mesh-catalog/modules/mesh-build-image/cmd/mesh-build-image/module.go

package main

import (
	"context"
	"fmt"
	"net/http"
	"sync"
	"time"

	"git.novox.be/novox/mesh-sdk/go/buildstep"
	"git.novox.be/novox/mesh-sdk/go/delivery"
	"git.novox.be/novox/mesh-sdk/go/forgekey"
	"git.novox.be/novox/mesh-sdk/go/health"
)

// CheckRound is how often the module looks at itself again, beside the look before every step and at every health look.
const CheckRound = 10 * time.Minute

// Module is the image build module's one running state.
type Module struct {
	Node string
	// Account and UID are the account the module runs as; Home is its home.
	Account, UID, Home string
	// Steps is the Put of the steps state; ReadSteps reads it back for the read tools.
	Steps     buildstep.Put
	ReadSteps StateRead
	// Ctx is the process's context, which a step runs under (the tool call's is cut at 30 s, the step's is not).
	Ctx context.Context
	Say func(format string, a ...any)
	// Run runs the commands of a step (StepRunner); Work holds the workspaces and Store buildah's image store, both
	// outside the account's home (ADR 0466 §1).
	Run         forgekey.Runner
	Work, Store string
	// SubUIDFile and SubGIDFile are the subordinate id files; /etc/subuid and /etc/subgid when empty.
	SubUIDFile, SubGIDFile string
	// RegistryFile holds the registry's address, host:port, which the manifest binds from the artifact-store provision.
	RegistryFile string
	// RemoteBase is where repositories are fetched from, "ssh://mesh-forge/" when empty; FetchOptions are the options of
	// the SDK's fetch and merge. A test points them at a local repository (buildstep.AllowFileRemote).
	RemoteBase   string
	FetchOptions []buildstep.Option
	// HTTP talks to the registry; a client of its own when nil. RegistryWait and RegistryPause bound the wait for a
	// registry held still (RegistryWait and RegistryFirstPause when zero).
	HTTP          *http.Client
	RegistryWait  time.Duration
	RegistryPause time.Duration
	// Now is the clock; time.Now when nil.
	Now func() time.Time
	// Floor refuses every fetch and build while the work or the image store's filesystem has less free than it (issue
	// 1839); main sets floorOf(node), and a zero Floor checks nothing.
	Floor buildstep.Floor

	spacesOnce sync.Once
	workspaces *buildstep.Workspaces
}

// Look is what the module found out about its machine.
type Look struct {
	Buildah    string
	UIDs, GIDs int
	Account    string
}

// look proves the machine: buildah runs, the account holds ranges, a user namespace can be made. The first thing
// missing is a *buildstep.Refusal naming it, so a step ends refused and the health says the same.
func (m *Module) look(ctx context.Context) (Look, error) {
	l := Look{Account: m.Account}
	// The runtime directory comes first: buildah refuses before anything else when its XDG_RUNTIME_DIR is not there
	// (issue 1884), so a look that made it only after `buildah --version` never made it at all.
	if err := m.ensureRuntimeDir(); err != nil {
		return l, &buildstep.Refusal{Text: err.Error()}
	}
	var err error
	if l.Buildah, err = m.buildahVersion(ctx); err != nil {
		return l, &buildstep.Refusal{Text: err.Error()}
	}
	if l.UIDs, l.GIDs, err = m.ranges(); err != nil {
		return l, &buildstep.Refusal{Text: err.Error(), Have: l.Buildah}
	}
	if err := m.userNamespace(ctx); err != nil {
		return l, &buildstep.Refusal{Text: err.Error(), Have: l.Buildah}
	}
	return l, nil
}

// Check is the guard: nil when the machine can build, else the refusal.
func (m *Module) Check(ctx context.Context) error {
	_, err := m.look(ctx)
	return err
}

// Start looks once, as the module starts, and then every CheckRound until ctx ends; it also removes old workspaces.
func (m *Module) Start(ctx context.Context) {
	for {
		if err := m.Check(ctx); err != nil && m.Say != nil {
			m.Say("this machine cannot build images: %v", err)
		}
		m.CleanWorkspaces(m.clock())
		select {
		case <-ctx.Done():
			return
		case <-time.After(CheckRound):
		}
	}
}

// Health is the module's health (the runtime-health tool, ADR 0366): unhealthy while it cannot build, saying why,
// healthy it names the buildah installed and the account's ranges (ADR 0487 §2: the ranges are proven here, not declared).
func (m *Module) Health(ctx context.Context) health.Answer {
	l, err := m.look(ctx)
	if err != nil {
		return health.Unhealthy(err.Error())
	}
	if err := m.room(); err != nil {
		return health.Unhealthy(err.Error())
	}
	return health.Healthy(fmt.Sprintf("buildah %s installed; %s holds %d subordinate uids and %d gids; a user namespace can be made", l.Buildah, l.Account, l.UIDs, l.GIDs))
}

// Status is what the module reports of itself.
func (m *Module) Status(ctx context.Context) map[string]any {
	l, err := m.look(ctx)
	out := map[string]any{"node": m.Node, "account": m.Account, "buildah": l.Buildah, "subuids": l.UIDs, "subgids": l.GIDs, "refusing": err != nil}
	if err != nil {
		out["why"] = err.Error()
	}
	return out
}

// Long is a tool that runs a long step (ADR 0469 §2): it answers at once with the step's id, and the step ends on its
// key in the steps state. The guard runs inside the step, before run, so a machine that cannot build ends every step
// refused with the cause named.
func (m *Module) Long(tool string, run func(ctx context.Context, args map[string]any) (any, error)) func(map[string]any) (any, error) {
	return func(args map[string]any) (any, error) {
		id, err := buildstep.Start(m.Ctx, m.Steps, m.Node, tool, func(ctx context.Context) (any, error) {
			if err := m.Check(ctx); err != nil {
				return nil, err
			}
			if err := m.room(); err != nil {
				return nil, err
			}
			defer m.holdArg(args)()
			return run(ctx, args)
		})
		if err != nil {
			return nil, err
		}
		key, _ := delivery.StepKey(m.Node, id)
		return map[string]any{"step": id, "key": key, "state": delivery.StepRunning}, nil
	}
}

// Short is a tool that answers in its own call; the guard runs before it, and a refusal is the call's error.
func (m *Module) Short(run func(ctx context.Context, args map[string]any) (any, error)) func(map[string]any) (any, error) {
	return func(args map[string]any) (any, error) {
		if err := m.Check(m.Ctx); err != nil {
			return nil, err
		}
		if err := m.room(); err != nil {
			return nil, err
		}
		defer m.holdArg(args)()
		return run(m.Ctx, args)
	}
}