Compare commits

..
Author SHA1 Message Date
shcizo 8fe75b2cbf fix(master): seed the tag digest from running services and hide registry error text (#9) 2026-10-13 08:38:17 +02:00
shcizo 3166874433 fix(master): remember the tag's deployed digest after any tag job (#9)
Renames last_auto_digest to last_tag_digest. FinishJob sets it to the pinned
digest after any successful job whose to_ref had no digest, so a rollback
holds however the update was started.
2026-10-13 08:33:17 +02:00
shcizo 53a2a23f1b docs: auto rollbacks, bare image as latest and registry request scope (#9) 2026-10-13 08:30:08 +02:00
shcizo 73ac8f613e refactor: tidy poller, web test helper and GoDoc line widths (#9) 2026-10-13 08:29:22 +02:00
shcizo e2f71521bb fix(deploy): make the registry credentials mount of the master stack opt-in (#9) 2026-10-13 08:29:22 +02:00
shcizo 7e4b927293 fix(master): keep rollbacks of auto services until a new digest (#9)
Adds services.last_auto_digest so the poller starts one automatic update per
registry digest, and re-reads the service before starting it. Also records a
bare image's running version as tag latest, only records well-formed
digests, and shows a digest-less version unless a digest row of its tag was
first seen at or after it.
2026-10-13 08:28:50 +02:00
shcizo f169eddc4c fix(master): drop registry response bodies from poll errors (#9) 2026-10-13 08:26:29 +02:00
shcizo 92e7646221 fix(master): say why a pinned pick fails on a protocol 2 agent (#9) 2026-10-13 08:25:21 +02:00
shcizo 2e87d98012 docs: registry polling, version history and phase 4 plan (#9) 2026-10-13 08:16:47 +02:00
shcizo 687e411052 test(e2e): pick a pinned version and poll an auto service end to end (#9) 2026-10-13 08:15:29 +02:00
shcizo 2390b6151e feat(master): POLL_INTERVAL, poller wiring and version picker in the UI (#9) 2026-10-13 08:14:43 +02:00
shcizo c6ea2d3710 feat(master): registry digest lookup and polling loop (#9) 2026-10-13 08:11:37 +02:00
shcizo d0726ca992 feat(master,agent): deploy digest-pinned refs and route them to protocol 3 agents (#9) 2026-10-13 08:07:45 +02:00
shcizo af61f17dee feat(master): record image versions and track poll suggestions in the store (#9) 2026-10-13 08:05:21 +02:00
5 changed files with 22 additions and 196 deletions
-6
View File
@@ -105,12 +105,6 @@ DATABASE_URL=postgres://... go test -tags integration ./internal/master/store/
agent's own jobs always pass it explicitly.
- **Override entries are never pruned.** A service deleted from the stack file keeps its
`image:` line in `compose.override.yaml`.
- **The override file gets the owner of the existing override, else of the stack's first
compose file.** The exception is a root-owned existing override (written before this
fix): then the compose file's owner is used, so it stops being root-owned. The agent runs
as root, so `WriteOverride` chowns the open temp file before the rename (never the path
afterwards: a symlink could be swapped in). A failure is a `warning:` line in the job
output, never a failed job.
- **There is no `STACKS_ROOT`.** Stack directories must be mounted read-write at the host
path (`/path:/path`), and `SELF_ID` must resolve to the agent's own container. On Docker
Desktop/OrbStack bind sources are translated, so Compose jobs fail there.
+1 -7
View File
@@ -152,15 +152,9 @@ func (e *ComposeExecutor) Execute(ctx context.Context, job protocol.JobStart, ou
}
fmt.Fprintln(out, resolveNote(job.Ref, pinned))
// Giving the override the stack's owner is best effort: a failure is only
// a warning, the update itself is fine.
