dohertj2/scadalink-design
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

fix(site-event-log): record script errors and route queries to the active node

Browse Source 
Script execution failures were only written to Serilog, never to the
site event log — SiteRuntime did not reference the SiteEventLogging
project. ScriptExecutionActor now resolves ISiteEventLogger and emits a
'script'/'Error' event on timeout and exception.

The event-log query handler was a per-node actor bound to that node's
local SQLite. A ClusterClient query could land on the standby (which
records no events) and return nothing. The handler is now a cluster
singleton with a proxy, so queries always reach the active node.
This commit is contained in:
Joseph Doherty
2026-05-15 12:04:59 -04:00
parent 80ec16a6d0
commit 17e24ddd20
3 changed files with 33 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
src/ScadaLink.SiteRuntime/Actors/ScriptExecutionActor.cs
View File

@@ -6,6 +6,7 @@ using ScadaLink.Commons.Interfaces.Services;
using ScadaLink.Commons.Messages.ScriptExecution;
using ScadaLink.Commons.Types;
using ScadaLink.HealthMonitoring;
using ScadaLink.SiteEventLogging;
using ScadaLink.SiteRuntime.Scripts;
namespace ScadaLink.SiteRuntime.Actors;
@@ -71,6 +72,9 @@ public class ScriptExecutionActor : ReceiveActor
_ = Task.Run(async () =>
{
IServiceScope? serviceScope = null;
// ISiteEventLogger is a singleton; resolve from the root provider so
// it is available to the catch blocks regardless of scope state.
var siteEventLogger = serviceProvider?.GetService<ISiteEventLogger>();
using var cts = new CancellationTokenSource(timeout);
try
{
@@ -125,6 +129,10 @@ public class ScriptExecutionActor : ReceiveActor
var errorMsg = $"Script '{scriptName}' on instance '{instanceName}' timed out after {timeout.TotalSeconds}s";
logger.LogWarning(errorMsg);
// WP-32: Failures recorded to site event log; script NOT disabled after failure.
_ = siteEventLogger?.LogEventAsync(
"script", "Error", instanceName, $"ScriptActor:{scriptName}", errorMsg);
if (!replyTo.IsNobody())
{
replyTo.Tell(new ScriptCallResult(correlationId, false, null, errorMsg));
@@ -135,10 +143,13 @@ public class ScriptExecutionActor : ReceiveActor
catch (Exception ex)
{
healthCollector?.IncrementScriptError();
// WP-32: Failures logged to site event log; script NOT disabled after failure
// WP-32: Failures recorded to site event log; script NOT disabled after failure.
var errorMsg = $"Script '{scriptName}' on instance '{instanceName}' failed: {ex.Message}";
logger.LogError(ex, "Script execution failed: {Script} on {Instance}", scriptName, instanceName);
_ = siteEventLogger?.LogEventAsync(
"script", "Error", instanceName, $"ScriptActor:{scriptName}", errorMsg, ex.ToString());
if (!replyTo.IsNobody())
{
replyTo.Tell(new ScriptCallResult(correlationId, false, null, errorMsg));

1
src/ScadaLink.SiteRuntime/ScadaLink.SiteRuntime.csproj
View File

@@ -24,6 +24,7 @@
<ProjectReference Include="../ScadaLink.Commons/ScadaLink.Commons.csproj" />
<ProjectReference Include="../ScadaLink.Communication/ScadaLink.Communication.csproj" />
<ProjectReference Include="../ScadaLink.HealthMonitoring/ScadaLink.HealthMonitoring.csproj" />
<ProjectReference Include="../ScadaLink.SiteEventLogging/ScadaLink.SiteEventLogging.csproj" />
<ProjectReference Include="../ScadaLink.StoreAndForward/ScadaLink.StoreAndForward.csproj" />
</ItemGroup>