Compare commits
5 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| bb5cc8268f | |||
| cad6c1f421 | |||
| 22e6812d4b | |||
| 0415e905af | |||
| d4364a6cb7 |
@@ -1,15 +0,0 @@
|
||||
{
|
||||
"permissions": {
|
||||
"allow": [
|
||||
"Bash(go get *)",
|
||||
"Bash(go build *)",
|
||||
"Bash(go vet *)",
|
||||
"Read(//usr/lib/**)",
|
||||
"Read(//proc/**)",
|
||||
"Bash(systemctl show *)",
|
||||
"Bash(echo \"exit=$?\")",
|
||||
"Bash(systemctl list-units *)",
|
||||
"Bash(go test *)"
|
||||
]
|
||||
}
|
||||
}
|
||||
+2
-1
@@ -13,4 +13,5 @@ config.yml
|
||||
|
||||
CLAUDE.md
|
||||
|
||||
minisign.key
|
||||
minisign.key
|
||||
./.claude
|
||||
@@ -19,7 +19,7 @@ Functionality is organized into **modules**. Each module owns a slice of the
|
||||
API and declares its own permission vocabulary.
|
||||
|
||||
- **System** - Dashboard overview (OS/kernel, CPU, memory, disks, load, uptime,
|
||||
network interfaces, temperatures); get/set hostname; time, timezone, and NTP;
|
||||
network interfaces, GPU, temperatures); get/set hostname; time, timezone, and NTP;
|
||||
locale and console keymap; reboot and power off.
|
||||
- **Services** - List and inspect systemd units; start / stop / restart / enable
|
||||
/ disable; read service logs from the journal or an allowlisted file, as a
|
||||
@@ -29,10 +29,11 @@ API and declares its own permission vocabulary.
|
||||
- **Groups** - List, inspect, create, and delete local groups.
|
||||
- **Packages** - List installed packages and available updates; install, remove,
|
||||
and upgrade - streamed live over SSE. Auto-detects `dnf`, `apt`, or `pacman`.
|
||||
- **Networking** - List network interfaces, routing tables, and DNS settings; configure IPv4 settings with temporary applying and safety auto-rollback; bring interfaces up or down.
|
||||
- **Networking** - List network interfaces, routing tables, and DNS settings; configure IPv4 settings with temporary applying and safety auto-rollback; bring interfaces up or down; edit `/etc/hosts`.
|
||||
- **Storage** - List active mounts and `/etc/fstab` entries; add, edit, and delete fstab entries; mount and unmount filesystems.
|
||||
- **Audit** - Read-only trail of every privileged write (who, what, when, result).
|
||||
- **Meta** - Self-description for clients: `/api/_modules`, `/api/whoami`,
|
||||
`/api/health`.
|
||||
`/api/health`; trigger a self-update via `POST /api/update`.
|
||||
|
||||
### Security model at a glance
|
||||
|
||||
@@ -159,14 +160,18 @@ assigns the admin role to the installing user.
|
||||
|
||||
| Command | Effect |
|
||||
| ------------------------------------------------ | --------------------------------------------------------------------------- |
|
||||
| `nadir [run] [-d]` | Start the server. `-d` / `--detach` runs it in the background. |
|
||||
| `nadir --save-config` | Save the default configuration template to the target path and exit. |
|
||||
| `nadir install` | Install + enable the systemd service (starts now and on boot). |
|
||||
| `nadir uninstall` | Stop, disable, and remove the systemd service. |
|
||||
| `nadir start` \| `stop` \| `restart` \| `status` | Control the running service. |
|
||||
| `nadir enable` \| `disable` | Toggle start-on-boot without removing the unit. |
|
||||
| `nadir logs` | Follow logs - journald if installed as a service, otherwise the detach log. |
|
||||
| `nadir help` | Show usage. |
|
||||
| `nadir [run] [-d]` | Start the server. `-d` / `--detach` runs it in the background. |
|
||||
| `nadir --save-config` | Save the default configuration template to the target path and exit. |
|
||||
| `nadir install` | Install + enable the systemd service (starts now and on boot). |
|
||||
| `nadir uninstall` | Stop, disable, and remove the systemd service. |
|
||||
| `nadir start` \| `stop` \| `restart` \| `status` | Control the running service. |
|
||||
| `nadir enable` \| `disable` | Toggle start-on-boot without removing the unit. |
|
||||
| `nadir logs` | Follow logs - journald if installed as a service, otherwise the detach log. |
|
||||
| `nadir update [--check] [--force]` | Download and install the latest release (requires `server.release_repo` in config). `--check` reports the available version without downloading; `--force` re-downloads even when already current. |
|
||||
| `nadir token add <name>` | Mint a machine API token (shown once, not stored in plain text). |
|
||||
| `nadir token rm <name>` | Revoke a token immediately (no restart needed). |
|
||||
| `nadir token ls` | List token names (not the raw keys). |
|
||||
| `nadir help` | Show usage. |
|
||||
|
||||
Most commands need root.
|
||||
|
||||
@@ -187,6 +192,7 @@ server:
|
||||
# tls_key: /etc/nadir/tls/key.pem
|
||||
hostname: 100.64.0.189
|
||||
port: 9999
|
||||
# release_repo: https://gitea.example.com/owner/nadir # enables `nadir update`
|
||||
|
||||
# Quote "*" - bare * is YAML alias syntax and fails to parse.
|
||||
roles:
|
||||
@@ -216,6 +222,7 @@ log_files:
|
||||
| `tls_cert`, `tls_key` | - | PEM paths. When both are set (and `trust_proxy` is off), nadir terminates TLS with this pair. |
|
||||
| `hostname` | - | Address to bind. Use `127.0.0.1` for local-only, or an overlay/VPN address to expose nadir only on that interface. |
|
||||
| `port` | - | TCP port to listen on. |
|
||||
| `release_repo` | - | Gitea repo URL (`https://host/owner/repo`). When set, enables `nadir update` and `POST /api/update`. Must be `https://`. |
|
||||
|
||||
TLS selection is covered in [Deployment note 2](#2-tls-three-modes).
|
||||
|
||||
@@ -389,7 +396,27 @@ forwarded headers are trustworthy. Without step 1 you're trusting every peer on
|
||||
the overlay - fine for a single-tenant network you fully control, risky on a
|
||||
shared one.
|
||||
|
||||
### 4. Connecting a dashboard (machine clients)
|
||||
### 4. Self-update
|
||||
|
||||
When `server.release_repo` points at a Gitea repo, nadir can update itself:
|
||||
|
||||
```bash
|
||||
sudo nadir update # download + install latest, restart service
|
||||
sudo nadir update --check # report available version, do nothing
|
||||
sudo nadir update --force # re-download even if already at latest
|
||||
```
|
||||
|
||||
The updater:
|
||||
1. Fetches the latest release from the Gitea API.
|
||||
2. Downloads the binary for the host's architecture (`linux-amd64`, `linux-arm64`, …).
|
||||
3. Verifies the release: checks the minisign signature on `sha256sums.txt`, then checks the binary's SHA-256 against it. Refuses to install if either check fails.
|
||||
4. Atomically replaces the running binary (`os.Rename` on the same filesystem) and runs `systemctl restart nadir`.
|
||||
|
||||
The same flow is also reachable via `POST /api/update` (requires the admin wildcard role), which runs the updater detached and returns 202 immediately. Poll `GET /api/health` to confirm the new version is running after the restart drops in-flight connections.
|
||||
|
||||
`release_repo` must use `https://` — the update downloads and executes the binary, and a plaintext URL would expose the host to on-path replacement.
|
||||
|
||||
### 5. Connecting a dashboard (machine clients)
|
||||
|
||||
To manage one or more Nadir instances via a central dashboard or non-interactive client, authenticate requests using a static Bearer token rather than interactive PAM credentials.
|
||||
|
||||
@@ -439,22 +466,23 @@ To connect a browser-based dashboard hosted on a different origin, choose one of
|
||||
## Layout
|
||||
|
||||
```
|
||||
cmd/ process entry point + CLI (run / install / logs …), TLS, service wiring
|
||||
internal/auth PAM auth, sessions, login/logout, login throttle, PAM service install
|
||||
cmd/ process entry point + CLI (run / install / update / token / logs …), TLS, service wiring
|
||||
internal/auth PAM auth, sessions, login/logout, login throttle, bearer tokens, PAM service install
|
||||
internal/auditlog SQLite-backed audit log writer
|
||||
internal/config config.yaml loader + startup validation
|
||||
internal/meta /api/_modules, /api/whoami, /api/health discovery endpoints
|
||||
internal/meta /api/_modules, /api/whoami, /api/health, /api/update discovery + update endpoints
|
||||
internal/module the Module interface
|
||||
internal/modules concrete modules:
|
||||
system - info, hostname, time/timezone/NTP, locale/keymap, power
|
||||
services - systemd unit control + journal/file logs (snapshot + SSE)
|
||||
users - local accounts
|
||||
groups - local groups
|
||||
packages - dnf/apt/pacman install/remove/upgrade (streamed)
|
||||
audit - read-only audit trail
|
||||
networking - network interfaces, routing tables, DNS, and IP configurations
|
||||
system - info, hostname, time/timezone/NTP, locale/keymap, power
|
||||
services - systemd unit control + journal/file logs (snapshot + SSE)
|
||||
users - local accounts
|
||||
groups - local groups
|
||||
packages - dnf/apt/pacman install/remove/upgrade (streamed)
|
||||
networking - interfaces, routing tables, DNS, IP config, /etc/hosts
|
||||
storage - active mounts, /etc/fstab read/write, mount/unmount
|
||||
internal/mounts /proc/mounts parser (used by storage module)
|
||||
internal/oscmd shared command runner (timeouts, stderr surfacing) + helpers
|
||||
internal/rbac roles, permissions ("*" wildcards), HTTP middleware (RBAC + CSRF)
|
||||
internal/audit SQLite-backed audit log writer
|
||||
```
|
||||
|
||||
## API docs
|
||||
|
||||
+11
-2
@@ -24,7 +24,6 @@ import (
|
||||
"nadir/internal/config"
|
||||
"nadir/internal/meta"
|
||||
"nadir/internal/module"
|
||||
"nadir/internal/modules/audit"
|
||||
"nadir/internal/modules/groups"
|
||||
"nadir/internal/modules/networking"
|
||||
"nadir/internal/modules/packages"
|
||||
@@ -38,6 +37,15 @@ import (
|
||||
"github.com/danielgtaylor/huma/v2/adapters/humago"
|
||||
)
|
||||
|
||||
// auditModule is a synthetic module so the config validator knows the "audit"
|
||||
// permission vocabulary. The actual endpoint is registered by meta.RegisterAudit —
|
||||
// a full module for one GET is too shallow.
|
||||
type auditModule struct{}
|
||||
|
||||
func (auditModule) ID() string { return "audit" }
|
||||
func (auditModule) Permissions() []rbac.Permission { return []rbac.Permission{rbac.Read} }
|
||||
func (auditModule) Register(huma.API) {}
|
||||
|
||||
// main is a thin command dispatcher. With no subcommand (or "run") it starts the
|
||||
// server; the rest manage nadir as a systemd service or tail its logs. Service
|
||||
// plumbing lives in service.go, TLS in tls.go.
|
||||
@@ -210,7 +218,7 @@ func runServer() {
|
||||
packages.New(),
|
||||
networking.New(),
|
||||
storage.New(),
|
||||
audit.New(auditStore),
|
||||
auditModule{},
|
||||
}
|
||||
|
||||
roles := rbac.New()
|
||||
@@ -246,6 +254,7 @@ func runServer() {
|
||||
meta.RegisterHealth(api, sessions)
|
||||
meta.RegisterWhoami(api, sessions, tokenAuth, roles, mods)
|
||||
meta.RegisterUpdate(api, configPath)
|
||||
meta.RegisterAudit(api, auditStore)
|
||||
|
||||
auth.RegisterLogin(api, sessions, auditStore, cfg.SecureCookie())
|
||||
auth.RegisterLogout(api, sessions, cfg.SecureCookie())
|
||||
|
||||
+136
-8
@@ -1,6 +1,7 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"bufio"
|
||||
"flag"
|
||||
"fmt"
|
||||
"io"
|
||||
@@ -8,8 +9,11 @@ import (
|
||||
"os/exec"
|
||||
"path/filepath"
|
||||
"strconv"
|
||||
"strings"
|
||||
"syscall"
|
||||
|
||||
"github.com/mattn/go-isatty"
|
||||
|
||||
"nadir/internal/auth"
|
||||
"nadir/internal/config"
|
||||
)
|
||||
@@ -137,6 +141,125 @@ func installService(args []string) error {
|
||||
isUnsecure := *unsecureOpt || optCount == 0
|
||||
isTrustProxy := *trustProxyOpt
|
||||
|
||||
cfgPath, err := resolveConfigPath()
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
shouldWriteConfig := false
|
||||
if _, err := os.Stat(cfgPath); os.IsNotExist(err) {
|
||||
shouldWriteConfig = true
|
||||
}
|
||||
|
||||
username := getUsername()
|
||||
var logFiles map[string][]string
|
||||
|
||||
if fs.NFlag() == 0 && (isatty.IsTerminal(os.Stdin.Fd()) || isatty.IsCygwinTerminal(os.Stdin.Fd())) {
|
||||
reader := bufio.NewReader(os.Stdin)
|
||||
|
||||
if !shouldWriteConfig {
|
||||
fmt.Printf("Configuration file already exists at %s. Overwrite? [y/N] (default n): ", cfgPath)
|
||||
overwriteInput, _ := reader.ReadString('\n')
|
||||
overwriteInput = strings.ToLower(strings.TrimSpace(overwriteInput))
|
||||
if overwriteInput != "y" && overwriteInput != "yes" {
|
||||
fmt.Println("Keeping existing configuration. Proceeding with installation...")
