Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
b58578f88d | ||
|
|
6cb285dd5c | ||
|
|
46f324b10b | ||
|
|
d188eec318 | ||
|
|
c978aa7d64 | ||
|
|
0c7f42a18a | ||
|
|
9a5584b1b6 | ||
|
|
1bc099a2db | ||
|
|
3fc1feff38 | ||
|
|
ffe176f6d1 | ||
|
|
8057cc4888 |
@@ -46,6 +46,13 @@ func assign(ctx context.Context, open *stores, node, module string) (string, err
|
||||
return "", err
|
||||
}
|
||||
defer release()
|
||||
// **Before the new assignment can unsettle a seat somebody holds only by being alone**
|
||||
// (novox/hq 04-ISSUES/170): what the mesh derived so far is written down, and then the
|
||||
// assignment resolves against a record rather than against a coincidence.
|
||||
settled, err := recordDerivedHolders(ctx, open)
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
fresh, err := open.inventory.Assign(ctx, node, module)
|
||||
if err != nil {
|
||||
return "", err
|
||||
@@ -57,6 +64,9 @@ func assign(ctx context.Context, open *stores, node, module string) (string, err
|
||||
node, module), nil
|
||||
}
|
||||
said := fmt.Sprintf("%s is assigned %s", node, module)
|
||||
for _, line := range settled {
|
||||
said += "\n " + line
|
||||
}
|
||||
plan, _, err := planFor(ctx, open, node)
|
||||
if err != nil {
|
||||
// Kept, and still refused. Both halves are the answer, and the rest of the mesh is still
|
||||
|
||||
@@ -0,0 +1,92 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"sort"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/catalogue"
|
||||
)
|
||||
|
||||
// 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 := theRestOfTheMesh(ctx, inv, 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
|
||||
}
|
||||
@@ -0,0 +1,110 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/catalogue"
|
||||
)
|
||||
|
||||
// A seat nobody ever handed over is held by whichever assignment happened to be alone — and the
|
||||
// day a second module able to hold it is assigned, both claimed, both were refused, and the first
|
||||
// one's machine stopped resolving (novox/hq 04-ISSUES/170). The mesh now writes the derived holder
|
||||
// down before it acts, so the second assignment stands beside the holder on record.
|
||||
|
||||
func aSeatedStore() catalogue.Manifest {
|
||||
return catalogue.Manifest{Module: "store", Version: "1",
|
||||
Provides: []catalogue.Offer{{Name: "postgres-database", Scope: catalogue.ScopeMesh}},
|
||||
Serves: map[string]map[string]any{"postgres-database": {"port": 5432}},
|
||||
Claims: []catalogue.Claim{{Name: "mesh-store", Scope: catalogue.ScopeMesh}}}
|
||||
}
|
||||
|
||||
func TestASecondEligibleHolderStandsBesideTheOneHeldByBeingAlone(t *testing.T) {
|
||||
open := aMesh(t)
|
||||
ctx := t.Context()
|
||||
// Every deploy seeds the mesh's own seats; a record is a row against one of them.
|
||||
if _, err := open.inventory.SeedSeats(ctx, catalogue.DefaultSeats()); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
register(t, open, aSeatedStore())
|
||||
|
||||
if _, err := assign(ctx, open, "anchor", "store"); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
said, err := assign(ctx, open, "laptop", "store")
|
||||
if err != nil {
|
||||
t.Fatalf("a second store, eligible for the seat, was refused:\n%s\n%v", said, err)
|
||||
}
|
||||
if strings.Contains(said, "cannot be worked out") {
|
||||
t.Fatalf("assigning a second store unsettled the first one's machine:\n%s", said)
|
||||
}
|
||||
if !strings.Contains(said, "recorded store on anchor as the standing holder of mesh-store") {
|
||||
t.Fatalf("the holder by derivation was not written down:\n%s", said)
|
||||
}
|
||||
|
||||
holdings, err := open.inventory.Holdings(ctx)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
var found bool
|
||||
for _, h := range holdings {
|
||||
if h.Claim == "mesh-store" {
|
||||
found = true
|
||||
if h.Node != "anchor" || h.Module != "store" {
|
||||
t.Fatalf("mesh-store is recorded on %s/%s, not on the one that held it", h.Node, h.Module)
|
||||
}
|
||||
}
|
||||
}
|
||||
if !found {
|
||||
t.Fatalf("mesh-store has no holder on record after assigning: %v", holdings)
|
||||
}
|
||||
|
||||
// And the record decides from here: the anchor's plan holds the seat, the laptop's does not.
|
||||
for node, holds := range map[string]bool{"anchor": true, "laptop": false} {
|
||||
plan, _, err := planFor(ctx, open, node)
|
||||
if err != nil {
|
||||
t.Fatalf("%s no longer resolves: %v", node, err)
|
||||
}
|
||||
var claimed bool
|
||||
for _, c := range plan.Claims {
|
||||
if c.Claim == "mesh-store" {
|
||||
claimed = true
|
||||
}
|
||||
}
|
||||
if claimed != holds {
|
||||
t.Fatalf("%s holds mesh-store: %v, want %v", node, claimed, holds)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestAHolderOnRecordIsNotRewrittenByDerivation(t *testing.T) {
|
||||
open := aMesh(t)
|
||||
ctx := t.Context()
|
||||
if _, err := open.inventory.SeedSeats(ctx, catalogue.DefaultSeats()); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
register(t, open, aSeatedStore())
|
||||
for _, node := range []string{"anchor", "laptop"} {
|
||||
if _, err := assign(ctx, open, node, "store"); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
// A person hands the seat to the laptop. From here the record decides, and what the mesh
|
||||
// derives must never write over it.
|
||||
if err := open.inventory.HoldSeat(ctx, "mesh-store", catalogue.ScopeMesh, "laptop", "store"); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
said, err := recordDerivedHolders(ctx, open)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if len(said) != 0 {
|
||||
t.Fatalf("a seat on record was written again from derivation: %v", said)
|
||||
}
|
||||
holdings, _ := open.inventory.Holdings(ctx)
|
||||
for _, h := range holdings {
|
||||
if h.Claim == "mesh-store" && h.Node != "laptop" {
|
||||
t.Fatalf("the record moved to %s", h.Node)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -338,6 +338,12 @@ func pushCommand(ctx context.Context, args []string) error {
|
||||
sentDigest := map[string]string{}
|
||||
defer release()
|
||||
for _, s := range sending {
|
||||
// Numbered under the hold, one higher than the last, before the body exists — the number is
|
||||
// inside the signed bytes, so a replayed older declaration cannot borrow a newer one's
|
||||
// (novox/hq 04-ISSUES/107).
