Review of the fix for hq issue 104 found three faults in it. A file applied
on an enrolled node — the mesh's own last declaration included — is applied
as the bundle is, so its resources are recorded as the machine's own and
what the mesh declared reads as undeclared: the plan removed the foundation.
`apply FILE` is for a machine the mesh has not spoken to, and is now refused
saying so whenever declared.json exists. The plan looked at what is held
before what the declaration says is taken, so the one cutover ADR 0100 says
must be previewed read as a hold; it now decides in holdOnAdopted's order,
models a step run inside a held container, and a test holds the plan's
sequence to the apply's outcomes. Genesis wrote the mode on every run, so a
re-run after `converge` left the state saying adopted while the kept,
signed declaration said converged, and the reconcile loop refused every five
minutes with no delivery coming to end it: genesis now writes the mode only
when none is recorded, and where the state and the verified kept declaration
disagree, the kept declaration wins and the repair is said.
Also: a file lock beside the state, taken by the link service, the host's
own commands and the installer alike, so a `reconcile` run by hand no
longer races the loop's save — chosen over refusing while a named service is
active, which would miss a `mesh-host run` started by hand; `--json
--dry-run` emits {plan} like an apply emits {plan, report}; the README's
duplicate flag line; and the bundle refusal is about the digest, not a claim
the carried bytes can never match what genesis applied.
207 lines
7.9 KiB
Go
207 lines
7.9 KiB
Go
package apply
|
|
|
|
import (
|
|
"fmt"
|
|
"strings"
|
|
|
|
"github.com/novox/mesh-host/internal/declaration"
|
|
"github.com/novox/mesh-host/internal/firewall"
|
|
"github.com/novox/mesh-host/internal/store"
|
|
)
|
|
|
|
// A declaration is said before it is done.
|
|
//
|
|
// An apply that prints what it did after it did it is a report; what an operator reaching for
|
|
// `reconcile` under pressure needs is a preview — the base filter that closed an adopted
|
|
// control-node for forty-five minutes was listed nowhere until it was on disk (novox/hq issue
|
|
// 104). Converging already previews on the controller; the host's own commands now do too, and
|
|
// `--dry-run` is the preview and nothing else.
|
|
|
|
// Step is one thing an apply would do to this machine.
|
|
type Step struct {
|
|
// Verb is create · update · check · hold · run · remove · forget · disable · enable.
|
|
Verb string `json:"verb"`
|
|
Type string `json:"type,omitempty"`
|
|
ID string `json:"id,omitempty"`
|
|
Target string `json:"target,omitempty"`
|
|
Why string `json:"why,omitempty"`
|
|
}
|
|
|
|
func (s Step) String() string {
|
|
line := fmt.Sprintf("%-8s %-10s %s", s.Verb, s.Type, s.ID)
|
|
if s.Target != "" && s.Target != s.ID {
|
|
line += " (" + s.Target + ")"
|
|
}
|
|
if s.Why != "" {
|
|
line += " — " + s.Why
|
|
}
|
|
return line
|
|
}
|
|
|
|
// Plan says what applying a declaration would change, in the order ApplyKeeping would do it,
|
|
// before anything on the machine is touched.
|
|
//
|
|
// **Read from the declaration and the node's own record, not from the machine.** What the
|
|
// record cannot settle — whether a file recorded here has since drifted, whether a container
|
|
// runs the spec it was made from — is said as a check, because that is what the apply does: it
|
|
// reads the machine and corrects it. What the record does settle is said as it is: a resource
|
|
// with no record is created; a plain file whose declared content differs from what this host
|
|
// last wrote is updated; a hold is kept; an action is run — an action is a command, and a
|
|
// preview that folded it into "check" would hide the one kind of step that is not read back
|
|
// from state.
|
|
func Plan(d *declaration.Declaration, known store.State, origin string) []Step {
|
|
var steps []Step
|
|
|
|
declared := map[string]bool{}
|
|
for _, r := range d.Resources {
|
|
declared[r.Identity()] = true
|
|
}
|
|
rec := known.Firewall
|
|
ufw := rec != nil && rec.Kind == string(firewall.UFW)
|
|
|
|
if d.Adoption != nil && ufw && rec.DisabledByMesh {
|
|
steps = append(steps, Step{Verb: "enable", Type: "firewall", ID: "ufw",
|
|
Why: "this node is adopted again, so the firewall found on it is put back in force"})
|
|
}
|
|
|
|
// What is held and no longer declared is let go of on paper only (ApplyKeeping does this
|
|
// before the resources); the file or container itself is left as found.
|
|
if origin == store.OriginDeclared {
|
|
for _, h := range known.Held {
|
|
if declared[h.ID] {
|
|
continue
|
|
}
|
|
steps = append(steps, Step{Verb: "forget", Type: h.Kind, ID: h.ID, Target: h.Target,
|
|
Why: "held for " + h.Module + " and no longer declared; left as found"})
|
|
}
|
|
}
|
|
|
|
var protecting, orphans []Step
|
|
for _, orphan := range known.Orphans(declared, origin) {
|
|
step := Step{Verb: "remove", Type: orphan.Type, ID: orphan.ID, Target: orphan.Target,
|
|
Why: "recorded here and no longer declared"}
|
|
if d.Adoption == nil && strings.HasPrefix(orphan.ID, declaration.AdoptionPrefix) {
|
|
step.Why = "what protected this node while adopted; removed last, once everything else applied"
|
|
protecting = append(protecting, step)
|
|
continue
|
|
}
|
|
orphans = append(orphans, step)
|
|
}
|
|
|
|
// The guard goes up before anything is removed on an adopted node; on a converged one the
|
|
// removals go first (novox/hq ADR 0103).
