maxim/ProxmoxDash
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 47 Wiki Activity

Expand guest agent system monitoring

Browse Source
This commit is contained in:
Maxim
2026-08-06 20:48:27 +03:00
parent f1ff15e344
commit c618eb018c
5 changed files with 221 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

185
agent.go
View File

@@ -14,10 +14,12 @@ import (
"net"
"net/http"
"os"
"os/exec"
"path/filepath"
"runtime"
"strconv"
"strings"
"sync"
"syscall"
"time"
)
@@ -50,23 +52,56 @@ type AgentContainer struct {
Ports []string `json:"ports,omitempty"`
}
type AgentInterface struct {
Name string `json:"name"`
Addresses []string `json:"addresses"`
}
type AgentService struct {
Name string `json:"name"`
State string `json:"state"`
SubState string `json:"subState"`
Description string `json:"description"`
}
type AgentReport struct {
Hostname string `json:"hostname"`
MachineID string `json:"machineId"`
Version string `json:"version"`
OS string `json:"os"`
Arch string `json:"arch"`
UptimeSeconds int64 `json:"uptimeSeconds"`
Load1 float64 `json:"load1"`
CPUPercent float64 `json:"cpuPercent"`
MemoryTotal uint64 `json:"memoryTotal"`
MemoryUsed uint64 `json:"memoryUsed"`
RootTotal uint64 `json:"rootTotal"`
RootUsed uint64 `json:"rootUsed"`
DockerAvailable bool `json:"dockerAvailable"`
DockerError string `json:"dockerError,omitempty"`
Containers []AgentContainer `json:"containers"`
CollectedAt int64 `json:"collectedAt"`
Hostname string `json:"hostname"`
MachineID string `json:"machineId"`
Version string `json:"version"`
OS string `json:"os"`
Arch string `json:"arch"`
OSName string `json:"osName"`
Kernel string `json:"kernel"`
UptimeSeconds int64 `json:"uptimeSeconds"`
Load1 float64 `json:"load1"`
CPUPercent float64 `json:"cpuPercent"`
MemoryTotal uint64 `json:"memoryTotal"`
MemoryUsed uint64 `json:"memoryUsed"`
RootTotal uint64 `json:"rootTotal"`
RootUsed uint64 `json:"rootUsed"`
DockerAvailable bool `json:"dockerAvailable"`
DockerError string `json:"dockerError,omitempty"`
Containers []AgentContainer `json:"containers"`
Interfaces []AgentInterface `json:"interfaces"`
Services []AgentService `json:"services"`
UpdatesAvailable int `json:"updatesAvailable"`
RebootRequired bool `json:"rebootRequired"`
InventoryAt int64 `json:"inventoryAt"`
CollectedAt int64 `json:"collectedAt"`
}
type agentInventory struct {
OSName string
Kernel string
Services []AgentService
UpdatesAvailable int
RebootRequired bool
CollectedAt time.Time
}
var guestInventory struct {
sync.Mutex
value agentInventory
}
type ManagedAgent struct {
@@ -287,6 +322,7 @@ func collectAgentReport() AgentReport {
}
}
report.CPUPercent = sampleAgentCPU()
report.Interfaces = collectAgentInterfaces()
if data, err := os.ReadFile("/proc/meminfo"); err == nil {
values := map[string]uint64{}
for _, line := range strings.Split(string(data), "\n") {
@@ -312,9 +348,113 @@ func collectAgentReport() AgentReport {
}
report.Containers, report.DockerError = collectDockerContainers()
report.DockerAvailable = report.DockerError == ""
inventory := cachedAgentInventory()
report.OSName, report.Kernel, report.Services = inventory.OSName, inventory.Kernel, inventory.Services
report.UpdatesAvailable, report.RebootRequired, report.InventoryAt = inventory.UpdatesAvailable, inventory.RebootRequired, inventory.CollectedAt.Unix()
return report
}
func collectAgentInterfaces() []AgentInterface {
interfaces, err := net.Interfaces()
if err != nil {
return nil
}
result := []AgentInterface{}
for _, iface := range interfaces {
if iface.Flags&net.FlagLoopback != 0 {
continue
}
addresses, _ := iface.Addrs()
item := AgentInterface{Name: iface.Name}
for _, address := range addresses {
value := address.String()
if host, _, err := net.ParseCIDR(value); err == nil {
value = host.String()
}