|
||||
if err := number(ctx, inv, &s); err != nil {
|
||||
return err
|
||||
}
|
||||
body, err := s.declared.Body()
|
||||
if err != nil {
|
||||
return err
|
||||
@@ -564,6 +570,9 @@ func sendRound(ctx context.Context, open *stores, names []string,
|
||||
return compose(held, node)
|
||||
})
|
||||
for _, s := range sending {
|
||||
if err := number(ctx, open.inventory, &s); err != nil {
|
||||
return refused, err
|
||||
}
|
||||
body, err := s.declared.Body()
|
||||
if err != nil {
|
||||
return refused, err
|
||||
@@ -645,6 +654,9 @@ func sendTo(ctx context.Context, open *stores, names []string) error {
|
||||
defer server.Close()
|
||||
|
||||
for _, s := range sending {
|
||||
if err := number(ctx, inv, &s); err != nil {
|
||||
return err
|
||||
}
|
||||
body, err := s.declared.Body()
|
||||
if err != nil {
|
||||
return err
|
||||
@@ -694,6 +706,12 @@ func wouldSend(ctx context.Context, open *stores,
|
||||
if err != nil {
|
||||
continue
|
||||
}
|
||||
// Composed with the number the machine was LAST sent, so this is byte for byte what it was
|
||||
// sent when nothing else changed. A fresh number here would make every machine read as
|
||||
// behind for ever (novox/hq 04-ISSUES/107).
|
||||
if declared.Sequence, err = open.inventory.Sequence(ctx, n.ID); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
body, err := declared.Body()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
@@ -827,3 +845,17 @@ func seatHolders(ctx context.Context, inv *inventory.Inventory) (map[string]brok
|
||||
}
|
||||
return out, nil
|
||||
}
|
||||
|
||||
// number gives one send the next sequence for its node (novox/hq 04-ISSUES/107).
|
||||
func number(ctx context.Context, inv *inventory.Inventory, s *readyNode) error {
|
||||
record, err := inv.NodeByName(ctx, s.node)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
seq, err := inv.NextSequence(ctx, record.ID)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
s.declared.Sequence = seq
|
||||
return nil
|
||||
}
|
||||
|
||||
@@ -18,6 +18,10 @@ import (
|
||||
// make a machine look out of date for ever, or send something `plan` never showed.
|
||||
type sendable struct {
|
||||
Resources []map[string]any
|
||||
// Sequence orders this send against every other to the same node: one higher each time, taken
|
||||
// under the node's hold just before the body is made (novox/hq 04-ISSUES/107). Zero is not sent
|
||||
// at all, which a host reads as "no order claimed" — the shape of every declaration before this.
|
||||
Sequence int64
|
||||
// Adoption is nil for a converged node, and then the body is byte for byte what it was before
|
||||
// adoption existed: an older host parses the envelope strictly and would refuse the key.
|
||||
Adoption *adoptionEnvelope
|
||||
@@ -38,6 +42,9 @@ func (s sendable) Body() ([]byte, error) {
|
||||
if s.Adoption != nil {
|
||||
envelope["adoption"] = s.Adoption
|
||||
}
|
||||
if s.Sequence > 0 {
|
||||
envelope["sequence"] = s.Sequence
|
||||
}
|
||||
// An empty declaration is deliberate here — the node owns nothing the mesh put there
|
||||
// (novox/hq issue 127) — and the host refuses an empty body unless it is told the emptiness
|
||||
// is meant, so a truncated or mis-composed body is never mistaken for "own nothing".
|
||||
|
||||
@@ -0,0 +1,77 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// A declaration's only identity was the digest of its bytes; the controller already held a per-node
|
||||
// lock and recorded each send, so the order existed and was thrown away at the wire (novox/hq
|
||||
// 04-ISSUES/107).
|
||||
|
||||
func TestASendCarriesItsNumberInsideTheSignedBytes(t *testing.T) {
|
||||
body, err := sendable{Resources: []map[string]any{{"id": "x", "type": "file"}}, Sequence: 7}.Body()
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
var env map[string]any
|
||||
if err := json.Unmarshal(body, &env); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if got, _ := env["sequence"].(float64); got != 7 {
|
||||
t.Fatalf("the body carries sequence %v, wanted 7", env["sequence"])
|
||||
}
|
||||
}
|
||||
|
||||
func TestAnUnnumberedSendIsByteForByteWhatItWasBefore(t *testing.T) {
|
||||
// Zero is not sent at all. A host reads absence as "no order claimed" — the shape of every
|
||||
// declaration before this — so an older host, or the read-only comparison against a machine
|
||||
// sent nothing since sends were numbered, sees exactly the bytes it always saw.
|
||||
body, err := sendable{Resources: []map[string]any{{"id": "x", "type": "file"}}}.Body()
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
var env map[string]any
|
||||
if err := json.Unmarshal(body, &env); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if _, present := env["sequence"]; present {
|
||||
t.Fatalf("a send numbered zero put a sequence on the wire: %s", body)
|
||||
}
|
||||
}
|
||||
|
||||
func TestEachSendToANodeIsOneHigherAndReadable(t *testing.T) {
|
||||
open := aMesh(t)
|
||||
record, err := open.inventory.NodeByName(t.Context(), "anchor")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
// Sent nothing since numbering existed: what it would be sent is composed with zero, which is
|
||||
// not on the wire, which is what it was actually sent.
|
||||
if n, err := open.inventory.Sequence(t.Context(), record.ID); err != nil || n != 0 {
|
||||
t.Fatalf("a fresh node reads sequence %d, %v", n, err)
|
||||
}
|
||||
first, err := open.inventory.NextSequence(t.Context(), record.ID)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
second, err := open.inventory.NextSequence(t.Context(), record.ID)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if first != 1 || second != 2 {
|
||||
t.Fatalf("two sends were numbered %d and %d", first, second)
|
||||
}
|
||||
// And the read path sees the last one taken, so the comparison composes what was sent.
|
||||
if n, err := open.inventory.Sequence(t.Context(), record.ID); err != nil || n != 2 {
|
||||
t.Fatalf("after two sends the node reads sequence %d, %v", n, err)
|
||||
}
|
||||
// Another node counts on its own.
|
||||
other, err := open.inventory.NodeByName(t.Context(), "laptop")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if n, err := open.inventory.NextSequence(t.Context(), other.ID); err != nil || n != 1 {
|
||||
t.Fatalf("a second node's first send was numbered %d, %v", n, err)
|
||||
}
|
||||
}
|
||||
@@ -877,6 +877,21 @@ func compile(ctx context.Context, run Runner, tree string, chain Toolchain,
|
||||
base,
|
||||
}
|
||||
invocation = append(invocation, chain.Compile...)
|
||||
// **One `-ldflags`, composed here.** A repeated flag is not a merged one: the Go command takes
|
||||
// the last and drops the first, so passing the toolchain's flags and then the system stamp as a
|
||||
// second `-ldflags` produced a binary that knew its system and had lost `-s -w` — half again the
|
||||
// size, with its debug info (novox/hq 04-ISSUES/161).
|
||||
//
|
||||
// What it was built for is the one thing taken from the artifact, and ADR 0142 says why: the
|
||||
// target is a property of the artifact rather than of the recipe. A host with no system refuses
|
||||
// every declaration before it applies anything.
|
||||
linker := append([]string(nil), chain.LinkerFlags...)
