0.0.1-alpha.7

.github/workflows/docker-images.yml

@@ -30,7 +30,7 @@ jobs:
         uses: oven-sh/setup-bun@v2
 
       - name: Install dependencies
-        run: bun install --cwd ./hub/site
+        run: bun install --no-save --cwd ./hub/site
 
       - name: Build site
         run: bun run --cwd ./hub/site build

.github/workflows/goreleaser-action.yml

@@ -21,7 +21,7 @@ jobs:
         uses: oven-sh/setup-bun@v2
 
       - name: Install dependencies
-        run: bun install --cwd ./hub/site
+        run: bun install --no-save --cwd ./hub/site
 
       - name: Build site
         run: bun run --cwd ./hub/site build

.gitignore

@@ -6,4 +6,5 @@ temp
 beszel
 beszel-agent
 beszel_data
+beszel_data*
 dist

agent/docker-compose.yml

@@ -5,7 +5,7 @@ services:
     restart: unless-stopped
     network_mode: host
     volumes:
-      - /var/run/docker.sock:/var/run/docker.sock
+      - /var/run/docker.sock:/var/run/docker.sock:ro
     environment:
       PORT: 45876
       KEY: 'ssh-ed25519 YOUR_PUBLIC_KEY'

agent/main.go

@@ -2,7 +2,6 @@ package main
 
 import (
 	"encoding/json"
-	"errors"
 	"fmt"
 	"io"
 	"log"
@@ -11,7 +10,6 @@ import (
 	"net/http"
 	"os"
 	"strings"
-	"sync"
 	"time"
 
 	sshServer "github.com/gliderlabs/ssh"
@@ -23,10 +21,11 @@ import (
 	psutilNet "github.com/shirou/gopsutil/v4/net"
 )
 
-var Version = "0.0.1-alpha.5"
+var Version = "0.0.1-alpha.7"
 
 var containerCpuMap = make(map[string][2]uint64)
-var containerCpuMutex = &sync.Mutex{}
+
+// var containerCpuMutex = &sync.Mutex{}
 
 var diskIoStats = DiskIoStats{
 	Read:       0,
@@ -44,16 +43,16 @@ var netIoStats = NetIoStats{
 
 // client for docker engine api
 var client = &http.Client{
-	Timeout: time.Second * 5,
+	Timeout: time.Second,
 	Transport: &http.Transport{
 		Dial: func(proto, addr string) (net.Conn, error) {
 			return net.Dial("unix", "/var/run/docker.sock")
 		},
-		ForceAttemptHTTP2:   false,
-		MaxIdleConns:        100,
-		MaxIdleConnsPerHost: 100,
-		IdleConnTimeout:     90 * time.Second,
-		DisableKeepAlives:   false,
+		ForceAttemptHTTP2:  false,
+		IdleConnTimeout:    90 * time.Second,
+		DisableCompression: true,
+		MaxIdleConns:       10,
+		DisableKeepAlives:  false,
 	},
 }
 
@@ -194,20 +193,19 @@ func getDockerStats() ([]ContainerStats, error) {
 		panic(err)
 	}
 
-	var wg sync.WaitGroup
 	var containerStats []ContainerStats
 
 	for _, ctr := range containers {
-		wg.Add(1)
-		go func() {
-			defer wg.Done()
-			cstats, err := getContainerStats(ctr)
+		cstats, err := getContainerStats(ctr)
+		if err != nil {
+			// retry once
+			cstats, err = getContainerStats(ctr)
 			if err != nil {
 				log.Printf("Error getting container stats: %+v\n", err)
-				return
+				continue
 			}
-			containerStats = append(containerStats, cstats)
-		}()
+		}
+		containerStats = append(containerStats, cstats)
 	}
 
 	// clean up old containers from map
@@ -221,8 +219,6 @@ func getDockerStats() ([]ContainerStats, error) {
 		}
 	}
 
-	wg.Wait()
-
 	return containerStats, nil
 }
 
@@ -246,8 +242,8 @@ func getContainerStats(ctr Container) (ContainerStats, error) {
 
