fix(runtime): derive the write cap from the configured write timeout (lmxopcua#774)
DriverInstanceActor.RunWriteAsync cancelled every write with a hard-coded,
undilated 5 s CancellationTokenSource, so writeTimeout / DefaultWriteTimeout
(then 10 s) only ever served as the pessimistic abandon bound: a configured
bound above 5 s never took effect.
The write's token is now cancelled at the configured write timeout; a write
that ignores its token is abandoned WriteAbandonGrace later (half the
timeout, at most 2 s) so a token-honouring driver still gets to answer the
cancellation itself. Both bounds run on an injectable TimeProvider
(Props writeClock, System by default).
DefaultWriteTimeout is now 5 s (cancel 5 s, abandon 7 s), not 10 s: the
host's write Ask is 8 s, and a write allowed to run past it would already
have been reported as a timeout and its node reverted while the device could
still take the value - the exact failure the off-mailbox write work fixed.
Production behaviour is therefore unchanged for the cancel (5 s) and tighter
for a token-ignoring driver (abandoned at 7 s instead of 10 s, i.e. inside
the Ask). DriverHostActor's Ask comment updated to match.
Tests (DriverInstanceActorConcurrentWriteTests, manual clock copied from
Ab.Transport.Tests into Runtime.Tests/Harness/ManualTimeProvider):
- a write held past 6 s under a 10 s write timeout succeeds;
- positive control: at 10 s the token is cancelled ("write timeout");
- a token-ignoring write is still pending at 10 s and abandoned (BadTimeout)
after the grace.
Mutation checks: a fixed 5 s token on the same clock fails the first test;
dropping the grace fails the third (and the second, where the abandon then
races the cancellation).
342a825d re-check: its held-write tests were written around the undilated
5 s cap. Connect() now defaults the write timeout to the DILATED presence
budget, so a held, explicitly-released write no longer races any undilated
deadline; tests about the bound pass their own. AwaitWritesEntered keeps its
20 ms interval (doc updated).
Runtime.Tests: 946 passed / 3 skipped / 0 failed at AKKA_TEST_TIMEFACTOR 3
and 1. Solution Release build: 0 warnings.
Claude-Session: https://claude.ai/code/session_01GT67AEHd2Acv1YPwGfXEoV
This commit is contained in:
+99
-5
@@ -26,21 +26,31 @@ public sealed class DriverInstanceActorConcurrentWriteTests : RuntimeActorTestBa
|
||||
/// Polls for <paramref name="count"/> writes inside the driver with an EXPLICIT short interval. Akka's
|
||||
/// <c>AwaitCondition</c> without one polls every <c>max / 10</c> of the DILATED budget — 1.5 s locally, 4.5 s
|
||||
/// under CI's <c>AKKA_TEST_TIMEFACTOR=3</c>. The write under test is already held inside the driver by then,
|
||||
/// and <c>DriverInstanceActor.RunWriteAsync</c> bounds it with a fixed (undilated) 5 s token, so one missed
|
||||
/// first poll plus the test's own settle window cancelled it ("write timeout") before
|
||||
/// and it was bounded by <c>DriverInstanceActor.RunWriteAsync</c>'s fixed (undilated) 5 s token, so one
|
||||
/// missed first poll plus the test's own settle window cancelled it ("write timeout") before
|
||||
/// <c>ReleaseWrites()</c>: <c>A_queued_write_older_than_the_budget…</c> failed every CI run that hit it
|
||||
/// (hosted runs 2215 and 2260), and fails locally at timefactor 3.
|
||||
/// (hosted runs 2215 and 2260), and failed locally at timefactor 3. Since lmxopcua#774 that token follows
|
||||
/// the actor's write timeout, and <see cref="Connect"/> sets it to the dilated presence budget, so a held
|
||||
/// write no longer races an undilated bound at all; the short interval stays to keep the tests fast.
|
||||
/// </summary>
|
||||
private void AwaitWritesEntered(SlowWritableDriver driver, int count) =>
|
||||
AwaitCondition(() => driver.WritesEntered == count, PresenceBudget, TimeSpan.FromMilliseconds(20));
|
||||
|
||||
/// <summary>
|
||||
/// Spawns and connects the actor. Unless a test passes its own <paramref name="writeTimeout"/>, the write
|
||||
/// bound is the DILATED presence budget: these tests hold writes inside the driver and release them
|
||||
/// explicitly, and are not about the bound — the production 5 s default would be an undilated deadline
|
||||
/// racing every held write under CI's timefactor (the 342a825d failure mode).
|
||||
/// </summary>
|
||||
private (IActorRef Actor, Akka.TestKit.TestProbe Parent) Connect(
|
||||
IDriver driver, int? maxWritesInFlight = null, TimeSpan? queuedWriteBudget = null, TimeSpan? writeTimeout = null)
|
||||
IDriver driver, int? maxWritesInFlight = null, TimeSpan? queuedWriteBudget = null, TimeSpan? writeTimeout = null,
|
||||
TimeProvider? writeClock = null)
|
||||
{
|
||||
var parent = CreateTestProbe();
|
||||
var actor = parent.ChildActorOf(DriverInstanceActor.Props(
|
||||
driver, commsLossTimeout: TimeSpan.Zero, maxWritesInFlight: maxWritesInFlight,
|
||||
queuedWriteBudget: queuedWriteBudget, writeTimeout: writeTimeout));
|
||||
queuedWriteBudget: queuedWriteBudget, writeTimeout: writeTimeout ?? Dilated(PresenceBudget),
|
||||
writeClock: writeClock));
|
||||
actor.Tell(new DriverInstanceActor.InitializeRequested("{}"));
|
||||
parent.ExpectMsg<DriverInstanceActor.ConnectivityChanged>(m => m.Connected, PresenceBudget);
|
||||
return (actor, parent);
|
||||
@@ -213,6 +223,90 @@ public sealed class DriverInstanceActorConcurrentWriteTests : RuntimeActorTestBa
|
||||
driver.Writes.Select(w => w.Value).ShouldBe(new object[] { 2 }, "only the later write reached the device's commit");
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// lmxopcua#774: the write's cancellation token was a hard-coded 5 s, so a configured write timeout above
|
||||
/// 5 s never took effect. On a manual clock: a write held past 6 s under a 10 s write timeout still
|
||||
/// succeeds when the device answers. (Mutation-checked: a fixed 5 s token on the same clock fails this
|
||||
/// with "write timeout".)