|
||||
if chain.SystemStamp != "" && strings.TrimSpace(a.System) != "" {
|
||||
linker = append(linker, "-X", chain.SystemStamp+"="+strings.TrimSpace(a.System))
|
||||
}
|
||||
if len(linker) > 0 {
|
||||
invocation = append(invocation, "-ldflags", strings.Join(linker, " "))
|
||||
}
|
||||
if chain.OutputFlag != "" {
|
||||
// A compiler pointed at a package is told the file to write, not the directory: the name a
|
||||
// machine runs it by is not always the name of the package that built it. The host's command
|
||||
|
||||
@@ -0,0 +1,76 @@
|
||||
package builder
|
||||
|
||||
import (
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// A host built without knowing its system refuses every declaration before applying anything —
|
||||
// safely, totally, and with nothing reporting it. The mesh built one, delivered it, started it, and
|
||||
// it would have refused the first thing it was asked to do (novox/hq 04-ISSUES/161).
|
||||
|
||||
func TestTheGoToolchainStampsTheArtifactsSystem(t *testing.T) {
|
||||
chain, err := ToolchainFor("go")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if chain.SystemStamp != "main.builtFor" {
|
||||
t.Fatalf("the go toolchain fills %q", chain.SystemStamp)
|
||||
}
|
||||
}
|
||||
|
||||
func TestALanguageWithNoPinnedSystemStampsNothing(t *testing.T) {
|
||||
// Interpreted output is not pinned to a system, and a manifest declaring one for it is already
|
||||
// refused. Nothing to fill.
|
||||
for _, language := range []string{"typescript", "python"} {
|
||||
chain, err := ToolchainFor(language)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if chain.SystemStamp != "" {
|
||||
t.Fatalf("%s fills %q, and its output is not pinned to a system",
|
||||
language, chain.SystemStamp)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestTheStampIsTheOneThingTakenFromTheArtifact(t *testing.T) {
|
||||
// The toolchain accepts nothing else from the module — anything it could override it would be
|
||||
// writing a Dockerfile to override. The system is the stated exception, because a compiled
|
||||
// binary is per system and the artifact is what declares one (ADR 0142).
|
||||
chain, err := ToolchainFor("go")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
joined := strings.Join(chain.Compile, " ")
|
||||
if strings.Contains(joined, "${") || strings.Contains(joined, "%s") {
|
||||
t.Fatalf("the compile line takes something from the module: %q", joined)
|
||||
}
|
||||
}
|
||||
|
||||
func TestTheLinkerIsToldOnceNotTwice(t *testing.T) {
|
||||
// A repeated flag is not a merged one: the Go command takes the last -ldflags and drops the
|
||||
// first. Passing the toolchain's flags and then the stamp separately produced a binary that knew
|
||||
// its system and had lost -s -w — 12.2MB against 8.5MB, with its debug info (04-ISSUES/161).
|
||||
chain, err := ToolchainFor("go")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
for _, arg := range chain.Compile {
|
||||
if arg == "-ldflags" {
|
||||
t.Fatal("the compile line carries -ldflags, so composing one here makes two")
|
||||
}
|
||||
}
|
||||
if len(chain.LinkerFlags) == 0 {
|
||||
t.Fatal("the go toolchain passes no linker flags, so the binary keeps its debug info")
|
||||
}
|
||||
var stripped bool
|
||||
for _, f := range chain.LinkerFlags {
|
||||
if f == "-s" {
|
||||
stripped = true
|
||||
}
|
||||
}
|
||||
if !stripped {
|
||||
t.Fatalf("the go toolchain does not strip: %v", chain.LinkerFlags)
|
||||
}
|
||||
}
|
||||
@@ -49,6 +49,26 @@ type Toolchain struct {
|
||||
// is named as it will be FOUND, inside the unpacked bundle, so the source is the same path with
|
||||
// the output directory taken off the front and this on the end.
|
||||
SourceExt string
|
||||
// LinkerFlags are passed to the linker as one flag, together with the system stamp below.
|
||||
//
|
||||
// **Separate from Compile because a repeated flag is not a merged one.** They were in the compile
|
||||
// line, and appending the stamp as a second `-ldflags` meant the Go command took the last and
|
||||
// dropped the first — so the binary gained its system and lost `-s -w`, growing by half and
|
||||
// carrying its debug info. The mistake was believing a comment rather than reading the file it
|
||||
// produced (novox/hq 04-ISSUES/161).
|
||||
LinkerFlags []string
|
||||
// SystemStamp is the variable this language's linker fills with the artifact's declared system,
|
||||
// for a language whose binaries are pinned to one at link time (novox/hq ADR 0005).
|
||||
//
|
||||
// **The one thing a toolchain takes from the artifact, and 0142 says why**: the target is a
|
||||
// property of the artifact rather than of the recipe, because a compiled binary is per system
|
||||
// and a toolchain that accepted it from the module would be accepting a build instruction. This
|
||||
// is the narrow exception, named here rather than inferred.
|
||||
//
|
||||
// Empty for a language that compiles to nothing pinned. A host built without it refuses every
|
||||
// declaration before applying anything — safely, totally, and with nothing reporting it
|
||||
// (novox/hq 04-ISSUES/161).
|
||||
SystemStamp string
|
||||
}
|
||||
|
||||
// What a toolchain is pointed at.
|
||||
@@ -114,14 +134,20 @@ var toolchains = []Toolchain{
|
||||
// rather than from the linker: two builds of one commit produce the same bytes.
|
||||
Compile: []string{
|
||||
"env", "CGO_ENABLED=0", "GOFLAGS=-trimpath",
|
||||
"go", "build", "-ldflags", "-s -w",
|
||||
"go", "build",
|
||||
},
|
||||
OutputFlag: "-o",
|
||||
// Stripped of symbols and debug info: what a machine holds is a file it runs, not one it
|
||||
// debugs, and the difference measured 12.2MB against 8.5MB.
|
||||
LinkerFlags: []string{"-s", "-w"},
|
||||
OutputFlag: "-o",
|
||||
// Pointed at the package the artifact is built `from`, compiled whole. Go writes the binary
|
||||
// into the output directory, named after the package — so the bundle a machine unpacks is a
|
||||
// directory holding one executable, which is what the delivery mechanism expects
|
||||
// (novox/hq ADR 0141).
|
||||
Unit: UnitPackage,
|
||||
// The mesh's own Go components read the system they were built for from this variable, and
|
||||
// refuse to touch a machine without one.
|
||||
SystemStamp: "main.builtFor",
|
||||
},
|
||||
{
|
||||
Language: "python",
|
||||
|
||||
@@ -618,17 +618,15 @@ func (r Resolution) compose(with Rendering, owner map[string]string) ([]map[stri
|
||||
// merging earlier would throw away the files it still needs.
|
||||
resources = append(append([]map[string]any{}, first...), resources...)
|
||||
|
||||
// Every container is given the mesh's names. Not a choice a module makes: a module that
|
||||
// listed them would go stale the day a machine joins, and one that did not would be a
|
||||
// module whose containers cannot reach anything by name.
|
||||
//
|
||||
// A container that was given names of its own keeps them and gets the mesh's beside them:
|
||||
// the mesh does not know what else a workload needs to reach, and taking something away
|
||||
// to add something is not what "also" means.
