using Google.Protobuf.WellKnownTypes;
using Microsoft.Extensions.Logging;
using ZB.MOM.WW.MxGateway.Contracts.Proto.Galaxy;
using ZB.MOM.WW.MxGateway.Server.Dashboard;
using ZB.MOM.WW.MxGateway.Server.Grpc;
namespace ZB.MOM.WW.MxGateway.Server.Galaxy;
///
/// Server-side cache of Galaxy Repository browse data. All gRPC clients share the same
/// entry — the materialized is produced once per
/// refresh and reused across requests. Refreshes are deploy-time gated: every tick
/// queries galaxy.time_of_last_deploy (cheap), and the heavy hierarchy +
/// attributes rowsets are pulled only when that timestamp has advanced.
/// Each successful heavy refresh is persisted to disk through
/// ; the first refresh restores that
/// snapshot (as ) so clients can browse
/// last-known data when the Galaxy database is unreachable on a cold start.
///
public sealed class GalaxyHierarchyCache : IGalaxyHierarchyCache
{
private static readonly TimeSpan StaleThreshold = TimeSpan.FromMinutes(5);
private readonly IGalaxyRepository _repository;
private readonly IGalaxyDeployNotifier _notifier;
private readonly IGalaxyHierarchySnapshotStore? _snapshotStore;
private readonly TimeProvider _timeProvider;
private readonly ILogger? _logger;
private readonly TaskCompletionSource _firstLoad = new(TaskCreationOptions.RunContinuationsAsynchronously);
private readonly SemaphoreSlim _refreshGate = new(1, 1);
private GalaxyHierarchyCacheEntry _current = GalaxyHierarchyCacheEntry.Empty;
private bool _restoreAttempted;
/// Initializes a new instance of the class.
/// Galaxy Repository client for SQL queries.
/// Galaxy deploy event notifier.
/// Provider for current time; defaults to system time.
/// Optional logger for diagnostic output.
///
/// Optional on-disk snapshot store. When supplied, the cache persists each
/// successful refresh and restores the last snapshot on first load.
///
public GalaxyHierarchyCache(
IGalaxyRepository repository,
IGalaxyDeployNotifier notifier,
TimeProvider? timeProvider = null,
ILogger? logger = null,
IGalaxyHierarchySnapshotStore? snapshotStore = null)
{
_repository = repository;
_notifier = notifier;
_timeProvider = timeProvider ?? TimeProvider.System;
_logger = logger;
_snapshotStore = snapshotStore;
}
/// Gets the current Galaxy hierarchy cache entry with projected status.
public GalaxyHierarchyCacheEntry Current
{
get
{
GalaxyHierarchyCacheEntry snapshot = Volatile.Read(ref _current);
GalaxyCacheStatus projected = ProjectStatus(snapshot);
return projected == snapshot.Status
? snapshot
: snapshot with
{
Status = projected,
DashboardSummary = snapshot.DashboardSummary with
{
Status = MapDashboardStatus(projected),
},
};
}
}
/// Refreshes the Galaxy hierarchy cache if the deploy time has advanced.
/// Token to cancel the asynchronous operation.
/// Asynchronous task representing the refresh operation.
public async Task RefreshAsync(CancellationToken cancellationToken)
{
await _refreshGate.WaitAsync(cancellationToken).ConfigureAwait(false);
try
{
await RefreshCoreAsync(cancellationToken).ConfigureAwait(false);
}
finally
{
_refreshGate.Release();
}
}
/// Waits for the Galaxy hierarchy cache to complete its first load.
/// Token to cancel the asynchronous operation.
/// Asynchronous task representing the wait operation.
public Task WaitForFirstLoadAsync(CancellationToken cancellationToken)
{
return _firstLoad.Task.WaitAsync(cancellationToken);
}
private async Task RefreshCoreAsync(CancellationToken cancellationToken)
{
// First refresh only: seed the cache from the on-disk snapshot before
// querying SQL, so a cold start with an unreachable Galaxy database can
// still serve last-known browse data. Runs under the refresh gate.
if (!_restoreAttempted)
{
_restoreAttempted = true;
await TryRestoreFromDiskAsync(cancellationToken).ConfigureAwait(false);
}
GalaxyHierarchyCacheEntry previous = Volatile.Read(ref _current);
DateTimeOffset queriedAt = _timeProvider.GetUtcNow();
try
{
DateTime? deployRaw = await _repository.GetLastDeployTimeAsync(cancellationToken).ConfigureAwait(false);
DateTimeOffset? deployTime = deployRaw.HasValue
? new DateTimeOffset(DateTime.SpecifyKind(deployRaw.Value, DateTimeKind.Utc))
: null;
bool hasPriorData = previous.HasData;
bool deployChanged = !hasPriorData || deployTime != previous.LastDeployTime;
if (!deployChanged)
{
// No deploy change — skip heavy queries; just bump LastSuccessAt.
