Files
felhom-controller/controller/internal/system/info_cgroup_test.go
T
admin 4989513a96 F1 (rework): source guest RAM cap from docker info; deploy guard uses committed memory
The cgroup-only approach was a no-op on the demo: the controller container's OWN
cgroup is unlimited (the 2GB cap is on the LXC ancestor, hidden), and /proc has no
lxcfs, so it kept reporting the host's 16GB. The Docker daemon runs IN the LXC, so
'docker info' MemTotal reports the guest's real cap (2048MB) — now the authoritative
source (cgroup limit preferred when present, e.g. non-nested). The deploy memory
guard now uses the controller's committed-app memory (sum of running mem requests)
for 'used' — accurate and cheap — instead of host /proc RSS (unobservable per guest;
would make the guard never/always fire). /api/system/info reports the guest cap as
total and committed memory as used. Tests: cgroup-limit path, docker-info fallback
(nested case), GuestMemTotalMB fallback (dockerMemTotalFn stub).
2026-06-14 10:18:22 +02:00

144 lines
4.6 KiB
Go

//go:build linux
package system
import (
"os"
"path/filepath"
"testing"
)
// TestReadMemInfoUsesCgroupV2Limit asserts F1: when a cgroup v2 memory.max caps the container well
// below the host /proc/meminfo total, readMemInfo reports the cgroup cap (the guest's real ceiling),
// not the host RAM. On the pre-fix code this test fails because readMemInfo ignored cgroup entirely.
func TestReadMemInfoUsesCgroupV2Limit(t *testing.T) {
dir := t.TempDir()
const twoGiB = uint64(2 * 1024 * 1024 * 1024)
mustWriteFile(t, filepath.Join(dir, "memory.max"), []byte(itoa(twoGiB)))
old := cgroupRoot
cgroupRoot = dir
defer func() { cgroupRoot = old }()
var info SystemInfo
readMemInfo(&info)
// Host /proc/meminfo total is whatever the test machine has; the cgroup cap must win when smaller.
if info.TotalMemMB != 2048 {
t.Fatalf("TotalMemMB = %d, want 2048 (cgroup cap), not host RAM", info.TotalMemMB)
}
// Used is a scaled estimate (the container cannot read guest-wide RSS); just assert it is sane.
if info.UsedMemMB > info.TotalMemMB {
t.Fatalf("UsedMemMB = %d exceeds TotalMemMB = %d", info.UsedMemMB, info.TotalMemMB)
}
if info.AvailMemMB != info.TotalMemMB-info.UsedMemMB {
t.Fatalf("AvailMemMB inconsistent: %d != %d-%d", info.AvailMemMB, info.TotalMemMB, info.UsedMemMB)
}
}
// TestReadMemInfoUsesDockerInfoWhenCgroupUnlimited asserts the NESTED-LXC case (the real demo): the
// container's own cgroup is unlimited ("max"), so the guest cap must come from `docker info` MemTotal.
// Pre-fix (and the cgroup-only attempt) reports the host RAM here.
func TestReadMemInfoUsesDockerInfoWhenCgroupUnlimited(t *testing.T) {
dir := t.TempDir()
mustWriteFile(t, filepath.Join(dir, "memory.max"), []byte("max")) // container cgroup unlimited
old := cgroupRoot
cgroupRoot = dir
defer func() { cgroupRoot = old }()
oldFn := dockerMemTotalFn
dockerMemTotalFn = func() (uint64, bool) { return 2048, true }
defer func() { dockerMemTotalFn = oldFn }()
var info SystemInfo
readMemInfo(&info)
if info.TotalMemMB != 2048 {
t.Fatalf("TotalMemMB = %d, want 2048 (docker-info guest cap)", info.TotalMemMB)
}
}
// TestGuestMemTotalMB_DockerInfoFallback asserts GuestMemTotalMB (used by the deploy guard) falls back
// to docker-info when no cgroup limit is present.
func TestGuestMemTotalMB_DockerInfoFallback(t *testing.T) {
dir := t.TempDir() // no cgroup files → no limit
old := cgroupRoot
cgroupRoot = dir
defer func() { cgroupRoot = old }()
oldFn := dockerMemTotalFn
dockerMemTotalFn = func() (uint64, bool) { return 2048, true }
defer func() { dockerMemTotalFn = oldFn }()
if v, ok := GuestMemTotalMB(); !ok || v != 2048 {
t.Fatalf("GuestMemTotalMB = (%d, %v), want (2048, true)", v, ok)
}
}
// TestReadMemInfoCgroupMaxIsUnlimited asserts that a v2 "max" sentinel does NOT override /proc/meminfo
// (an uncapped container keeps the host view rather than a bogus 0).
func TestReadMemInfoCgroupMaxIsUnlimited(t *testing.T) {
dir := t.TempDir()
mustWriteFile(t, filepath.Join(dir, "memory.max"), []byte("max"))
old := cgroupRoot
cgroupRoot = dir
defer func() { cgroupRoot = old }()
var info SystemInfo
readMemInfo(&info)
if info.TotalMemMB == 0 {
t.Fatalf("TotalMemMB = 0 with an unlimited cgroup; expected the /proc/meminfo host total")
}
}
// TestReadCgroupMemLimitV1Unlimited asserts the v1 near-uint64-max sentinel is treated as unlimited.
func TestReadCgroupMemLimitV1Unlimited(t *testing.T) {
dir := t.TempDir()
memDir := filepath.Join(dir, "memory")
if err := os.MkdirAll(memDir, 0o755); err != nil {
t.Fatal(err)
}
// Typical v1 "unlimited" value.
mustWriteFile(t, filepath.Join(memDir, "memory.limit_in_bytes"), []byte("9223372036854771712"))
if _, ok := readCgroupMemLimitMB(dir); ok {
t.Fatalf("readCgroupMemLimitMB treated the v1 unlimited sentinel as a real limit")
}
}
// TestReadCgroupMemLimitV1Real asserts a finite v1 limit is read.
func TestReadCgroupMemLimitV1Real(t *testing.T) {
dir := t.TempDir()
memDir := filepath.Join(dir, "memory")
if err := os.MkdirAll(memDir, 0o755); err != nil {
t.Fatal(err)
}
const oneGiB = uint64(1024 * 1024 * 1024)
mustWriteFile(t, filepath.Join(memDir, "memory.limit_in_bytes"), []byte(itoa(oneGiB)))
mb, ok := readCgroupMemLimitMB(dir)
if !ok || mb != 1024 {
t.Fatalf("readCgroupMemLimitMB = (%d, %v), want (1024, true)", mb, ok)
}
}
func mustWriteFile(t *testing.T, path string, data []byte) {
t.Helper()
if err := os.WriteFile(path, data, 0o644); err != nil {
t.Fatal(err)
}
}
func itoa(v uint64) string {
if v == 0 {
return "0"
}
var buf [20]byte
i := len(buf)
for v > 0 {
i--
buf[i] = byte('0' + v%10)
v /= 10
}
return string(buf[i:])
}