|
||||
if len(with.Names) > 0 {
|
||||
resources = withMeshNames(resources, with.Names)
|
||||
}
|
||||
|
||||
// No container is given the mesh's names (novox/hq ADR 0148). It used to be: every
|
||||
// container got the whole roster as `--add-host` entries at creation, and a name that
|
||||
// moved afterwards was wrong inside it for as long as it ran (issues 109, 135) — and once
|
||||
// the roster was made part of a container's identity so that could be caught, one name
|
||||
// moving anywhere replaced every container in the mesh (issue 151). A container resolves a
|
||||
// mesh name through its machine's resolver at the moment it asks, which the runtime is
|
||||
// told once per machine, as a file, by the resolver's own module. The names a module
|
||||
// declares for itself are its own and stay exactly as written: they are part of what the
|
||||
// module is, and the mesh does not know what they mean.
|
||||
// What this module may name from inside one of its own files. Gathered once per module
|
||||
// rather than per file, because it is a fact about the module.
|
||||
sealed, err := sealedFor(m, r.Needs, with)
|
||||
@@ -1103,7 +1101,7 @@ func (r Resolution) contributions(settings SettingsBy, grants []Grant,
|
||||
return nil, fmt.Errorf("%s contributing to %s: %w", m.Module, to, err)
|
||||
}
|
||||
portOfEndpoint(values, endpointPorts(m))
|
||||
composeName(values, r.PublicDomain, r.At, reaches, endpointPorts(m), blocks)
|
||||
composeName(values, r.PublicDomain, servingAt(r, to), reaches, endpointPorts(m), blocks)
|
||||
out[to] = append(out[to], Contribution{From: m.Module, Values: values})
|
||||
}
|
||||
// Several contributions to one requirement (ADR 0094's sibling for `contributes`): an
|
||||
@@ -1126,7 +1124,7 @@ func (r Resolution) contributions(settings SettingsBy, grants []Grant,
|
||||
return nil, fmt.Errorf("%s contributing %s to %s: %w", m.Module, local, to, err)
|
||||
}
|
||||
portOfEndpoint(values, endpointPorts(m))
|
||||
composeName(values, r.PublicDomain, r.At, reaches, endpointPorts(m), blocks)
|
||||
composeName(values, r.PublicDomain, servingAt(r, to), reaches, endpointPorts(m), blocks)
|
||||
out[to] = append(out[to], Contribution{From: m.Module, Values: values})
|
||||
}
|
||||
}
|
||||
@@ -1226,6 +1224,24 @@ func composeName(values map[string]any, publicDomain, internalDomain string, rea
|
||||
}
|
||||
}
|
||||
|
||||
// servingAt is the private-network name of the node a contribution to `to` arrives at: the
|
||||
// provider's, when the provision is answered elsewhere, and this machine's own when it is answered
|
||||
// here or not yet settled.
|
||||
//
|
||||
// A route's internal name is composed under it (novox/hq ADR 0151, issue 139). `<label>.<node>.internal`
|
||||
// is answered by every machine's resolver as *anything under that node's name goes to that node* —
|
||||
// so the node in the name has to be the one whose proxy answers, or the name sends a client to a
|
||||
// machine with nothing listening while the public name, published at the serving node's address,
|
||||
// works. Where the proxy runs beside the module the two are the same machine and nothing changes.
|
||||
func servingAt(r Resolution, to string) string {
|
||||
for _, n := range r.Needs {
|
||||
if n.Name == to && n.At != "" {
|
||||
return n.At
|
||||
}
|
||||
}
|
||||
return r.At
|
||||
}
|
||||
|
||||
// receivedFile is the file a provider is given its consumers' contributions in.
|
||||
func receivedFile(requirement, path string, given []Contribution) (map[string]any, error) {
|
||||
if given == nil {
|
||||
@@ -1482,43 +1498,6 @@ func (r Resolution) servedOnThisMachine(provision string, with Rendering) (map[s
|
||||
return nil, false, nil
|
||||
}
|
||||
|
||||
// withMeshNames gives every container in a set the mesh's names.
|
||||
//
|
||||
// Copied rather than edited in place: these maps come from a module's manifest, and mutating one
|
||||
// would change what the catalogue holds for every other machine running that module.
|
||||
//
|
||||
// A host-network container gets the names too. It was once skipped, on the belief that it "shares
|
||||
// the machine's hosts file already" — but it does not: `docker run --network host` still gives the
|
||||
// container its own /etc/hosts (localhost and its own id only), so every `<node>.internal` name the
|
||||
// mesh wrote for the machine is invisible inside it, and a client that dials one gets EAI_AGAIN. The
|
||||
// remedy is the same `--add-host` every other container gets — the runtime accepts it with
|
||||
// `--network host` (verified), and without it a host-network consumer cannot reach a provider by the
|
||||
// `.internal` address the mesh hands it as `${bound:...:at}`.
|
||||
func withMeshNames(resources []map[string]any, names map[string]string) []map[string]any {
|
||||
out := make([]map[string]any, 0, len(resources))
|
||||
for _, r := range resources {
|
||||
if r["type"] != "container" {
|
||||
out = append(out, r)
|
||||
continue
|
||||
}
|
||||
|
||||
copied := map[string]any{}
|
||||
for k, v := range r {
|
||||
copied[k] = v
|
||||
}
|
||||
var given []any
|
||||
if already, ok := copied["hosts"].([]any); ok {
|
||||
given = append(given, already...)
|
||||
}
|
||||
for _, name := range sortedKeys(names) {
|
||||
given = append(given, name+":"+names[name])
|
||||
}
|
||||
copied["hosts"] = given
|
||||
out = append(out, copied)
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// pinned refuses an image that is not really pinned, on its way to a machine.
|
||||
//
|
||||
// **Here and not at parse** (novox/hq 04-ISSUES/025). A manifest in a repository names artifacts
|
||||
|
||||
@@ -158,3 +158,16 @@ func TestAStoreRowWithoutAProtocolKeepsTheCompiledOne(t *testing.T) {
|
||||
t.Fatalf("the store's own columns were not kept: %+v", got)
|
||||
}
|
||||
}
|
||||
|
||||
func TestARefusalWithNothingOnRecordNamesTheHandover(t *testing.T) {
|
||||
busSeatDelivering(t, "mesh-bus")
|
||||
elsewhere := []Held{{Claim: "mesh-broker", Scope: ScopeMesh, Node: "anchor", Module: "old-broker"}}
|
||||
|
||||
_, problems := checkClaims([]Manifest{newBroker()}, Node{Name: "laptop"}, elsewhere, nil)
|
||||
if len(problems) != 1 {
|
||||
t.Fatalf("two derived claimants across machines were not refused: %v", problems)
|
||||
}
|
||||
if !strings.Contains(problems[0], "`seat mesh-broker --to anchor/old-broker`") {
|
||||
t.Fatalf("the refusal does not name the handover that records the holder: %s", problems[0])
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
package catalogue
|
||||
|
||||
import (
|
||||
"reflect"
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
@@ -30,36 +31,38 @@ func namesOf(r map[string]any) []string {
|
||||
return out
|
||||
}
|
||||
|
||||
// A container does not inherit the machine's names, so the mesh gives them to it.
