lerkolabs/uptop
1
1
Fork 0
Code Issues 1 Pull Requests 1 Actions Packages Projects Releases 2 Wiki Activity

feat: show error reason when monitors go DOWN
CI / test (pull_request) Successful in 2m42s
Details
CI / lint (pull_request) Successful in 1m11s
Details
CI / vulncheck (pull_request) Successful in 51s
Details

Browse Source 
Propagate check failure reasons through the entire stack:
- Checker captures specific errors (DNS, timeout, HTTP status, SSL, etc.)
- Engine tracks LastError, StatusChangedAt, LastSuccessAt per monitor
- State transitions persisted to new state_changes table
- Detail panel shows error reason, HTTP code, state duration, last
  success time, and last 5 state change events
- Monitor table shows inline error preview for DOWN services
- Alert messages include error reason
- Probe nodes forward error reasons to leader

15 files changed across models, checker, engine, store, TUI, and probes.
This commit is contained in:
Tyler Koenig
2026-05-27 19:32:30 -04:00
parent d8a2cab90f
commit bc3a44beac
15 changed files with 299 additions and 96 deletions
Download Patch File Download Diff File Expand all files Collapse all files
internal/monitor/aggregator.go
+5 -4
View File
@@ -11,10 +11,11 @@ const (
)
type NodeResult struct {
NodeID string
IsUp bool
LatencyNs int64
CheckedAt time.Time
NodeID string
IsUp bool
LatencyNs int64
CheckedAt time.Time
ErrorReason string
}
func AggregateStatus(results []NodeResult, strategy AggregationStrategy) (isUp bool, avgLatencyNs int64) {
internal/monitor/checker.go
+34 -15
View File
@@ -2,6 +2,7 @@ package monitor
import (
"context"
"fmt"
"net"
"net/http"
"strconv"
@@ -15,12 +16,13 @@ import (
)
type CheckResult struct {
SiteID int
Status string // "UP", "DOWN", "SSL EXP"
StatusCode int
LatencyNs int64
HasSSL bool
CertExpiry time.Time
SiteID int
Status string // "UP", "DOWN", "SSL EXP"
StatusCode int
LatencyNs int64
HasSSL bool
CertExpiry time.Time
ErrorReason string
}
func RunCheck(site models.Site, strict, insecure *http.Client, globalInsecure bool, allowPrivate ...bool) CheckResult {
@@ -35,7 +37,7 @@ func RunCheck(site models.Site, strict, insecure *http.Client, globalInsecure bo
if ips, err := net.LookupIP(host); err == nil {
for _, ip := range ips {
if isPrivateIP(ip) {
return CheckResult{SiteID: site.ID, Status: "DOWN"}
return CheckResult{SiteID: site.ID, Status: "DOWN", ErrorReason: "target resolves to private IP"}
}
}
}
@@ -52,7 +54,7 @@ func RunCheck(site models.Site, strict, insecure *http.Client, globalInsecure bo
case "dns":
return runDNSCheck(site)
default:
return CheckResult{SiteID: site.ID, Status: "DOWN"}
return CheckResult{SiteID: site.ID, Status: "DOWN", ErrorReason: "unsupported monitor type: " + site.Type}
}
}
@@ -68,7 +70,7 @@ func runHTTPCheck(site models.Site, strict, insecure *http.Client, globalInsecur
req, err := http.NewRequestWithContext(ctx, method, site.URL, nil)
if err != nil {
return CheckResult{SiteID: site.ID, Status: "DOWN"}
return CheckResult{SiteID: site.ID, Status: "DOWN", ErrorReason: "invalid request: " + err.Error()}
}
client := strict
@@ -88,6 +90,7 @@ func runHTTPCheck(site models.Site, strict, insecure *http.Client, globalInsecur