|
||||
if existingCfg, loadErr := config.Load(cfgPath); loadErr == nil {
|
||||
*hostnameOpt = existingCfg.Server.Hostname
|
||||
if p, err := strconv.Atoi(existingCfg.Server.Port); err == nil {
|
||||
*portOpt = p
|
||||
}
|
||||
isTLS = existingCfg.Server.TLSCert != "" && existingCfg.Server.TLSKey != ""
|
||||
isTrustProxy = existingCfg.Server.TrustProxy
|
||||
isUnsecure = !isTLS && !isTrustProxy
|
||||
}
|
||||
goto skipConfigPrompt
|
||||
}
|
||||
shouldWriteConfig = true
|
||||
}
|
||||
|
||||
fmt.Println("Configuring Nadir installation:")
|
||||
fmt.Println(" 1) Serve plaintext HTTP directly (unsecure) [default]")
|
||||
fmt.Println(" 2) Generate persistent self-signed TLS cert/key and enable HTTPS (tls)")
|
||||
fmt.Println(" 3) Serve plaintext HTTP behind a trusted TLS-terminating reverse proxy (trust-proxy)")
|
||||
fmt.Print("Enter choice [1-3] (default 1): ")
|
||||
choice, _ := reader.ReadString('\n')
|
||||
choice = strings.TrimSpace(choice)
|
||||
if choice == "" || choice == "1" {
|
||||
isUnsecure = true
|
||||
isTLS = false
|
||||
isTrustProxy = false
|
||||
} else if choice == "2" {
|
||||
isTLS = true
|
||||
isUnsecure = false
|
||||
isTrustProxy = false
|
||||
} else if choice == "3" {
|
||||
isTrustProxy = true
|
||||
isTLS = false
|
||||
isUnsecure = false
|
||||
} else {
|
||||
return fmt.Errorf("invalid choice: %q", choice)
|
||||
}
|
||||
|
||||
fmt.Printf("Enter hostname to bind to (default %s): ", *hostnameOpt)
|
||||
hostChoice, _ := reader.ReadString('\n')
|
||||
hostChoice = strings.TrimSpace(hostChoice)
|
||||
if hostChoice != "" {
|
||||
*hostnameOpt = hostChoice
|
||||
}
|
||||
|
||||
fmt.Printf("Enter port to bind to (default %d): ", *portOpt)
|
||||
portChoice, _ := reader.ReadString('\n')
|
||||
portChoice = strings.TrimSpace(portChoice)
|
||||
if portChoice != "" {
|
||||
p, err := strconv.Atoi(portChoice)
|
||||
if err != nil || p <= 0 || p > 65535 {
|
||||
return fmt.Errorf("invalid port: %q", portChoice)
|
||||
}
|
||||
*portOpt = p
|
||||
}
|
||||
|
||||
fmt.Printf("Enter main admin username (default %s): ", username)
|
||||
userChoice, _ := reader.ReadString('\n')
|
||||
userChoice = strings.TrimSpace(userChoice)
|
||||
if userChoice != "" {
|
||||
username = userChoice
|
||||
}
|
||||
|
||||
fmt.Print("Would you like to expose any log files to the Nadir UI? [y/N] (default n): ")
|
||||
logInput, _ := reader.ReadString('\n')
|
||||
logInput = strings.ToLower(strings.TrimSpace(logInput))
|
||||
if logInput == "y" || logInput == "yes" {
|
||||
logFiles = make(map[string][]string)
|
||||
for {
|
||||
fmt.Print(" Enter service/unit name (e.g. nginx): ")
|
||||
unit, _ := reader.ReadString('\n')
|
||||
unit = strings.TrimSpace(unit)
|
||||
if unit == "" {
|
||||
fmt.Println(" Service name cannot be empty. Skipping.")
|
||||
continue
|
||||
}
|
||||
|
||||
fmt.Printf(" Enter absolute path to log file for %s: ", unit)
|
||||
path, _ := reader.ReadString('\n')
|
||||
path = strings.TrimSpace(path)
|
||||
if path == "" {
|
||||
fmt.Println(" Path cannot be empty. Skipping.")
|
||||
continue
|
||||
}
|
||||
|
||||
logFiles[unit] = append(logFiles[unit], path)
|
||||
|
||||
fmt.Print(" Add another log file? [y/N] (default n): ")
|
||||
another, _ := reader.ReadString('\n')
|
||||
another = strings.ToLower(strings.TrimSpace(another))
|
||||
if another != "y" && another != "yes" {
|
||||
break
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
skipConfigPrompt:
|
||||
// Provision the PAM service the server authenticates against, so it exists
|
||||
// before the unit starts rather than appearing on first login. Idempotent:
|
||||
// EnsurePAMService leaves an existing /etc/pam.d/nadir untouched. runServer
|
||||
@@ -181,11 +304,6 @@ func installService(args []string) error {
|
||||
}
|
||||
}
|
||||
|
||||
cfgPath, err := resolveConfigPath()
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
// Construct configuration template content based on installation options
|
||||
secureTLSVal := "true"
|
||||
trustProxyLine := "# trust_proxy: false"
|
||||
@@ -204,11 +322,21 @@ func installService(args []string) error {
|
||||
keyLine = "# tls_key: /var/lib/nadir/tls/key.pem"
|
||||
}
|
||||
|
||||
username := getUsername()
|
||||
configContent := fmt.Sprintf(configTemplateBase, secureTLSVal, trustProxyLine, certLine, keyLine, *hostnameOpt, *portOpt, username)
|
||||
if len(logFiles) > 0 {
|
||||
var logFilesSection strings.Builder
|
||||
logFilesSection.WriteString("\nlog_files:\n")
|
||||
for unit, paths := range logFiles {
|
||||
logFilesSection.WriteString(fmt.Sprintf(" %s:\n", unit))
|
||||
for _, path := range paths {
|
||||
logFilesSection.WriteString(fmt.Sprintf(" - %s\n", path))
|
||||
}
|
||||
}
|
||||
configContent += logFilesSection.String()
|
||||
}
|
||||
|
||||
// Ensure default config file exists
|
||||
if _, err := os.Stat(cfgPath); os.IsNotExist(err) {
|
||||
// Ensure default config file exists or we explicitly overwrote it
|
||||
if shouldWriteConfig {
|
||||
if err := saveDefaultConfig(cfgPath, configContent); err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
@@ -16,7 +16,7 @@ require (
|
||||
github.com/dustin/go-humanize v1.0.1 // indirect
|
||||
github.com/google/uuid v1.6.0 // indirect
|
||||
github.com/jedisct1/go-minisign v0.0.0-20260527172527-a09352b57a22
|
||||
github.com/mattn/go-isatty v0.0.21 // indirect
|
||||
github.com/mattn/go-isatty v0.0.21
|
||||
github.com/ncruces/go-strftime v1.0.0 // indirect
|
||||
github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec // indirect
|
||||
golang.org/x/crypto v0.52.0 // indirect
|
||||
|
||||
+5
-1
@@ -99,7 +99,11 @@ do_install() {
|
||||
|
||||
echo "binary installed at /usr/local/bin/nadir"
|
||||
echo "installing as a systemd service ..."
|
||||
/usr/local/bin/nadir install
|
||||
if [ -c /dev/tty ]; then
|
||||
/usr/local/bin/nadir install < /dev/tty
|
||||
else
|
||||
/usr/local/bin/nadir install
|
||||
fi
|
||||
|
||||
echo
|
||||
echo "done. check status with: nadir status"
|
||||
|
||||
@@ -1,33 +1,13 @@
|
||||
package audit
|
||||
package meta
|
||||
|
||||
import (
|
||||
"context"
|
||||
|
||||
"nadir/internal/auditlog"
|
||||
"nadir/internal/rbac"
|
||||
|
||||
"github.com/danielgtaylor/huma/v2"
|
||||
)
|
||||
|
||||
const ModuleID = "audit"
|
||||
|
||||
type Module struct {
|
||||
store *auditlog.Store
|
||||
}
|
||||
|
||||
func New(store *auditlog.Store) *Module { return &Module{store: store} }
|
||||
|
||||
func (m *Module) ID() string { return ModuleID }
|
||||
|
||||
// Permissions: read to view the audit trail. There is no write - entries are
|
||||
// produced by the middleware, never by an API call.
|
||||
func (m *Module) Permissions() []rbac.Permission {
|
||||
return []rbac.Permission{rbac.Read}
|
||||
}
|
||||
|
||||
// Types are named AuditList* (not ListInput/ListOutput) because Huma derives
|
||||
// OpenAPI schema names from the Go type name alone, not package-qualified, so a
|
||||
// bare "ListOutput" here would collide with the packages module's.
|
||||
type AuditListInput struct {
|
||||
Limit int `query:"limit" default:"200" minimum:"1" maximum:"10000" doc:"Max entries to return, newest first"`
|
||||
}
|
||||
@@ -38,7 +18,11 @@ type AuditListOutput struct {
|
||||
}
|
||||
}
|
||||
|
||||
func (m *Module) Register(api huma.API) {
|
||||
// RegisterAudit wires GET /api/audit. It lives in meta because a full module
|
||||
// for a single read-only endpoint is too shallow — the interface is nearly as
|
||||
// wide as the implementation. The audit trail is produced by the RBAC
|
||||
// middleware; this endpoint provides read-only access to it.
|
||||
func RegisterAudit(api huma.API, store *auditlog.Store) {
|
||||
huma.Register(api, huma.Operation{
|
||||
OperationID: "audit-list",
|
||||
Method: "GET",
|
||||
@@ -46,11 +30,11 @@ func (m *Module) Register(api huma.API) {
|
||||
Summary: "List recorded actions",
|
||||
Description: "Returns the audit trail of privileged write operations " +
|
||||
"(who, what, when, result), newest first.",
|
||||
Tags: []string{"Audit"},
|
||||
Metadata: map[string]any{"module": ModuleID, "permission": "read"},
|
||||
Tags: []string{"Meta", "Audit"},
|
||||
Metadata: map[string]any{"module": "audit", "permission": "read"},
|
||||
Errors: []int{401, 403, 500},
|
||||
}, func(ctx context.Context, in *AuditListInput) (*AuditListOutput, error) {
|
||||
entries, err := m.store.List(in.Limit)
|
||||
entries, err := store.List(in.Limit)
|
||||
if err != nil {
|
||||
return nil, huma.Error500InternalServerError("read audit log failed", err)
|
||||
}
|
||||
@@ -3,10 +3,8 @@ package services
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"os/exec"
|
||||
"regexp"
|
||||
"strings"
|
||||
"syscall"
|
||||
|
||||
"nadir/internal/oscmd"
|
||||
|
||||
@@ -166,14 +164,11 @@ func isSelf(unit string) bool {
|
||||
// Returns success once the subprocess has *started* — the actual systemd
|
||||
// operation may complete after the response is sent, which is the whole point.
|
||||
func runDetached(action, unit string) (*oscmd.StatusOutput, error) {
|
||||
cmd := exec.Command("systemctl", action, "--", unit)
|
||||
cmd.SysProcAttr = &syscall.SysProcAttr{Setsid: true}
|
||||
if err := cmd.Start(); err != nil {
|
||||
out, err := oscmd.RunDetached("systemctl", action, "--", unit)
|
||||
if err != nil {
|
||||
return nil, huma.Error500InternalServerError("could not start detached systemctl", err)
|
||||
}
|
||||
// Reap in the background so the child doesn't become a zombie.
|
||||
go cmd.Wait()
|
||||
return oscmd.OK(), nil
|
||||
return out, nil
|
||||
}
|
||||
|
||||
// validateUnit guards against empty, flag-like, or malformed unit names.