|
||||
// No mesh name is written into a container (novox/hq ADR 0148). It resolves them through its
|
||||
// machine's resolver at the moment it asks, so a name that moves is answered differently by the
|
||||
// next lookup, in every container, with nothing recreated.
|
||||
//
|
||||
// It gets its own hosts file holding only its own hostname — every internal name the mesh wrote
|
||||
// for the machine is invisible to what the machine runs. A database client on one node could not
|
||||
// resolve another node, on a mesh where both names were correct and present on both machines.
|
||||
func TestEveryContainerIsGivenTheMeshsNames(t *testing.T) {
|
||||
got := containersOf(t, Resolution{Node: "laptop", Modules: []Manifest{{
|
||||
Module: "app",
|
||||
Resources: []map[string]any{{"id": "web", "type": "container", "name": "web",
|
||||
"image": "registry.example/web@sha256:" + strings.Repeat("a", 64)}},
|
||||
}}}, Rendering{Names: map[string]string{
|
||||
"anchor.internal": "10.42.0.1", "laptop.internal": "10.42.0.2",
|
||||
}})
|
||||
if len(got) != 1 {
|
||||
t.Fatalf("expected one container, got %d", len(got))
|
||||
// Checked the way the record says: the declaration a container gets does not move when the mesh's
|
||||
// roster does. A roster with one machine and a roster with three produce the same container, byte
|
||||
// for byte, so the digest a host computes from it cannot move either — which is what stopped one
|
||||
// name moving from replacing every container in the mesh (issue 151).
|
||||
func TestAContainerIsTheSameWhateverTheMeshsRosterSays(t *testing.T) {
|
||||
module := Manifest{Module: "app", Resources: []map[string]any{{"id": "web", "type": "container",
|
||||
"name": "web", "image": "registry.example/web@sha256:" + strings.Repeat("a", 64)}}}
|
||||
one := containersOf(t, Resolution{Node: "laptop", Modules: []Manifest{module}},
|
||||
Rendering{Names: map[string]string{"laptop.internal": "10.42.0.2"}})
|
||||
three := containersOf(t, Resolution{Node: "laptop", Modules: []Manifest{module}},
|
||||
Rendering{Names: map[string]string{
|
||||
"anchor.internal": "10.42.0.1", "laptop.internal": "10.42.0.2", "git.example.tld": "10.42.0.1",
|
||||
}})
|
||||
if len(one) != 1 || len(three) != 1 {
|
||||
t.Fatalf("expected one container each, got %d and %d", len(one), len(three))
|
||||
}
|
||||
given := namesOf(got[0])
|
||||
if len(given) != 2 {
|
||||
t.Fatalf("the container was given %d name(s): %v", len(given), given)
|
||||
if given := namesOf(three[0]); len(given) != 0 {
|
||||
t.Fatalf("the mesh's names were copied into the container: %v", given)
|
||||
}
|
||||
if given[0] != "anchor.internal:10.42.0.1" {
|
||||
t.Fatalf("the name is not in the form a runtime writes: %v", given)
|
||||
if !reflect.DeepEqual(one[0], three[0]) {
|
||||
t.Fatalf("the container moved with the roster:\n%v\n%v", one[0], three[0])
|
||||
}
|
||||
}
|
||||
|
||||
// A container that named its own keeps them and gets the mesh's beside them.
|
||||
//
|
||||
// The mesh does not know what else a workload needs to reach, and taking something away in order
|
||||
// to add something is not what "also" means.
|
||||
func TestAContainersOwnNamesAreKept(t *testing.T) {
|
||||
// The names a module declares for itself are its own: part of what the module is, kept exactly as
|
||||
// written, and the mesh does not know what they mean. They are the one thing in a container's
|
||||
// hosts that does move its identity, because they do not move when the mesh's roster does.
|
||||
func TestAContainersOwnNamesAreKeptAsWritten(t *testing.T) {
|
||||
got := containersOf(t, Resolution{Node: "laptop", Modules: []Manifest{{
|
||||
Module: "app",
|
||||
Resources: []map[string]any{{"id": "web", "type": "container", "name": "web",
|
||||
@@ -68,62 +71,15 @@ func TestAContainersOwnNamesAreKept(t *testing.T) {
|
||||
}}}, Rendering{Names: map[string]string{"anchor.internal": "10.42.0.1"}})
|
||||
|
||||
given := namesOf(got[0])
|
||||
if len(given) != 2 || given[0] != "something.else:203.0.113.9" {
|
||||
t.Fatalf("the container's own names were lost: %v", given)
|
||||
if len(given) != 1 || given[0] != "something.else:203.0.113.9" {
|
||||
t.Fatalf("the container's own names were not kept as written: %v", given)
|
||||
}
|
||||
}
|
||||
|
||||
// A container on the machine's own network gets the names too — it does NOT share the machine's
|
||||
// hosts file. `docker run --network host` still gives the container its own /etc/hosts (localhost
|
||||
// and its own id only), so every `<node>.internal` name the mesh wrote is invisible inside it, and a
|
||||
// client that dials one gets EAI_AGAIN. It gets the same `--add-host` entries every other container
|
||||
// gets (the runtime accepts them with `--network host`), so a host-network consumer can reach a
|
||||
// provider by the `.internal` address the mesh hands it.
|
||||
func TestAContainerOnTheMachinesNetworkIsGivenTheNamesToo(t *testing.T) {
|
||||
got := containersOf(t, Resolution{Node: "anchor", Modules: []Manifest{{
|
||||
Module: "control",
|
||||
Resources: []map[string]any{{"id": "c", "type": "container", "name": "c",
|
||||
"image": "registry.example/c@sha256:" + strings.Repeat("a", 64), "network": "host"}},
|
||||
}}}, Rendering{Names: map[string]string{"anchor.internal": "10.42.0.1"}})
|
||||
|
||||
given := namesOf(got[0])
|
||||
if len(given) != 1 || given[0] != "anchor.internal:10.42.0.1" {
|
||||
t.Fatalf("a host-networked container was not given the mesh's names: %v", got[0])
|
||||
}
|
||||
}
|
||||
|
||||
// A mesh with no private network gives nothing, rather than a name with no address behind it.
|
||||
func TestAMeshWithNoNamesGivesNone(t *testing.T) {
|
||||
got := containersOf(t, Resolution{Node: "alone", Modules: []Manifest{{
|
||||
Module: "app",
|
||||
Resources: []map[string]any{{"id": "web", "type": "container", "name": "web",
|
||||
"image": "registry.example/web@sha256:" + strings.Repeat("a", 64)}},
|
||||
}}}, Rendering{})
|
||||
if len(namesOf(got[0])) != 0 {
|
||||
t.Fatalf("names were invented for a mesh that has none: %v", got[0])
|
||||
}
|
||||
}
|
||||
|
||||
// The catalogue's copy is not edited: these maps come from a manifest, and mutating one would
|
||||
// change what every other machine running that module is given.
