Phase 6.1 Stream B (partial) - Tier registry invariant + MemoryTracking with hybrid formula #79

Merged
dohertj2 merged 2 commits from phase-6-1-stream-b-stability into v2 2026-04-19 08:05:04 -04:00
4 changed files with 282 additions and 3 deletions
Showing only changes of commit ef6b0bb8fc - Show all commits

View File

@@ -69,12 +69,20 @@ public sealed class DriverTypeRegistry
/// <param name="DriverConfigJsonSchema">JSON Schema (Draft 2020-12) the driver's <c>DriverConfig</c> column must validate against.</param>
/// <param name="DeviceConfigJsonSchema">JSON Schema for <c>DeviceConfig</c> (multi-device drivers); null if the driver has no device layer.</param>
/// <param name="TagConfigJsonSchema">JSON Schema for <c>TagConfig</c>; required for every driver since every driver has tags.</param>
/// <param name="Tier">
/// Stability tier per <c>docs/v2/driver-stability.md</c> §2-4 and <c>docs/v2/plan.md</c>
/// decisions #63-74. Drives the shared resilience pipeline defaults
/// (<see cref="Tier"/> × capability → <c>CapabilityPolicy</c>), the <c>MemoryTracking</c>
/// hybrid-formula constants, and whether process-level <c>MemoryRecycle</c> / scheduled-
/// recycle protections apply (Tier C only). Every registered driver type must declare one.
/// </param>
public sealed record DriverTypeMetadata(
string TypeName,
NamespaceKindCompatibility AllowedNamespaceKinds,
string DriverConfigJsonSchema,
string? DeviceConfigJsonSchema,
string TagConfigJsonSchema);
string TagConfigJsonSchema,
DriverTier Tier);
/// <summary>Bitmask of namespace kinds a driver type may populate. Per decision #111.</summary>
[Flags]

View File

@@ -0,0 +1,136 @@
using ZB.MOM.WW.OtOpcUa.Core.Abstractions;
namespace ZB.MOM.WW.OtOpcUa.Core.Stability;
/// <summary>
/// Tier-agnostic memory-footprint tracker. Captures the post-initialize <b>baseline</b>
/// from the first samples after <c>IDriver.InitializeAsync</c>, then classifies each
/// subsequent sample against a hybrid soft/hard threshold per
/// <c>docs/v2/plan.md</c> decision #146 — <c>soft = max(multiplier × baseline, baseline + floor)</c>,
/// <c>hard = 2 × soft</c>.
/// </summary>
/// <remarks>
/// <para>Per decision #145, this tracker <b>never kills a process</b>. Soft and hard breaches
/// log + surface to the Admin UI via <c>DriverInstanceResilienceStatus</c>. The matching
/// process-level recycle protection lives in a separate <c>MemoryRecycle</c> that activates
/// for Tier C drivers only (where the driver runs out-of-process behind a supervisor that
/// can safely restart it without tearing down the OPC UA session or co-hosted in-proc
/// drivers).</para>
///
/// <para>Baseline capture: the tracker starts in <see cref="TrackingPhase.WarmingUp"/> for
/// <see cref="BaselineWindow"/> (default 5 min). During that window samples are collected;
/// the baseline is computed as the median once the window elapses. Before that point every
/// classification returns <see cref="MemoryTrackingAction.Warming"/>.</para>
/// </remarks>
public sealed class MemoryTracking
{
private readonly DriverTier _tier;
private readonly TimeSpan _baselineWindow;
private readonly List<long> _warmupSamples = [];
private long _baselineBytes;
private TrackingPhase _phase = TrackingPhase.WarmingUp;
private DateTime? _warmupStartUtc;
/// <summary>Tier-default multiplier/floor constants per decision #146.</summary>
public static (int Multiplier, long FloorBytes) GetTierConstants(DriverTier tier) => tier switch
{
DriverTier.A => (Multiplier: 3, FloorBytes: 50L * 1024 * 1024),
DriverTier.B => (Multiplier: 3, FloorBytes: 100L * 1024 * 1024),
DriverTier.C => (Multiplier: 2, FloorBytes: 500L * 1024 * 1024),
_ => throw new ArgumentOutOfRangeException(nameof(tier), tier, $"No memory-tracking constants defined for tier {tier}."),
};
/// <summary>Window over which post-init samples are collected to compute the baseline.</summary>
public TimeSpan BaselineWindow => _baselineWindow;
/// <summary>Current phase: <see cref="TrackingPhase.WarmingUp"/> or <see cref="TrackingPhase.Steady"/>.</summary>
public TrackingPhase Phase => _phase;
/// <summary>Captured baseline; 0 until warmup completes.</summary>
public long BaselineBytes => _baselineBytes;
/// <summary>Effective soft threshold (zero while warming up).</summary>
public long SoftThresholdBytes => _baselineBytes == 0 ? 0 : ComputeSoft(_tier, _baselineBytes);
/// <summary>Effective hard threshold = 2 × soft (zero while warming up).</summary>
public long HardThresholdBytes => _baselineBytes == 0 ? 0 : ComputeSoft(_tier, _baselineBytes) * 2;
public MemoryTracking(DriverTier tier, TimeSpan? baselineWindow = null)
{
_tier = tier;
_baselineWindow = baselineWindow ?? TimeSpan.FromMinutes(5);
}
/// <summary>
/// Submit a memory-footprint sample. Returns the action the caller should surface.
/// During warmup, always returns <see cref="MemoryTrackingAction.Warming"/> and accumulates
/// samples; once the window elapses the first steady-phase sample triggers baseline capture
/// (median of warmup samples).
/// </summary>
public MemoryTrackingAction Sample(long footprintBytes, DateTime utcNow)
{
if (_phase == TrackingPhase.WarmingUp)
{
_warmupStartUtc ??= utcNow;
_warmupSamples.Add(footprintBytes);
if (utcNow - _warmupStartUtc.Value >= _baselineWindow && _warmupSamples.Count > 0)
{
_baselineBytes = ComputeMedian(_warmupSamples);
_phase = TrackingPhase.Steady;
}
else
{
return MemoryTrackingAction.Warming;
}
}
if (footprintBytes >= HardThresholdBytes) return MemoryTrackingAction.HardBreach;
if (footprintBytes >= SoftThresholdBytes) return MemoryTrackingAction.SoftBreach;
return MemoryTrackingAction.None;
}
private static long ComputeSoft(DriverTier tier, long baseline)
{
var (multiplier, floor) = GetTierConstants(tier);
return Math.Max(multiplier * baseline, baseline + floor);
}
private static long ComputeMedian(List<long> samples)
{
var sorted = samples.Order().ToArray();
var mid = sorted.Length / 2;
return sorted.Length % 2 == 1
? sorted[mid]
: (sorted[mid - 1] + sorted[mid]) / 2;
}
}
/// <summary>Phase of a <see cref="MemoryTracking"/> lifecycle.</summary>
public enum TrackingPhase
{
/// <summary>Collecting post-init samples; baseline not yet computed.</summary>
WarmingUp,
/// <summary>Baseline captured; every sample classified against soft/hard thresholds.</summary>
Steady,
}
/// <summary>Classification the tracker returns per sample.</summary>
public enum MemoryTrackingAction
{
/// <summary>Baseline not yet captured; sample collected, no threshold check.</summary>
Warming,
/// <summary>Below soft threshold.</summary>
None,
/// <summary>Between soft and hard thresholds — log + surface, no action.</summary>
SoftBreach,
/// <summary>
/// ≥ hard threshold. Log + surface + (Tier C only, via <c>MemoryRecycle</c>) request
/// process recycle via the driver supervisor. Tier A/B breach never invokes any
/// kill path per decisions #145 and #74.
/// </summary>
HardBreach,
}