|
||||
|
||||
@@ -0,0 +1,146 @@
|
||||
package system
|
||||
|
||||
import (
|
||||
"math"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"runtime"
|
||||
"strconv"
|
||||
"strings"
|
||||
|
||||
"nadir/internal/oscmd"
|
||||
)
|
||||
|
||||
type CPUInfo struct {
|
||||
Model string `json:"model" example:"AMD Ryzen 7 7840U" doc:"CPU model name"`
|
||||
LogicalCPUs int `json:"logical_cpus" example:"16" doc:"Number of logical CPUs (cores × threads)"`
|
||||
MinMHz int `json:"min_mhz" example:"400" doc:"Lowest frequency the scaling governor can select"`
|
||||
MaxMHz int `json:"max_mhz" example:"5137" doc:"Highest frequency (boost ceiling)"`
|
||||
CurrentMHz int `json:"current_mhz" example:"3157" doc:"Peak current clock across all cores (instantaneous snapshot; 0 if cpufreq unavailable)"`
|
||||
}
|
||||
|
||||
func cpuInfo() CPUInfo {
|
||||
data, _ := os.ReadFile("/proc/cpuinfo")
|
||||
c := CPUInfo{Model: cpuModel(string(data)), LogicalCPUs: runtime.NumCPU()}
|
||||
c.MinMHz, c.MaxMHz, c.CurrentMHz = cpuFreqMHz("/sys/devices/system/cpu")
|
||||
mhz := cpuinfoMaxMHz(string(data))
|
||||
if c.Model == "" || mhz == 0 {
|
||||
model, lscpuMHz := lscpuFallback()
|
||||
if c.Model == "" {
|
||||
c.Model = model
|
||||
}
|
||||
if mhz == 0 {
|
||||
mhz = lscpuMHz
|
||||
}
|
||||
}
|
||||
if mhz > 0 {
|
||||
if c.CurrentMHz == 0 {
|
||||
c.CurrentMHz = mhz
|
||||
}
|
||||
if c.MaxMHz == 0 {
|
||||
c.MaxMHz = mhz
|
||||
}
|
||||
if c.MinMHz == 0 {
|
||||
c.MinMHz = mhz
|
||||
}
|
||||
}
|
||||
return c
|
||||
}
|
||||
|
||||
func lscpuFallback() (model string, mhz int) {
|
||||
out, err := oscmd.Run("lscpu")
|
||||
if err != nil {
|
||||
return "", 0
|
||||
}
|
||||
for line := range strings.SplitSeq(out, "\n") {
|
||||
k, v, ok := strings.Cut(line, ":")
|
||||
if !ok {
|
||||
continue
|
||||
}
|
||||
k, v = strings.TrimSpace(k), strings.TrimSpace(v)
|
||||
switch k {
|
||||
case "Model name":
|
||||
if model == "" {
|
||||
model = v
|
||||
}
|
||||
case "BIOS Model name":
|
||||
if model == "" {
|
||||
model = v
|
||||
}
|
||||
case "CPU max MHz", "CPU MHz":
|
||||
if f, err := strconv.ParseFloat(v, 64); err == nil && int(f) > mhz {
|
||||
mhz = int(math.Round(f))
|
||||
}
|
||||
}
|
||||
}
|
||||
if mhz == 0 {
|
||||
mhz = parseGHzSuffix(model)
|
||||
}
|
||||
return model, mhz
|
||||
}
|
||||
|
||||
func parseGHzSuffix(s string) int {
|
||||
i := strings.LastIndex(s, "@")
|
||||
if i < 0 {
|
||||
return 0
|
||||
}
|
||||
rest := strings.TrimSpace(s[i+1:])
|
||||
rest = strings.TrimSuffix(strings.TrimSuffix(rest, "GHz"), "Ghz")
|
||||
rest = strings.TrimSpace(strings.TrimSuffix(rest, "G"))
|
||||
f, err := strconv.ParseFloat(strings.TrimSpace(rest), 64)
|
||||
if err != nil {
|
||||
return 0
|
||||
}
|
||||
return int(math.Round(f * 1000))
|
||||
}
|
||||
|
||||
func cpuinfoMaxMHz(cpuinfo string) int {
|
||||
var max float64
|
||||
for line := range strings.SplitSeq(cpuinfo, "\n") {
|
||||
k, v, ok := strings.Cut(line, ":")
|
||||
if !ok || strings.TrimSpace(k) != "cpu MHz" {
|
||||
continue
|
||||
}
|
||||
if f, err := strconv.ParseFloat(strings.TrimSpace(v), 64); err == nil && f > max {
|
||||
max = f
|
||||
}
|
||||
}
|
||||
return int(math.Round(max))
|
||||
}
|
||||
|
||||
func cpuFreqMHz(root string) (min, max, cur int) {
|
||||
min = readKHzAsMHz(filepath.Join(root, "cpu0/cpufreq/cpuinfo_min_freq"))
|
||||
max = readKHzAsMHz(filepath.Join(root, "cpu0/cpufreq/cpuinfo_max_freq"))
|
||||
cores, _ := filepath.Glob(filepath.Join(root, "cpu[0-9]*/cpufreq/scaling_cur_freq"))
|
||||
for _, f := range cores {
|
||||
if v := readKHzAsMHz(f); v > cur {
|
||||
cur = v
|
||||
}
|
||||
}
|
||||
return min, max, cur
|
||||
}
|
||||
|
||||
func readKHzAsMHz(path string) int {
|
||||
khz, err := strconv.Atoi(readTrim(path))
|
||||
if err != nil {
|
||||
return 0
|
||||
}
|
||||
return khz / 1000
|
||||
}
|
||||
|
||||
func cpuModel(cpuinfo string) string {
|
||||
var fallback string
|
||||
for line := range strings.SplitSeq(cpuinfo, "\n") {
|
||||
k, v, ok := strings.Cut(line, ":")
|
||||
if !ok {
|
||||
continue
|
||||
}
|
||||
switch strings.TrimSpace(k) {
|
||||
case "model name":
|
||||
return strings.TrimSpace(v)
|
||||
case "Model":
|
||||
fallback = strings.TrimSpace(v)
|
||||
}
|
||||
}
|
||||
return fallback
|
||||
}
|
||||
@@ -0,0 +1,137 @@
|
||||
package system
|
||||
|
||||
import (
|
||||
"context"
|
||||
"math"
|
||||
"os"
|
||||
"strconv"
|
||||
"strings"
|
||||
"sync"
|
||||
"time"
|
||||
)
|
||||
|
||||
// Sampler samples /proc/stat periodically and caches per-core CPU usage
|
||||
// percentages. Create with New, start the background goroutine with Start, and
|
||||
// read the latest snapshot with Snapshot.
|
||||
type Sampler struct {
|
||||
statPath string
|
||||
interval time.Duration
|
||||
mu sync.RWMutex
|
||||
cache []CoreUsage
|
||||
once sync.Once
|
||||
}
|
||||
|
||||
// NewSampler creates a Sampler that reads statPath and samples every interval.
|
||||
func NewSampler(statPath string, interval time.Duration) *Sampler {
|
||||
return &Sampler{statPath: statPath, interval: interval}
|
||||
}
|
||||
|
||||
// Start launches the background sampling goroutine. Only the first call starts
|
||||
// it; subsequent calls are no-ops. The goroutine exits when ctx is cancelled.
|
||||
func (s *Sampler) Start(ctx context.Context) {
|
||||
s.once.Do(func() {
|
||||
go s.loop(ctx)
|
||||
})
|
||||
}
|
||||
|
||||
// Snapshot returns a copy of the latest per-core usage snapshot. Returns nil
|
||||
// before the first sample completes.
|
||||
func (s *Sampler) Snapshot() []CoreUsage {
|
||||
s.mu.RLock()
|
||||
defer s.mu.RUnlock()
|
||||
if s.cache == nil {
|
||||
return nil
|
||||
}
|
||||
out := make([]CoreUsage, len(s.cache))
|
||||
copy(out, s.cache)
|
||||
return out
|
||||
}
|
||||
|
||||
func (s *Sampler) loop(ctx context.Context) {
|
||||
prev := readProcStat(s.statPath)
|
||||
ticker := time.NewTicker(s.interval)
|
||||
defer ticker.Stop()
|
||||
for {
|
||||
select {
|
||||
case <-ctx.Done():
|
||||
return
|
||||
case <-ticker.C:
|
||||
cur := readProcStat(s.statPath)
|
||||
usage := computeUsage(prev, cur)
|
||||
s.mu.Lock()
|
||||
s.cache = usage
|
||||
s.mu.Unlock()
|
||||
prev = cur
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// cpuCoreTicks holds the cumulative jiffies for one "cpuN" line.
|
||||
type cpuCoreTicks struct {
|
||||
core int
|
||||
total uint64
|
||||
idle uint64
|
||||
}
|
||||
|
||||
// readProcStat reads /proc/stat and returns per-core tick totals. The
|
||||
// aggregate "cpu" line (no digit suffix) is skipped.
|
||||
func readProcStat(path string) []cpuCoreTicks {
|
||||
data, _ := os.ReadFile(path)
|
||||
var cores []cpuCoreTicks
|
||||
for line := range strings.SplitSeq(string(data), "\n") {
|
||||
if !strings.HasPrefix(line, "cpu") {
|
||||
continue
|
||||
}
|
||||
fields := strings.Fields(line)
|
||||
if len(fields) < 5 {
|
||||
continue
|
||||
}
|
||||
name := fields[0]
|
||||
if name == "cpu" {
|
||||
continue
|
||||
}
|
||||
coreIdx, err := strconv.Atoi(strings.TrimPrefix(name, "cpu"))
|
||||
if err != nil {
|
||||
continue
|
||||
}
|
||||
var total, idle uint64
|
||||
for _, f := range fields[1:] {
|
||||
v, _ := strconv.ParseUint(f, 10, 64)
|
||||
total += v
|
||||
}
|
||||
if len(fields) > 5 {
|
||||
v4, _ := strconv.ParseUint(fields[4], 10, 64)
|
||||
v5, _ := strconv.ParseUint(fields[5], 10, 64)
|
||||
idle = v4 + v5
|
||||
} else {
|
||||
v4, _ := strconv.ParseUint(fields[4], 10, 64)
|
||||
idle = v4
|
||||
}
|
||||
cores = append(cores, cpuCoreTicks{core: coreIdx, total: total, idle: idle})
|
||||
}
|
||||
return cores
|
||||
}
|
||||
|
||||
// computeUsage converts two snapshots into per-core usage percentages.
|
||||
func computeUsage(prev, cur []cpuCoreTicks) []CoreUsage {
|
||||
prevMap := make(map[int]cpuCoreTicks, len(prev))
|
||||
for _, c := range prev {
|
||||
prevMap[c.core] = c
|
||||
}
|
||||
usage := make([]CoreUsage, 0, len(cur))
|
||||
for _, c := range cur {
|
||||
p, ok := prevMap[c.core]
|
||||
if !ok {
|
||||
continue
|
||||
}
|
||||
dTotal := c.total - p.total
|
||||
dIdle := c.idle - p.idle
|
||||
var pct float64
|
||||
if dTotal > 0 {
|
||||
pct = float64(dTotal-dIdle) / float64(dTotal) * 100
|
||||
pct = math.Round(pct*10) / 10
|
||||
}
|
||||
usage = append(usage, CoreUsage{Core: c.core, UsagePct: pct})
|
||||
}
|
||||
return usage
|
||||
}
|
||||
@@ -0,0 +1,134 @@
|
||||
package system
|
||||
|
||||
import (
|
||||
"context"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"reflect"
|
||||
"testing"
|
||||
"time"
|
||||
)
|
||||
|
||||
func TestNewSampler(t *testing.T) {
|
||||
s := NewSampler("/proc/stat", time.Second)
|
||||
if s == nil {
|
||||
t.Fatal("NewSampler returned nil")
|
||||
}
|
||||
if s.statPath != "/proc/stat" {
|
||||
t.Errorf("statPath = %q, want /proc/stat", s.statPath)
|
||||
}
|
||||
if s.interval != time.Second {
|
||||
t.Errorf("interval = %v, want 1s", s.interval)
|
||||
}
|
||||
}
|
||||
|
||||
func TestSamplerSnapshotsRealProcStat(t *testing.T) {
|
||||
ctx, cancel := context.WithCancel(context.Background())
|
||||
defer cancel()
|
||||
|
||||
s := NewSampler("/proc/stat", 10*time.Millisecond)
|
||||
s.Start(ctx)
|
||||
// Wait for at least two samples so there is a delta to compute.
|
||||
time.Sleep(50 * time.Millisecond)
|
||||
|
||||
snap := s.Snapshot()
|
||||
if snap == nil {
|
||||
t.Fatal("Snapshot returned nil (expected at least one sample)")
|
||||
}
|
||||
if len(snap) == 0 {
|
||||
t.Fatal("Snapshot returned empty (expected at least one core)")
|
||||
}
|
||||
for _, c := range snap {
|
||||
if c.UsagePct < 0 || c.UsagePct > 100 {
|
||||
t.Errorf("core %d: usage_pct = %f, want 0–100", c.Core, c.UsagePct)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestSamplerReturnsCopy(t *testing.T) {
|
||||
ctx, cancel := context.WithCancel(context.Background())
|
||||
defer cancel()
|
||||
|
||||
s := NewSampler("/proc/stat", 10*time.Millisecond)
|
||||
s.Start(ctx)
|
||||
time.Sleep(50 * time.Millisecond)
|
||||
|
||||
snap1 := s.Snapshot()
|
||||
snap2 := s.Snapshot()
|
||||
|
||||
// Both should be non-nil and deep-equal.
|
||||
if snap1 == nil || snap2 == nil {
|
||||
t.Fatal("Snapshot returned nil")
|
||||
}
|
||||
if !reflect.DeepEqual(snap1, snap2) {
|
||||
t.Error("two sequential snapshots should be deep-equal")
|
||||
}
|
||||
|
||||
// Mutating the returned slice should not affect the sampler.