|
||||
func TestGivingNamesDoesNotChangeTheCatalogue(t *testing.T) {
|
||||
held := map[string]any{"id": "web", "type": "container", "name": "web",
|
||||
"image": "registry.example/web@sha256:" + strings.Repeat("a", 64)}
|
||||
module := Manifest{Module: "app", Resources: []map[string]any{held}}
|
||||
|
||||
for _, node := range []string{"one", "two"} {
|
||||
containersOf(t, Resolution{Node: node, Modules: []Manifest{module}},
|
||||
Rendering{Names: map[string]string{"anchor.internal": "10.42.0.1"}})
|
||||
}
|
||||
if _, changed := held["hosts"]; changed {
|
||||
t.Fatal("the manifest the catalogue holds was edited, so every machine now carries this")
|
||||
}
|
||||
}
|
||||
|
||||
// Only containers. A file or a service given a `hosts` key is a declaration the host refuses
|
||||
// outright — it takes no unknown field — so getting this wrong breaks the whole machine rather
|
||||
// than one resource, and breaks it for something that was never about names.
|
||||
func TestNothingButAContainerIsGivenNames(t *testing.T) {
|
||||
// No resource is given a `hosts` key it did not declare. A file or a service carrying one is a
|
||||
// declaration the host refuses outright — it takes no unknown field — so an invented key breaks
|
||||
// the whole machine rather than one resource.
|
||||
func TestNothingIsGivenNamesItDidNotDeclare(t *testing.T) {
|
||||
out, err := Resolution{Node: "laptop", Modules: []Manifest{{
|
||||
Module: "app",
|
||||
Resources: []map[string]any{
|
||||
@@ -137,11 +93,8 @@ func TestNothingButAContainerIsGivenNames(t *testing.T) {
|
||||
t.Fatal(err)
|
||||
}
|
||||
for _, r := range out {
|
||||
if r["type"] == "container" {
|
||||
continue
|
||||
}
|
||||
if _, given := r["hosts"]; given {
|
||||
t.Fatalf("a %v was given names, which the host will refuse: %v", r["type"], r)
|
||||
t.Fatalf("a %v was given names it never declared: %v", r["type"], r)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -98,8 +98,7 @@ func portInto(resource map[string]any, module string, listens []Listening, with
|
||||
|
||||
// **A fresh map, and only when something changes.** This map came out of the module's
|
||||
// manifest and the resource around it is a shallow copy, so filling a value in place would
|
||||
// change what the catalogue holds for every other machine running the module — the trap
|
||||
// withMeshNames is written to avoid, one field along.
|
||||
// change what the catalogue holds for every other machine running the module.
|
||||
var filled map[string]any
|
||||
for _, key := range named {
|
||||
written, ok := env[key].(string)
|
||||
|
||||
@@ -707,9 +707,14 @@ func checkClaims(modules []Manifest, node Node, elsewhere []Held, holdings []Hel
|
||||
}
|
||||
switch h.Scope {
|
||||
case ScopeMesh:
|
||||
// Both claim and nobody is on record, or this refusal could not have happened.
|
||||
// The remedy is the handover that records the holder (novox/hq ADR 0131,
|
||||
// 04-ISSUES/170), so it is named here rather than left to be found.
|
||||
problems = append(problems, fmt.Sprintf(
|
||||
"%s on %s claims %q, which %s on %s already holds — one per mesh",
|
||||
h.Module, node.Name, h.Claim, e.Module, e.Node))
|
||||
"%s on %s claims %q, which %s on %s already holds — one per mesh. Nothing is "+
|
||||
"on record for it; `seat %s --to %s/%s` records the holder, and the other "+
|
||||
"assignment then stands beside it, eligible and silent",
|
||||
h.Module, node.Name, h.Claim, e.Module, e.Node, h.Claim, e.Node, e.Module))
|
||||
case ScopeSite:
|
||||
if node.Site != "" && node.Site == e.Site {
|
||||
problems = append(problems, fmt.Sprintf(
|
||||
|
||||
@@ -48,7 +48,7 @@ func TestTheResolverForwardsToFixedUpstreamsAndNeverReadsResolvConf(t *testing.T
|
||||
}
|
||||
for _, want := range []string{
|
||||
"\nno-resolv\n", "\nserver=1.1.1.1\n", "\nserver=8.8.8.8\n",
|
||||
"\nlisten-address=127.0.0.1\n", "\ninterface=mesh0\n", "\nbind-dynamic\n",
|
||||
"\nlisten-address=127.0.0.1\n", "\nlisten-address=${machine:address}\n", "\nbind-dynamic\n",
|
||||
"\ndomain-needed\n", "\nbogus-priv\n",
|
||||
"\nconf-file=" + m.Facts["node-zones"].Path + "\n",
|
||||
} {
|
||||
@@ -56,6 +56,14 @@ func TestTheResolverForwardsToFixedUpstreamsAndNeverReadsResolvConf(t *testing.T
|
||||
t.Errorf("the resolver's configuration lacks %q:\n%s", strings.TrimSpace(want), config)
|
||||
}
|
||||
}
|
||||
// By address and never by interface: dnsmasq admits a query by the interface it arrives on
|
||||
// when told one, and a container's query to the private address arrives on the runtime's
|
||||
// bridge — `interface=mesh0` dropped every such query, silently (novox/hq issue 110).
|
||||
for _, line := range strings.Split(config, "\n") {
|
||||
if strings.HasPrefix(line, "interface=") {
|
||||
t.Errorf("the resolver answers by interface, so a container's query on a bridge is dropped: %s", line)
|
||||
}
|
||||
}
|
||||
// Not .53 or .54, which systemd-resolved holds; and not .55 any more, which was a convention
|
||||
// beside the one every machine already followed — the predecessor's resolv.conf says .1.
|
||||
for _, taken := range []string{"127.0.0.53", "127.0.0.54", "127.0.0.55"} {
|
||||
@@ -137,23 +145,39 @@ func TestTheResolverAndWhatAsksItComposeOnOneMachine(t *testing.T) {
|
||||
t.Errorf("the daemon does not restart on its configuration and the machines file both: %v", service["restart-on"])
|
||||
}
|
||||
|
||||
// The runtime's own file, written into (novox/hq ADR 0102) with the one key this module states.
|
||||
// The runtime's own file, written into (novox/hq ADR 0102) with the keys this module states:
|
||||
// where containers resolve, and that a restart keeps them running — because the runtime reads
|
||||
// `dns` only when it starts, and the one restart that needs is the operator's (issue 110).
|
||||
runtime := ids["dnsmasq.runtime-dns"]
|
||||
if runtime == nil || runtime["path"] != "/etc/docker/daemon.json" || runtime["into"] != "json" {
|
||||
t.Fatalf("the runtime's dns is not written into its file: %v", runtime)
|
||||
}
|
||||
var keys map[string][]string
|
||||
var keys map[string]any
|
||||
if err := json.Unmarshal([]byte(runtime["content"].(string)), &keys); err != nil {
|
||||
t.Fatalf("the runtime's keys are not JSON: %v", err)
|
||||
}
|
||||
if len(keys) != 1 || len(keys["dns"]) != 1 || keys["dns"][0] != "10.42.0.1" {
|
||||
t.Errorf("the runtime is pointed at %v; containers resolve at this machine's own private-network address, and nothing else is written", keys)
|
||||
dns, _ := keys["dns"].([]any)
|
||||
if len(keys) != 2 || len(dns) != 1 || dns[0] != "10.42.0.1" || keys["live-restore"] != true {
|
||||
t.Errorf("the runtime is given %v; containers resolve at this machine's own private-network address, a restart keeps them, and nothing else is written", keys)
|
||||
}
|
||||
// The runtime is reloaded when that file changes, and never restarted: a restart stops every
|
||||
// container on the machine (ADR 0102), and a reload is what turns live-restore on.
