mesh-delivery/modules/mesh-delivery-checker/internal/check/lostask.go

package check

import (
	"context"
	"fmt"
	"strconv"
	"strings"
	"sync"
	"time"

	"git.novox.be/novox/mesh-sdk/go/delivery"
	"git.novox.be/novox/mesh-sdk/go/delivery/buildrun"
)

// **An ask the build seat gave up on ends its step** (novox/hq issue 734). A build seat's worker offers an ask
// delivery.AskMaxDeliver times; one handed out that often without an answer (a bus reload that drops every hand-out, a node
// that dies taking it each time) is given up by the server, and the controller keeps a copy of it in DEAD_LETTERS under
// mesh.events.dead.<seat stream>.<worker>, with the ask's message id (its ask id), how often it was handed out and when it
// was given up. No build node writes a step for it, so an asker that waits for the step waits for ever: a try stays
// running and holds a try place, a check's verdict stays running and its pull request waits.
//
// The checker hears those copies (DeadLetters, an ordered consumer on DEAD_LETTERS filtered to the build seats' streams,
// granted to a user of a seat pulled by kind, mesh-sdk buscompose DeadLetterReads) and LostAskWaiter ends the waiting step
// at once as failed, its words saying LostWords. A try ends as error; a check asks again (Checker.try).
//
// Belt and braces, for a try only (NotTakenBound): an ask no build node took within the step bound ends the same way,
// saying NotTakenWords. A check's ask waits in the stream as long as the backlog is (ADR 0525 §9): a backlog is no fault,
// and a check ended for one would owe its pull request a failure.

// The words of a step the checker ended for its ask.
const (
	LostWords     = "its ask was given up by the build seat"
	NotTakenWords = "no build node took its ask"
)

// LostAskTries is how often a check asks again whose ask was given up, before it fails as not heard (UnheardWords) and is
// judged again when the nodes change.
const LostAskTries = 3

// The headers the controller keeps a given-up message's copy with in DEAD_LETTERS (mesh-controller internal/link
// deadletters.go): the original message id (an ask's is its ask id), how often it was handed out, when it was given up.
const (
	DeadHeaderMsgID      = "Mesh-Dead-Msg-Id"
	DeadHeaderDeliveries = "Mesh-Dead-Deliveries"
	DeadHeaderGaveUp     = "Mesh-Dead-Gave-Up"
	DeadHeaderStream     = "Mesh-Dead-Stream"
)

// DeadLettersStream is the stream the controller keeps given-up messages in, and DeadLetterFilter the subjects of one seat
// stream's copies there (mesh-sdk buscompose DeadLetterSubject).
const DeadLettersStream = "DEAD_LETTERS"

// DeadLetterFilter is the subjects DEAD_LETTERS keeps a seat stream's given-up messages under.
func DeadLetterFilter(stream string) string { return "mesh.events.dead." + stream + ".>" }

// BuildSeatStreams are the build seats' streams the checker asks on (mesh-sdk buscompose seatStreamName of node-build-go
// and node-build-node).
var BuildSeatStreams = []string{"SEAT_NODE_BUILD_GO", "SEAT_NODE_BUILD_NODE"}

// GivenUp is one ask a build seat gave up on, as DEAD_LETTERS keeps it.
type GivenUp struct {
	AskID      string
	Stream     string
	Deliveries int
	At         time.Time
}

// GivenUpOf reads a DEAD_LETTERS copy's headers; false when it names no message id.
func GivenUpOf(header map[string][]string) (GivenUp, bool) {
	get := func(k string) string {
		if v := header[k]; len(v) > 0 {
			return strings.TrimSpace(v[0])
		}
		return ""
	}
	g := GivenUp{AskID: get(DeadHeaderMsgID), Stream: get(DeadHeaderStream)}
	if g.AskID == "" {
		return GivenUp{}, false
	}
	g.Deliveries, _ = strconv.Atoi(get(DeadHeaderDeliveries))
	g.At, _ = time.Parse(time.RFC3339Nano, get(DeadHeaderGaveUp))
	return g, true
}

// Words are what a step ended for the given-up ask says.
func (g GivenUp) Words() string {
	at := "at an unknown time"
	if !g.At.IsZero() {
		at = "at " + g.At.UTC().Format(time.RFC3339)
	}
	return fmt.Sprintf("%s after %d deliveries %s (kept in %s); ask again", LostWords, g.Deliveries, at, DeadLettersStream)
}

// keptGivenUp is how many given-up asks DeadLetters remembers for a waiter that starts after the copy was heard.
const keptGivenUp = 1024

// DeadLetters holds the given-up asks heard, and hands each to the waiter of its ask. Safe for concurrent use.
type DeadLetters struct {
	mu       sync.Mutex
	heard    map[string]GivenUp
	order    []string
	watchers map[string][]chan GivenUp
}