|
||||
if len(snap1) > 0 {
|
||||
snap1[0].UsagePct = 999
|
||||
if snap2[0].UsagePct == 999 {
|
||||
t.Error("mutating one snapshot affected the other — expected a copy")
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestSamplerStartOnce(t *testing.T) {
|
||||
ctx, cancel := context.WithCancel(context.Background())
|
||||
defer cancel()
|
||||
|
||||
s := NewSampler("/proc/stat", 10*time.Millisecond)
|
||||
s.Start(ctx)
|
||||
s.Start(ctx) // second call must not panic or create a second goroutine
|
||||
time.Sleep(30 * time.Millisecond)
|
||||
|
||||
if snap := s.Snapshot(); snap == nil {
|
||||
t.Fatal("Snapshot returned nil after Start")
|
||||
}
|
||||
}
|
||||
|
||||
func TestSamplerContextCancelStopsGoroutine(t *testing.T) {
|
||||
ctx, cancel := context.WithCancel(context.Background())
|
||||
s := NewSampler("/proc/stat", 10*time.Millisecond)
|
||||
s.Start(ctx)
|
||||
|
||||
time.Sleep(30 * time.Millisecond)
|
||||
if snap := s.Snapshot(); snap == nil {
|
||||
t.Fatal("Snapshot returned nil before cancel")
|
||||
}
|
||||
|
||||
cancel()
|
||||
// Give the goroutine time to exit. If it doesn't, the test will hang.
|
||||
time.Sleep(20 * time.Millisecond)
|
||||
// Snapshot should still return the last cached value (no panic).
|
||||
if snap := s.Snapshot(); snap == nil {
|
||||
t.Fatal("Snapshot returned nil after cancel (cache should persist)")
|
||||
}
|
||||
}
|
||||
|
||||
func TestSamplerWithFakeStat(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
statPath := filepath.Join(dir, "stat")
|
||||
content := []byte("cpu 100 20 30 400 10 5 3 2 0 0\ncpu0 50 10 15 200 5 3 1 1 0 0\ncpu1 50 10 15 200 5 2 2 1 0 0\n")
|
||||
if err := os.WriteFile(statPath, content, 0o644); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
ctx, cancel := context.WithCancel(context.Background())
|
||||
defer cancel()
|
||||
|
||||
s := NewSampler(statPath, 20*time.Millisecond)
|
||||
s.Start(ctx)
|
||||
time.Sleep(50 * time.Millisecond)
|
||||
|
||||
snap := s.Snapshot()
|
||||
if snap == nil {
|
||||
t.Fatal("Snapshot returned nil")
|
||||
}
|
||||
// With the stat file not changing between reads, deltas are zero → 0% usage.
|
||||
for _, c := range snap {
|
||||
if c.UsagePct != 0 {
|
||||
t.Errorf("core %d: expected 0%% usage (static stat file), got %f", c.Core, c.UsagePct)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,73 @@
|
||||
package system
|
||||
|
||||
import (
|
||||
"syscall"
|
||||
|
||||
"nadir/internal/mounts"
|
||||
)
|
||||
|
||||
type DiskInfo struct {
|
||||
Mountpoint string `json:"mountpoint" example:"/"`
|
||||
Filesystem string `json:"filesystem" example:"/dev/nvme0n1p2" doc:"Backing device"`
|
||||
FSType string `json:"fstype" example:"btrfs"`
|
||||
TotalBytes uint64 `json:"total_bytes" example:"512000000000"`
|
||||
FreeBytes uint64 `json:"free_bytes" example:"256000000000" doc:"Space available to unprivileged users"`
|
||||
UsedBytes uint64 `json:"used_bytes" example:"256000000000"`
|
||||
}
|
||||
|
||||
func diskInfo() []DiskInfo {
|
||||
entries, err := mounts.Proc()
|
||||
if err != nil {
|
||||
return nil
|
||||
}
|
||||
disks := []DiskInfo{}
|
||||
seen := map[string]bool{}
|
||||
for _, e := range entries {
|
||||
if pseudoFS[e.FSType] || seen[e.Mountpoint] {
|
||||
continue
|
||||
}
|
||||
var st syscall.Statfs_t
|
||||
if syscall.Statfs(e.Mountpoint, &st) != nil || st.Blocks == 0 {
|
||||
continue
|
||||
}
|
||||
seen[e.Mountpoint] = true
|
||||
bs := uint64(st.Bsize)
|
||||
disks = append(disks, DiskInfo{
|
||||
Mountpoint: e.Mountpoint,
|
||||
Filesystem: e.Device,
|
||||
FSType: e.FSType,
|
||||
TotalBytes: st.Blocks * bs,
|
||||
FreeBytes: st.Bavail * bs,
|
||||
UsedBytes: (st.Blocks - st.Bfree) * bs,
|
||||
})
|
||||
}
|
||||
return disks
|
||||
}
|
||||
|
||||
var pseudoFS = map[string]bool{
|
||||
"autofs": true,
|
||||
"binfmt_misc": true,
|
||||
"bpf": true,
|
||||
"cgroup": true,
|
||||
"cgroup2": true,
|
||||
"configfs": true,
|
||||
"debugfs": true,
|
||||
"devpts": true,
|
||||
"devtmpfs": true,
|
||||
"fuse.gvfsd-fuse": true,
|
||||
"fuse.lxcfs": true,
|
||||
"fusectl": true,
|
||||
"hugetlbfs": true,
|
||||
"mqueue": true,
|
||||
"nsfs": true,
|
||||
"overlay": true,
|
||||
"proc": true,
|
||||
"pstore": true,
|
||||
"ramfs": true,
|
||||
"rpc_pipefs": true,
|
||||
"securityfs": true,
|
||||
"squashfs": true,
|
||||
"sysfs": true,
|
||||
"tmpfs": true,
|
||||
"tracefs": true,
|
||||
}
|
||||
@@ -0,0 +1,187 @@
|
||||
package system
|
||||
|
||||
import (
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strconv"
|
||||
"strings"
|
||||
|
||||
"nadir/internal/oscmd"
|
||||
)
|
||||
|
||||
type GPUInfo struct {
|
||||
Model string `json:"model" example:"AMD Radeon RX 7900 XTX" doc:"GPU model name, or vendor:device hex ID if lspci unavailable"`
|
||||
Vendor string `json:"vendor" example:"1002" doc:"PCI vendor ID (hex)"`
|
||||
DeviceID string `json:"device_id" example:"744c" doc:"PCI device ID (hex)"`
|
||||
Driver string `json:"driver" example:"amdgpu" doc:"Kernel driver in use"`
|
||||
MemoryTotalBytes uint64 `json:"memory_total_bytes" example:"8589934592" doc:"Total VRAM in bytes (driver-dependent; 0 if unavailable)"`
|
||||
MemoryUsedBytes uint64 `json:"memory_used_bytes" example:"27267072" doc:"Used VRAM in bytes (driver-dependent; 0 if unavailable)"`
|
||||
UtilizationPct float64 `json:"utilization_pct" example:"23.5" doc:"GPU compute utilization percentage (driver-dependent; 0 if unavailable)"`
|
||||
MemUtilizationPct float64 `json:"mem_utilization_pct" example:"15.0" doc:"GPU memory controller utilization percentage (driver-dependent; 0 if unavailable)"`
|
||||
}
|
||||
|
||||
func gpuInfo() []GPUInfo {
|
||||
return readGPUsFromSysfs("/sys/class/drm")
|
||||
}
|
||||
|
||||
func readGPUsFromSysfs(drmRoot string) []GPUInfo {
|
||||
entries, err := os.ReadDir(drmRoot)
|
||||
if err != nil {
|
||||
return nil
|
||||
}
|
||||
|
||||
seen := map[string]bool{}
|
||||
var gpus []GPUInfo
|
||||
|
||||
for _, e := range entries {
|
||||
if !isGPUCard(e.Name()) {
|
||||
continue
|
||||
}
|
||||
|
||||
pciAddr, vendor, device, driver := readGPUFromCard(drmRoot, e.Name())
|
||||
if pciAddr == "" || seen[pciAddr] {
|
||||
continue
|
||||
}
|
||||
seen[pciAddr] = true
|
||||
|
||||
model := vendor + ":" + device
|
||||
if m := lookupGPUName(pciAddr); m != "" {
|
||||
model = m
|
||||
}
|
||||
|
||||
gpu := GPUInfo{
|
||||
Model: model,
|
||||
Vendor: vendor,
|
||||
DeviceID: device,
|
||||
Driver: driver,
|
||||
}
|
||||
|
||||
devPath := filepath.Join(drmRoot, e.Name(), "device")
|
||||
enrichGPUInfo(&gpu, devPath, pciAddr, driver)
|
||||
gpus = append(gpus, gpu)
|
||||
}
|
||||
|
||||
return gpus
|
||||
}
|
||||
|
||||
func enrichGPUInfo(gpu *GPUInfo, devPath, pciAddr, driver string) {
|
||||
switch driver {
|
||||
case "amdgpu":
|
||||
enrichAMDGPU(gpu, devPath)
|
||||
case "nvidia":
|
||||
enrichNvidiaGPU(gpu, pciAddr)
|
||||
}
|
||||
}
|
||||
|
||||
func enrichAMDGPU(gpu *GPUInfo, devPath string) {
|
||||
if total := readUint64FromFile(filepath.Join(devPath, "mem_info_vram_total")); total > 0 {
|
||||
gpu.MemoryTotalBytes = total
|
||||
gpu.MemoryUsedBytes = readUint64FromFile(filepath.Join(devPath, "mem_info_vram_used"))
|
||||
}
|
||||
if pct := readIntFromFile(filepath.Join(devPath, "gpu_busy_percent")); pct >= 0 {
|
||||
gpu.UtilizationPct = float64(pct)
|
||||
}
|
||||
if pct := readIntFromFile(filepath.Join(devPath, "mem_busy_percent")); pct >= 0 {
|
||||
gpu.MemUtilizationPct = float64(pct)
|
||||
}
|
||||
}
|
||||
|
||||
func enrichNvidiaGPU(gpu *GPUInfo, pciAddr string) {
|
||||
out, err := oscmd.Run("nvidia-smi",
|
||||
"-i", pciAddr,
|
||||
"--query-gpu=memory.total,memory.used,utilization.gpu,utilization.memory",
|
||||
"--format=csv,noheader,nounits",
|
||||
)
|
||||
if err != nil {
|
||||
return
|
||||
}
|
||||
parts := strings.Split(strings.TrimSpace(out), ", ")
|
||||
if len(parts) < 4 {
|
||||
return
|
||||
}
|
||||
if total, err := strconv.ParseUint(parts[0], 10, 64); err == nil && total > 0 {
|
||||
gpu.MemoryTotalBytes = total * 1024 * 1024
|
||||
if used, err := strconv.ParseUint(parts[1], 10, 64); err == nil {
|
||||
gpu.MemoryUsedBytes = used * 1024 * 1024
|
||||
}
|
||||
}
|
||||
if pct, err := strconv.ParseFloat(parts[2], 64); err == nil {
|
||||
gpu.UtilizationPct = pct
|
||||
}
|
||||
if pct, err := strconv.ParseFloat(parts[3], 64); err == nil {
|
||||
gpu.MemUtilizationPct = pct
|
||||
}
|
||||
}
|
||||
|
||||
func isGPUCard(name string) bool {
|
||||
if !strings.HasPrefix(name, "card") {
|
||||
return false
|
||||
}
|
||||
if len(name) == 4 {
|
||||
return false
|
||||
}
|
||||
ch := name[4]
|
||||
return ch >= '0' && ch <= '9'
|
||||
}
|
||||
|
||||
func readGPUFromCard(drmRoot, name string) (pciAddr, vendor, device, driver string) {
|
||||
cardPath := filepath.Join(drmRoot, name)
|
||||
devPath := filepath.Join(cardPath, "device")
|
||||
|
||||
resolved, err := filepath.EvalSymlinks(cardPath)
|
||||
if err != nil {
|
||||
return "", "", "", ""
|
||||
}
|
||||
|
||||
parts := strings.Split(resolved, "/")
|
||||
for i, p := range parts {
|
||||
if p == "drm" && i > 0 {
|
||||
pciAddr = parts[i-1]
|
||||
break
|
||||
}
|
||||
}
|
||||
if pciAddr == "" {
|
||||
return "", "", "", ""
|
||||
}
|
||||
|
||||
vendor = strings.TrimPrefix(readTrim(filepath.Join(devPath, "vendor")), "0x")
|
||||
device = strings.TrimPrefix(readTrim(filepath.Join(devPath, "device")), "0x")
|
||||
driver = readDriver(devPath)
|
||||
return
|
||||
}
|
||||
|
||||
func readDriver(devPath string) string {
|
||||
target, err := os.Readlink(filepath.Join(devPath, "driver"))
|
||||
if err != nil {
|
||||
return ""
|
||||
}
|
||||
return filepath.Base(target)
|
||||
}
|
||||
|
||||
func lookupGPUName(pciAddr string) string {
|
||||
out, err := oscmd.Run("lspci", "-nns", pciAddr)
|
||||
if err != nil {
|
||||
return ""
|
||||
}
|
||||
_, rest, ok := strings.Cut(out, " ")
|
||||
if !ok {
|
||||
return ""
|
||||
}
|
||||
return strings.TrimSpace(rest)
|
||||
}
|
||||
|
||||
func readUint64FromFile(path string) uint64 {
|
||||
v, err := strconv.ParseUint(readTrim(path), 10, 64)
|
||||
if err != nil {
|
||||
return 0
|
||||
}
|
||||
return v
|
||||
}
|
||||
|
||||
func readIntFromFile(path string) int {
|
||||
v, err := strconv.Atoi(readTrim(path))
|
||||
if err != nil {
|
||||
return -1
|
||||
}
|
||||
return v
|
||||
}
|
||||
@@ -2,26 +2,16 @@ package system
|
||||
|
||||
import (
|
||||
"context"
|
||||
"math"
|
||||
"net"
|
||||
"os"
|
||||
"os/exec"
|
||||
"path/filepath"
|
||||
"runtime"
|
||||
"strconv"
|
||||
"strings"
|
||||
"sync"
|
||||
"syscall"
|
||||
"time"
|
||||
|
||||
"nadir/internal/mounts"
|
||||
"nadir/internal/oscmd"
|
||||
|
||||
"github.com/danielgtaylor/huma/v2"
|
||||
)
|
||||
|
||||
// SystemInfoBody is the dashboard overview: OS identity plus live CPU, memory,
|
||||
// disk, load, network, and temperature readings. Every section is best-effort —
|
||||
// disk, load, network, GPU, and temperature readings. Every section is best-effort —
|
||||
// a source that's unavailable (e.g. no thermal zones in a VM) yields a zero
|
||||
// value or empty list rather than failing the whole call.