|
||||
/// </summary>
|
||||
[Fact]
|
||||
public async Task A_write_longer_than_5s_but_within_the_configured_write_timeout_succeeds()
|
||||
{
|
||||
var clock = new ManualTimeProvider();
|
||||
var driver = new SlowWritableDriver { HoldWrites = true };
|
||||
var (actor, _) = Connect(driver, writeTimeout: TimeSpan.FromSeconds(10), writeClock: clock);
|
||||
|
||||
var write = actor.Ask<DriverInstanceActor.WriteAttributeResult>(
|
||||
new DriverInstanceActor.WriteAttribute("tag-a", 1), PresenceBudget);
|
||||
AwaitWritesEntered(driver, 1);
|
||||
AwaitWriteBoundsArmed(clock);
|
||||
|
||||
clock.Advance(TimeSpan.FromSeconds(6));
|
||||
await Task.Delay(100);
|
||||
write.IsCompleted.ShouldBeFalse("the write was cut off before its configured 10 s bound");
|
||||
driver.ReleaseWrites();
|
||||
|
||||
var result = await write;
|
||||
result.Success.ShouldBeTrue(result.Reason);
|
||||
driver.Writes.Select(w => w.FullReference).ShouldBe(new[] { "tag-a" });
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Positive control for the test above: the configured write timeout DOES bound the write — at 10 s its
|
||||
/// token is cancelled and a token-honouring driver answers "write timeout" (not the abandon path).
|
||||
/// </summary>
|
||||
[Fact]
|
||||
public async Task The_configured_write_timeout_cancels_the_write_when_it_elapses()
|
||||
{
|
||||
var clock = new ManualTimeProvider();
|
||||
var driver = new SlowWritableDriver { HoldWrites = true };
|
||||
var (actor, _) = Connect(driver, writeTimeout: TimeSpan.FromSeconds(10), writeClock: clock);
|
||||
|
||||
var write = actor.Ask<DriverInstanceActor.WriteAttributeResult>(
|
||||
new DriverInstanceActor.WriteAttribute("tag-a", 1), PresenceBudget);
|
||||
AwaitWritesEntered(driver, 1);
|
||||
AwaitWriteBoundsArmed(clock);
|
||||
|
||||
clock.Advance(TimeSpan.FromSeconds(10));
|
||||
var result = await write;
|
||||
result.Success.ShouldBeFalse();
|
||||
result.Reason.ShouldBe("write timeout");
|
||||
driver.Writes.ShouldBeEmpty();
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// A token-IGNORING write is abandoned <see cref="DriverInstanceActor.WriteAbandonGrace"/> after its token
|
||||
/// is cancelled, not at the same instant (a token-honouring driver gets the grace to answer itself).
|
||||
/// </summary>
|
||||
[Fact]
|
||||
public async Task A_token_ignoring_write_is_abandoned_a_grace_after_the_configured_write_timeout()
|
||||
{
|
||||
var clock = new ManualTimeProvider();
|
||||
var driver = new SlowWritableDriver { HangFirstWriteIgnoringCancellation = true };
|
||||
var (actor, _) = Connect(driver, writeTimeout: TimeSpan.FromSeconds(10), writeClock: clock);
|
||||
|
||||
var write = actor.Ask<DriverInstanceActor.WriteAttributeResult>(
|
||||
new DriverInstanceActor.WriteAttribute("tag-a", 1), PresenceBudget);
|
||||
AwaitWritesEntered(driver, 1);
|
||||
AwaitWriteBoundsArmed(clock);
|
||||
|
||||
clock.Advance(TimeSpan.FromSeconds(10));
|
||||
await Task.Delay(100);
|
||||
write.IsCompleted.ShouldBeFalse("abandoned at the cancel instant — no grace for the driver to answer");
|
||||
|
||||
clock.Advance(DriverInstanceActor.WriteAbandonGrace(TimeSpan.FromSeconds(10)));
|
||||
var result = await write;
|
||||
result.Success.ShouldBeFalse();
|
||||
result.Reason!.ShouldContain("800A0000", customMessage: "BadTimeout");
|
||||
result.Reason!.ShouldContain("within 10000 ms");
|
||||
}
|
||||
|
||||
/// <summary>Waits until the write task has armed BOTH of its bounds on <paramref name="clock"/> (the token
|
||||
/// cancel and the abandon), so an Advance cannot run ahead of them. Counts the timers rather than matching their
|
||||
/// due times, so a bound armed at the WRONG time fails the test's own assertion instead of this wait.</summary>
|
||||
private void AwaitWriteBoundsArmed(ManualTimeProvider clock) =>
|
||||
AwaitCondition(() => clock.ArmedTimers == 2, PresenceBudget, TimeSpan.FromMilliseconds(20));
|
||||
|
||||
[Fact]
|
||||
public async Task Queued_writes_fail_fast_when_the_driver_leaves_Connected()
|
||||
{
|
||||
|
||||
Reference in New Issue
Block a user