if err != nil {
result.Status = "DOWN"
result.ErrorReason = truncateError(err.Error(), 256)
return result
}
defer resp.Body.Close()
@@ -95,6 +98,11 @@ func runHTTPCheck(site models.Site, strict, insecure *http.Client, globalInsecur
result.StatusCode = resp.StatusCode
if !isCodeAccepted(resp.StatusCode, site.AcceptedCodes) {
result.Status = "DOWN"
expected := site.AcceptedCodes
if expected == "" {
expected = "200-299"
}
result.ErrorReason = fmt.Sprintf("HTTP %d (expected %s)", resp.StatusCode, expected)
}
if site.CheckSSL && resp.TLS != nil && len(resp.TLS.PeerCertificates) > 0 {
@@ -103,6 +111,7 @@ func runHTTPCheck(site models.Site, strict, insecure *http.Client, globalInsecur
result.CertExpiry = cert.NotAfter
if time.Now().After(cert.NotAfter) {
result.Status = "SSL EXP"
result.ErrorReason = "SSL certificate expired"
}
}
@@ -117,7 +126,7 @@ func runPingCheck(site models.Site) CheckResult {
pinger, err := probing.NewPinger(host)
if err != nil {
return CheckResult{SiteID: site.ID, Status: "DOWN"}
return CheckResult{SiteID: site.ID, Status: "DOWN", ErrorReason: "ping setup: " + err.Error()}
}
pinger.Count = 1
pinger.Timeout = siteTimeout(site)
@@ -127,8 +136,11 @@ func runPingCheck(site models.Site) CheckResult {
err = pinger.Run()
latency := time.Since(start)
if err != nil || pinger.Statistics().PacketsRecv == 0 {
return CheckResult{SiteID: site.ID, Status: "DOWN", LatencyNs: latency.Nanoseconds()}
if err != nil {
return CheckResult{SiteID: site.ID, Status: "DOWN", LatencyNs: latency.Nanoseconds(), ErrorReason: "ping failed: " + err.Error()}
}
if pinger.Statistics().PacketsRecv == 0 {
return CheckResult{SiteID: site.ID, Status: "DOWN", LatencyNs: latency.Nanoseconds(), ErrorReason: "no ICMP response"}
}
stats := pinger.Statistics()
@@ -148,7 +160,7 @@ func runPortCheck(site models.Site) CheckResult {
latency := time.Since(start)
if err != nil {
return CheckResult{SiteID: site.ID, Status: "DOWN", LatencyNs: latency.Nanoseconds()}
return CheckResult{SiteID: site.ID, Status: "DOWN", LatencyNs: latency.Nanoseconds(), ErrorReason: truncateError(err.Error(), 256)}
}
_ = conn.Close()
return CheckResult{SiteID: site.ID, Status: "UP", LatencyNs: latency.Nanoseconds()}
@@ -199,10 +211,10 @@ func runDNSCheck(site models.Site) CheckResult {
latency := time.Since(start)
if err != nil {
return CheckResult{SiteID: site.ID, Status: "DOWN", LatencyNs: latency.Nanoseconds()}
return CheckResult{SiteID: site.ID, Status: "DOWN", LatencyNs: latency.Nanoseconds(), ErrorReason: "DNS query failed: " + err.Error()}
}
if r.Rcode != dns.RcodeSuccess {
return CheckResult{SiteID: site.ID, Status: "DOWN", StatusCode: r.Rcode, LatencyNs: latency.Nanoseconds()}
return CheckResult{SiteID: site.ID, Status: "DOWN", StatusCode: r.Rcode, LatencyNs: latency.Nanoseconds(), ErrorReason: "DNS RCODE: " + dns.RcodeToString[r.Rcode]}
}
return CheckResult{SiteID: site.ID, Status: "UP", LatencyNs: latency.Nanoseconds()}
}
@@ -235,3 +247,10 @@ func isCodeAccepted(code int, accepted string) bool {
}
return false
}
func truncateError(s string, max int) string {
if len(s) <= max {
return s
}
return s[:max-3] + "..."