GalaxyHierarchyCacheEntry refreshed = previous with
{
Status = GalaxyCacheStatus.Healthy,
LastQueriedAt = queriedAt,
LastSuccessAt = queriedAt,
LastError = null,
DashboardSummary = previous.DashboardSummary with
{
Status = DashboardGalaxyStatus.Healthy,
LastQueriedAt = queriedAt,
LastSuccessAt = queriedAt,
LastDeployTime = deployTime,
LastError = null,
},
};
Volatile.Write(ref _current, refreshed);
_firstLoad.TrySetResult();
return;
}
Task> hierarchyTask = _repository.GetHierarchyAsync(cancellationToken);
Task> attributesTask = _repository.GetAttributesAsync(cancellationToken);
await Task.WhenAll(hierarchyTask, attributesTask).ConfigureAwait(false);
List hierarchy = hierarchyTask.Result;
List attributes = attributesTask.Result;
long nextSequence = previous.Sequence + 1;
GalaxyHierarchyCacheEntry next = BuildEntry(
status: GalaxyCacheStatus.Healthy,
sequence: nextSequence,
lastQueriedAt: queriedAt,
lastSuccessAt: queriedAt,
lastDeployTime: deployTime,
lastError: null,
hierarchy: hierarchy,
attributes: attributes);
Volatile.Write(ref _current, next);
_firstLoad.TrySetResult();
_notifier.Publish(new GalaxyDeployEventInfo(
Sequence: nextSequence,
ObservedAt: queriedAt,
TimeOfLastDeploy: deployTime,
ObjectCount: hierarchy.Count,
AttributeCount: attributes.Count));
await PersistSnapshotAsync(deployTime, queriedAt, hierarchy, attributes, cancellationToken).ConfigureAwait(false);
}
catch (OperationCanceledException) when (cancellationToken.IsCancellationRequested)
{
throw;
}
catch (Exception exception)
{
// Catch every non-cancellation failure — not just SqlException /
// InvalidOperationException. A TimeoutException or Win32Exception
// from connection establishment, or another DbException subtype,
// must still degrade gracefully to Stale/Unavailable and complete
// _firstLoad rather than escape and fault the refresh BackgroundService.
_logger?.LogWarning(exception, "Galaxy hierarchy cache refresh failed.");
GalaxyHierarchyCacheEntry failed = previous with
{
Status = previous.HasData ? GalaxyCacheStatus.Stale : GalaxyCacheStatus.Unavailable,
LastQueriedAt = queriedAt,
LastError = exception.Message,
DashboardSummary = previous.DashboardSummary with
{
Status = MapDashboardStatus(previous.HasData ? GalaxyCacheStatus.Stale : GalaxyCacheStatus.Unavailable),
LastQueriedAt = queriedAt,
LastError = exception.Message,
},
};
Volatile.Write(ref _current, failed);
_firstLoad.TrySetResult();
}
}
///
/// Materializes a complete from raw
/// hierarchy and attribute rowsets. Shared by the live refresh path and the
/// on-disk restore path so both produce an identical object list, index, and
/// dashboard summary.