_, ownerErr, err := WriteOverride(dir, service, pinned, files[0])
if err != nil {
if _, err := WriteOverride(dir, service, pinned); err != nil {
return "", err
}
if ownerErr != nil {
fmt.Fprintf(out, "warning: could not give the override the stack's owner: %v\n", ownerErr)
}
base := composeBase(project, workingDir, files, envs)
for _, step := range [][]string{{"pull", service}, {"up", "-d", service}} {
-14
View File
@@ -69,7 +69,6 @@ func TestComposeExecutor(t *testing.T) {
root, _ := filepath.EvalSymlinks(t.TempDir())
stack := filepath.Join(root, "slusk")
require.NoError(t, os.MkdirAll(stack, 0o755))
composeFile := stackFile(t, stack)
job := protocol.JobStart{Kind: protocol.KindCompose, ComposeProject: "slusk", ComposeService: "web", Ref: "gitea.shcizo.se/shcizo/slusk:1.4"}
pinned := job.Ref + "@" + d
@@ -108,19 +107,6 @@ func TestComposeExecutor(t *testing.T) {
_, doc := readOverride(t, stack)
assert.Equal(t, pinned, serviceImage(doc, "web"))
assert.Contains(t, out.String(), "resolved "+pinned)
assert.NotContains(t, out.String(), "warning")
})
t.Run("an unreadable owner is a warning and the job still succeeds", func(t *testing.T) {
t.Cleanup(cleanOverride)
require.NoError(t, os.Rename(composeFile, composeFile+".bak"))
t.Cleanup(func() { os.Rename(composeFile+".bak", composeFile) })
var out strings.Builder
got, err := setup(fakeCompose{rw, []container.Summary{ct}}, &fakeDist{digest: d}, &recorder{}).Execute(context.Background(), job, &out)
require.NoError(t, err)
assert.Equal(t, pinned, got)
assert.Contains(t, out.String(), "warning: could not give the override the stack's owner: read owner: ")
_, doc := readOverride(t, stack)
assert.Equal(t, pinned, serviceImage(doc, "web"))
})
t.Run("a pinned ref is written verbatim and not resolved", func(t *testing.T) {
t.Cleanup(cleanOverride)
+13 -75
View File
@@ -8,7 +8,6 @@ import (
"os"
"path/filepath"
"strings"
"syscall"
"github.com/docker/docker/api/types/container"
"github.com/docker/docker/api/types/mount"
@@ -35,68 +34,15 @@ var overrideNames = []string{
// keeping every other entry in the file, and returns the file's path. It
// refuses when the file exists without the header, or when another
// auto-loaded override file exists in dir. The write is atomic.
//
// composeFile is the stack's first compose file. The new file gets the owner
// of the existing override, or of composeFile when there is none or the
// existing one is owned by root (see pickOwner). The agent runs as root and the
// rename creates a new file, so without this the stack's owner would lose
// control of the file. ownerErr reports that the owner could not be read or
// set; the override is still written. err means it was not written.
func WriteOverride(dir, service, ref, composeFile string) (path string, ownerErr error, err error) {
overridePath := filepath.Join(dir, OverrideName)
return writeOverride(dir, service, ref, func() (fileOwner, error) {
return resolveOwner(overridePath, composeFile)
})
}
// fileOwner is the uid and gid of a file.
type fileOwner struct{ uid, gid int }
// readOwner returns the owner of the file at path.
func readOwner(path string) (fileOwner, error) {
fi, err := os.Stat(path)
if err != nil {
return fileOwner{}, fmt.Errorf("read owner: %w", err)
}
st, ok := fi.Sys().(*syscall.Stat_t)
if !ok {
return fileOwner{}, fmt.Errorf("read owner of %s: not available on this platform", path)
}
return fileOwner{int(st.Uid), int(st.Gid)}, nil
}
// pickOwner chooses the owner of a new override: the existing override's
// (nil when there is none), unless that is root, then the compose file's.