View File

@@ -7,11 +7,13 @@ public sealed class DriverTypeRegistryTests
{
private static DriverTypeMetadata SampleMetadata(
string typeName = "Modbus",
NamespaceKindCompatibility allowed = NamespaceKindCompatibility.Equipment) =>
NamespaceKindCompatibility allowed = NamespaceKindCompatibility.Equipment,
DriverTier tier = DriverTier.B) =>
new(typeName, allowed,
DriverConfigJsonSchema: "{\"type\": \"object\"}",
DeviceConfigJsonSchema: "{\"type\": \"object\"}",
TagConfigJsonSchema: "{\"type\": \"object\"}");
TagConfigJsonSchema: "{\"type\": \"object\"}",
Tier: tier);
[Fact]
public void Register_ThenGet_RoundTrips()
@@ -24,6 +26,20 @@ public sealed class DriverTypeRegistryTests
registry.Get("Modbus").ShouldBe(metadata);
}
[Theory]
[InlineData(DriverTier.A)]
[InlineData(DriverTier.B)]
[InlineData(DriverTier.C)]
public void Register_Requires_NonNullTier(DriverTier tier)
{
var registry = new DriverTypeRegistry();
var metadata = SampleMetadata(typeName: $"Driver-{tier}", tier: tier);
registry.Register(metadata);
registry.Get(metadata.TypeName).Tier.ShouldBe(tier);
}
[Fact]
public void Get_IsCaseInsensitive()
{

