llmgw/internal/cli/ctl_restart.go

package cli

import (
	"encoding/json"
	"errors"
	"fmt"

	"github.com/spf13/cobra"

	"gitea.mynodes.xyz/ilker/llmgw/internal/control/adminapi"
)

func newRestartCmd(client func() *ctlClient) *cobra.Command {
	var (
		models             []string
		all                bool
		inPlace            bool
		surge, unavailable int
	)
	c := &cobra.Command{
		Use:   "restart [REPLICA...]",
		Short: "Replace replicas with new ones, starting each replacement before stopping the old",
		Long: "How a running engine picks up what only applies at start: an engine key,\n" +
			"an edited profile, a new engine version.\n\n" +
			"Each replacement is placed beside the replica it replaces, and the old one\n" +
			"keeps serving until the new one is ready. Replicas of one model are\n" +
			"replaced one at a time.\n\n" +
			"Where there is no room for a second copy and the old replica is all that\n" +
			"is in the way — one GPU, every card that fits held — it is stopped at once\n" +
			"and the new one starts in its place; a model with only that replica is\n" +
			"unserved while it loads. Where the new one would not fit even then — a\n" +
			"profile edited to need more than any node has — the restart is given up\n" +
			"and the old replica keeps serving: llmgw ctl replicas says so, and why.\n\n" +
			"--in-place stops each replica first, whatever room there is.\n\n" +
			"A model's replicas are replaced one at a time. --max-surge N replaces N at\n" +
			"once, each beside itself, needing room for N more; --max-unavailable N\n" +
			"stops N at once first, needing no room and leaving N fewer serving while\n" +
			"they load. Together, the first N are stopped first and the rest surged.\n\n" +
			"  llmgw ctl restart qwen2.5-7b-3f2a91c0\n" +
			"  llmgw ctl restart --model qwen2.5-7b\n" +
			"  llmgw ctl restart --all",
		RunE: func(cmd *cobra.Command, args []string) error {
			if len(args) == 0 && len(models) == 0 && !all {
				return errors.New("name replicas, --model, or --all")
			}
			body, _ := json.Marshal(adminapi.RestartRequest{Replicas: args, Models: models, All: all, InPlace: inPlace,
				MaxSurge: surge, MaxUnavailable: unavailable})
			var res adminapi.RestartResult
			if err := client().post(cmd.Context(), "/api/v1/restart", body, &res); err != nil {
				return err
			}
			fmt.Printf("%d replica(s) queued for restart; watch with: llmgw ctl replicas\n", len(res.Queued))
			return nil
		},
	}
	c.Flags().StringArrayVar(&models, "model", nil, "every replica of this model; repeatable")
	c.Flags().BoolVar(&all, "all", false, "every ready replica in the cluster")
	c.Flags().BoolVar(&inPlace, "in-place", false, "stop each replica before starting its replacement")
	c.Flags().IntVar(&surge, "max-surge", 0, "replicas of a model replaced beside themselves at once (default 1)")
	c.Flags().IntVar(&unavailable, "max-unavailable", 0,
		"replicas of a model stopped first at once, each out while its replacement loads")
	return c
}

func newRetryCmd(client func() *ctlClient) *cobra.Command {
	return &cobra.Command{
		Use:   "retry MODEL",
		Short: "Try a parked model again, and clear its backoff",
		Long: "A model whose replicas fail every time they start is parked after five\n" +
			"failures in a row: it is not placed again until its definition changes\n" +
			"or this is run. Run it once the cause — the weights, the engine, the\n" +
			"profile — has been dealt with; `llmgw ctl status` lists parked models with\n" +
			"their last error.",
		Args: cobra.ExactArgs(1),
		RunE: func(cmd *cobra.Command, args []string) error {
			var res struct {
				WasParked bool `json:"was_parked"`
			}
			if err := client().post(cmd.Context(), "/api/v1/models/"+args[0]+"/retry", []byte(`{}`), &res); err != nil {
				return err
			}
			if res.WasParked {
				fmt.Printf("%s unparked; it is placed on the next pass\n", args[0])
			} else {
				fmt.Printf("%s was not parked; its backoff is cleared\n", args[0])
			}
			return nil
		},
	}
}