|
||||
type SystemInfoBody struct {
|
||||
@@ -34,71 +24,12 @@ type SystemInfoBody struct {
|
||||
Disks []DiskInfo `json:"disks" doc:"Mounted block-device filesystems"`
|
||||
NetworkInterfaces []NetInterface `json:"network_interfaces" doc:"Network interfaces and their addresses"`
|
||||
Temperatures []Temperature `json:"temperatures" doc:"Thermal sensor readings in Celsius"`
|
||||
}
|
||||
|
||||
type OSInfo struct {
|
||||
PrettyName string `json:"pretty_name" example:"Fedora Linux 44 (Workstation Edition)" doc:"Distro name from /etc/os-release PRETTY_NAME"`
|
||||
Kernel string `json:"kernel" example:"7.0.12-201.fc44.x86_64" doc:"Running kernel release (uname -r)"`
|
||||
Architecture string `json:"architecture" example:"x86_64" doc:"Machine hardware architecture (uname -m)"`
|
||||
Hostname string `json:"hostname" example:"server01" doc:"System hostname"`
|
||||
}
|
||||
|
||||
type CPUInfo struct {
|
||||
Model string `json:"model" example:"AMD Ryzen 7 7840U" doc:"CPU model name"`
|
||||
LogicalCPUs int `json:"logical_cpus" example:"16" doc:"Number of logical CPUs (cores × threads)"`
|
||||
MinMHz int `json:"min_mhz" example:"400" doc:"Lowest frequency the scaling governor can select"`
|
||||
MaxMHz int `json:"max_mhz" example:"5137" doc:"Highest frequency (boost ceiling)"`
|
||||
CurrentMHz int `json:"current_mhz" example:"3157" doc:"Peak current clock across all cores (instantaneous snapshot; 0 if cpufreq unavailable)"`
|
||||
}
|
||||
|
||||
type MemoryInfo struct {
|
||||
TotalBytes uint64 `json:"total_bytes" example:"16384000000"`
|
||||
AvailableBytes uint64 `json:"available_bytes" example:"8192000000" doc:"Memory available for new allocations without swapping"`
|
||||
UsedBytes uint64 `json:"used_bytes" example:"8192000000" doc:"total - available"`
|
||||
SwapTotalBytes uint64 `json:"swap_total_bytes" example:"8589934592"`
|
||||
SwapFreeBytes uint64 `json:"swap_free_bytes" example:"8589934592"`
|
||||
}
|
||||
|
||||
type LoadInfo struct {
|
||||
Load1 float64 `json:"load1" example:"0.42"`
|
||||
Load5 float64 `json:"load5" example:"0.55"`
|
||||
Load15 float64 `json:"load15" example:"0.61"`
|
||||
CPUUsage []CoreUsage `json:"cpu_usage" doc:"Per-core CPU usage percentage (sampled over ~1 s); empty until the first sample completes"`
|
||||
}
|
||||
|
||||
// CoreUsage holds the usage percentage for a single logical core, computed as
|
||||
// the delta of non-idle ticks over total ticks between two /proc/stat reads.
|
||||
type CoreUsage struct {
|
||||
Core int `json:"core" example:"0" doc:"Logical core index"`
|
||||
UsagePct float64 `json:"usage_pct" example:"23.4" doc:"Usage percentage (0–100)"`
|
||||
}
|
||||
|
||||
type DiskInfo struct {
|
||||
Mountpoint string `json:"mountpoint" example:"/"`
|
||||
Filesystem string `json:"filesystem" example:"/dev/nvme0n1p2" doc:"Backing device"`
|
||||
FSType string `json:"fstype" example:"btrfs"`
|
||||
TotalBytes uint64 `json:"total_bytes" example:"512000000000"`
|
||||
FreeBytes uint64 `json:"free_bytes" example:"256000000000" doc:"Space available to unprivileged users"`
|
||||
UsedBytes uint64 `json:"used_bytes" example:"256000000000"`
|
||||
}
|
||||
|
||||
type NetInterface struct {
|
||||
Name string `json:"name" example:"eth0"`
|
||||
MAC string `json:"mac" example:"aa:bb:cc:dd:ee:ff"`
|
||||
Up bool `json:"up" doc:"Interface is administratively up"`
|
||||
Addresses []string `json:"addresses" doc:"Assigned addresses in CIDR notation"`
|
||||
}
|
||||
|
||||
type Temperature struct {
|
||||
Chip string `json:"chip" example:"k10temp" doc:"hwmon chip name; identifies the source (k10temp/coretemp=CPU, amdgpu/nvidia=GPU, nvme=disk)"`
|
||||
Label string `json:"label" example:"Tctl" doc:"Per-sensor label, or the chip name when the sensor is unlabelled"`
|
||||
Celsius float64 `json:"celsius" example:"47.5"`
|
||||
GPUs []GPUInfo `json:"gpus" doc:"Graphics processors detected via DRM sysfs"`
|
||||
}
|
||||
|
||||
type GetInfoOutput struct{ Body SystemInfoBody }
|
||||
|
||||
func registerInfo(api huma.API) {
|
||||
startCPUSampler()
|
||||
func registerInfo(api huma.API, sampler *Sampler) {
|
||||
huma.Register(api, huma.Operation{
|
||||
OperationID: "system-get-info",
|
||||
Method: "GET",
|
||||
@@ -106,9 +37,9 @@ func registerInfo(api huma.API) {
|
||||
Summary: "Get system information",
|
||||
Description: "Returns an overview for a dashboard: OS/kernel identity, CPU, " +
|
||||
"memory and swap, mounted disks, load averages, uptime, network " +
|
||||
"interfaces, and temperatures. All values come from cheap local reads " +
|
||||
"(/proc, /sys, syscalls) with no D-Bus dependency; each section is " +
|
||||
"best-effort.",
|
||||
"interfaces, temperatures, and GPU information. All values come from cheap " +
|
||||
"local reads (/proc, /sys, syscalls) with no D-Bus dependency; each " +
|
||||
"section is best-effort.",
|
||||
Tags: []string{tagSystem},
|
||||
Metadata: op("read"),
|
||||
Errors: readErrors,
|
||||
@@ -118,360 +49,17 @@ func registerInfo(api huma.API) {
|
||||
OS: osInfo(),
|
||||
CPU: cpuInfo(),
|
||||
Memory: memInfo(),
|
||||
Load: loadInfo(),
|
||||
Load: loadInfo(sampler),
|
||||
UptimeSec: uptime,
|
||||
BootTime: boot.Format(time.RFC3339),
|
||||
Disks: diskInfo(),
|
||||
NetworkInterfaces: netInfo(),
|
||||
Temperatures: tempInfo(),
|
||||
GPUs: gpuInfo(),
|
||||
}}, nil
|
||||
})
|
||||
}
|
||||
|
||||
func osInfo() OSInfo {
|
||||
host, _ := os.Hostname()
|
||||
return OSInfo{
|
||||
PrettyName: osReleasePretty(),
|
||||
Kernel: firstLine(oscmd.Run("uname", "-r")),
|
||||
Architecture: firstLine(oscmd.Run("uname", "-m")),
|
||||
Hostname: host,
|
||||
}
|
||||
}
|
||||
|
||||
// firstLine discards a command error and returns its (already trimmed) output,
|
||||
// used where a missing value is acceptable.
|
||||
func firstLine(out string, _ error) string { return out }
|
||||
|
||||
func osReleasePretty() string {
|
||||
data, err := os.ReadFile("/etc/os-release")
|
||||
if err != nil {
|
||||
return ""
|
||||
}
|
||||
for line := range strings.SplitSeq(string(data), "\n") {
|
||||
if v, ok := strings.CutPrefix(line, "PRETTY_NAME="); ok {
|
||||
return strings.Trim(v, `"`)
|
||||
}
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
func cpuInfo() CPUInfo {
|
||||
data, _ := os.ReadFile("/proc/cpuinfo")
|
||||
c := CPUInfo{Model: cpuModel(string(data)), LogicalCPUs: runtime.NumCPU()}
|
||||
c.MinMHz, c.MaxMHz, c.CurrentMHz = cpuFreqMHz("/sys/devices/system/cpu")
|
||||
// ponytail: cpufreq sysfs is absent on many VMs and stock Ubuntu server
|
||||
// kernels; fall back to /proc/cpuinfo "cpu MHz" — VMs have a fixed clock,
|
||||
// so min == max == cur is the honest answer.
|
||||
mhz := cpuinfoMaxMHz(string(data))
|
||||
// ponytail: ARM /proc/cpuinfo has no "cpu MHz" and often no "model name";
|
||||
// lscpu decodes the ARM part-id table and reads DMI, so use it as last resort.
|
||||
if c.Model == "" || mhz == 0 {
|
||||
model, lscpuMHz := lscpuFallback()
|
||||
if c.Model == "" {
|
||||
c.Model = model
|
||||
}
|
||||
if mhz == 0 {
|
||||
mhz = lscpuMHz
|
||||
}
|
||||
}
|
||||
if mhz > 0 {
|
||||
if c.CurrentMHz == 0 {
|
||||
c.CurrentMHz = mhz
|
||||
}
|
||||
if c.MaxMHz == 0 {
|
||||
c.MaxMHz = mhz
|
||||
}
|
||||
if c.MinMHz == 0 {
|
||||
c.MinMHz = mhz
|
||||
}
|
||||
}
|
||||
return c
|
||||
}
|
||||
|
||||
// lscpuFallback parses `lscpu` for "Model name" and any embedded "@ X.X GHz"
|
||||
// or "CPU max MHz:" value. Returns zeros when lscpu is missing or silent.
|
||||
func lscpuFallback() (model string, mhz int) {
|
||||
out, err := exec.Command("lscpu").Output()
|
||||
if err != nil {
|
||||
return "", 0
|
||||
}
|
||||
for line := range strings.SplitSeq(string(out), "\n") {
|
||||
k, v, ok := strings.Cut(line, ":")
|
||||
if !ok {
|
||||
continue
|
||||
}
|
||||
k, v = strings.TrimSpace(k), strings.TrimSpace(v)
|
||||
switch k {
|
||||
case "Model name":
|
||||
if model == "" {
|
||||
model = v
|
||||
}
|
||||
case "BIOS Model name":
|
||||
if model == "" {
|
||||
model = v
|
||||
}
|
||||
case "CPU max MHz", "CPU MHz":
|
||||
if f, err := strconv.ParseFloat(v, 64); err == nil && int(f) > mhz {
|
||||
mhz = int(math.Round(f))
|
||||
}
|
||||
}
|
||||
}
|
||||
if mhz == 0 {
|
||||
mhz = parseGHzSuffix(model)
|
||||
}
|
||||
return model, mhz
|
||||
}
|
||||
|
||||
// parseGHzSuffix pulls "2.0GHz" / "@ 2.0 GHz" out of a model string.
|
||||
func parseGHzSuffix(s string) int {
|
||||
i := strings.LastIndex(s, "@")
|
||||
if i < 0 {
|
||||
return 0
|
||||
}
|
||||
rest := strings.TrimSpace(s[i+1:])
|
||||
rest = strings.TrimSuffix(strings.TrimSuffix(rest, "GHz"), "Ghz")
|
||||
rest = strings.TrimSpace(strings.TrimSuffix(rest, "G"))
|
||||
f, err := strconv.ParseFloat(strings.TrimSpace(rest), 64)
|
||||
if err != nil {
|
||||
return 0
|
||||
}
|
||||
return int(math.Round(f * 1000))
|
||||
}
|
||||
|
||||
// cpuinfoMaxMHz returns the highest "cpu MHz" value across all cores in
|
||||
// /proc/cpuinfo, rounded to an int. Returns 0 when no such line exists.
