mesh-controller/cmd/mesh-controller/holdings.go

package main

import (
	"context"
	"fmt"
	"sort"

	"git.novox.be/novox/mesh-sdk/go/catalogue"
	"git.novox.be/novox/mesh-sdk/go/overlay"
	"github.com/novox/mesh-controller/internal/inventory"
)

// recordDerivedHolders writes down who holds each mesh-scoped seat that nobody was ever recorded
// as holding.
//
// **A seat held by derivation is a seat held by accident of being alone** (novox/hq
// 04-ISSUES/170). ADR 0131 lets a holder on record settle a seat, and lets any other assignment
// whose module could hold it stand beside the holder, eligible and silent. But a seat nobody
// ever handed over has no record, so its holder is whichever assignment happened to be the sole
// claimant — and the day a second one is assigned, both claim, both are refused, and the first
// one's whole machine stops resolving. That is what assigning a second postgres did to the
// control plane's own store.
//
// So the mesh writes the derived answer down before it acts on an assignment: for every
// mesh-scoped seat with exactly one resolved holder and nothing on record, that holder is
// recorded as the standing one — the same record `seat <name> --to <node>/<module>` makes by
// hand, made from what the mesh already resolved. A seat with two derived claimants is left
// alone: that is the ambiguity a person settles, and recording either would be guessing.
//
// Node-scoped seats are untouched: a record is one holder per seat, and a node-scoped seat has
// one holder per machine (ADR 0121), so there is nothing for a record to settle there.
func recordDerivedHolders(ctx context.Context, open *stores) ([]string, error) {
	inv := open.inventory
	shelf, err := inv.Catalogue(ctx)
	if err != nil {
		return nil, err
	}
	// exclude nobody: every node's claims, resolved with the holdings on record.
	world, err := restOfTheMesh(ctx, open, shelf, "")
	if err != nil {
		return nil, err
	}
	recorded, err := inv.Holdings(ctx)
	if err != nil {
		return nil, err
	}
	// A record is a row against a seat the store knows. A seat it does not — a mesh whose seats
	// were never seeded, a seat a module declares for itself — stays held by derivation, as it
	// always was; a missing row is not a reason an assignment fails.
	known, err := inv.Seats(ctx)
	if err != nil {
		return nil, err
	}
	recordable := map[string]bool{}
	for _, s := range known {
		recordable[s.Name] = true
	}
	onRecord := map[string]bool{}
	for _, h := range recorded {
		if s, ok := catalogue.SeatNamed(h.Claim); ok {
			onRecord[s.Name] = true
		}
	}
	holders := map[string][]catalogue.Held{}
	for _, h := range world.Held {
		if h.Scope != catalogue.ScopeMesh {
			continue
		}
		s, ok := catalogue.SeatNamed(h.Claim)
		if !ok || onRecord[s.Name] || !recordable[s.Name] {
			continue
		}
		holders[s.Name] = append(holders[s.Name], h)
	}
	names := make([]string, 0, len(holders))
	for name := range holders {
		names = append(names, name)
	}
	sort.Strings(names)
	var said []string
	for _, name := range names {
		if len(holders[name]) != 1 {
			continue
		}
		h := holders[name][0]
		if err := inv.HoldSeat(ctx, name, catalogue.ScopeMesh, h.Node, h.Module); err != nil {
			return said, err
		}
		said = append(said, fmt.Sprintf(
			"recorded %s on %s as the standing holder of %s, which it held only by being alone",
			h.Module, h.Node, name))
	}
	return said, nil
}

// replicatedHolders is, for each replicated mesh seat, every machine on the private network holding
// it — by internal name, at its private address (novox/hq ADR 0223). What a machine's resolver file
// lists for `mesh-dns-resolver`; the rendering puts the machine itself first when it is one.
//
// **The holders on record, and only the sole claimant when there are none** — the same answer the
// resolver gives about who holds (ADR 0131, issue 170). An assignment standing beside the holders,
// eligible and silent, is not listed: it becomes a holder by `seat <name> --add`, an act, never by
// being assigned. Two claimants with nothing on record are refused at resolution, so neither is
// listed here. A holder off the private network is left out: a resolver named at an address nothing
// answers is a lookup that waits out its timeout on every name.
func replicatedHolders(ctx context.Context, inv *inventory.Inventory,
	shelf map[string]catalogue.Manifest) (map[string]map[string]string, error) {
	var replicated []catalogue.Seat
	for _, s := range catalogue.Seats() {
		if s.Replicated && s.Scope == catalogue.ScopeMesh {
			replicated = append(replicated, s)
		}
	}
	if len(replicated) == 0 {
		return nil, nil
	}
	recorded, err := inv.Holdings(ctx)
	if err != nil {
		return nil, err
	}
	places, err := onTheNetwork(ctx, inv, shelf)
	if err != nil {
		return nil, err
	}
	address := map[string]string{}
	for _, p := range places {
		address[p.Name] = p.Address
	}
	entries, err := inv.Catalogued(ctx)
	if err != nil {
		return nil, err
	}
	out := map[string]map[string]string{}
	for _, seat := range replicated {
		var nodes []string
		for _, h := range recorded {
			if hs, ok := catalogue.SeatNamed(h.Claim); ok && hs.Name == seat.Name && h.Scope == seat.Scope {
				nodes = append(nodes, h.Node)
			}
		}
		if len(nodes) == 0 {
			var derived []string
			for _, e := range entries {
				for _, c := range e.Manifest.Claims {
					if cs, ok := catalogue.SeatNamed(c.Name); ok && cs.Name == seat.Name && c.At() == seat.Scope {
						derived = append(derived, e.On...)
					}
				}
			}
			if len(derived) == 1 {
				nodes = derived
			}
		}
		at := map[string]string{}
		for _, n := range nodes {
			if address[n] != "" {
				at[overlay.InternalName(n)] = address[n]
			}
		}
		out[seat.Name] = at
	}
	return out, nil
}