// Overrides written before the agent set owners are root-owned and would
// otherwise stay so. compose is only called when needed.
func pickOwner(override *fileOwner, compose func() (fileOwner, error)) (fileOwner, error) {
if override != nil && override.uid != 0 {
return *override, nil
}
return compose()
}
// resolveOwner applies pickOwner to the files on disk.
func resolveOwner(overridePath, composeFile string) (fileOwner, error) {
var existing *fileOwner
if o, err := readOwner(overridePath); err == nil {
existing = &o
} else if !errors.Is(err, os.ErrNotExist) {
return fileOwner{}, err
}
return pickOwner(existing, func() (fileOwner, error) { return readOwner(composeFile) })
}
// writeOverride is WriteOverride with the owner lookup injected, for tests.
func writeOverride(dir, service, ref string, owner func() (fileOwner, error)) (string, error, error) {
func WriteOverride(dir, service, ref string) (string, error) {
for _, name := range overrideNames {
if name == OverrideName {
continue
}
if _, err := os.Lstat(filepath.Join(dir, name)); err == nil {
return "", nil, fmt.Errorf("refused: %s exists; the agent only manages %s and never edits operator files", name, OverrideName)
return "", fmt.Errorf("refused: %s exists; the agent only manages %s and never edits operator files", name, OverrideName)
} else if !errors.Is(err, os.ErrNotExist) {
return "", nil, fmt.Errorf("check %s: %w", name, err)
return "", fmt.Errorf("check %s: %w", name, err)
}
}
path := filepath.Join(dir, OverrideName)
@@ -105,12 +51,12 @@ func writeOverride(dir, service, ref string, owner func() (fileOwner, error)) (s
switch {
case errors.Is(err, os.ErrNotExist):
case err != nil:
return "", nil, fmt.Errorf("read override: %w", err)
return "", fmt.Errorf("read override: %w", err)
case !bytes.HasPrefix(raw, []byte(overrideHeader)):
return "", nil, fmt.Errorf("refused: %s exists and was not written by package-updater", path)
return "", fmt.Errorf("refused: %s exists and was not written by package-updater", path)
default:
if err := yaml.Unmarshal(raw, &doc); err != nil {
return "", nil, fmt.Errorf("parse override: %w", err)
return "", fmt.Errorf("parse override: %w", err)
}
if doc == nil {
doc = map[string]any{}
@@ -129,38 +75,30 @@ func writeOverride(dir, service, ref string, owner func() (fileOwner, error)) (s
doc["services"] = services
body, err := yaml.Marshal(doc)
if err != nil {
return "", nil, fmt.Errorf("encode override: %w", err)
return "", fmt.Errorf("encode override: %w", err)
}
// Temp file in the same directory + rename: a crash never leaves a
// half-written override that compose would then load.
tmp, err := os.CreateTemp(dir, "."+OverrideName+".*")
if err != nil {
return "", nil, fmt.Errorf("write override: %w", err)
return "", fmt.Errorf("write override: %w", err)
}
defer os.Remove(tmp.Name()) // no-op after a successful rename
if _, err := tmp.WriteString(overrideHeader + string(body)); err != nil {
tmp.Close()
return "", nil, fmt.Errorf("write override: %w", err)
return "", fmt.Errorf("write override: %w", err)
}
if err := tmp.Chmod(0o644); err != nil {
tmp.Close()
return "", nil, fmt.Errorf("write override: %w", err)
}
// Chown the open file, not the path after the rename: a path could have
// been swapped for a symlink by someone with write access to the stack.
var ownerErr error
if o, err := owner(); err != nil {
ownerErr = err
} else if err := tmp.Chown(o.uid, o.gid); err != nil {
ownerErr = fmt.Errorf("set owner %d:%d: %w", o.uid, o.gid, err)
return "", fmt.Errorf("write override: %w", err)
}
if err := tmp.Close(); err != nil {
return "", nil, fmt.Errorf("write override: %w", err)
return "", fmt.Errorf("write override: %w", err)
}
if err := os.Rename(tmp.Name(), path); err != nil {
return "", nil, fmt.Errorf("write override: %w", err)
return "", fmt.Errorf("write override: %w", err)
}
return path, ownerErr, nil
return path, nil
}
// SelfInspector is the subset of the Docker SDK MountRoots needs.
