Phase 6.1 Stream B.1/B.2 — DriverTier on DriverTypeMetadata + Core.Stability.MemoryTracking with hybrid-formula soft/hard thresholds
Stream B.1 — registry invariant: - DriverTypeMetadata gains a required `DriverTier Tier` field. Every registered driver type must declare its stability tier so the downstream MemoryTracking, MemoryRecycle, and resilience-policy layers can resolve the right defaults. Stamped-at-registration-time enforcement makes the "every driver type has a non-null Tier" compliance check structurally impossible to fail. - DriverTypeRegistry API unchanged; one new property on the record. Stream B.2 — MemoryTracking (Core.Stability): - Tier-agnostic tracker per decision #146: captures baseline as the median of samples collected during a post-init warmup window (default 5 min), then classifies each subsequent sample with the hybrid formula `soft = max(multiplier × baseline, baseline + floor)`, `hard = 2 × soft`. - Per-tier constants wired: Tier A mult=3 floor=50 MB, Tier B mult=3 floor=100 MB, Tier C mult=2 floor=500 MB. - Never kills. Hard-breach action returns HardBreach; the supervisor that acts on that signal (MemoryRecycle) is Tier C only per decisions #74, #145 and lands in the next B.3 commit on this branch. - Two phases: WarmingUp (samples collected, Warming returned) and Steady (baseline captured, soft/hard checks active). Transition is automatic when the warmup window elapses. Tests (15 new, all pass): - Warming phase returns Warming until the window elapses. - Window-elapsed captures median baseline + transitions to Steady. - Per-tier constants match decision #146 table exactly. - Soft threshold uses max() — small baseline → floor wins; large baseline → multiplier wins. - Hard = 2 × soft. - Sample below soft = None; at soft = SoftBreach; at/above hard = HardBreach. - DriverTypeRegistry: theory asserts Tier round-trips for A/B/C. Full solution dotnet test: 963 passing (baseline 906, +57 net for Phase 6.1 Stream A + Stream B.1/B.2). Pre-existing Client.CLI Subscribe flake unchanged. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
136
src/ZB.MOM.WW.OtOpcUa.Core/Stability/MemoryTracking.cs
Normal file
136
src/ZB.MOM.WW.OtOpcUa.Core/Stability/MemoryTracking.cs
Normal 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,
|
||||
}
|
||||
Reference in New Issue
Block a user