feat(hosts): driver diagnostics channel on /hosts, S7 negotiated PDU size first (#640)

Claude-Session: https://claude.ai/code/session_01Ef2ozxS7QPanGT8uoATbTe
This commit is contained in:
Joseph Doherty
2026-10-08 16:57:38 -04:00
parent a8b07ae12d
commit c2bdb7d5de
23 changed files with 469 additions and 20 deletions
@@ -189,6 +189,17 @@ else
@* Own line — inline after the name the two identifiers ran together. *@
<div class="mono small text-muted">@d.DriverInstanceId</div>
}
@if (d.DiagnosticItems.Count > 0)
{
@* Driver-reported diagnostics (Gitea #640), e.g. S7 negotiated PDU size.
Renders nothing for a driver with none. *@
<div class="small text-muted" data-testid="driver-diagnostics">
@foreach (var kv in d.DiagnosticItems)
{
<div class="mono">@kv.Key: @kv.Value</div>
}
</div>
}
</td>
<td>@(d.DriverType ?? "—")</td>
<td><span class="chip @DriverChipClass(d.State)">@d.State</span></td>
@@ -52,6 +52,8 @@ public sealed record HostsDriverInstanceInfo(
/// is no answer — the driver cannot report skips, or it faulted before building a tag table. Lets
/// "ignoring 20 of 22 tags" show even while every other column on the row — state, last read, error
/// count, last error — reads perfectly healthy (Gitea #541).</param>
/// <param name="Diagnostics">Driver-reported diagnostics (e.g. S7 negotiated PDU size); null or empty when
/// the driver has none to show (Gitea #640).</param>
/// <param name="Enabled">Whether the matching configured instance is authored enabled; <see langword="true"/>
/// when no instance matched. Fed to the row's expandable <c>DriverStatusPanel</c> (Gitea #546). An
/// unmatched row defaults to enabled on purpose: the row only exists because a live snapshot arrived,
@@ -62,8 +64,16 @@ public sealed record HostsDriverRow(
DateTime? RediscoveryNeededUtc = null, string? RediscoveryReason = null,
IReadOnlyList<HostConnectivityStatus>? HostStatuses = null,
SkippedTagReport? SkippedTags = null,
bool Enabled = true)
bool Enabled = true,
IReadOnlyDictionary<string, string>? Diagnostics = null)
{
/// <summary>Diagnostics as ordered key/value pairs for rendering; empty when there are none, in which
/// case the page renders nothing.</summary>
public IReadOnlyList<KeyValuePair<string, string>> DiagnosticItems { get; } =
(Diagnostics ?? new Dictionary<string, string>())
.OrderBy(k => k.Key, StringComparer.Ordinal)
.ToList();
/// <summary>Whether this driver is ignoring at least one authored tag — the condition the whole
/// column exists to make visible.</summary>
public bool HasSkippedTags => SkippedTags is { SkippedCount: > 0 };
@@ -177,7 +187,8 @@ public static class HostsDriverView
s.RediscoveryReason,
s.HostStatuses,
s.SkippedTags,
instance?.Enabled ?? true);
instance?.Enabled ?? true,
s.Diagnostics);
})
.OrderBy(d => d.Name ?? d.DriverInstanceId, StringComparer.OrdinalIgnoreCase)
.ThenBy(d => d.DriverInstanceId, StringComparer.OrdinalIgnoreCase)
@@ -130,7 +130,8 @@ public static class TelemetryProtoMapCentral
RediscoveryNeededUtc: msg.RediscoveryNeededUtc?.ToDateTime(),
RediscoveryReason: msg.HasRediscoveryReason ? msg.RediscoveryReason : null,
HostStatuses: ToHostStatuses(msg),
SkippedTags: ToSkippedTags(msg));
SkippedTags: ToSkippedTags(msg),
Diagnostics: msg.HasDiagnostics ? new Dictionary<string, string>(msg.Diagnostics) : null);
}
/// <summary>
@@ -164,6 +164,14 @@ public static class TelemetryProtoMapNode
msg.SkippedTags = payload;
}
// Gitea #640. Presence flag first - an empty map cannot say whether the driver has the capability.
if (e.Diagnostics is not null)
{
msg.HasDiagnostics = true;
foreach (var kv in e.Diagnostics)
msg.Diagnostics[kv.Key ?? ""] = kv.Value ?? "";
}
return msg;
}
@@ -38,7 +38,8 @@ public sealed class AkkaDriverHealthPublisher : IDriverHealthPublisher
DateTime? rediscoveryNeededUtc = null,
string? rediscoveryReason = null,
IReadOnlyList<HostConnectivityStatus>? hostStatuses = null,
SkippedTagReport? skippedTags = null)
SkippedTagReport? skippedTags = null,
IReadOnlyDictionary<string, string>? diagnostics = null)
{
var msg = new DriverHealthChanged(
clusterId,
@@ -51,7 +52,8 @@ public sealed class AkkaDriverHealthPublisher : IDriverHealthPublisher
rediscoveryNeededUtc,
rediscoveryReason,
hostStatuses,
skippedTags);
skippedTags,
diagnostics);
DistributedPubSub.Get(_system).Mediator.Tell(new Publish(TopicName, msg));
// Phase 5: fan the same snapshot into the node-local live-telemetry hub (no-op until a gRPC
// client subscribes). The DPS publish above is unchanged — the hub is a strictly additive tap.