}
internal/monitor/monitor.go
+50 -11
View File
@@ -283,6 +283,9 @@ func (e *Engine) UpdateSiteConfig(site models.Site) {
site.LastCheck = existing.LastCheck
site.SentSSLWarning = existing.SentSSLWarning
site.FailureCount = existing.FailureCount
site.LastError = existing.LastError
site.StatusChangedAt = existing.StatusChangedAt
site.LastSuccessAt = existing.LastSuccessAt
e.liveState[site.ID] = site
e.addToTokenIndex(site)
}
@@ -393,33 +396,45 @@ func (e *Engine) checkByID(id int) {
updatedSite.CertExpiry = result.CertExpiry
updatedSite.Latency = time.Duration(result.LatencyNs)
updatedSite.LastCheck = time.Now()
e.handleStatusChange(updatedSite, result.Status, result.StatusCode, time.Duration(result.LatencyNs))
e.handleStatusChange(updatedSite, result.Status, result.StatusCode, time.Duration(result.LatencyNs), result.ErrorReason)
}
}
func (e *Engine) checkPush(site models.Site) {
deadline := site.LastCheck.Add(time.Duration(site.Interval) * time.Second).Add(pushGracePeriod)
if time.Now().After(deadline) {
e.handleStatusChange(site, "DOWN", 0, 0)
e.handleStatusChange(site, "DOWN", 0, 0, "heartbeat missed")
} else if site.Status != "UP" {
e.handleStatusChange(site, "UP", 200, 0)
e.handleStatusChange(site, "UP", 200, 0, "")
}
}
func (e *Engine) handleStatusChange(site models.Site, rawStatus string, code int, latency time.Duration) {
func (e *Engine) handleStatusChange(site models.Site, rawStatus string, code int, latency time.Duration, errorReason string) {
if !e.IsActive() {
return
}
newState := site
newState.StatusCode = code
newState.LastError = errorReason
if rawStatus == "UP" {
newState.LastSuccessAt = time.Now()
newState.LastError = ""
} else {
newState.LastSuccessAt = site.LastSuccessAt
}
if site.Status == "UP" && rawStatus != "UP" {
newState.FailureCount++
if newState.FailureCount > site.MaxRetries {
newState.Status = rawStatus
newState.FailureCount = site.MaxRetries + 1
e.AddLog(fmt.Sprintf("Monitor '%s' confirmed DOWN", site.Name))
if errorReason != "" {
e.AddLog(fmt.Sprintf("Monitor '%s' confirmed DOWN: %s", site.Name, errorReason))
} else {
e.AddLog(fmt.Sprintf("Monitor '%s' confirmed DOWN", site.Name))
}
} else {
e.AddLog(fmt.Sprintf("Monitor '%s' failed check %d/%d", site.Name, newState.FailureCount, site.MaxRetries))
}
@@ -431,6 +446,14 @@ func (e *Engine) handleStatusChange(site models.Site, rawStatus string, code int
newState.FailureCount = site.MaxRetries + 1
}
if newState.Status != site.Status && site.Status != "PENDING" {
newState.StatusChangedAt = time.Now()
} else if site.StatusChangedAt.IsZero() && newState.Status != "PENDING" {
newState.StatusChangedAt = time.Now()
} else {
newState.StatusChangedAt = site.StatusChangedAt
}
inMaint := e.isInMaintenance(site.ID)
if site.Type == "http" && site.CheckSSL && site.HasSSL {
@@ -455,12 +478,19 @@ func (e *Engine) handleStatusChange(site models.Site, rawStatus string, code int
e.recordCheck(site.ID, latency, rawStatus == "UP")
if newState.Status != site.Status && site.Status != "PENDING" {
go func() { _ = e.db.SaveStateChange(site.ID, site.Status, newState.Status, errorReason) }()
}
isBroken := func(s string) bool { return s == "DOWN" || s == "SSL EXP" }
if !isBroken(site.Status) && isBroken(newState.Status) && newState.Status != "PENDING" {
if inMaint {
e.AddLog(fmt.Sprintf("Monitor '%s' is DOWN (alerts suppressed — maintenance)", site.Name))
} else {
msg := fmt.Sprintf("Monitor '%s' is DOWN (%s)", site.Name, rawStatus)
if errorReason != "" {
msg = fmt.Sprintf("Monitor '%s' is DOWN: %s", site.Name, errorReason)
}
if site.Type == "push" {
msg = fmt.Sprintf("Push Monitor '%s' missed heartbeat.", site.Name)
}
@@ -554,16 +584,17 @@ func (e *Engine) SetAggStrategy(strategy AggregationStrategy) {