|
|
var guard, rest []declaration.Resource
|
|
for _, r := range d.Resources {
|
|
if d.Adoption != nil && strings.HasPrefix(r.Identity(), guardPrefix) {
|
|
guard = append(guard, r)
|
|
continue
|
|
}
|
|
rest = append(rest, r)
|
|
}
|
|
for _, r := range guard {
|
|
steps = append(steps, planned(r, d, known))
|
|
}
|
|
steps = append(steps, orphans...)
|
|
for _, r := range rest {
|
|
steps = append(steps, planned(r, d, known))
|
|
}
|
|
|
|
// Only a declaration from the mesh converges a node; a bundle or a file never retires the
|
|
// firewall found here, and neither says so in a plan.
|
|
if d.Adoption == nil && origin == store.OriginDeclared && ufw && rec.WasActive && !rec.DisabledByMesh {
|
|
steps = append(steps, Step{Verb: "disable", Type: "firewall", ID: "ufw",
|
|
Why: "this node converges: retired once the mesh's own filter is loaded, never before; " +
|
|
"its configuration stays on disk"})
|
|
}
|
|
steps = append(steps, protecting...)
|
|
return steps
|
|
}
|
|
|
|
// planned is what one declared resource would come to.
|
|
//
|
|
// **In the order holdOnAdopted decides it**, because the one cutover ADR 0100 says must be
|
|
// previewed is the one a plan gets backwards if it looks at the record first: a resource this
|
|
// node holds for a module the declaration now says is taken is not held any longer — it is
|
|
// applied, and what was found is replaced. The declaration's word on which modules are untaken
|
|
// comes first; the record of what is held only says what that replacement replaces.
|
|
func planned(r declaration.Resource, d *declaration.Declaration, known store.State) Step {
|
|
step := Step{Type: string(r.Kind()), ID: r.Identity(), Target: r.Target()}
|
|
|
|
if d.Adoption != nil {
|
|
// Something run inside a held container is held with it, while that container's module
|
|
// is untaken; once the module is taken the container is replaced before this runs.
|
|
if in := runsIn(r); in != "" {
|
|
if container, isHeld := heldContainer(known, in); isHeld {
|
|
if _, untaken := d.Adoption.Untaken[container.Module]; untaken {
|
|
step.Verb = "hold"
|
|
step.Why = "runs in " + in + ", which is held as found; not run until " + container.Module + " is taken"
|
|
return step
|
|
}
|
|
}
|
|
}
|
|
// A file written into replaces nothing that was found, so it is never held (ADR 0102).
|
|
into := false
|
|
if f, ok := r.(*declaration.File); ok && f.Into != "" {
|
|
into = true
|
|
}
|
|
h, held := known.HeldAt(r.Identity())
|
|
module, untaken := d.Adoption.UntakenModuleOf(r.Identity())
|
|
switch {
|
|
case into:
|
|
case untaken && held:
|
|
step.Verb, step.Why = "hold", "found on this machine and kept as it is until "+module+" is taken"
|
|
return step
|
|
case untaken:
|
|
step.Verb = "create"
|
|
step.Why = "unless it is found on this machine — then held as it is until " + module + " is taken"
|
|
return step
|
|
case held:
|
|
// The cutover: the module is taken, and what was held for it is replaced.
|
|
step.Verb = "create"
|
|
if _, recorded := known.Find(r.Identity()); recorded {
|
|
step.Verb = "update"
|
|
}
|
|
step.Why = h.Module + " is taken: replaces what was found and held"
|
|
if h.Kept != "" {
|
|
step.Why += "; the original stays at " + h.Kept
|
|
}
|
|
return step
|
|
}
|
|
}
|
|
|
|
if a, ok := r.(*declaration.Action); ok {
|
|
// Named as what it is. Its verify decides whether it runs, and that is read from the
|
|
// machine, not the record.
|
|
step.Verb = "run"
|
|
step.Target = ""
|
|
step.Why = fmt.Sprintf("an action: `%s`, unless its verify `%s` already passes; if it fails, "+
|
|
"nothing after it is attempted", strings.Join(a.Command, " "), strings.Join(a.Verify, " "))
|
|
if a.In != "" {
|
|
step.Why = "in " + a.In + ", " + step.Why
|
|
}
|
|
return step
|
|
}
|
|
|
|
was, recorded := known.Find(r.Identity())
|
|
if !recorded {
|
|
step.Verb, step.Why = "create", "no record of it on this node"
|
|
return step
|
|
}
|
|
if want := wouldWrite(r); want != "" && was.Wrote != "" && want != was.Wrote {
|
|
step.Verb, step.Why = "update", "the declaration changed since this host applied it"
|
|
return step
|
|
}
|
|
step.Verb, step.Why = "check", "recorded here; corrected if this machine drifted from it"
|
|
return step
|
|
}
|
|
|
|
// wouldWrite is the digest a plain file would be recorded under, or empty where only the apply
|
|
// can know: a sealed file, one with secrets in it, one written into, one carrying bytes.
|
|
func wouldWrite(r declaration.Resource) string {
|
|
f, ok := r.(*declaration.File)
|
|
if !ok || f.Into != "" || f.Bytes != "" || f.Secret() || len(f.Secrets) > 0 {
|
|
return ""
|
|
}
|
|
return digestOf(f.Content)
|
|
}
|