View File

@@ -0,0 +1,119 @@
using Shouldly;
using Xunit;
using ZB.MOM.WW.OtOpcUa.Core.Abstractions;
using ZB.MOM.WW.OtOpcUa.Core.Stability;
namespace ZB.MOM.WW.OtOpcUa.Core.Tests.Stability;
[Trait("Category", "Unit")]
public sealed class MemoryTrackingTests
{
private static readonly DateTime T0 = new(2026, 4, 19, 12, 0, 0, DateTimeKind.Utc);
[Fact]
public void WarmingUp_Returns_Warming_UntilWindowElapses()
{
var tracker = new MemoryTracking(DriverTier.A, TimeSpan.FromMinutes(5));
tracker.Sample(100_000_000, T0).ShouldBe(MemoryTrackingAction.Warming);
tracker.Sample(105_000_000, T0.AddMinutes(1)).ShouldBe(MemoryTrackingAction.Warming);
tracker.Sample(102_000_000, T0.AddMinutes(4.9)).ShouldBe(MemoryTrackingAction.Warming);
tracker.Phase.ShouldBe(TrackingPhase.WarmingUp);
tracker.BaselineBytes.ShouldBe(0);
}
[Fact]
public void WindowElapsed_CapturesBaselineAsMedian_AndTransitionsToSteady()
{
var tracker = new MemoryTracking(DriverTier.A, TimeSpan.FromMinutes(5));
tracker.Sample(100_000_000, T0);
tracker.Sample(200_000_000, T0.AddMinutes(1));
tracker.Sample(150_000_000, T0.AddMinutes(2));
var first = tracker.Sample(150_000_000, T0.AddMinutes(5));
tracker.Phase.ShouldBe(TrackingPhase.Steady);
tracker.BaselineBytes.ShouldBe(150_000_000L, "median of 4 samples [100, 200, 150, 150] = (150+150)/2 = 150");
first.ShouldBe(MemoryTrackingAction.None, "150 MB is the baseline itself, well under soft threshold");
}
[Theory]
[InlineData(DriverTier.A, 3, 50)]
[InlineData(DriverTier.B, 3, 100)]
[InlineData(DriverTier.C, 2, 500)]
public void GetTierConstants_MatchesDecision146(DriverTier tier, int expectedMultiplier, long expectedFloorMB)
{
var (multiplier, floor) = MemoryTracking.GetTierConstants(tier);
multiplier.ShouldBe(expectedMultiplier);
floor.ShouldBe(expectedFloorMB * 1024 * 1024);
}
[Fact]
public void SoftThreshold_UsesMax_OfMultiplierAndFloor_SmallBaseline()
{
// Tier A: mult=3, floor=50 MB. Baseline 10 MB → 3×10=30 MB < 10+50=60 MB → floor wins.
var tracker = WarmupWithBaseline(DriverTier.A, 10L * 1024 * 1024);
tracker.SoftThresholdBytes.ShouldBe(60L * 1024 * 1024);
}
[Fact]
public void SoftThreshold_UsesMax_OfMultiplierAndFloor_LargeBaseline()
{
// Tier A: mult=3, floor=50 MB. Baseline 200 MB → 3×200=600 MB > 200+50=250 MB → multiplier wins.
var tracker = WarmupWithBaseline(DriverTier.A, 200L * 1024 * 1024);
tracker.SoftThresholdBytes.ShouldBe(600L * 1024 * 1024);
}
[Fact]
public void HardThreshold_IsTwiceSoft()
{
var tracker = WarmupWithBaseline(DriverTier.B, 200L * 1024 * 1024);
tracker.HardThresholdBytes.ShouldBe(tracker.SoftThresholdBytes * 2);
}
[Fact]
public void Sample_Below_Soft_Returns_None()
{
var tracker = WarmupWithBaseline(DriverTier.A, 100L * 1024 * 1024);
tracker.Sample(200L * 1024 * 1024, T0.AddMinutes(10)).ShouldBe(MemoryTrackingAction.None);
}
[Fact]
public void Sample_AtSoft_Returns_SoftBreach()
{
// Tier A, baseline 200 MB → soft = 600 MB. Sample exactly at soft.
var tracker = WarmupWithBaseline(DriverTier.A, 200L * 1024 * 1024);
tracker.Sample(tracker.SoftThresholdBytes, T0.AddMinutes(10))
.ShouldBe(MemoryTrackingAction.SoftBreach);
}
[Fact]
public void Sample_AtHard_Returns_HardBreach()
{
var tracker = WarmupWithBaseline(DriverTier.A, 200L * 1024 * 1024);
tracker.Sample(tracker.HardThresholdBytes, T0.AddMinutes(10))
.ShouldBe(MemoryTrackingAction.HardBreach);
}
[Fact]
public void Sample_AboveHard_Returns_HardBreach()
{
var tracker = WarmupWithBaseline(DriverTier.A, 200L * 1024 * 1024);
tracker.Sample(tracker.HardThresholdBytes + 100_000_000, T0.AddMinutes(10))
.ShouldBe(MemoryTrackingAction.HardBreach);
}
private static MemoryTracking WarmupWithBaseline(DriverTier tier, long baseline)
{
var tracker = new MemoryTracking(tier, TimeSpan.FromMinutes(5));
tracker.Sample(baseline, T0);
tracker.Sample(baseline, T0.AddMinutes(5));
tracker.BaselineBytes.ShouldBe(baseline);
return tracker;
}
}