item.Addresses = append(item.Addresses, value)
}
if len(item.Addresses) > 0 {
result = append(result, item)
}
}
return result
}
func cachedAgentInventory() agentInventory {
guestInventory.Lock()
defer guestInventory.Unlock()
if time.Since(guestInventory.value.CollectedAt) < 15*time.Minute {
return guestInventory.value
}
value := agentInventory{CollectedAt: time.Now()}
value.OSName = readOSPrettyName()
value.Kernel = strings.TrimSpace(runAgentCommand(3*time.Second, "uname", "-r"))
value.Services = collectAgentServices()
value.UpdatesAvailable = countAgentUpdates()
_, err := os.Stat("/var/run/reboot-required")
value.RebootRequired = err == nil
guestInventory.value = value
return value
}
func readOSPrettyName() string {
data, err := os.ReadFile("/etc/os-release")
if err != nil {
return runtime.GOOS
}
for _, line := range strings.Split(string(data), "\n") {
if strings.HasPrefix(line, "PRETTY_NAME=") {
return strings.Trim(strings.TrimPrefix(line, "PRETTY_NAME="), "\"")
}
}
return runtime.GOOS
}
func runAgentCommand(timeout time.Duration, name string, args ...string) string {
ctx, cancel := context.WithTimeout(context.Background(), timeout)
defer cancel()
output, err := exec.CommandContext(ctx, name, args...).Output()
if err != nil {
return ""
}
return string(output)
}
func collectAgentServices() []AgentService {
output := runAgentCommand(5*time.Second, "systemctl", "list-units", "--type=service", "--state=running,failed", "--no-legend", "--plain", "--no-pager")
result := []AgentService{}
for _, line := range strings.Split(output, "\n") {
fields := strings.Fields(line)
offset := 0
if len(fields) > 0 && fields[0] == "●" {
offset = 1
}
if len(fields) < offset+4 {
continue
}
description := ""
if len(fields) > offset+4 {
description = strings.Join(fields[offset+4:], " ")
}
result = append(result, AgentService{Name: fields[offset], State: fields[offset+2], SubState: fields[offset+3], Description: description})
if len(result) >= 150 {
break
}
}
return result
}
func countAgentUpdates() int {
output := runAgentCommand(45*time.Second, "apt-get", "-s", "-o", "Debug::NoLocking=1", "upgrade")
count := 0
for _, line := range strings.Split(output, "\n") {
if strings.HasPrefix(line, "Inst ") {
count++
}
}
return count
}
func sampleAgentCPU() float64 {
total1, idle1 := readAgentCPU()
time.Sleep(100 * time.Millisecond)
@@ -323,6 +463,9 @@ func sampleAgentCPU() float64 {
return 0
}
totalDelta, idleDelta := total2-total1, idle2-idle1
if idleDelta > totalDelta {
return 0
}
return float64(totalDelta-idleDelta) / float64(totalDelta) * 100
}
@@ -357,6 +500,7 @@ func collectDockerContainers() ([]AgentContainer, string) {
transport := &http.Transport{DialContext: func(ctx context.Context, _, _ string) (net.Conn, error) {
return (&net.Dialer{}).DialContext(ctx, "unix", "/var/run/docker.sock")
}}
defer transport.CloseIdleConnections()
client := &http.Client{Transport: transport, Timeout: 5 * time.Second}
response, err := client.Get("http://docker/containers/json?all=1")
if err != nil {
@@ -423,8 +567,13 @@ func collectDockerContainers() ([]AgentContainer, string) {
} `json:"memory_stats"`
}
if json.NewDecoder(statsResponse.Body).Decode(&stats) == nil {
cpuDelta := stats.CPUStats.CPUUsage.TotalUsage - stats.PreCPUStats.CPUUsage.TotalUsage
systemDelta := stats.CPUStats.SystemCPUUsage - stats.PreCPUStats.SystemCPUUsage
cpuDelta, systemDelta := uint64(0), uint64(0)
if stats.CPUStats.CPUUsage.TotalUsage >= stats.PreCPUStats.CPUUsage.TotalUsage {
cpuDelta = stats.CPUStats.CPUUsage.TotalUsage - stats.PreCPUStats.CPUUsage.TotalUsage
}
if stats.CPUStats.SystemCPUUsage >= stats.PreCPUStats.SystemCPUUsage {
systemDelta = stats.CPUStats.SystemCPUUsage - stats.PreCPUStats.SystemCPUUsage
}
cpus := stats.CPUStats.OnlineCPUs
if cpus == 0 {
cpus = 1