@@ -1153,6 +1153,28 @@ public sealed class DriverInstanceActor : ReceiveActor, IWithTimers
}
}
/// <summary>Bounded driver diagnostics, or null when the driver is not an <see cref="IDriverDiagnostics"/>
/// (Gitea #640). Pulled fresh and called UNGUARDED for the same reasons as
/// <see cref="CurrentSkippedTags"/>; a throwing implementation loses only the diagnostics.</summary>
private IReadOnlyDictionary<string, string>? CurrentDiagnostics()
{
if (_driver is not IDriverDiagnostics diag) return null;
try
{
return DriverDiagnostics.Bound(diag.GetDiagnostics());
}
catch (Exception ex)
{
_log.Warning(ex, "DriverInstance {Id}: GetDiagnostics threw during health publish; omitting diagnostics", _driverInstanceId);
return null;
}
}
/// <summary>Value digest of the diagnostics bag for the publish fingerprint. Null in, null out. The bag is
/// already in ordinal key order (<see cref="DriverDiagnostics.Bound"/>), so equal facts digest equally.</summary>
private static string? DiagnosticsDigest(IReadOnlyDictionary<string, string>? d) =>
d is null ? null : string.Join('|', d.Select(kv => $"{kv.Key}={kv.Value}"));
/// <summary>Records the driver's rediscovery raise and re-publishes health so the signal reaches the
/// AdminUI promptly rather than waiting for the next 30 s heartbeat.
/// <para><b>Advisory only.</b> The served address space is deliberately NOT rebuilt: v3 authors raw tags
@@ -1357,6 +1379,7 @@ public sealed class DriverInstanceActor : ReceiveActor, IWithTimers
var errorCount = ErrorCount5Min();
var hostStatuses = CurrentHostStatuses();
var skippedTags = CurrentSkippedTags();
var diagnostics = CurrentDiagnostics();
// _rediscoveryNeededUtc is PART OF THE FINGERPRINT on purpose. A rediscovery raise on an
// otherwise-unchanged Healthy driver leaves (state, lastSuccess, lastError, errorCount)
// identical, so without it the dedup below would swallow the very publish that carries the
@@ -1375,14 +1398,20 @@ public sealed class DriverInstanceActor : ReceiveActor, IWithTimers
// is identical to a clean driver's and the publish that carries the signal is exactly the one
// dedup would swallow. Flattened to a STRING for the same reason as the host digest — the
// report holds an IReadOnlyList, which a tuple compares by reference.
//
// The diagnostics digest (Gitea #640) is the fourth instance: a diagnostic fact (S7's PDU size
// changing across a reconnect) moves none of the other components, so without it the publish
// that carries it is deduped away. Flattened to a STRING - the bag is a dictionary, which a
// tuple compares by reference.
var fingerprint = (health.State, health.LastSuccessfulRead, health.LastError, errorCount,
_rediscoveryNeededUtc, HostStatusDigest(hostStatuses), SkippedTagDigest(skippedTags));
_rediscoveryNeededUtc, HostStatusDigest(hostStatuses), SkippedTagDigest(skippedTags),
DiagnosticsDigest(diagnostics));
if (_lastPublishedFingerprint is { } prev && prev.Equals(fingerprint))
return observed;
_lastPublishedFingerprint = fingerprint;
_healthPublisher.Publish(
_clusterId, _driverInstanceId, health, errorCount, _rediscoveryNeededUtc, _rediscoveryReason,
hostStatuses, skippedTags);
hostStatuses, skippedTags, diagnostics);
}
catch (Exception ex)
{
@@ -1418,7 +1447,8 @@ public sealed class DriverInstanceActor : ReceiveActor, IWithTimers
/// <summary>Fingerprint of the last <see cref="PublishHealthSnapshot"/> call; null until first publish.</summary>
private (DriverState State, DateTime? LastSuccess, string? LastError, int ErrorCount,
DateTime? RediscoveryNeededUtc, string? HostStatusDigest, string? SkippedTagDigest)? _lastPublishedFingerprint;
DateTime? RediscoveryNeededUtc, string? HostStatusDigest, string? SkippedTagDigest,
string? DiagnosticsDigest)? _lastPublishedFingerprint;
/// <inheritdoc />
protected override void PostStop()