Ilker ManapandClaude Opus 5.5
5cf0003e74
Collects rc.1 to rc.14: the mirror page in tabs with a card per model, one line per record in every admin table, reserved CPU cores and required memory, capacity classes and preemption, tenant capacity quotas, sizing by measured throughput, and node sensor readings. Adds `llmgw upgrade` for the mirror host, which `ctl upgrade` does not reach, and says so when it ends. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
88 lines
3.1 KiB
Go
88 lines
3.1 KiB
Go
package cli
|
|
|
|
import (
|
|
"errors"
|
|
"fmt"
|
|
"os"
|
|
"os/exec"
|
|
"runtime"
|
|
"strings"
|
|
"time"
|
|
|
|
"github.com/spf13/cobra"
|
|
|
|
"gitea.mynodes.xyz/ilker/llmgw/internal/release"
|
|
"gitea.mynodes.xyz/ilker/llmgw/internal/version"
|
|
)
|
|
|
|
// newSelfUpgradeCmd upgrades this machine's llmgw on its own, for the machines
|
|
// `llmgw ctl upgrade` does not reach: a mirror host, above all, whose service
|
|
// runs unprivileged with the filesystem read-only and so cannot replace its own
|
|
// binary the way an agent does.
|
|
func newSelfUpgradeCmd() *cobra.Command {
|
|
var releases, service string
|
|
c := &cobra.Command{
|
|
Use: "upgrade VERSION [--service UNIT]",
|
|
Short: "Upgrade this machine's llmgw, and restart the service that runs it",
|
|
Long: "For a machine the control plane does not upgrade — the model mirror's host.\n" +
|
|
"The control plane and the nodes are upgraded with `llmgw ctl upgrade`.\n\n" +
|
|
"Fetches the release for this platform, checks it against the release's\n" +
|
|
"checksums, keeps the old binary beside the new one, and restarts --service,\n" +
|
|
"waiting for it to be running again. Run it with sudo.",
|
|
Args: cobra.ExactArgs(1),
|
|
RunE: func(cmd *cobra.Command, args []string) error {
|
|
v := args[0]
|
|
out := cmd.OutOrStdout()
|
|
if !release.Tag.MatchString(v) {
|
|
return fmt.Errorf("%q is not a release version (v1.2.3 or v1.2.3-rc.4)", v)
|
|
}
|
|
if version.Version == v {
|
|
fmt.Fprintf(out, "this machine already runs %s\n", v)
|
|
return nil
|
|
}
|
|
if os.Geteuid() != 0 {
|
|
return errors.New("replacing this machine's binary needs root: run it with sudo")
|
|
}
|
|
self, err := os.Executable()
|
|
if err != nil {
|
|
return err
|
|
}
|
|
backup, err := release.Install(cmd.Context(), nil, releases, v, runtime.GOOS, runtime.GOARCH, self)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
fmt.Fprintf(out, "%s -> %s: installed, checksum verified; the old binary is %s\n",
|
|
version.Version, v, backup)
|
|
if service == "" {
|
|
return nil
|
|
}
|
|
//nolint:gosec // the unit name is the operator's own flag
|
|
if b, err := exec.CommandContext(cmd.Context(), "systemctl", "restart", service).CombinedOutput(); err != nil {
|
|
return fmt.Errorf("restarting %s: %v: %s", service, err, strings.TrimSpace(string(b)))
|
|
}
|
|
// Running, and still running a few seconds on: a unit that starts
|
|
// and dies on a bad flag is "active" for a moment first.
|
|
deadline := time.Now().Add(30 * time.Second)
|
|
steady := 0
|
|
for time.Now().Before(deadline) {
|
|
//nolint:gosec // as above
|
|
b, _ := exec.CommandContext(cmd.Context(), "systemctl", "is-active", service).Output()
|
|
if strings.TrimSpace(string(b)) == "active" {
|
|
if steady++; steady >= 3 {
|
|
fmt.Fprintf(out, "%s restarted and running\n", service)
|
|
return nil
|
|
}
|
|
} else {
|
|
steady = 0
|
|
}
|
|
time.Sleep(2 * time.Second)
|
|
}
|
|
return fmt.Errorf("%s is not running after the upgrade; see journalctl -u %s, and %s holds the previous binary",
|
|
service, service, backup)
|
|
},
|
|
}
|
|
c.Flags().StringVar(&releases, "releases", release.DefaultBase, "where release binaries are fetched from")
|
|
c.Flags().StringVar(&service, "service", "", "the systemd unit to restart afterwards, e.g. llmgw-mirror")
|
|
return c
|
|
}
|