved behind Bunny. It now skips any domain whose DNS does not resolve to the LB. - Each prompt built its own bufio.Scanner on stdin, so the first swallowed every piped answer and the second read EOF and took the default, which re-ran cloud-init on the production hold. One shared reader, and no answer now means skip. Also: STARTER- plans take standard storage (maxiops fails with TIER_INVALID), and the cloud-init wait polls for up to 20 minutes instead of one SSH call capped at five, which a first boot with npm exceeds. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Hho5da4daoCoPBJ9tCrL7s
130 lines
3.4 KiB
Go
130 lines
3.4 KiB
Go
package main
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
"strings"
|
|
"time"
|
|
|
|
"github.com/UpCloudLtd/upcloud-go-api/v8/upcloud/request"
|
|
"github.com/spf13/cobra"
|
|
)
|
|
|
|
var statusCmd = &cobra.Command{
|
|
Use: "status",
|
|
Short: "Show infrastructure state and health",
|
|
Args: cobra.NoArgs,
|
|
RunE: func(cmd *cobra.Command, args []string) error {
|
|
token, _ := cmd.Root().PersistentFlags().GetString("token")
|
|
return cmdStatus(token)
|
|
},
|
|
}
|
|
|
|
func init() {
|
|
rootCmd.AddCommand(statusCmd)
|
|
}
|
|
|
|
func cmdStatus(token string) error {
|
|
state, err := loadState()
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
naming := state.Naming()
|
|
|
|
svc, err := newService(token)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
|
|
defer cancel()
|
|
|
|
fmt.Printf("Zone: %s\n\n", state.Zone)
|
|
|
|
// Server status
|
|
servers := []struct {
|
|
name string
|
|
ss ServerState
|
|
serviceName string
|
|
healthURL string
|
|
}{
|
|
{"Appview", state.Appview, naming.Appview(), "http://localhost:5000/health"},
|
|
{"Hold", state.Hold, naming.Hold(), "http://localhost:8080/xrpc/_health"},
|
|
}
|
|
if state.ScannerEnabled || state.Scanner.UUID != "" {
|
|
servers = append(servers, struct {
|
|
name string
|
|
ss ServerState
|
|
serviceName string
|
|
healthURL string
|
|
}{"Scanner", state.Scanner, naming.Scanner(), "http://localhost:9090/healthz"})
|
|
}
|
|
for _, s := range servers {
|
|
fmt.Printf("%-8s UUID: %s\n", s.name, s.ss.UUID)
|
|
fmt.Printf(" Public: %s\n", s.ss.PublicIP)
|
|
fmt.Printf(" Private: %s\n", s.ss.PrivateIP)
|
|
|
|
if s.ss.UUID != "" {
|
|
details, err := svc.GetServerDetails(ctx, &request.GetServerDetailsRequest{
|
|
UUID: s.ss.UUID,
|
|
})
|
|
if err != nil {
|
|
fmt.Printf(" State: error (%v)\n", err)
|
|
} else {
|
|
fmt.Printf(" State: %s\n", details.State)
|
|
}
|
|
}
|
|
|
|
// SSH health check
|
|
if s.ss.PublicIP != "" {
|
|
output, err := runSSH(s.ss.PublicIP, fmt.Sprintf(
|
|
"systemctl is-active %s 2>/dev/null || echo 'inactive'; curl -sf %s > /dev/null 2>&1 && echo 'health:ok' || echo 'health:fail'",
|
|
s.serviceName, s.healthURL,
|
|
), false)
|
|
if err != nil {
|
|
fmt.Printf(" Service: unreachable\n")
|
|
} else {
|
|
lines := strings.SplitSeq(strings.TrimSpace(output), "\n")
|
|
for line := range lines {
|
|
line = strings.TrimSpace(line)
|
|
if line == "active" || line == "inactive" {
|
|
fmt.Printf(" Service: %s\n", line)
|
|
} else if after, ok := strings.CutPrefix(line, "health:"); ok {
|
|
fmt.Printf(" Health: %s\n", after)
|
|
}
|
|
}
|
|
}
|
|
}
|
|
fmt.Println()
|
|
}
|
|
|
|
// LB status
|
|
if state.LB.UUID != "" {
|
|
fmt.Printf("Load Balancer: %s\n", state.LB.UUID)
|
|
lb, err := svc.GetLoadBalancer(ctx, &request.GetLoadBalancerRequest{
|
|
UUID: state.LB.UUID,
|
|
})
|
|
if err != nil {
|
|
fmt.Printf(" State: error (%v)\n", err)
|
|
} else {
|
|
fmt.Printf(" State: %s\n", lb.OperationalState)
|
|
for _, n := range lb.Networks {
|
|
fmt.Printf(" Network (%s): %s\n", n.Type, n.DNSName)
|
|
}
|
|
}
|
|
}
|
|
|
|
fmt.Printf("\nNetwork: %s\n", state.Network.UUID)
|
|
|
|
if state.ObjectStorage.UUID != "" {
|
|
fmt.Printf("\nObject Storage: %s\n", state.ObjectStorage.UUID)
|
|
fmt.Printf(" Endpoint: %s\n", state.ObjectStorage.Endpoint)
|
|
fmt.Printf(" Region: %s\n", state.ObjectStorage.Region)
|
|
fmt.Printf(" Bucket: %s\n", state.ObjectStorage.Bucket)
|
|
fmt.Printf(" Access Key: %s\n", state.ObjectStorage.AccessKeyID)
|
|
}
|
|
|
|
return nil
|
|
}
|