 	// cpu
 	// add default values to containerCpu if it doesn't exist
-	containerCpuMutex.Lock()
-	defer containerCpuMutex.Unlock()
+	// containerCpuMutex.Lock()
+	// defer containerCpuMutex.Unlock()
 	if _, ok := containerCpuMap[name]; !ok {
 		containerCpuMap[name] = [2]uint64{0, 0}
 	}
@@ -255,7 +251,7 @@ func getContainerStats(ctr Container) (ContainerStats, error) {
 	systemDelta := statsJson.CPUStats.SystemUsage - containerCpuMap[name][1]
 	cpuPct := float64(cpuDelta) / float64(systemDelta) * 100
 	if cpuPct > 100 {
-		return ContainerStats{}, errors.New("cpu pct is greater than 100")
+		return ContainerStats{}, fmt.Errorf("%s cpu pct greater than 100: %+v", name, cpuPct)
 	}
 	containerCpuMap[name] = [2]uint64{statsJson.CPUStats.CPUUsage.TotalUsage, statsJson.CPUStats.SystemUsage}
 

hub/dockerfile

@@ -31,4 +31,4 @@ COPY --from=builder /etc/ssl/certs/ca-certificates.crt /etc/ssl/certs/
 EXPOSE 8090
 
 ENTRYPOINT [ "/beszel" ]
-CMD ["serve", "--http=localhost:8090"]
+CMD ["serve", "--http=0.0.0.0:8090"]

hub/main.go

@@ -15,24 +15,26 @@ import (
 	"net/url"
 	"os"
 	"strings"
+	"sync"
 	"time"
 
 	"github.com/labstack/echo/v5"
-	"github.com/pocketbase/dbx"
 	"github.com/pocketbase/pocketbase"
 	"github.com/pocketbase/pocketbase/apis"
 	"github.com/pocketbase/pocketbase/core"
 	"github.com/pocketbase/pocketbase/models"
 	"github.com/pocketbase/pocketbase/plugins/migratecmd"
 	"github.com/pocketbase/pocketbase/tools/cron"
+	"github.com/pocketbase/pocketbase/tools/types"
 	"github.com/spf13/cobra"
 	"golang.org/x/crypto/ssh"
 )
 
-var Version = "0.0.1-alpha.5"
+var Version = "0.0.1-alpha.7"
 
 var app *pocketbase.PocketBase
-var serverConnections = make(map[string]Server)
+var serverConnections = make(map[string]*Server)
+var serverConnectionsLock = sync.Mutex{}
 
 func main() {
 	app = pocketbase.NewWithConfig(pocketbase.Config{
@@ -207,49 +209,53 @@ func startSystemUpdateTicker() {
 }
 
 func updateSystems() {
-	// handle max of 1/3 + 1 servers at a time
-	numServers := len(serverConnections)/3 + 1
-	// find systems that are not paused and updated more than 58 seconds ago
-	fiftyEightSecondsAgo := time.Now().UTC().Add(-58 * time.Second).Format("2006-01-02 15:04:05")
 	records, err := app.Dao().FindRecordsByFilter(
-		"2hz5ncl8tizk5nx", // collection
-		"status != 'paused' && updated < {:updated}", // filter
-		"updated",  // sort
-		numServers, // limit
-		0,          // offset
-		dbx.Params{"updated": fiftyEightSecondsAgo},
+		"2hz5ncl8tizk5nx",    // collection
+		"status != 'paused'", // filter
+		"updated",            // sort
+		-1,                   // limit
+		0,                    // offset
 	)
+	// log.Println("records", len(records))
 	if err != nil {
 		app.Logger().Error("Failed to query systems: ", "err", err.Error())
 		return
 	}
-	for _, record := range records {
-		updateSystem(record)
+	fiftyFiveSecondsAgo := time.Now().UTC().Add(-55 * time.Second)
+	batchSize := len(records)/4 + 1
+	for i := 0; i < batchSize; i++ {
+		if records[i].Get("updated").(types.DateTime).Time().After(fiftyFiveSecondsAgo) {
+			break
+		}
+		// log.Println("updating", records[i].Get(("name")))
+		go updateSystem(records[i])
 	}
 }
 
 func updateSystem(record *models.Record) {
-	var server Server
+	var server *Server
 	// check if server connection data exists
 	if _, ok := serverConnections[record.Id]; ok {
 		server = serverConnections[record.Id]
 	} else {
 		// create server connection struct
-		server = Server{
+		server = &Server{
 			Host: record.Get("host").(string),
 			Port: record.Get("port").(string),
 		}
-		client, err := getServerConnection(&server)
+		client, err := getServerConnection(server)
 		if err != nil {
 			app.Logger().Error("Failed to connect:", "err", err.Error(), "server", server.Host, "port", server.Port)
 			updateServerStatus(record, "down")
 			return
 		}
 		server.Client = client
+		serverConnectionsLock.Lock()
 		serverConnections[record.Id] = server
+		serverConnectionsLock.Unlock()
 	}
 	// get server stats from agent
-	systemData, err := requestJson(&server)
+	systemData, err := requestJson(server)
 	if err != nil {
 		if err.Error() == "retry" {
 			// if previous connection was closed, try again
@@ -310,6 +316,8 @@ func deleteServerConnection(record *models.Record) {
 		if serverConnections[record.Id].Client != nil {
 			serverConnections[record.Id].Client.Close()
 		}
+		serverConnectionsLock.Lock()
+		defer serverConnectionsLock.Unlock()
 		delete(serverConnections, record.Id)
 	}
 }