e.aggStrategy = strategy
}
func (e *Engine) IngestProbeResult(nodeID string, siteID int, latencyNs int64, isUp bool) {
func (e *Engine) IngestProbeResult(nodeID string, siteID int, latencyNs int64, isUp bool, errorReason string) {
e.probeResultsMu.Lock()
if e.probeResults[siteID] == nil {
e.probeResults[siteID] = make(map[string]NodeResult)
}
e.probeResults[siteID][nodeID] = NodeResult{
NodeID: nodeID,
IsUp: isUp,
LatencyNs: latencyNs,
CheckedAt: time.Now(),
NodeID: nodeID,
IsUp: isUp,
LatencyNs: latencyNs,
CheckedAt: time.Now(),
ErrorReason: errorReason,
}
results := make([]NodeResult, 0, len(e.probeResults[siteID]))
for _, r := range e.probeResults[siteID] {
@@ -588,7 +619,7 @@ func (e *Engine) IngestProbeResult(nodeID string, siteID int, latencyNs int64, i
updatedSite := site
updatedSite.Latency = time.Duration(avgLatency)
updatedSite.LastCheck = time.Now()
e.handleStatusChange(updatedSite, rawStatus, 0, time.Duration(avgLatency))
e.handleStatusChange(updatedSite, rawStatus, 0, time.Duration(avgLatency), errorReason)
}
func (e *Engine) GetProbeResults(siteID int) map[string]NodeResult {
@@ -601,3 +632,11 @@ func (e *Engine) GetProbeResults(siteID int) map[string]NodeResult {
}
return cp
}
func (e *Engine) GetStateChanges(siteID int, limit int) []models.StateChange {
changes, err := e.db.GetStateChanges(siteID, limit)
if err != nil {
return nil
}
return changes
}
internal/monitor/monitor_test.go
+25 -22
View File
@@ -2,10 +2,11 @@ package monitor
import (
"fmt"
"gitea.lerkolabs.com/lerko/uptop/internal/models"
"sync"
"testing"
"time"
"gitea.lerkolabs.com/lerko/uptop/internal/models"
)
// --- Mock Store ---
@@ -68,12 +69,14 @@ func (m *mockStore) GetActiveMaintenanceWindows() ([]models.MaintenanceWindow, e
func (m *mockStore) GetAllMaintenanceWindows(int) ([]models.MaintenanceWindow, error) {
return nil, nil
}
func (m *mockStore) AddMaintenanceWindow(models.MaintenanceWindow) error { return nil }
func (m *mockStore) EndMaintenanceWindow(int) error { return nil }
func (m *mockStore) DeleteMaintenanceWindow(int) error { return nil }
func (m *mockStore) GetPreference(string) (string, error) { return "", nil }
func (m *mockStore) SetPreference(string, string) error { return nil }
func (m *mockStore) Close() error { return nil }
func (m *mockStore) AddMaintenanceWindow(models.MaintenanceWindow) error { return nil }
func (m *mockStore) EndMaintenanceWindow(int) error { return nil }
func (m *mockStore) DeleteMaintenanceWindow(int) error { return nil }
func (m *mockStore) GetPreference(string) (string, error) { return "", nil }
func (m *mockStore) SetPreference(string, string) error { return nil }
func (m *mockStore) SaveStateChange(int, string, string, string) error { return nil }
func (m *mockStore) GetStateChanges(int, int) ([]models.StateChange, error) { return nil, nil }
func (m *mockStore) Close() error { return nil }
func (m *mockStore) GetAllAlerts() ([]models.AlertConfig, error) {
m.mu.Lock()
@@ -174,7 +177,7 @@ func TestHandleStatusChange_PendingToUp(t *testing.T) {
site := models.Site{ID: 1, Name: "test", Status: "PENDING", MaxRetries: 3, AlertID: 1}
injectSite(e, site)
e.handleStatusChange(site, "UP", 200, 10*time.Millisecond)
e.handleStatusChange(site, "UP", 200, 10*time.Millisecond, "")
s, _ := getSite(e, 1)
if s.Status != "UP" {
@@ -195,7 +198,7 @@ func TestHandleStatusChange_UpIncrementFailure(t *testing.T) {
site := models.Site{ID: 1, Name: "test", Status: "UP", MaxRetries: 3, FailureCount: 0}
injectSite(e, site)
e.handleStatusChange(site, "DOWN", 500, 0)
e.handleStatusChange(site, "DOWN", 500, 0, "test error")
s, _ := getSite(e, 1)
if s.Status != "UP" {
@@ -213,7 +216,7 @@ func TestHandleStatusChange_UpToDown_ExceedsRetries(t *testing.T) {