+8 -94
View File
@@ -29,96 +29,11 @@ func serviceImage(doc map[string]any, name string) any {
return entry["image"]
}
// stackFile creates dir/compose.yaml and returns its path.
func stackFile(t *testing.T, dir string) string {
t.Helper()
p := filepath.Join(dir, "compose.yaml")
require.NoError(t, os.WriteFile(p, []byte("services: {}\n"), 0o644))
return p
}
func TestPickOwner(t *testing.T) {
compose := fileOwner{1000, 1000}
fromCompose := func() (fileOwner, error) { return compose, nil }
failing := func() (fileOwner, error) { return fileOwner{}, errors.New("boom") }
tests := []struct {
name string
override *fileOwner
compose func() (fileOwner, error)
want fileOwner
wantErr bool
}{
{"no override uses the compose file", nil, fromCompose, compose, false},
{"override owned by a user wins", &fileOwner{1001, 1002}, fromCompose, fileOwner{1001, 1002}, false},
{"root-owned override uses the compose file", &fileOwner{0, 0}, fromCompose, compose, false},
{"compose file is not read when the override decides", &fileOwner{1001, 1002}, failing, fileOwner{1001, 1002}, false},
{"unreadable compose file is an error", nil, failing, fileOwner{}, true},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
got, err := pickOwner(tt.override, tt.compose)
assert.Equal(t, tt.wantErr, err != nil)
assert.Equal(t, tt.want, got)
})
}
}
func TestResolveOwner(t *testing.T) {
me := fileOwner{os.Getuid(), os.Getgid()}
t.Run("no override uses the compose file", func(t *testing.T) {
dir := t.TempDir()
got, err := resolveOwner(filepath.Join(dir, OverrideName), stackFile(t, dir))
require.NoError(t, err)
assert.Equal(t, me, got)
})
t.Run("existing override is used without the compose file", func(t *testing.T) {
dir := t.TempDir()
require.NoError(t, os.WriteFile(filepath.Join(dir, OverrideName), nil, 0o644))
got, err := resolveOwner(filepath.Join(dir, OverrideName), filepath.Join(dir, "missing.yaml"))
require.NoError(t, err)
assert.Equal(t, me, got)
})
t.Run("neither file is an error", func(t *testing.T) {
dir := t.TempDir()
_, err := resolveOwner(filepath.Join(dir, OverrideName), filepath.Join(dir, "missing.yaml"))
assert.Error(t, err)
})
}
func TestWriteOverride_Owner(t *testing.T) {
t.Run("success sets no ownerErr", func(t *testing.T) {
dir := t.TempDir()
_, ownerErr, err := WriteOverride(dir, "web", "a:1@sha256:aa", stackFile(t, dir))
require.NoError(t, err)
assert.NoError(t, ownerErr)
})
t.Run("unreadable owner is reported and the file is still written", func(t *testing.T) {
dir := t.TempDir()
_, ownerErr, err := WriteOverride(dir, "web", "a:1@sha256:aa", filepath.Join(dir, "missing.yaml"))
require.NoError(t, err)
assert.ErrorContains(t, ownerErr, "read owner")
_, doc := readOverride(t, dir)
assert.Equal(t, "a:1@sha256:aa", serviceImage(doc, "web"))
})
t.Run("chown failure is reported and the file is still written", func(t *testing.T) {
if os.Getuid() == 0 {
t.Skip("root can chown to anyone")
}
dir := t.TempDir()
_, ownerErr, err := writeOverride(dir, "web", "a:1@sha256:aa", func() (fileOwner, error) { return fileOwner{0, 0}, nil })
require.NoError(t, err)
assert.ErrorContains(t, ownerErr, "set owner 0:0")