|
||||
func cpuinfoMaxMHz(cpuinfo string) int {
|
||||
var max float64
|
||||
for line := range strings.SplitSeq(cpuinfo, "\n") {
|
||||
k, v, ok := strings.Cut(line, ":")
|
||||
if !ok || strings.TrimSpace(k) != "cpu MHz" {
|
||||
continue
|
||||
}
|
||||
if f, err := strconv.ParseFloat(strings.TrimSpace(v), 64); err == nil && f > max {
|
||||
max = f
|
||||
}
|
||||
}
|
||||
return int(math.Round(max))
|
||||
}
|
||||
|
||||
// cpuFreqMHz reads cpufreq sysfs: min/max are stable hardware limits (from
|
||||
// cpu0); current is the highest scaling_cur_freq across all cores — the "is it
|
||||
// boosting" figure. Values are kHz in sysfs. Returns zeros when cpufreq is
|
||||
// absent (e.g. some VMs).
|
||||
func cpuFreqMHz(root string) (min, max, cur int) {
|
||||
min = readKHzAsMHz(filepath.Join(root, "cpu0/cpufreq/cpuinfo_min_freq"))
|
||||
max = readKHzAsMHz(filepath.Join(root, "cpu0/cpufreq/cpuinfo_max_freq"))
|
||||
cores, _ := filepath.Glob(filepath.Join(root, "cpu[0-9]*/cpufreq/scaling_cur_freq"))
|
||||
for _, f := range cores {
|
||||
if v := readKHzAsMHz(f); v > cur {
|
||||
cur = v
|
||||
}
|
||||
}
|
||||
return min, max, cur
|
||||
}
|
||||
|
||||
func readKHzAsMHz(path string) int {
|
||||
khz, err := strconv.Atoi(readTrim(path))
|
||||
if err != nil {
|
||||
return 0
|
||||
}
|
||||
return khz / 1000
|
||||
}
|
||||
|
||||
// cpuModel extracts the processor model from /proc/cpuinfo. x86 uses "model
|
||||
// name"; many ARM boards use "Model" instead, so fall back to it.
|
||||
func cpuModel(cpuinfo string) string {
|
||||
var fallback string
|
||||
for line := range strings.SplitSeq(cpuinfo, "\n") {
|
||||
k, v, ok := strings.Cut(line, ":")
|
||||
if !ok {
|
||||
continue
|
||||
}
|
||||
switch strings.TrimSpace(k) {
|
||||
case "model name":
|
||||
return strings.TrimSpace(v)
|
||||
case "Model":
|
||||
fallback = strings.TrimSpace(v)
|
||||
}
|
||||
}
|
||||
return fallback
|
||||
}
|
||||
|
||||
func memInfo() MemoryInfo {
|
||||
data, _ := os.ReadFile("/proc/meminfo")
|
||||
return parseMeminfo(data)
|
||||
}
|
||||
|
||||
// parseMeminfo reads the kB values in /proc/meminfo and converts them to bytes.
|
||||
func parseMeminfo(data []byte) MemoryInfo {
|
||||
kv := map[string]uint64{}
|
||||
for line := range strings.SplitSeq(string(data), "\n") {
|
||||
k, v, ok := strings.Cut(line, ":")
|
||||
if !ok {
|
||||
continue
|
||||
}
|
||||
fields := strings.Fields(v) // e.g. "16384000 kB"
|
||||
if len(fields) == 0 {
|
||||
continue
|
||||
}
|
||||
if n, err := strconv.ParseUint(fields[0], 10, 64); err == nil {
|
||||
kv[k] = n * 1024 // values are in kB
|
||||
}
|
||||
}
|
||||
return MemoryInfo{
|
||||
TotalBytes: kv["MemTotal"],
|
||||
AvailableBytes: kv["MemAvailable"],
|
||||
UsedBytes: kv["MemTotal"] - kv["MemAvailable"],
|
||||
SwapTotalBytes: kv["SwapTotal"],
|
||||
SwapFreeBytes: kv["SwapFree"],
|
||||
}
|
||||
}
|
||||
|
||||
func loadInfo() LoadInfo {
|
||||
data, _ := os.ReadFile("/proc/loadavg")
|
||||
l := parseLoadavg(string(data))
|
||||
l.CPUUsage = cachedCPUUsage()
|
||||
return l
|
||||
}
|
||||
|
||||
// parseLoadavg reads the three load averages from /proc/loadavg.
|
||||
func parseLoadavg(loadavg string) LoadInfo {
|
||||
f := strings.Fields(loadavg)
|
||||
if len(f) < 3 {
|
||||
return LoadInfo{}
|
||||
}
|
||||
at := func(i int) float64 { v, _ := strconv.ParseFloat(f[i], 64); return v }
|
||||
return LoadInfo{Load1: at(0), Load5: at(1), Load15: at(2)}
|
||||
}
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// Per-core CPU usage sampler
|
||||
// ---------------------------------------------------------------------------
|
||||
//
|
||||
// /proc/stat exposes cumulative jiffies per core:
|
||||
//
|
||||
// cpuN user nice system idle iowait irq softirq steal guest guest_nice
|
||||
//
|
||||
// We sample every second, compute the delta, and derive:
|
||||
//
|
||||
// usage% = (totalΔ − idleΔ) / totalΔ × 100
|
||||
//
|
||||
// The result is cached behind a RWMutex so the HTTP handler never blocks.
|
||||
|
||||
var (
|
||||
usageMu sync.RWMutex
|
||||
usageCache []CoreUsage
|
||||
)
|
||||
|
||||
func cachedCPUUsage() []CoreUsage {
|
||||
usageMu.RLock()
|
||||
defer usageMu.RUnlock()
|
||||
// Return a copy so callers can't mutate the cache.
|
||||
if usageCache == nil {
|
||||
return nil
|
||||
}
|
||||
out := make([]CoreUsage, len(usageCache))
|
||||
copy(out, usageCache)
|
||||
return out
|
||||
}
|
||||
|
||||
// startCPUSampler launches a goroutine that samples /proc/stat once per second
|
||||
// for the lifetime of the process. Safe to call multiple times (only the first
|
||||
// call starts the goroutine).
|
||||
var samplerOnce sync.Once
|
||||
|
||||
func startCPUSampler() {
|
||||
samplerOnce.Do(func() {
|
||||
go cpuSamplerLoop("/proc/stat", 1*time.Second)
|
||||
})
|
||||
}
|
||||
|
||||
func cpuSamplerLoop(statPath string, interval time.Duration) {
|
||||
prev := readProcStat(statPath)
|
||||
for {
|
||||
time.Sleep(interval)
|
||||
cur := readProcStat(statPath)
|
||||
usage := computeUsage(prev, cur)
|
||||
usageMu.Lock()
|
||||
usageCache = usage
|
||||
usageMu.Unlock()
|
||||
prev = cur
|
||||
}
|
||||
}
|
||||
|
||||
// cpuCoreTicks holds the cumulative jiffies for one "cpuN" line.
|
||||
type cpuCoreTicks struct {
|
||||
core int
|
||||
total uint64
|
||||
idle uint64
|
||||
}
|
||||
|
||||
// readProcStat reads /proc/stat and returns per-core tick totals. The
|
||||
// aggregate "cpu" line (no digit suffix) is skipped.
|
||||
func readProcStat(path string) []cpuCoreTicks {
|
||||
data, _ := os.ReadFile(path)
|
||||
var cores []cpuCoreTicks
|
||||
for line := range strings.SplitSeq(string(data), "\n") {
|
||||
if !strings.HasPrefix(line, "cpu") {
|
||||
continue
|
||||
}
|
||||
fields := strings.Fields(line)
|
||||
if len(fields) < 5 {
|
||||
continue
|
||||
}
|
||||
// Skip the aggregate "cpu" line; we only want "cpu0", "cpu1", …
|
||||
name := fields[0]
|
||||
if name == "cpu" {
|
||||
continue
|
||||
}
|
||||
coreIdx, err := strconv.Atoi(strings.TrimPrefix(name, "cpu"))
|
||||
if err != nil {
|
||||
continue
|
||||
}
|
||||
// Fields: user(1) nice(2) system(3) idle(4) iowait(5) irq(6) softirq(7) steal(8) …
|
||||
var total, idle uint64
|
||||
for _, f := range fields[1:] {
|
||||
v, _ := strconv.ParseUint(f, 10, 64)
|
||||
total += v
|
||||
}
|
||||
// idle = idle + iowait (indices 4 and 5 in the original line).
|
||||
if len(fields) > 5 {
|
||||
v4, _ := strconv.ParseUint(fields[4], 10, 64)
|
||||
v5, _ := strconv.ParseUint(fields[5], 10, 64)
|
||||
idle = v4 + v5
|
||||
} else {
|
||||
v4, _ := strconv.ParseUint(fields[4], 10, 64)
|
||||
idle = v4
|
||||
}
|
||||
cores = append(cores, cpuCoreTicks{core: coreIdx, total: total, idle: idle})
|
||||
}
|
||||
return cores
|
||||
}
|
||||
|
||||
func computeUsage(prev, cur []cpuCoreTicks) []CoreUsage {
|
||||
prevMap := make(map[int]cpuCoreTicks, len(prev))
|
||||
for _, c := range prev {
|
||||
prevMap[c.core] = c
|
||||
}
|
||||
usage := make([]CoreUsage, 0, len(cur))
|
||||
for _, c := range cur {
|
||||
p, ok := prevMap[c.core]
|
||||
if !ok {
|
||||
continue
|
||||
}
|
||||
dTotal := c.total - p.total
|
||||
dIdle := c.idle - p.idle
|
||||
var pct float64
|
||||
if dTotal > 0 {
|
||||
pct = float64(dTotal-dIdle) / float64(dTotal) * 100
|
||||
// Round to one decimal.
|
||||
pct = math.Round(pct*10) / 10
|
||||
}
|
||||
usage = append(usage, CoreUsage{Core: c.core, UsagePct: pct})
|
||||
}
|
||||
return usage
|
||||
}
|
||||
|
||||
// uptimeAndBoot reads /proc/uptime (seconds since boot) and derives boot time.
|
||||
// On any read error it returns zero values rather than failing the request.
|
||||
func uptimeAndBoot() (int64, time.Time) {
|
||||
@@ -490,163 +78,3 @@ func uptimeAndBoot() (int64, time.Time) {
|
||||
boot := time.Now().Add(-time.Duration(secs * float64(time.Second))).UTC()
|
||||
return int64(secs), boot
|
||||
}
|
||||
|
||||
func diskInfo() []DiskInfo {
|
||||
entries, err := mounts.Proc()
|
||||
if err != nil {
|
||||
return nil
|
||||
}
|
||||
disks := []DiskInfo{}
|
||||
seen := map[string]bool{}
|
||||
for _, e := range entries {
|
||||
// ponytail: filter by fstype, not device path. LXC/Docker containers
|
||||
// expose their rootfs as a ZFS dataset name, an overlayfs, or a bind
|
||||
// path — never /dev/* — so a "must start with /dev/" check silently
|
||||
// returned no disks on those hosts. statfs + non-zero blocks already
|
||||
// excludes mounts that aren't real storage.
|
||||
if pseudoFS[e.FSType] || seen[e.Mountpoint] {
|
||||
continue
|
||||
}
|
||||
var st syscall.Statfs_t
|
||||
if syscall.Statfs(e.Mountpoint, &st) != nil || st.Blocks == 0 {
|
||||
continue
|
||||
}
|
||||
seen[e.Mountpoint] = true
|
||||
bs := uint64(st.Bsize)
|
||||
disks = append(disks, DiskInfo{
|
||||
Mountpoint: e.Mountpoint,
|
||||
Filesystem: e.Device,
|
||||
FSType: e.FSType,
|
||||
TotalBytes: st.Blocks * bs,
|
||||
FreeBytes: st.Bavail * bs,
|
||||
UsedBytes: (st.Blocks - st.Bfree) * bs,
|
||||
})
|
||||
}
|
||||
return disks
|
||||
}
|
||||
|
||||
// pseudoFS lists kernel-virtual filesystems that show up in /proc/mounts but
|
||||
// aren't user-facing storage. squashfs covers snap loop mounts; fuse.lxcfs is
|
||||
// LXC's per-container /proc/* shim. Anything not on this list and statfs-able
|
||||
// with non-zero blocks is treated as real storage — covers ext*, btrfs, xfs,
|
||||
// zfs, nfs, cifs, overlay, and the bind-mount cases inside Proxmox LXC.
|
||||
var pseudoFS = map[string]bool{
|
||||
"autofs": true,
|
||||
"binfmt_misc": true,
|
||||
"bpf": true,
|
||||
"cgroup": true,
|
||||
"cgroup2": true,
|
||||
"configfs": true,
|
||||
"debugfs": true,
|
||||
"devpts": true,
|
||||
"devtmpfs": true,
|
||||
"fuse.gvfsd-fuse": true,
|
||||
"fuse.lxcfs": true,
|
||||
"fusectl": true,
|
||||
"hugetlbfs": true,
|
||||
"mqueue": true,
|
||||
"nsfs": true,
|
||||
"overlay": true,
|
||||
"proc": true,
|
||||
"pstore": true,
|
||||
"ramfs": true,
|
||||
"rpc_pipefs": true,
|
||||
"securityfs": true,
|
||||
"squashfs": true,
|
||||
"sysfs": true,
|
||||
"tmpfs": true,
|
||||
"tracefs": true,
|
||||
}
|
||||
|
||||
func netInfo() []NetInterface {
|
||||
ifaces, err := net.Interfaces()
|
||||
if err != nil {
|
||||
return nil
|
||||
}
|
||||
out := []NetInterface{}
|
||||
for _, ifi := range ifaces {
|
||||
addrs, _ := ifi.Addrs()
|
||||
strs := []string{}
|
||||
for _, a := range addrs {
|
||||
strs = append(strs, a.String())
|
||||
}
|
||||
out = append(out, NetInterface{
|
||||
Name: ifi.Name,
|
||||
MAC: ifi.HardwareAddr.String(),
|
||||
Up: ifi.Flags&net.FlagUp != 0,
|
||||
Addresses: strs,
|
||||
})
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
func tempInfo() []Temperature {
|
||||
if t := readHwmonTemps("/sys/class/hwmon"); len(t) > 0 {
|
||||
return t
|
||||
}
|
||||
// ponytail: stock Ubuntu server has no coretemp/k10temp loaded, so hwmon
|
||||
// is empty; thermal_zone exposes ACPI sensors (coarser, no chip name).