hub/site/src/components/add-system.tsx

@@ -32,7 +32,7 @@ export function AddSystemButton() {
     restart: unless-stopped
     network_mode: host
     volumes:
-      - /var/run/docker.sock:/var/run/docker.sock
+      - /var/run/docker.sock:/var/run/docker.sock:ro
     environment:
       PORT: ${port}
       KEY: "${publicKey}"

hub/site/src/components/charts/bandwidth-chart.tsx

@@ -47,7 +47,13 @@ export default function BandwidthChart({
 				<YAxis
 					className="tracking-tighter"
 					width={75}
-					domain={[0, (max: number) => (max < 0.4 ? 0.4 : Math.ceil(max))]}
+					domain={[0, (max: number) => (max <= 0.4 ? 0.4 : Math.ceil(max))]}
+					tickFormatter={(value) => {
+						if (value >= 100) {
+							return value.toFixed(0)
+						}
+						return value.toFixed((value * 100) % 1 === 0 ? 1 : 2)
+					}}
 					tickLine={false}
 					axisLine={false}
 					unit={' MB/s'}

hub/site/src/components/charts/container-cpu-chart.tsx

@@ -69,7 +69,7 @@ export default function ContainerCpuChart({
 			>
 				<CartesianGrid vertical={false} />
 				<YAxis
-					domain={[0, (max: number) => Math.max(Math.ceil(max), 0.4)]}
+					// domain={[0, (max: number) => Math.max(Math.ceil(max), 0.4)]}
 					width={47}
 					tickLine={false}
 					axisLine={false}

hub/site/src/components/charts/disk-io-chart.tsx

@@ -47,7 +47,7 @@ export default function DiskIoChart({
 				<YAxis
 					className="tracking-tighter"
 					width={75}
-					domain={[0, (max: number) => (max < 0.4 ? 0.4 : Math.ceil(max))]}
+					domain={[0, (max: number) => (max <= 0.4 ? 0.4 : Math.ceil(max))]}
 					tickFormatter={(value) => {
 						if (value >= 100) {
 							return value.toFixed(0)

hub/site/src/components/table-alerts.tsx

@@ -71,21 +71,21 @@ export default function AlertsButton({ system }: { system: SystemRecord }) {
 						system={system}
 						alerts={systemAlerts}
 						name="CPU"
-						title="CPU usage"
+						title="CPU Usage"
 						description="Triggers when CPU usage exceeds a threshold."
 					/>
 					<AlertWithSlider
 						system={system}
 						alerts={systemAlerts}
 						name="Memory"
-						title="Memory usage"
+						title="Memory Usage"
 						description="Triggers when memory usage exceeds a threshold."
 					/>
 					<AlertWithSlider
 						system={system}
 						alerts={systemAlerts}
 						name="Disk"
-						title="Disk usage"
+						title="Disk Usage"
 						description="Triggers when disk usage exceeds a threshold."
 					/>
 				</div>
@@ -104,11 +104,11 @@ function AlertStatus({ system, alerts }: { system: SystemRecord; alerts: AlertRe
 	return (
 		<label
 			htmlFor="alert-status"
-			className="space-y-2 flex flex-row items-center justify-between rounded-lg border p-4 cursor-pointer"
+			className="flex flex-row items-center justify-between gap-4 rounded-lg border p-4 cursor-pointer"
 		>
-			<div className="grid gap-0.5 select-none">
-				<p className="font-medium text-[1.05em]">System status</p>
-				<span className="block text-[0.85em] text-foreground opacity-80">
+			<div className="grid gap-1 select-none">
+				<p className="font-semibold">System Status</p>
+				<span className="block text-sm text-foreground opacity-80">
 					Triggers when status switches between up and down.
 				</span>
 			</div>
@@ -171,13 +171,13 @@ function AlertWithSlider({
 		<div className="rounded-lg border">
 			<label
 				htmlFor={`alert-${name}`}
-				className={cn('space-y-2 flex flex-row items-center justify-between cursor-pointer p-4', {
+				className={cn('flex flex-row items-center justify-between gap-4 cursor-pointer p-4', {
 					'pb-0': !!alert,
 				})}
 			>
-				<div className="grid gap-0.5 select-none">
-					<p className="font-medium text-[1.05em]">{title}</p>
-					<span className="block text-[0.85em] text-foreground opacity-80">{description}</span>
+				<div className="grid gap-1 select-none">
+					<p className="font-semibold">{title}</p>
+					<span className="block text-sm text-foreground opacity-80">{description}</span>
 				</div>
 				<Switch
 					id={`alert-${name}`}

