Refuse build steps under a free-space floor and release workspaces, so the build modules stop filling a build node's disk (issue 1839)

mesh-build-go, mesh-build-node and mesh-build-image refuse every fetch, test
and build, and say unhealthy, while their work or cache filesystem has less
than 20 GiB free (build-agent's floor), so the builder chooses another node
instead of filling this one. Each serves build_<x>_release, removing a
workspace once its caller's last step answered; a failed fetch removes its
own; a workspace never released goes two hours after its last use (ADR 0509)
in place of a day, never while a step holds it. Pins mesh-sdk's
fix/1839-build-floor (buildstep.Floor, buildstep.Workspaces).

modules/mesh-build-node/cmd/mesh-build-node/fetch.go

@@ -33,9 +33,6 @@ const ForgeAlias = "mesh-forge"
 // sdkPackage is the package the toolchain carries and a module's own dependencies never supply.
 const sdkPackage = "@novox/mesh-sdk"
 
-// WorkspaceAge is how long a workspace is kept.
-const WorkspaceAge = 24 * time.Hour
-
 var commitOK = regexp.MustCompile(`^[0-9a-f]{40}$`)
 
 var repositoryOK = regexp.MustCompile(`^[A-Za-z0-9][A-Za-z0-9._-]*/[A-Za-z0-9][A-Za-z0-9._-]*$`)
@@ -105,20 +102,36 @@ func (m *Module) fetchTool() StepTool {
 	}
 }
 
-func (m *Module) fetch(ctx context.Context, args map[string]any) (any, error) {
+// fetch makes a workspace and fills it. The workspace is held while the fetch runs, and removed when the fetch fails,
+// since nobody learns its id to release it (issue 1839).
+func (m *Module) fetch(ctx context.Context, args map[string]any) (res any, err error) {
 	// What the builder and the checker ask, in mesh-sdk's one form (ADR 0499 §4): with the module's directory and its
 	// named paths, the workspace is narrowed to them (buildstep.Narrow).
 	req, err := buildstep.ParseFetchRequest(args)
 	if err != nil {
 		return nil, err
 	}
-	repository, commit, ref, base := req.Repository, req.Commit, req.Ref, req.Base
 	group, err := groupPackageArg(args["package"])
 	if err != nil {
 		return nil, err
 	}
 	m.CleanWorkspaces(m.now())
 	id := buildstep.NewID()
+	done := m.spaces().Hold(id)
+	defer func() {
+		done()
+		if err != nil {
+			if rerr := m.spaces().Release(id); rerr != nil && m.Say != nil {
+				m.Say("the failed fetch's workspace %s: %v", id, rerr)
+			}
+		}
+	}()
+	return m.fetchInto(ctx, req, group, id)
+}
+
+func (m *Module) fetchInto(ctx context.Context, req buildstep.FetchRequest, group *groupPackage, id string) (any, error) {
+	repository, commit, ref, base := req.Repository, req.Commit, req.Ref, req.Base
+	var err error
 	root := filepath.Join(m.Work, id)
 	tree := filepath.Join(root, "tree")
 	if err := os.MkdirAll(tree, 0o700); err != nil {
@@ -354,19 +367,8 @@ func removeSDKCopies(nm string) error {
 	return nil
 }
 
-// CleanWorkspaces removes the workspaces older than WorkspaceAge from the work directory.
+// CleanWorkspaces removes the workspaces no step holds whose last use is older than buildstep.UnheldBound: the safety
+// net for a caller that never released one (issue 1839, ADR 0509).
 func (m *Module) CleanWorkspaces(now time.Time) {
-	entries, err := os.ReadDir(m.Work)
-	if err != nil {
-		return
-	}
-	for _, e := range entries {
-		info, err := e.Info()
-		if err != nil || !e.IsDir() || !workspaceOK.MatchString(e.Name()) || now.Sub(info.ModTime()) < WorkspaceAge {
-			continue
-		}
-		if err := os.RemoveAll(filepath.Join(m.Work, e.Name())); err != nil && m.Say != nil {
-			m.Say("the workspace %s could not be removed: %v", e.Name(), err)
-		}
-	}
+	m.sweepSaid(m.spaces().Sweep(now, buildstep.UnheldBound))
 }