|
||||
return readThermalZones("/sys/class/thermal")
|
||||
}
|
||||
|
||||
// readThermalZones reads /sys/class/thermal/thermal_zone*/temp as a fallback
|
||||
// for hosts without hwmon chip drivers. "type" names the zone (e.g. acpitz,
|
||||
// x86_pkg_temp); used as both chip and label.
|
||||
func readThermalZones(root string) []Temperature {
|
||||
zones, _ := filepath.Glob(filepath.Join(root, "thermal_zone*"))
|
||||
temps := []Temperature{}
|
||||
for _, dir := range zones {
|
||||
milli, err := strconv.Atoi(readTrim(filepath.Join(dir, "temp")))
|
||||
if err != nil {
|
||||
continue
|
||||
}
|
||||
c := float64(milli) / 1000
|
||||
if c <= 0 || c >= 150 {
|
||||
continue
|
||||
}
|
||||
name := readTrim(filepath.Join(dir, "type"))
|
||||
if name == "" {
|
||||
name = filepath.Base(dir)
|
||||
}
|
||||
temps = append(temps, Temperature{Chip: name, Label: name, Celsius: c})
|
||||
}
|
||||
return temps
|
||||
}
|
||||
|
||||
// readHwmonTemps walks /sys/class/hwmon, which (unlike /sys/class/thermal, that
|
||||
// only exposes generic ACPI zones like "acpitz") names each chip — so callers
|
||||
// can split CPU (k10temp/coretemp) from GPU (amdgpu/nvidia) from disk (nvme).
|
||||
// Each tempN_input may carry a tempN_label; when absent we fall back to the
|
||||
// chip name. Best-effort: unreadable, empty, or implausible sensors are skipped.
|
||||
func readHwmonTemps(root string) []Temperature {
|
||||
chips, _ := filepath.Glob(filepath.Join(root, "hwmon*"))
|
||||
temps := []Temperature{}
|
||||
for _, dir := range chips {
|
||||
chip := readTrim(filepath.Join(dir, "name"))
|
||||
inputs, _ := filepath.Glob(filepath.Join(dir, "temp*_input"))
|
||||
for _, in := range inputs {
|
||||
milli, err := strconv.Atoi(readTrim(in))
|
||||
if err != nil {
|
||||
continue
|
||||
}
|
||||
c := float64(milli) / 1000
|
||||
// Disabled/placeholder sensors report absurd values (e.g. -0.15 or
|
||||
// 179.8 °C). Drop anything outside a plausible band.
|
||||
if c <= 0 || c >= 150 {
|
||||
continue
|
||||
}
|
||||
label := readTrim(strings.TrimSuffix(in, "_input") + "_label")
|
||||
if label == "" {
|
||||
label = chip
|
||||
}
|
||||
temps = append(temps, Temperature{Chip: chip, Label: label, Celsius: c})
|
||||
}
|
||||
}
|
||||
return temps
|
||||
}
|
||||
|
||||
// readTrim reads a sysfs file and trims it; a missing file yields "".
|
||||
func readTrim(path string) string {
|
||||
b, _ := os.ReadFile(path)
|
||||
return strings.TrimSpace(string(b))
|
||||
}
|
||||
|
||||
@@ -6,6 +6,106 @@ import (
|
||||
"testing"
|
||||
)
|
||||
|
||||
func TestReadGPUsFromSysfs(t *testing.T) {
|
||||
root := t.TempDir()
|
||||
|
||||
// card0 — AMD GPU with VRAM and utilization files
|
||||
pciDev := filepath.Join(root, "devices/pci0000:00/0000:00:02.0")
|
||||
mkdirAll(t, pciDev)
|
||||
write(t, pciDev, ".", "vendor", "0x1002")
|
||||
write(t, pciDev, ".", "device", "0x7480")
|
||||
write(t, pciDev, ".", "mem_info_vram_total", "8573157376")
|
||||
write(t, pciDev, ".", "mem_info_vram_used", "27267072")
|
||||
write(t, pciDev, ".", "gpu_busy_percent", "23")
|
||||
write(t, pciDev, ".", "mem_busy_percent", "15")
|
||||
|
||||
driverDir := filepath.Join(root, "bus/pci/drivers/amdgpu")
|
||||
mkdirAll(t, driverDir)
|
||||
mustSymlink(t, driverDir, filepath.Join(pciDev, "driver"))
|
||||
|
||||
cardTarget := filepath.Join(pciDev, "drm", "card0")
|
||||
mkdirAll(t, cardTarget)
|
||||
mustSymlink(t, pciDev, filepath.Join(cardTarget, "device"))
|
||||
mustSymlink(t, cardTarget, filepath.Join(root, "card0"))
|
||||
|
||||
// Distractors
|
||||
write(t, root, ".", "card0-HDMI-1", "distract")
|
||||
write(t, root, ".", "renderD128", "distract")
|
||||
|
||||
gpus := readGPUsFromSysfs(root)
|
||||
if len(gpus) != 1 {
|
||||
t.Fatalf("want 1 GPU, got %d: %+v", len(gpus), gpus)
|
||||
}
|
||||
if gpus[0].Vendor != "1002" {
|
||||
t.Errorf("vendor = %q, want 1002", gpus[0].Vendor)
|
||||
}
|
||||
if gpus[0].DeviceID != "7480" {
|
||||
t.Errorf("device_id = %q, want 7480", gpus[0].DeviceID)
|
||||
}
|
||||
if gpus[0].Driver != "amdgpu" {
|
||||
t.Errorf("driver = %q, want amdgpu", gpus[0].Driver)
|
||||
}
|
||||
if gpus[0].MemoryTotalBytes != 8573157376 {
|
||||
t.Errorf("MemoryTotalBytes = %d, want 8573157376", gpus[0].MemoryTotalBytes)
|
||||
}
|
||||
if gpus[0].MemoryUsedBytes != 27267072 {
|
||||
t.Errorf("MemoryUsedBytes = %d, want 27267072", gpus[0].MemoryUsedBytes)
|
||||
}
|
||||
if gpus[0].UtilizationPct != 23.0 {
|
||||
t.Errorf("UtilizationPct = %f, want 23.0", gpus[0].UtilizationPct)
|
||||
}
|
||||
if gpus[0].MemUtilizationPct != 15.0 {
|
||||
t.Errorf("MemUtilizationPct = %f, want 15.0", gpus[0].MemUtilizationPct)
|
||||
}
|
||||
}
|
||||
|
||||
func TestReadGPUsFromSysfsNoEnrichment(t *testing.T) {
|
||||
root := t.TempDir()
|
||||
|
||||
// i915 GPU with no VRAM or utilization files
|
||||
pciDev := filepath.Join(root, "devices/pci0000:00/0000:00:02.0")
|
||||
mkdirAll(t, pciDev)
|
||||
write(t, pciDev, ".", "vendor", "0x8086")
|
||||
write(t, pciDev, ".", "device", "0x46a6")
|
||||
|
||||
driverDir := filepath.Join(root, "bus/pci/drivers/i915")
|
||||
mkdirAll(t, driverDir)
|
||||
mustSymlink(t, driverDir, filepath.Join(pciDev, "driver"))
|
||||
|
||||
cardTarget := filepath.Join(pciDev, "drm", "card0")
|
||||
mkdirAll(t, cardTarget)
|
||||
mustSymlink(t, pciDev, filepath.Join(cardTarget, "device"))
|
||||
mustSymlink(t, cardTarget, filepath.Join(root, "card0"))
|
||||
|
||||
gpus := readGPUsFromSysfs(root)
|
||||
if len(gpus) != 1 {
|
||||
t.Fatalf("want 1 GPU, got %d", len(gpus))
|
||||
}
|
||||
if gpus[0].MemoryTotalBytes != 0 || gpus[0].MemoryUsedBytes != 0 {
|
||||
t.Errorf("expected 0 VRAM for i915, got total=%d used=%d", gpus[0].MemoryTotalBytes, gpus[0].MemoryUsedBytes)
|
||||
}
|
||||
if gpus[0].UtilizationPct != 0 || gpus[0].MemUtilizationPct != 0 {
|
||||
t.Errorf("expected 0 utilization for i915, got gpu=%f mem=%f", gpus[0].UtilizationPct, gpus[0].MemUtilizationPct)
|
||||
}
|
||||
}
|
||||
|
||||
func TestReadGPUsFromSysfsMissingDir(t *testing.T) {
|
||||
gpus := readGPUsFromSysfs("/nonexistent/drm")
|
||||
if gpus != nil {
|
||||
t.Errorf("expected nil, got %+v", gpus)
|
||||
}
|
||||
}
|
||||
|
||||
func TestReadGPUsFromSysfsSkipsNonGPU(t *testing.T) {
|
||||
root := t.TempDir()
|
||||
write(t, root, ".", "renderD128", "x")
|
||||
write(t, root, ".", "card0-HDMI-1", "x")
|
||||
gpus := readGPUsFromSysfs(root)
|
||||
if len(gpus) != 0 {
|
||||
t.Errorf("expected 0 GPUs, got %d", len(gpus))
|
||||
}
|
||||
}
|
||||
|
||||
func TestReadHwmonTemps(t *testing.T) {
|
||||
root := t.TempDir()
|
||||
// k10temp: CPU, labelled Tctl.
|
||||
@@ -33,6 +133,20 @@ func TestReadHwmonTemps(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
func mkdirAll(t *testing.T, path string) {
|
||||
t.Helper()
|
||||
if err := os.MkdirAll(path, 0o755); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
|
||||
func mustSymlink(t *testing.T, target, link string) {
|
||||
t.Helper()
|
||||
if err := os.Symlink(target, link); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
|
||||
func write(t *testing.T, root, chip, file, val string) {
|
||||
t.Helper()
|
||||
dir := filepath.Join(root, chip)
|
||||
|
||||
@@ -0,0 +1,37 @@
|
||||
package system
|
||||
|
||||
import (
|
||||
"os"
|
||||
"strconv"
|
||||
"strings"
|
||||
)
|
||||
|
||||
// CoreUsage holds the usage percentage for a single logical core, computed as
|
||||
// the delta of non-idle ticks over total ticks between two /proc/stat reads.
