Files
mesh-controller/cmd/mesh-controller/plans_follow.go
T
jschoubben 2819915e8e
mesh/merge-gate out of date: judged against trunk e63af0df17f5, the trunk is now 21ac8fd8586d; judged again on a recheck or when it is merged
mesh/repo-check out of date: judged against trunk e63af0df17f5, the trunk is now 21ac8fd8586d; judged again on a recheck or when it is merged
mesh/delivery superseded: a newer head of the same pull request
Stop the controller's tests waiting out fixed intervals
Reading the build events waited two seconds on every queue read, the race
detector's exit sleep cost a second per command line a test runs, and the
lease and plan-wait tests waited out production intervals (novox/hq issue 591).
2026-10-12 23:53:06 +02:00

160 lines
6.3 KiB
Go

package main
import (
"context"
"encoding/json"
"fmt"
"os"
"strconv"
"strings"
"time"
"github.com/novox/mesh-controller/internal/inventory"
"github.com/novox/mesh-controller/internal/link"
)
// Following a plan (novox/hq issue 229): `plans wait <id>` holds its answer until the plan moves, reaches its
// next tier or ends, or until its bound passes, and says which. Before it, an agent following a rollout had
// `plans` answer once, in prose, and wrote a loop of its own round the mesh's tools to be told the plan moved.
//
// **No wait is longer than a call is answered within** (link.LongestAnswer, inside the console's thirty
// seconds): a longer one would answer "still running" and leave its caller to ask `calls` — the loop again.
// So a caller following a plan to its end asks again; each call answers the moment the plan moves.
// maxPlanWait is the longest bound a wait takes, and the bound when none is given: what a call is answered
// within, less the time a verb's command takes to start and read the store.
var maxPlanWait = link.LongestAnswer - planWaitStart
// planWaitStart is what the verb's window allows beyond the bound: starting the command and opening the stores.
// A store slow enough to push the read and the answer past it degrades as any long call does: the caller is
// answered that the call is still running, and `calls` with its id says what came of it.
const planWaitStart = 5 * time.Second
// planWaitEvery is how often a wait reads the plan again. A variable so a test reads it more often
// (novox/hq issue 591).
var planWaitEvery = time.Second
// The things a wait waits until.
var planWaitUntil = []string{"moved", "tier", "done"}
// planWaitAsked checks what a wait is asked for: until (moved when empty) and a bound (a duration, or a number
// of seconds; maxPlanWait when empty).
func planWaitAsked(until, bound string) (string, time.Duration, error) {
if until == "" {
until = "moved"
}
known := false
for _, u := range planWaitUntil {
known = known || u == until
}
if !known {
return "", 0, fmt.Errorf("a wait is until %s, not %q", strings.Join(planWaitUntil, ", "), until)
}
d := maxPlanWait
if bound = strings.TrimSpace(bound); bound != "" {
var err error
if secs, isNumber := strconv.Atoi(bound); isNumber == nil {
d = time.Duration(secs) * time.Second
} else if d, err = time.ParseDuration(bound); err != nil {
return "", 0, fmt.Errorf("the bound %q is not a duration (such as 20s) or a number of seconds", bound)
}
if d <= 0 || d > maxPlanWait {
return "", 0, fmt.Errorf("the bound is at most %s, the longest a call is answered within; %s was asked "+
"— to follow a plan longer, ask again: each call answers the moment the plan moves", maxPlanWait, d)
}
}
return until, d, nil
}
// planEnded is a plan that will not move again: done, failed or superseded. A batch being assembled is not one.
func planEnded(p inventory.Plan) bool { return !p.Open() && !p.Batch() }
// waitOnPlan reads the plan until what it waits for happens or the bound passes, and answers the plan as last
// read and what ended the wait: moved (any save of it), tier (its tier changed), done (it ended — which ends
// every wait, since nothing comes after it), or bound. Moved and tier are judged against the plan as first read.
func waitOnPlan(ctx context.Context, read func(context.Context) (inventory.Plan, error), until string,
bound, every time.Duration) (inventory.Plan, string, error) {
first, err := read(ctx)
if err != nil {
return inventory.Plan{}, "", err
}
if planEnded(first) {
return first, "done", nil
}
deadline := time.Now().Add(bound)
tick := time.NewTicker(every)
defer tick.Stop()
last := first
for {
select {
case <-ctx.Done():
return last, "", ctx.Err()
case <-tick.C:
}
if !time.Now().Before(deadline) {
return last, "bound", nil
}
p, err := read(ctx)
if err != nil {
return last, "", err
}
last = p
switch {
case planEnded(p):
return p, "done", nil
case until == "moved" && p.Revision != first.Revision:
return p, "moved", nil
case until == "tier" && p.Tier != first.Tier:
return p, "tier", nil
}
}
}
// planWaited is what `plans wait` answers: the plan, what ended the wait, and the line a person reads (`text`,
// which the verb answers as its output and not again in the data).
type planWaited struct {
// Came is what ended the wait: moved, tier, done, or bound when nothing did.
Came string `json:"came"`
Until string `json:"until"`
Waited string `json:"waited"`
Plan planStatus `json:"plan"`
// Revision is the plan's as read: a caller asking again with the same plan sees whether it moved since.
Revision int64 `json:"revision"`
Text string `json:"text"`
}
func planWaitedDoc(p inventory.Plan, st planStatus, until, came string, waited time.Duration, line string) planWaited {
said := map[string]string{
"moved": "moved", "tier": "reached another tier", "done": "ended",
"bound": "did not " + map[string]string{"moved": "move", "tier": "reach another tier", "done": "end"}[until],
}[came]
text := fmt.Sprintf("%s %s in %s (waited until %s)\n%s — %s\n", p.ID, said, waited.Round(time.Second), until,
p.ID, line)
return planWaited{Came: came, Until: until, Waited: waited.Round(time.Millisecond).String(), Plan: st,
Revision: p.Revision, Text: text}
}
// planWaitCommand is `plans wait <id>`: the plan followed until it moves, or the bound passes.
func planWaitCommand(ctx context.Context, inv *inventory.Inventory, id, untilAsked, boundAsked string) error {
until, bound, err := planWaitAsked(untilAsked, boundAsked)
if err != nil {
return err
}
began := time.Now()
p, came, err := waitOnPlan(ctx, func(ctx context.Context) (inventory.Plan, error) {
return inv.PlanByID(ctx, id)
}, until, bound, planWaitEvery)
if err != nil {
return err
}
// Said as `plans <id>` says its first line, and as `status` says the plan.
now, one := time.Now(), []inventory.Plan{p}
bounds, pause := readTierBounds(ctx, inv, now), buildSeatPause(ctx, inv, one)
line := planLineSaid(p, now, pause, bounds.of(p.Repository), func(module string) []string {
on, _ := inv.Running(ctx, module)
return on
}, waitsOf(ctx, inv, one))
doc := planWaitedDoc(p, planStatuses(one, now, pause, bounds)[0], until, came, now.Sub(began), line)
return json.NewEncoder(os.Stdout).Encode(doc)
}