///
private static GalaxyHierarchyCacheEntry BuildEntry(
GalaxyCacheStatus status,
long sequence,
DateTimeOffset? lastQueriedAt,
DateTimeOffset? lastSuccessAt,
DateTimeOffset? lastDeployTime,
string? lastError,
IReadOnlyList hierarchy,
IReadOnlyList attributes)
{
IReadOnlyList objects = BuildObjects(hierarchy, attributes);
GalaxyHierarchyIndex index = GalaxyHierarchyIndex.Build(objects);
int areaCount = hierarchy.Count(row => row.IsArea);
int historized = attributes.Count(row => row.IsHistorized);
int alarms = attributes.Count(row => row.IsAlarm);
DashboardGalaxySummary dashboardSummary = BuildDashboardSummary(
status: status,
lastQueriedAt: lastQueriedAt,
lastSuccessAt: lastSuccessAt,
lastDeployTime: lastDeployTime,
lastError: lastError,
hierarchy: hierarchy,
objectCount: hierarchy.Count,
areaCount: areaCount,
attributeCount: attributes.Count,
historizedAttributeCount: historized,
alarmAttributeCount: alarms);
return new GalaxyHierarchyCacheEntry(
Status: status,
Sequence: sequence,
LastQueriedAt: lastQueriedAt,
LastSuccessAt: lastSuccessAt,
LastDeployTime: lastDeployTime,
LastError: lastError,
Objects: objects,
Index: index,
DashboardSummary: dashboardSummary,
ObjectCount: hierarchy.Count,
AreaCount: areaCount,
AttributeCount: attributes.Count,
HistorizedAttributeCount: historized,
AlarmAttributeCount: alarms);
}
///
/// Seeds the cache from the on-disk snapshot when no live data has loaded yet.
/// The restored entry is marked — it is
/// last-known data, not live. A later refresh that observes the same deploy
/// time promotes it to healthy; one that observes a newer deploy replaces it.
///
private async Task TryRestoreFromDiskAsync(CancellationToken cancellationToken)
{
if (_snapshotStore is null)
{
return;
}
if (Volatile.Read(ref _current).HasData)
{
return;
}
GalaxyHierarchySnapshot? snapshot;
try
{
snapshot = await _snapshotStore.TryLoadAsync(cancellationToken).ConfigureAwait(false);
}
catch (OperationCanceledException) when (cancellationToken.IsCancellationRequested)
{
throw;
}
catch (Exception exception)
{
_logger?.LogWarning(exception, "Failed to restore the Galaxy hierarchy from the on-disk snapshot.");
return;
}
if (snapshot is null)
{
return;
}
long sequence = Volatile.Read(ref _current).Sequence + 1;
GalaxyHierarchyCacheEntry restored = BuildEntry(
status: GalaxyCacheStatus.Stale,
sequence: sequence,
lastQueriedAt: snapshot.SavedAt,
lastSuccessAt: snapshot.SavedAt,
lastDeployTime: snapshot.LastDeployTime,
lastError: null,
hierarchy: snapshot.Hierarchy,
attributes: snapshot.Attributes);
Volatile.Write(ref _current, restored);
// Restored data is a valid completed first load: unblock callers waiting on
// the bootstrap gate immediately, rather than making them wait out the full
// wait budget for a live query that — when the database is unreachable, the
// scenario this restore exists for — may not return for seconds.
_firstLoad.TrySetResult();
_notifier.Publish(new GalaxyDeployEventInfo(
Sequence: sequence,
ObservedAt: _timeProvider.GetUtcNow(),
TimeOfLastDeploy: snapshot.LastDeployTime,
ObjectCount: snapshot.Hierarchy.Count,
AttributeCount: snapshot.Attributes.Count));
_logger?.LogInformation(
"Restored Galaxy hierarchy from on-disk snapshot saved {SavedAt:o}: {ObjectCount} objects, {AttributeCount} attributes (status Stale until the Galaxy database confirms).",
snapshot.SavedAt,
snapshot.Hierarchy.Count,
snapshot.Attributes.Count);
}
///
/// Persists a successful refresh to disk. Persistence failures are logged and
/// swallowed — a cache that cannot write its backup is still fully usable.
///
private async Task PersistSnapshotAsync(
DateTimeOffset? deployTime,
DateTimeOffset savedAt,
IReadOnlyList hierarchy,
IReadOnlyList attributes,
CancellationToken cancellationToken)
{
if (_snapshotStore is null)
{
return;
}
try
{
await _snapshotStore.SaveAsync(
new GalaxyHierarchySnapshot(deployTime, savedAt, hierarchy, attributes),
cancellationToken).ConfigureAwait(false);
}
catch (OperationCanceledException) when (cancellationToken.IsCancellationRequested)
{
// The refresh was cancelled (gateway shutdown) before the write finished.
// That is not a persistence failure — do not log it as a warning.