// Heard takes one given-up ask in.
func (d *DeadLetters) Heard(g GivenUp) {
	d.mu.Lock()
	if d.heard == nil {
		d.heard, d.watchers = map[string]GivenUp{}, map[string][]chan GivenUp{}
	}
	if _, ok := d.heard[g.AskID]; !ok {
		d.order = append(d.order, g.AskID)
		if len(d.order) > keptGivenUp {
			delete(d.heard, d.order[0])
			d.order = d.order[1:]
		}
	}
	d.heard[g.AskID] = g
	ws := d.watchers[g.AskID]
	delete(d.watchers, g.AskID)
	d.mu.Unlock()
	for _, w := range ws {
		w <- g // buffered, one each
	}
}

// watch answers a channel that gets the ask's given-up copy once (at once when it was heard already), and its cancel.
func (d *DeadLetters) watch(askID string) (<-chan GivenUp, func()) {
	ch := make(chan GivenUp, 1)
	d.mu.Lock()
	defer d.mu.Unlock()
	if d.heard == nil {
		d.heard, d.watchers = map[string]GivenUp{}, map[string][]chan GivenUp{}
	}
	if g, ok := d.heard[askID]; ok {
		ch <- g
		return ch, func() {}
	}
	d.watchers[askID] = append(d.watchers[askID], ch)
	return ch, func() {
		d.mu.Lock()
		defer d.mu.Unlock()
		ws := d.watchers[askID]
		for i, w := range ws {
			if w == ch {
				d.watchers[askID] = append(ws[:i], ws[i+1:]...)
				break
			}
		}
		if len(d.watchers[askID]) == 0 {
			delete(d.watchers, askID)
		}
	}
}

type notTakenKey struct{}

// NotTakenBound says, in ctx, that an ask no build node took within bound ends its step (a try's, never a check's).
func NotTakenBound(ctx context.Context, bound time.Duration) context.Context {
	return context.WithValue(ctx, notTakenKey{}, bound)
}

func notTakenBoundOf(ctx context.Context) time.Duration {
	d, _ := ctx.Value(notTakenKey{}).(time.Duration)
	return d
}

// LostAskWaiter is a buildrun.AskWaiter that ends an ask's step when the build seat gave the ask up (DeadLetters), or, under
// NotTakenBound, when no build node took it within the bound: it hands the asker a failed step whose reason says why, on
// the node "bus". Every step the build module writes is handed on as it is.
type LostAskWaiter struct {
	Inner buildrun.AskWaiter
	Dead  *DeadLetters
	Now   func() time.Time
}

func (w LostAskWaiter) now() time.Time {
	if w.Now != nil {
		return w.Now()
	}
	return time.Now()
}

// WatchAsk is AskWaiter's.
func (w LostAskWaiter) WatchAsk(ctx context.Context, module, askID string) (<-chan delivery.Step, error) {
	inner, err := w.Inner.WatchAsk(ctx, module, askID)
	if err != nil {
		return nil, err
	}
	var dead <-chan GivenUp
	cancel := func() {}
	if w.Dead != nil {
		dead, cancel = w.Dead.watch(askID)
	}
	// The not-taken bound is a context's (ADR 0437 §8: no timer), ended when a node takes the ask.
	var notTaken <-chan struct{}
	bound := notTakenBoundOf(ctx)
	stopBound := func() {}
	if bound > 0 {
		var nt context.Context
		nt, stopBound = context.WithTimeout(context.Background(), bound)
		notTaken = nt.Done()
	}
	out := make(chan delivery.Step)
	go func() {
		defer close(out)
		defer cancel()
		defer func() { stopBound() }()
		send := func(s delivery.Step) bool {
			select {
			case out <- s:
				return true
			case <-ctx.Done():
				return false
			}
		}
		ended := func(reason string) delivery.Step {
			at := w.now().UTC()
			return delivery.Step{ID: askID, Node: "bus", State: delivery.StepFailed, Reason: reason, Ended: at}
		}
		for {
			select {
			case <-ctx.Done():
				return
			case s, ok := <-inner:
				if !ok {
					return
				}
				if notTaken != nil {
					stopBound() // a node took it: its step is bounded by the asker from its start
					notTaken = nil
				}
				if !send(s) {
					return
				}
			case g := <-dead:
				dead = nil
				send(ended(g.Words()))
				return
			case <-notTaken:
				send(ended(fmt.Sprintf("%s within %s of its put; it was lost or waits behind a backlog; ask again", NotTakenWords, bound)))
				return
			}
		}
	}()
	return out, nil
}

// IsLostAsk says whether a verdict failed because the build seat gave its ask up (LostWords).
func IsLostAsk(v delivery.Verdict) bool {
	return v.State == delivery.VerdictFail && strings.Contains(v.Failed.Words, LostWords)
}

// IsNotTaken says whether a verdict failed because no build node took its ask within the bound (NotTakenWords).
func IsNotTaken(v delivery.Verdict) bool {
	return v.State == delivery.VerdictFail && strings.Contains(v.Failed.Words, NotTakenWords)
}