|
||||
var reloaded bool
|
||||
for _, r := range out {
|
||||
if r["type"] == "service" && r["unit"] == "docker.service" && r["id"] != "" &&
|
||||
strings.HasPrefix(r["id"].(string), "dnsmasq.") {
|
||||
t.Errorf("the resolver orders the runtime restarted or reloaded, which stops every container (ADR 0102) or does nothing for dns: %v", r)
|
||||
if r["type"] != "service" || r["unit"] != "docker.service" {
|
||||
continue
|
||||
}
|
||||
if _, restarts := r["restart-on"]; restarts {
|
||||
t.Errorf("the resolver orders the runtime restarted, which stops every container (ADR 0102): %v", r)
|
||||
}
|
||||
for _, on := range asStrings(r["reload-on"]) {
|
||||
if on == "dnsmasq.runtime-dns" {
|
||||
reloaded = true
|
||||
}
|
||||
}
|
||||
}
|
||||
if !reloaded {
|
||||
t.Errorf("the runtime is not reloaded when its file changes, so live-restore never takes effect")
|
||||
}
|
||||
|
||||
resolv := ids["resolv-conf.resolv"]
|
||||
|
||||
@@ -162,6 +162,13 @@ func renderRoster(tmpl string, view rosterView) (string, error) {
|
||||
func entriesFrom(addresses, accounts map[string]string, suffix string) []rosterEntry {
|
||||
out := make([]rosterEntry, 0, len(addresses))
|
||||
for _, name := range sortedNames(addresses) {
|
||||
if routed(name, suffix) {
|
||||
// A routed name is already a full name under a public domain, and it has no mesh
|
||||
// form: appending the suffix made `<name>.<suffix>`, which every machine's hosts file
|
||||
// carried and nothing served (novox/hq issue 157). It is published as itself, once.
|
||||
out = append(out, rosterEntry{Name: name, FQDN: name, Address: addresses[name], Account: accounts[name]})
|
||||
continue
|
||||
}
|
||||
internal, bare := meshName(name, suffix)
|
||||
// The account is looked up by whichever key the caller keys accounts on — the internal name
|
||||
// or the bare one — so a template gets the right login however the maps were built.
|
||||
@@ -187,6 +194,14 @@ func meshName(name, suffix string) (internal, bare string) {
|
||||
return name + dotted, name
|
||||
}
|
||||
|
||||
// routed says whether a name the mesh serves is a routed public name rather than a machine's: it
|
||||
// carries a domain of its own and not the mesh's suffix. A machine's name is bare (`homer`) or
|
||||
// internal (`homer.internal`); anything else with a dot in it was composed under a public domain.
|
||||
func routed(name, suffix string) bool {
|
||||
dotted := "." + strings.TrimPrefix(suffixOr(suffix), ".")
|
||||
return strings.Contains(name, ".") && !strings.HasSuffix(name, dotted)
|
||||
}
|
||||
|
||||
// suffixOr is the suffix given, or the one the mesh composes names with when none was handed down.
|
||||
// The one place the default is written, so a fact and a name cannot disagree about it.
|
||||
func suffixOr(suffix string) string {
|
||||
|
||||
@@ -258,3 +258,24 @@ func TestAHomeFactIsSkippedWhereThereIsNoAccount(t *testing.T) {
|
||||
t.Fatalf("a home fact was placed on a machine with no operator account: %v", given)
|
||||
}
|
||||
}
|
||||
|
||||
// A routed name is already a full name under a public domain and has no mesh form. Appending the
|
||||
// suffix to it made `git.example.tld.internal` — carried by every machine's hosts file, served by
|
||||
// nothing, and refused by the proxy at the handshake (novox/hq issue 157). It is published as
|
||||
// itself, and only a machine has a bare name beside its full one.
|
||||
func TestARoutedNameIsPublishedAsItselfAndNotSuffixed(t *testing.T) {
|
||||
names := map[string]string{"homer.internal": "10.42.0.1", "git.example.tld": "10.42.0.1"}
|
||||
tmpl := RosterFile{Path: "/f", Template: "{{range .Names}}{{.FQDN}} {{.Name}}\n{{end}}"}
|
||||
out, err := FactsInto(Manifest{Module: "a", Facts: map[string]RosterFile{"f": tmpl}},
|
||||
Resolution{Node: "homer"}, names, map[string]string{"homer.internal": "10.42.0.1"}, nil, "internal")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
got := out[0]["content"].(string)
|
||||
if strings.Contains(got, "tld.internal") {
|
||||
t.Fatalf("the routed name was given a suffixed alias that nothing serves:\n%s", got)
|
||||
}
|
||||
if !strings.Contains(got, "git.example.tld git.example.tld\n") || !strings.Contains(got, "homer.internal homer\n") {
|
||||
t.Fatalf("the roster does not carry the routed name as itself beside the machine's two forms:\n%s", got)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -198,37 +198,59 @@ func TestTheApexLabelComposesToTheBarePrivateAddress(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// novox/hq ADR 0066 propagate, by ADR 0148's means: a granted route name is published into the
|
||||
// machine's roster mapped to the node that serves it, beside the `<node>.internal` names, and the
|
||||
// machine's resolver answers it to every container. Nothing is written into the container itself —
|
||||
// a routed name that moved would otherwise be wrong inside every container until each was recreated.
|
||||
func TestARoutedNameResolvesToTheServingNode(t *testing.T) {
|
||||
// novox/hq ADR 0066 propagate: a granted route name is published into internal resolution,
|
||||
// mapped to the node that serves it, alongside the `<node>.internal` names — so every
|
||||
// container, and an in-mesh ACME validator, resolves a routed name to the proxy that serves it.
|
||||
// The names map is what withMeshNames writes into every container as `--add-host`; a route name
|
||||
// mapped to the serving node's address rides the same mechanism.