|
||||
type CoreUsage struct {
|
||||
Core int `json:"core" example:"0" doc:"Logical core index"`
|
||||
UsagePct float64 `json:"usage_pct" example:"23.4" doc:"Usage percentage (0–100)"`
|
||||
}
|
||||
|
||||
type LoadInfo struct {
|
||||
Load1 float64 `json:"load1" example:"0.42"`
|
||||
Load5 float64 `json:"load5" example:"0.55"`
|
||||
Load15 float64 `json:"load15" example:"0.61"`
|
||||
CPUUsage []CoreUsage `json:"cpu_usage" doc:"Per-core CPU usage percentage (sampled over ~1 s); empty until the first sample completes"`
|
||||
}
|
||||
|
||||
func loadInfo(sampler *Sampler) LoadInfo {
|
||||
data, _ := os.ReadFile("/proc/loadavg")
|
||||
l := parseLoadavg(string(data))
|
||||
l.CPUUsage = sampler.Snapshot()
|
||||
return l
|
||||
}
|
||||
|
||||
func parseLoadavg(loadavg string) LoadInfo {
|
||||
f := strings.Fields(loadavg)
|
||||
if len(f) < 3 {
|
||||
return LoadInfo{}
|
||||
}
|
||||
at := func(i int) float64 { v, _ := strconv.ParseFloat(f[i], 64); return v }
|
||||
return LoadInfo{Load1: at(0), Load5: at(1), Load15: at(2)}
|
||||
}
|
||||
@@ -0,0 +1,44 @@
|
||||
package system
|
||||
|
||||
import (
|
||||
"os"
|
||||
"strconv"
|
||||
"strings"
|
||||
)
|
||||
|
||||
type MemoryInfo struct {
|
||||
TotalBytes uint64 `json:"total_bytes" example:"16384000000"`
|
||||
AvailableBytes uint64 `json:"available_bytes" example:"8192000000" doc:"Memory available for new allocations without swapping"`
|
||||
UsedBytes uint64 `json:"used_bytes" example:"8192000000" doc:"total - available"`
|
||||
SwapTotalBytes uint64 `json:"swap_total_bytes" example:"8589934592"`
|
||||
SwapFreeBytes uint64 `json:"swap_free_bytes" example:"8589934592"`
|
||||
}
|
||||
|
||||
func memInfo() MemoryInfo {
|
||||
data, _ := os.ReadFile("/proc/meminfo")
|
||||
return parseMeminfo(data)
|
||||
}
|
||||
|
||||
func parseMeminfo(data []byte) MemoryInfo {
|
||||
kv := map[string]uint64{}
|
||||
for line := range strings.SplitSeq(string(data), "\n") {
|
||||
k, v, ok := strings.Cut(line, ":")
|
||||
if !ok {
|
||||
continue
|
||||
}
|
||||
fields := strings.Fields(v)
|
||||
if len(fields) == 0 {
|
||||
continue
|
||||
}
|
||||
if n, err := strconv.ParseUint(fields[0], 10, 64); err == nil {
|
||||
kv[k] = n * 1024
|
||||
}
|
||||
}
|
||||
return MemoryInfo{
|
||||
TotalBytes: kv["MemTotal"],
|
||||
AvailableBytes: kv["MemAvailable"],
|
||||
UsedBytes: kv["MemTotal"] - kv["MemAvailable"],
|
||||
SwapTotalBytes: kv["SwapTotal"],
|
||||
SwapFreeBytes: kv["SwapFree"],
|
||||
}
|
||||
}
|
||||
@@ -1,6 +1,9 @@
|
||||
package system
|
||||
|
||||
import (
|
||||
"context"
|
||||
"time"
|
||||
|
||||
"nadir/internal/rbac"
|
||||
|
||||
"github.com/danielgtaylor/huma/v2"
|
||||
@@ -8,9 +11,15 @@ import (
|
||||
|
||||
const ModuleID = "system"
|
||||
|
||||
type Module struct{}
|
||||
type Module struct {
|
||||
sampler *Sampler
|
||||
}
|
||||
|
||||
func New() *Module { return &Module{} }
|
||||
func New() *Module {
|
||||
return &Module{
|
||||
sampler: NewSampler("/proc/stat", 1*time.Second),
|
||||
}
|
||||
}
|
||||
|
||||
func (m *Module) ID() string { return ModuleID }
|
||||
|
||||
@@ -19,7 +28,8 @@ func (m *Module) Permissions() []rbac.Permission {
|
||||
}
|
||||
|
||||
func (m *Module) Register(api huma.API) {
|
||||
registerInfo(api)
|
||||
m.sampler.Start(context.Background())
|
||||
registerInfo(api, m.sampler)
|
||||
registerHostname(api)
|
||||
registerTimedate(api)
|
||||
registerLocale(api)
|
||||
|
||||
@@ -0,0 +1,32 @@
|
||||
package system
|
||||
|
||||
import "net"
|
||||
|
||||
type NetInterface struct {
|
||||
Name string `json:"name" example:"eth0"`
|
||||
MAC string `json:"mac" example:"aa:bb:cc:dd:ee:ff"`
|
||||
Up bool `json:"up" doc:"Interface is administratively up"`
|
||||
Addresses []string `json:"addresses" doc:"Assigned addresses in CIDR notation"`
|
||||
}
|
||||
|
||||
func netInfo() []NetInterface {
|
||||
ifaces, err := net.Interfaces()
|
||||
if err != nil {
|
||||
return nil
|
||||
}
|
||||
out := []NetInterface{}
|
||||
for _, ifi := range ifaces {
|
||||
addrs, _ := ifi.Addrs()
|
||||
strs := []string{}
|
||||
for _, a := range addrs {
|
||||
strs = append(strs, a.String())
|
||||
}
|
||||
out = append(out, NetInterface{
|
||||
Name: ifi.Name,
|
||||
MAC: ifi.HardwareAddr.String(),
|
||||
Up: ifi.Flags&net.FlagUp != 0,
|
||||
Addresses: strs,
|
||||
})
|
||||
}
|
||||
return out
|
||||
}
|
||||
@@ -0,0 +1,42 @@
|
||||
package system
|
||||
|
||||
import (
|
||||
"os"
|
||||
"strings"
|
||||
|
||||
"nadir/internal/oscmd"
|
||||
)
|
||||
|
||||
type OSInfo struct {
|
||||
PrettyName string `json:"pretty_name" example:"Fedora Linux 44 (Workstation Edition)" doc:"Distro name from /etc/os-release PRETTY_NAME"`
|
||||
Kernel string `json:"kernel" example:"7.0.12-201.fc44.x86_64" doc:"Running kernel release (uname -r)"`
|
||||
Architecture string `json:"architecture" example:"x86_64" doc:"Machine hardware architecture (uname -m)"`
|
||||
Hostname string `json:"hostname" example:"server01" doc:"System hostname"`
|
||||
}
|
||||
|
||||
func osInfo() OSInfo {
|
||||
host, _ := os.Hostname()
|
||||
return OSInfo{
|
||||
PrettyName: osReleasePretty(),
|
||||
Kernel: firstLine(oscmd.Run("uname", "-r")),
|
||||
Architecture: firstLine(oscmd.Run("uname", "-m")),
|
||||
Hostname: host,
|
||||
}
|
||||
}
|
||||
|
||||
// firstLine discards a command error and returns its (already trimmed) output,
|
||||
// used where a missing value is acceptable.
|
||||
func firstLine(out string, _ error) string { return out }
|
||||
|
||||
func osReleasePretty() string {
|
||||
data, err := os.ReadFile("/etc/os-release")
|
||||
if err != nil {
|
||||
return ""
|
||||
}
|
||||
for line := range strings.SplitSeq(string(data), "\n") {
|
||||
if v, ok := strings.CutPrefix(line, "PRETTY_NAME="); ok {
|
||||
return strings.Trim(v, `"`)
|
||||
}
|
||||
}
|
||||
return ""
|
||||
}
|
||||
@@ -22,7 +22,7 @@ func TestSystemHandlers(t *testing.T) {
|
||||
registerTimedate(api)
|
||||
registerLocale(api)
|
||||
registerPower(api)
|
||||
registerInfo(api)
|
||||
registerInfo(api, NewSampler("/proc/stat", 0))
|
||||
|
||||
// Mock uname for GET /api/system/info
|
||||
oscmd.SetMock("uname", func(args []string) oscmd.MockCommand {
|
||||
@@ -34,6 +34,14 @@ func TestSystemHandlers(t *testing.T) {
|
||||
}
|
||||
return oscmd.MockCommand{ExitCode: 1}
|
||||
})
|
||||
// Mock lspci to prevent real calls in case the test host has GPUs.
|
||||
oscmd.SetMock("lspci", func(args []string) oscmd.MockCommand {
|
||||
return oscmd.MockCommand{ExitCode: 1}
|
||||
})
|
||||
// Mock nvidia-smi: return failure so enrichment is a no-op.
|
||||
oscmd.SetMock("nvidia-smi", func(args []string) oscmd.MockCommand {
|
||||
return oscmd.MockCommand{ExitCode: 1}
|
||||
})
|
||||
defer oscmd.ClearMocks()
|
||||
|
||||
// 1. Test GET /api/system/info
|
||||
|
||||
@@ -0,0 +1,73 @@
|
||||
package system
|
||||
|
||||
import (
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strconv"
|
||||
"strings"
|
||||
)
|
||||
|
||||
type Temperature struct {
|
||||
Chip string `json:"chip" example:"k10temp" doc:"hwmon chip name; identifies the source (k10temp/coretemp=CPU, amdgpu/nvidia=GPU, nvme=disk)"`
|
||||
Label string `json:"label" example:"Tctl" doc:"Per-sensor label, or the chip name when the sensor is unlabelled"`
|
||||
Celsius float64 `json:"celsius" example:"47.5"`
|
||||
}
|
||||
|
||||
func tempInfo() []Temperature {
|
||||
if t := readHwmonTemps("/sys/class/hwmon"); len(t) > 0 {
|
||||
return t
|
||||
}
|
||||
return readThermalZones("/sys/class/thermal")
|
||||
}
|
||||
|
||||
func readThermalZones(root string) []Temperature {
|
||||
zones, _ := filepath.Glob(filepath.Join(root, "thermal_zone*"))
|
||||
temps := []Temperature{}
|
||||
for _, dir := range zones {
|
||||
milli, err := strconv.Atoi(readTrim(filepath.Join(dir, "temp")))
|
||||
if err != nil {
|
||||
continue
|
||||
}
|
||||
c := float64(milli) / 1000
|
||||
if c <= 0 || c >= 150 {
|
||||
continue
|
||||
}
|
||||
name := readTrim(filepath.Join(dir, "type"))
|
||||
if name == "" {
|
||||
name = filepath.Base(dir)
|
||||
}
|
||||
temps = append(temps, Temperature{Chip: name, Label: name, Celsius: c})
|
||||
}
|
||||
return temps
|
||||
}
|
||||
|
||||
func readHwmonTemps(root string) []Temperature {
|
||||
chips, _ := filepath.Glob(filepath.Join(root, "hwmon*"))
|
||||
temps := []Temperature{}
|
||||
for _, dir := range chips {
|
||||
chip := readTrim(filepath.Join(dir, "name"))
|
||||
inputs, _ := filepath.Glob(filepath.Join(dir, "temp*_input"))
|
||||
for _, in := range inputs {
|
||||
milli, err := strconv.Atoi(readTrim(in))
|
||||
if err != nil {
|
||||
continue
|
||||
}
|
||||
c := float64(milli) / 1000
|
||||
if c <= 0 || c >= 150 {
|
||||
continue
|
||||
}
|
||||
label := readTrim(strings.TrimSuffix(in, "_input") + "_label")
|
||||
if label == "" {
|
||||
label = chip
|
||||
}
|
||||
temps = append(temps, Temperature{Chip: chip, Label: label, Celsius: c})
|
||||
}
|
||||
}
|
||||
return temps
|
||||
}
|
||||
|
||||
// readTrim reads a sysfs file and trims it; a missing file yields "".
|
||||
func readTrim(path string) string {
|
||||
b, _ := os.ReadFile(path)
|
||||
return strings.TrimSpace(string(b))
|
||||
}
|
||||
@@ -14,7 +14,6 @@ import (
|
||||
"nadir/internal/auth"
|
||||
"nadir/internal/meta"
|
||||
"nadir/internal/module"
|
||||
"nadir/internal/modules/audit"
|
||||
"nadir/internal/modules/groups"
|
||||
"nadir/internal/modules/networking"
|
||||
"nadir/internal/modules/packages"
|
||||
@@ -28,6 +27,12 @@ import (
|
||||
"github.com/danielgtaylor/huma/v2/adapters/humago"
|
||||
)
|
||||
|
||||
type auditModule struct{}
|
||||
|
||||
func (auditModule) ID() string { return "audit" }
|
||||
func (auditModule) Permissions() []rbac.Permission { return []rbac.Permission{rbac.Read} }
|
||||
func (auditModule) Register(huma.API) {}
|
||||
|
||||
func TestOpenAPISchemaNoCollisions(t *testing.T) {
|
||||
auditStore, err := auditlog.New(filepath.Join(t.TempDir(), "audit.db"))
|
||||
if err != nil {
|
||||
@@ -48,7 +53,7 @@ func TestOpenAPISchemaNoCollisions(t *testing.T) {
|
||||
packages.New(),
|
||||
networking.New(),
|
||||
storage.New(),
|
||||
audit.New(auditStore),
|
||||
auditModule{},
|
||||
}
|
||||
|
||||
mux := http.NewServeMux()
|
||||
@@ -59,6 +64,7 @@ func TestOpenAPISchemaNoCollisions(t *testing.T) {
|
||||
meta.Register(api, mods)
|
||||
meta.RegisterHealth(api, sessions)
|
||||
meta.RegisterWhoami(api, sessions, nil, roles, mods)
|
||||
meta.RegisterAudit(api, auditStore)
|
||||
auth.RegisterLogin(api, sessions, auditStore, true)
|
||||
auth.RegisterLogout(api, sessions, true)
|
||||
|
||||
|
||||
@@ -14,6 +14,7 @@ import (
|
||||
"os/exec"
|
||||
"strings"
|
||||
"sync"
|
||||
"syscall"
|
||||
"time"
|
||||
)
|
||||
|
||||
@@ -276,6 +277,23 @@ func ParseKV(lines []string) map[string]string {
|
||||
return m
|
||||
}
|
||||
|
||||
// RunDetached starts name with args in a new process group (Setsid) and returns
|
||||
// immediately once the child has started. The child is reaped in the background
|
||||
// so it does not become a zombie.
|
||||
//
|
||||
// Use this for operations where the synchronous path would kill the caller
|
||||
// (e.g. "systemctl restart nadir" would SIGTERM the process serving the
|
||||
// request before the response is written).
|
||||
func RunDetached(name string, args ...string) (*StatusOutput, error) {
|
||||
cmd := exec.Command(name, args...)
|
||||
cmd.SysProcAttr = &syscall.SysProcAttr{Setsid: true}
|
||||
if err := cmd.Start(); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
go cmd.Wait()
|
||||
return OK(), nil
|
||||
}
|
||||
|
||||
// StatusOutput is the shared response for write operations that just report
|
||||
// success. Reusing one type means all such endpoints share a single OpenAPI
|
||||
// schema.
|
||||
|
||||
Reference in New Issue
Block a user