readme.md

@@ -1,28 +1,22 @@
-# Beszel \*WIP\*
+# Beszel
 
 A lightweight server resource monitoring hub with historical data, docker stats, and alerts.
 
-<!-- <table width="100%">
-  <tbody>
-    <tr>
-      <td width="50%"><img src="https://henrygd-assets.b-cdn.net/social-image-server/before-capture.png" alt="example of turso.tech/pricing link which is missing an og:image as of may 11 2024"/></td>
-      <td width="50%"><img src="https://henrygd-assets.b-cdn.net/social-image-server/after-capture.webp" alt="example of turso.tech/pricing link using an image generated by the server as it's og:image"/></td>
-    </tr>
-  </tbody>
-</table> -->
+[![Docker Image Size (tag)](https://img.shields.io/docker/image-size/henrygd/beszel-agent/0.0.1-alpha.6?logo=docker&label=agent%20image%20size)](https://hub.docker.com/r/henrygd/beszel-agent)
+[![Docker Image Size (tag)](https://img.shields.io/docker/image-size/henrygd/beszel/0.0.1-alpha.6?logo=docker&label=hub%20image%20size)](https://hub.docker.com/r/henrygd/beszel)
 
-<!-- ## Features
+![Screenshot of the hub](https://henrygd-assets.b-cdn.net/beszel/screenshot.png)
+
+## Features
 
 - **Lightweight**: Much smaller and less demanding than leading solutions.
-- **Historical data**: Stats are available for up to 30 days.
 - **Docker stats**: CPU and memory usage history for each container.
-- **Alerts**: Lorem ipsum dolor sit amet, consectetur adipiscing elit.
-- **Simple**: Lorem ipsum dolor sit amet, consectetur adipiscing elit.
+- **Alerts**: Configurable alerts for CPU, memory, and disk usage, and system status.
 - **Multi-user**: Each user has their own systems. Admins can share systems across users.
-- **Secure**: Lorem ipsum dolor sit amet, consectetur adipiscing elit.
-- **Oauth / OIDC**: Supports many OAuth2 providers and password auth can be disabled.
-- **Automated backups**: Automatically back up your data to S3-compatible storage.
-- **Open source**: MIT license and no paywalled features. -->
+- **Simple**: Easy setup and doesn't require anything to be publicly available online.
+- **OAuth / OIDC**: Supports many OAuth2 providers. Password auth can be disabled.
+- **Automated backups**: Automatically back up your data to disk or S3-compatible storage.
+- **REST API**: Use your metrics in your own scripts and applications.
 
 ## Introduction
 
@@ -32,9 +26,6 @@ The hub is a web application that provides a dashboard to view and manage your c
 
 The agent runs on each system you want to monitor. It creates a minimal SSH server through which it communicates system metrics to the hub.
 
-[![Docker Image Size (tag)](https://img.shields.io/docker/image-size/henrygd/beszel-agent/0.0.1-alpha.3?logo=docker&label=agent%20image%20size)](https://hub.docker.com/r/henrygd/beszel-agent)
-[![Docker Image Size (tag)](https://img.shields.io/docker/image-size/henrygd/beszel/0.0.1-alpha.3?logo=docker&label=hub%20image%20size)](https://hub.docker.com/r/henrygd/beszel)
-
 ## Getting started
 
 If using the binary instead of docker, ignore 4-5 and run the agent using the binary instead.
@@ -169,3 +160,8 @@ If it's not set, the agent will try to find the filesystem mounted on `/` and us
 Records for longer time periods are made by averaging stats from the shorter time periods. They require the agent to be running uninterrupted for long enough to get a full set of data.
 
 If you pause / unpause the agent for longer than one minute, the data will be incomplete and the timing for the current interval will reset.
+
+<!--
+## Support
+
+My country, the USA, and many others, are actively involved in the genocide of the Palestinian people. I would greatly appreciate any effort you could make to pressure your government to stop enabling this violence. -->