|
||||
names := map[string]string{
|
||||
"anchor.internal": "10.42.0.1",
|
||||
"git.example.tld": "10.42.0.1",
|
||||
}
|
||||
got := containersOf(t, Resolution{Node: "anchor", Modules: []Manifest{{
|
||||
Module: "app",
|
||||
Resources: []map[string]any{{"id": "web", "type": "container", "name": "web",
|
||||
"image": "registry.example/web@sha256:" + strings.Repeat("a", 64)}},
|
||||
}}}, Rendering{Names: map[string]string{
|
||||
"anchor.internal": "10.42.0.1",
|
||||
"git.example.tld": "10.42.0.1",
|
||||
}})
|
||||
}}}, Rendering{Names: names})
|
||||
if len(got) != 1 {
|
||||
t.Fatalf("expected one container, got %d", len(got))
|
||||
}
|
||||
given := namesOf(got[0])
|
||||
var sawNode, sawRoute bool
|
||||
for _, h := range given {
|
||||
if h == "anchor.internal:10.42.0.1" {
|
||||
sawNode = true
|
||||
}
|
||||
if h == "git.example.tld:10.42.0.1" {
|
||||
if given := namesOf(got[0]); len(given) != 0 {
|
||||
t.Fatalf("the routed name was copied into the container, where it would go stale: %v", given)
|
||||
}
|
||||
var sawRoute bool
|
||||
for _, e := range entriesFrom(names, nil, "internal") {
|
||||
if e.Name == "git.example.tld" && e.Address == "10.42.0.1" {
|
||||
sawRoute = true
|
||||
}
|
||||
}
|
||||
if !sawNode {
|
||||
t.Fatalf("the container lost the mesh's node names: %v", given)
|
||||
}
|
||||
if !sawRoute {
|
||||
t.Fatalf("the routed name was not published to the serving node: %v", given)
|
||||
t.Fatalf("the routed name is not in the roster the machine's resolver answers from")
|
||||
}
|
||||
}
|
||||
|
||||
// novox/hq issue 139, ADR 0151: `<label>.<node>.internal` is answered by every machine's resolver as
|
||||
// "anything under that node's name goes to that node", so the node in a route's internal name must
|
||||
// be the one whose proxy answers it. Composed under the consumer's own name, a route served from
|
||||
// another machine got an internal name that resolved to a machine with nothing listening, while the
|
||||
// public name — published at the serving node's address — worked.
|
||||
func TestARoutesInternalNameIsComposedUnderTheNodeThatServesIt(t *testing.T) {
|
||||
hub := proxy()
|
||||
hub.Provides = FromAnywhere("reverse-proxy")
|
||||
got, err := Resolve(shelf(hub, labelled("board", "git", 8080)), []string{"board"},
|
||||
withPrivateAddress("laptop.internal"), World{Offered: map[string][]Provider{
|
||||
"reverse-proxy": {{Node: "anchor", At: "anchor.internal", Module: "traefik"}},
|
||||
}})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
// Gathered the way the control plane gathers a consumer's contribution for a provider on
|
||||
// another machine.
|
||||
values, asks, err := got.ContributionsFrom("reverse-proxy", "board", nil)
|
||||
if err != nil || !asks {
|
||||
t.Fatalf("the route was not contributed: %v %v", asks, err)
|
||||
}
|
||||
if values["internal-name"] != "git.anchor.internal" {
|
||||
t.Fatalf("the internal name does not say where the request arrives: %v", values)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,11 @@
|
||||
-- The order of what a machine was sent, so a host can tell an older declaration from a newer.
|
||||
--
|
||||
-- novox/hq 04-ISSUES/107. A declaration's only identity was the digest of its bytes. The host could
|
||||
-- say "this is not the last one" and could not say "this is older", so a backlog drained out of
|
||||
-- order applied a declaration the mesh had already superseded. The controller already holds a
|
||||
-- per-node lock while it composes and records each send — the order existed and was thrown away at
|
||||
-- the wire.
|
||||
--
|
||||
-- One counter per node, taken under that hold, one higher per send. Null is a machine sent nothing
|
||||
-- since this existed, which is not the same as a machine sent nothing.
|
||||
alter table node add column sequence bigint;
|
||||
@@ -1005,3 +1005,34 @@ func (i *Inventory) RecordHostVersion(ctx context.Context, id, version string) e
|
||||
`update node set host_version = $2, last_seen = now() where id = $1`, id, version)
|
||||
return err
|
||||
}
|
||||
|
||||
// NextSequence takes the next number for a declaration to this node, one higher than the last it
|
||||
// was sent (novox/hq 04-ISSUES/107).
|
||||
//
|
||||
// **One statement, so two composers cannot take the same number.** The caller holds the node while it
|
||||
// composes and sends, so in practice there is one; the increment is atomic anyway, because a rule
|
||||
// that is true only while a lock is held somewhere else is a rule nobody can see from here.
|
||||
func (i *Inventory) NextSequence(ctx context.Context, id string) (int64, error) {
|
||||
var n int64
|
||||
err := i.store.Pool().QueryRow(ctx,
|
||||
`update node set sequence = coalesce(sequence, 0) + 1 where id = $1 returning sequence`, id).Scan(&n)
|
||||
if err != nil {
|
||||
return 0, fmt.Errorf("taking the next sequence for %s: %w", id, err)
|
||||
}
|
||||
return n, nil
|
||||
}
|
||||
|
||||
// Sequence is the number of the last declaration this node was sent, and zero for one sent nothing
|
||||
// since sends were numbered. Read, not taken: what the mesh WOULD send is composed with this, so it
|
||||
// is byte for byte what it DID send when nothing else changed — a comparison that took a fresh number
|
||||
// would read every machine as behind for ever (novox/hq 04-ISSUES/107).
|
||||
func (i *Inventory) Sequence(ctx context.Context, id string) (int64, error) {
|
||||
var n *int64
|
||||
if err := i.store.Pool().QueryRow(ctx, `select sequence from node where id = $1`, id).Scan(&n); err != nil {
|
||||
return 0, fmt.Errorf("reading the sequence of %s: %w", id, err)
|
||||
}
|
||||
if n == nil {
|
||||
return 0, nil
|
||||
}
|
||||
return *n, nil
|
||||
}
|
||||
|
||||
@@ -169,10 +169,12 @@ func (g *Generator) Graph() Graph { return g.graph }
|
||||
//
|
||||
// - No floor: no header, no localhost, no `127.0.1.1` — those are the machine's, above the region.
|
||||
// - A machine's own line is marked, and its mesh name resolves to its mesh address, not loopback.
|
||||
// - `.Names` is every name the mesh serves (issue 111), so a container reaching a routed name
|
||||
// finds the machine serving it; machines with no address yet are already left out of the set.
|
||||
// - `.Names` is every name the mesh serves (issue 111), so anything on the machine reaching a
|
||||
// routed name through its resolver finds the machine serving it; machines with no address yet
|
||||
// are already left out of the set. A routed name is one alias, itself — a machine has a bare
|
||||
// name beside its full one, a routed name has nothing beside it (issue 157).
|
||||
const hostsTemplate = "# The mesh's names. This region is replaced whenever a machine joins or leaves.\n" +
|
||||
"{{range .Names}}{{.Address}}\t{{.FQDN}}\t{{.Name}}{{if eq .Name $.Node}}\t# this machine{{end}}\n{{end}}"
|
||||
"{{range .Names}}{{.Address}}\t{{.FQDN}}{{if ne .Name .FQDN}}\t{{.Name}}{{end}}{{if eq .Name $.Node}}\t# this machine{{end}}\n{{end}}"
|
||||
|
||||
// Manifest is the module the mesh provides for itself.
|
||||
//
|
||||
|
||||
Reference in New Issue
Block a user