}
catch (Exception exception)
{
_logger?.LogWarning(exception, "Failed to persist the Galaxy hierarchy snapshot to disk.");
}
}
private static IReadOnlyList BuildObjects(
IReadOnlyList hierarchy,
IReadOnlyList attributes)
{
Dictionary> attributesByGobjectId = attributes
.GroupBy(a => a.GobjectId)
.ToDictionary(g => g.Key, g => g.ToList());
List objects = new(hierarchy.Count);
foreach (GalaxyHierarchyRow row in hierarchy)
{
objects.Add(GalaxyProtoMapper.MapObject(row, attributesByGobjectId));
}
return objects;
}
private static DashboardGalaxySummary BuildDashboardSummary(
GalaxyCacheStatus status,
DateTimeOffset? lastQueriedAt,
DateTimeOffset? lastSuccessAt,
DateTimeOffset? lastDeployTime,
string? lastError,
IReadOnlyList hierarchy,
int objectCount,
int areaCount,
int attributeCount,
int historizedAttributeCount,
int alarmAttributeCount)
{
IReadOnlyList topTemplates;
IReadOnlyList objectCategories;
if (hierarchy.Count == 0)
{
topTemplates = Array.Empty();
objectCategories = Array.Empty();
}
else
{
Dictionary objectsByCategory = new();
Dictionary templateUsage = new(StringComparer.OrdinalIgnoreCase);
foreach (GalaxyHierarchyRow row in hierarchy)
{
objectsByCategory.TryGetValue(row.CategoryId, out int categoryCount);
objectsByCategory[row.CategoryId] = categoryCount + 1;
if (row.TemplateChain.Count > 0)
{
string immediate = row.TemplateChain[0];
if (!string.IsNullOrWhiteSpace(immediate))
{
templateUsage.TryGetValue(immediate, out int templateCount);
templateUsage[immediate] = templateCount + 1;
}
}
}
topTemplates = templateUsage
.OrderByDescending(entry => entry.Value)
.ThenBy(entry => entry.Key, StringComparer.OrdinalIgnoreCase)
.Take(10)
.Select(entry => new DashboardGalaxyTemplateUsage(entry.Key, entry.Value))
.ToArray();
objectCategories = objectsByCategory
.OrderByDescending(entry => entry.Value)
.ThenBy(entry => entry.Key)
.Select(entry => new DashboardGalaxyCategoryCount(
entry.Key,
ResolveCategoryName(entry.Key),
entry.Value))
.ToArray();
}
return new DashboardGalaxySummary(
Status: MapDashboardStatus(status),
LastQueriedAt: lastQueriedAt,
LastSuccessAt: lastSuccessAt,
LastDeployTime: lastDeployTime,
LastError: lastError,
ObjectCount: objectCount,
AreaCount: areaCount,
AttributeCount: attributeCount,
HistorizedAttributeCount: historizedAttributeCount,
AlarmAttributeCount: alarmAttributeCount,
TopTemplates: topTemplates,
ObjectCategories: objectCategories);
}
private static DashboardGalaxyStatus MapDashboardStatus(GalaxyCacheStatus status) => status switch
{
GalaxyCacheStatus.Healthy => DashboardGalaxyStatus.Healthy,
GalaxyCacheStatus.Stale => DashboardGalaxyStatus.Stale,
GalaxyCacheStatus.Unavailable => DashboardGalaxyStatus.Unavailable,
_ => DashboardGalaxyStatus.Unknown,
};
private static string ResolveCategoryName(int categoryId) => categoryId switch
{
1 => "WinPlatform",
3 => "AppEngine",
4 => "InTouchViewApp",
10 => "UserDefined",
11 => "FieldReference",
13 => "Area",
17 => "DIObject",
24 => "DDESuiteLinkClient",
26 => "OPCClient",
_ => $"Category {categoryId}",
};
private GalaxyCacheStatus ProjectStatus(GalaxyHierarchyCacheEntry snapshot)
{
if (snapshot.Status is GalaxyCacheStatus.Unknown or GalaxyCacheStatus.Unavailable)
{
return snapshot.Status;
}
if (snapshot.LastSuccessAt is { } success
&& _timeProvider.GetUtcNow() - success > StaleThreshold)
{
return GalaxyCacheStatus.Stale;
}
return snapshot.Status;
}
}