_, doc := readOverride(t, dir)
assert.Equal(t, "a:1@sha256:aa", serviceImage(doc, "web"))
})
}
func TestWriteOverride(t *testing.T) {
t.Run("new file", func(t *testing.T) {
dir := t.TempDir()
path, ownerErr, err := WriteOverride(dir, "web", "a:1@sha256:aa", stackFile(t, dir))
path, err := WriteOverride(dir, "web", "a:1@sha256:aa")
require.NoError(t, err)
assert.NoError(t, ownerErr)
assert.Equal(t, filepath.Join(dir, OverrideName), path)
raw, doc := readOverride(t, dir)
assert.True(t, len(raw) > len(overrideHeader) && raw[:len(overrideHeader)] == overrideHeader)
@@ -127,7 +42,7 @@ func TestWriteOverride(t *testing.T) {
t.Run("keeps other services", func(t *testing.T) {
dir := t.TempDir()
require.NoError(t, os.WriteFile(filepath.Join(dir, OverrideName), []byte(overrideHeader+"services:\n db:\n image: db:1\n"), 0o644))
_, _, err := WriteOverride(dir, "web", "a:1@sha256:aa", stackFile(t, dir))
_, err := WriteOverride(dir, "web", "a:1@sha256:aa")
require.NoError(t, err)
_, doc := readOverride(t, dir)
assert.Equal(t, "db:1", serviceImage(doc, "db"))
@@ -136,7 +51,7 @@ func TestWriteOverride(t *testing.T) {
t.Run("replaces own entry", func(t *testing.T) {
dir := t.TempDir()
require.NoError(t, os.WriteFile(filepath.Join(dir, OverrideName), []byte(overrideHeader+"services:\n web:\n image: old\n"), 0o644))
_, _, err := WriteOverride(dir, "web", "a:2@sha256:bb", stackFile(t, dir))
_, err := WriteOverride(dir, "web", "a:2@sha256:bb")
require.NoError(t, err)
_, doc := readOverride(t, dir)
assert.Equal(t, "a:2@sha256:bb", serviceImage(doc, "web"))
@@ -145,7 +60,7 @@ func TestWriteOverride(t *testing.T) {
dir := t.TempDir()
const body = "services:\n web:\n environment: [A=1]\n"
require.NoError(t, os.WriteFile(filepath.Join(dir, OverrideName), []byte(body), 0o644))
_, _, err := WriteOverride(dir, "web", "a:1@sha256:aa", stackFile(t, dir))
_, err := WriteOverride(dir, "web", "a:1@sha256:aa")
assert.ErrorContains(t, err, "refused")
got, _ := os.ReadFile(filepath.Join(dir, OverrideName))
assert.Equal(t, body, string(got))
@@ -154,7 +69,7 @@ func TestWriteOverride(t *testing.T) {
t.Run("refuses next to "+other, func(t *testing.T) {
dir := t.TempDir()
require.NoError(t, os.WriteFile(filepath.Join(dir, other), []byte("services: {}\n"), 0o644))
_, _, err := WriteOverride(dir, "web", "a:1@sha256:aa", stackFile(t, dir))
_, err := WriteOverride(dir, "web", "a:1@sha256:aa")
assert.ErrorContains(t, err, other)
_, statErr := os.Stat(filepath.Join(dir, OverrideName))
assert.True(t, errors.Is(statErr, os.ErrNotExist))
@@ -162,13 +77,12 @@ func TestWriteOverride(t *testing.T) {
}
t.Run("leaves no temp files", func(t *testing.T) {
dir := t.TempDir()
_, _, err := WriteOverride(dir, "web", "a:1@sha256:aa", stackFile(t, dir))
_, err := WriteOverride(dir, "web", "a:1@sha256:aa")
require.NoError(t, err)
entries, err := os.ReadDir(dir)
require.NoError(t, err)
require.Len(t, entries, 2)
assert.Equal(t, "compose.override.yaml", entries[0].Name())
assert.Equal(t, "compose.yaml", entries[1].Name())
require.Len(t, entries, 1)
assert.Equal(t, OverrideName, entries[0].Name())
})
}