Add disk-load's cpu_top tool: CPU by systemd unit and container (issue 741)

No tool named which units or processes used CPU outside containers during the novox overload (issue 739). cpu_top reads each cgroup's cpu.stat (no root needed), ranks units or containers busiest first, and says the machine's CPU in use and the busy time no unit accounts for.
2026-10-15 14:51:08 +02:00
parent 8c60604eb7
commit a8d84d1730
6 changed files with 344 additions and 9 deletions
@@ -85,6 +85,57 @@ func Tools(m *Machine) []stdio.Tool {
 				return out, nil
 			},
 		},
+		{
+			Name: "cpu_top",
+			Description: "What used the most CPU over a few seconds, from each unit's cgroup cpu.stat, which needs no root: the machine's " +
+				"CPU in use (as % of all CPUs and as CPUs busy, from /proc/stat), then by=unit (the default) each systemd unit and " +
+				"container ranked by CPU, busiest first, with the busy time no unit accounts for; by=container only the containers, " +
+				"by name. Replaces top, systemd-cgtop. (r)",
+			Input: map[string]any{
+				"seconds": map[string]any{"type": "integer", "description": "how long to sample, in seconds (default 3, at most 10)"},
+				"limit":   map[string]any{"type": "integer", "description": "how many units or containers to name (default 15, at most 50)"},
+				"by":      map[string]any{"type": "string", "enum": []string{"unit", "container"}, "description": "what to rank (default unit)"},
+			},
+			Run: func(args map[string]any) (any, error) {
+				n, err := count(args, "seconds", 3, 1, 10)
+				if err != nil {
+					return nil, err
+				}
+				w := time.Duration(n) * time.Second
+				limit, err := count(args, "limit", 15, 1, 50)
+				if err != nil {
+					return nil, err
+				}
+				by := text(args, "by")
+				switch by {
+				case "":
+					by = "unit"
+				case "unit", "container":
+				default:
+					return nil, fmt.Errorf("by is unit or container, not %q", by)
+				}
+				ac, err := parseCPU(m.read("/proc/stat"))
+				if err != nil {
+					return nil, err
+				}
+				a := m.unitCPU()
+				m.Wait(w)
+				bc, err := parseCPU(m.read("/proc/stat"))
+				if err != nil {
+					return nil, err
+				}
+				b := m.unitCPU()
+				machine := machineCPUOver(ac, bc)
+				top, unaccounted := m.topCPU(a, b, w, by, limit, machine.CPUsBusy)
+				return map[string]any{
+					"window_s":        w.Seconds(),
+					"by":              by,
+					"cpu":             machine,
+					"top":             top,
+					"unaccounted_pct": unaccounted,
+				}, nil
+			},
+		},
 		{
 			Name: "disk_filesystems",
 			Description: "The space of every filesystem that stores data (not proc, tmpfs or overlay layers): size, used and free in GiB, " +