site := models.Site{ID: 1, Name: "test", Status: "UP", MaxRetries: 2, FailureCount: 2, AlertID: 1}
injectSite(e, site)
e.handleStatusChange(site, "DOWN", 500, 0)
e.handleStatusChange(site, "DOWN", 500, 0, "test error")
s, _ := getSite(e, 1)
if s.Status != "DOWN" {
@@ -236,7 +239,7 @@ func TestHandleStatusChange_UpToDown_ZeroRetries(t *testing.T) {
site := models.Site{ID: 1, Name: "test", Status: "UP", MaxRetries: 0, FailureCount: 0, AlertID: 1}
injectSite(e, site)
e.handleStatusChange(site, "DOWN", 0, 0)
e.handleStatusChange(site, "DOWN", 0, 0, "test error")
s, _ := getSite(e, 1)
if s.Status != "DOWN" {
@@ -255,7 +258,7 @@ func TestHandleStatusChange_DownToUp_Recovery(t *testing.T) {
site := models.Site{ID: 1, Name: "test", Status: "DOWN", FailureCount: 4, AlertID: 1}
injectSite(e, site)
e.handleStatusChange(site, "UP", 200, 5*time.Millisecond)
e.handleStatusChange(site, "UP", 200, 5*time.Millisecond, "")
s, _ := getSite(e, 1)
if s.Status != "UP" {
@@ -276,7 +279,7 @@ func TestHandleStatusChange_DownStaysDown(t *testing.T) {
site := models.Site{ID: 1, Name: "test", Status: "DOWN", MaxRetries: 2, FailureCount: 3}
injectSite(e, site)
e.handleStatusChange(site, "DOWN", 0, 0)
e.handleStatusChange(site, "DOWN", 0, 0, "test error")
s, _ := getSite(e, 1)
if s.Status != "DOWN" {
@@ -295,7 +298,7 @@ func TestHandleStatusChange_SSLExpired(t *testing.T) {
site := models.Site{ID: 1, Name: "test", Status: "UP", MaxRetries: 0, AlertID: 1}
injectSite(e, site)
e.handleStatusChange(site, "SSL EXP", 0, 0)
e.handleStatusChange(site, "SSL EXP", 0, 0, "SSL certificate expired")
s, _ := getSite(e, 1)
if s.Status != "SSL EXP" {
@@ -315,7 +318,7 @@ func TestHandleStatusChange_AlertSuppressedMaintenance(t *testing.T) {
site := models.Site{ID: 1, Name: "test", Status: "UP", MaxRetries: 0, AlertID: 1}
injectSite(e, site)
e.handleStatusChange(site, "DOWN", 0, 0)
e.handleStatusChange(site, "DOWN", 0, 0, "test error")
s, _ := getSite(e, 1)
if s.Status != "DOWN" {
@@ -346,7 +349,7 @@ func TestHandleStatusChange_RecoverySuppressedMaintenance(t *testing.T) {
site := models.Site{ID: 1, Name: "test", Status: "DOWN", AlertID: 1}
injectSite(e, site)
e.handleStatusChange(site, "UP", 200, 0)
e.handleStatusChange(site, "UP", 200, 0, "")
s, _ := getSite(e, 1)
if s.Status != "UP" {
@@ -370,7 +373,7 @@ func TestHandleStatusChange_SSLWarning(t *testing.T) {
}
injectSite(e, site)
e.handleStatusChange(site, "UP", 200, 0)
e.handleStatusChange(site, "UP", 200, 0, "")
s, _ := getSite(e, 1)
if !s.SentSSLWarning {
@@ -393,7 +396,7 @@ func TestHandleStatusChange_SSLWarningNotRepeated(t *testing.T) {
}
injectSite(e, site)
e.handleStatusChange(site, "UP", 200, 0)
e.handleStatusChange(site, "UP", 200, 0, "")
waitAsync()
if len(ms.getAlertCallsSnapshot()) != 0 {
@@ -412,7 +415,7 @@ func TestHandleStatusChange_SSLWarningReset(t *testing.T) {
}
injectSite(e, site)
e.handleStatusChange(site, "UP", 200, 0)
e.handleStatusChange(site, "UP", 200, 0, "")
s, _ := getSite(e, 1)
if s.SentSSLWarning {
@@ -433,7 +436,7 @@ func TestHandleStatusChange_SSLWarningSuppressedMaint(t *testing.T) {
}
injectSite(e, site)
e.handleStatusChange(site, "UP", 200, 0)
e.handleStatusChange(site, "UP", 200, 0, "")
s, _ := getSite(e, 1)
if !s.SentSSLWarning {
@@ -452,7 +455,7 @@ func TestHandleStatusChange_InactiveEngine(t *testing.T) {
injectSite(e, site)
e.SetActive(false)
e.handleStatusChange(site, "DOWN", 0, 0)
e.handleStatusChange(site, "DOWN", 0, 0, "test error")
s, _ := getSite(e, 1)
if s.Status != "UP" {
@@ -991,7 +994,7 @@ func TestConcurrent_HandleStatusChangeAndGetState(t *testing.T) {
wg.Add(2)
go func() {
defer wg.Done()
e.handleStatusChange(site, "DOWN", 500, 0)
e.handleStatusChange(site, "DOWN", 500, 0, "test error")
}()
go func() {
defer wg.Done()