refactor(ingress): 移除 G1 窗口补偿扫描与迟到到达检测

实际负载不足 10 条/秒，G1 属过度防御。删除迟到到达检测机制、 existingIds 接口、PipelineCounters 字段、lateDetect 配置，以及文档中 CLM-1/CLM-2 声明与 G1 缺口索引。
2026-09-13 08:08:43 +08:00
parent a6b2120836
commit b8738554e6
20 changed files with 10 additions and 322 deletions
@@ -48,16 +48,6 @@ class PipelineMetricsTest {
        assertEquals(-1.0, gauge("msgx.pipeline.watermark.lag"), 0.001)
    }

-    @Test
-    fun `permanent hole releases are exposed as a monotonic total`() {
-        val counters = ctx.getBean(PipelineCounters::class.java)
-        val before = gauge("msgx.pipeline.hole.aged_out.total")
-        counters.holeAgedOutIncrement()
-        counters.holeAgedOutIncrement()
-
-        assertEquals(before + 2.0, gauge("msgx.pipeline.hole.aged_out.total"), 0.001)
-    }
-
    @Test
    fun `job heartbeat gauges are registered and reflect job activity`() {
        val activity = ctx.getBean(JobActivity::class.java)
@@ -1,7 +1,6 @@
 package com.gzzn.omms.msgexchange.ingress

 import com.gzzn.omms.msgexchange.config.PipelineProps
-import com.gzzn.omms.msgexchange.infra.metrics.PipelineCounters
 import com.gzzn.omms.msgexchange.infra.persistence.InboxCursorRepository
 import com.gzzn.omms.msgexchange.infra.stub.StubInbox
 import com.gzzn.omms.msgexchange.infra.stub.StubInboxCursor
@@ -45,7 +44,7 @@ class CutoverSeedTest {
        props.pipeline.cutoverWatermark = null
        poller = InboxPoller(
            inbox, proc, cursor, StubPipelineTx(), props,
-            Clock.fixed(t0, ZoneOffset.UTC), PipelineCounters(),
+            Clock.fixed(t0, ZoneOffset.UTC),
        )
    }

@@ -42,7 +42,6 @@ class InboxPollerTest {
        poller = InboxPoller(
            inbox, proc, cursor, StubPipelineTx(), props,
            java.time.Clock.fixed(t0, java.time.ZoneOffset.UTC),
-            com.gzzn.omms.msgexchange.infra.metrics.PipelineCounters(),
        )
    }

@@ -150,31 +149,6 @@ class InboxPollerTest {
        assertEquals(first + 2, third)
    }

-    /**
-     * 【缺口基线 · G1】快路径只读 `ID > W`、从不回头：水位越过某个 ID 之后，该 ID 即使后来
-     * 出现在信箱里也不会再被发现。这不是期望行为，而是"没有补偿扫描"的**已知缺口**；
-     * 本用例把它固定成基线，补偿扫描（ACM2-41 / G1）落地后必须反转成"能被发现并安全处置"。
-     */
-    @Test
-    fun `baseline - an id that appears after the watermark passed it is never discovered`() {
-        inbox.simulateExternalWrite("<MSG/>")                       // 1
-        val hole = inbox.simulateExternalWrite("<MSG/>")            // 2
-        val third = inbox.simulateExternalWrite("<MSG/>")           // 3
-        inbox.removeRow(hole)
-
-        poller.pollOnce(t0)                                          // W 停在 1，空洞在 2
-        val agedOut = t0.plus(props.pipeline.maxCommitDelay)
-        poller.pollOnce(agedOut)                                     // 空洞判永久 → 放行
-        poller.pollOnce(agedOut)                                     // 发现 3
-        assertEquals(third, cursor.cursor.committedUpTo)
-
-        // 迟到的 2 现在才出现：水位已经越过它，快路径再也不会读它。
-        inbox.restoreRow(hole, "<MSG/>", agedOut)
-
-        assertEquals(0, poller.pollOnce(agedOut.plusSeconds(1)))
-        assertNull(proc.find(hole))
-    }
-
    /**
     * 兼容入口会把消息登记在水位**之外**（`msgId > W`），因此它天然成为"最小未完成行"。
     * 领取侧的守卫在主泵：只领 `msgId <= W`（端到端验收见 `PipelineSmokeTest` 的
@@ -2,7 +2,6 @@ package com.gzzn.omms.msgexchange.ingress

 import com.gzzn.omms.msgexchange.MutableClock
 import com.gzzn.omms.msgexchange.config.PipelineProps
-import com.gzzn.omms.msgexchange.infra.metrics.PipelineCounters
 import com.gzzn.omms.msgexchange.infra.persistence.CminmsgInboxRepository
 import com.gzzn.omms.msgexchange.infra.persistence.MailboxMarkResult
 import com.gzzn.omms.msgexchange.infra.persistence.MailboxRow
@@ -50,8 +49,6 @@ class InboxServiceTest {

        override fun minId(): Long? = null

-        override fun existingIds(msgIds: Collection<Long>): Set<Long> = emptySet()
-
        override fun markProcessedIfUnmarked(msgId: Long, value: String): MailboxMarkResult = MailboxMarkResult.MISSING
    }

@@ -106,7 +103,7 @@ class InboxServiceTest {
        val cursor = StubInboxCursor().apply { clear() }
        val clock = MutableClock(t0)
        val service = InboxService(inbox, FlakyProcState(proc), clock)
-        val poller = InboxPoller(inbox, proc, cursor, StubPipelineTx(), PipelineProps(), clock, PipelineCounters())
+        val poller = InboxPoller(inbox, proc, cursor, StubPipelineTx(), PipelineProps(), clock)

        val receipt = service.accept("<MSG/>")   // 落信成功；PG 入队失败但不抛
        assertEquals(1L, service.pgEnqueueFailures.get())
@@ -1,122 +0,0 @@
-package com.gzzn.omms.msgexchange.ingress
-
-import com.gzzn.omms.msgexchange.config.PipelineProps
-import com.gzzn.omms.msgexchange.infra.metrics.PipelineCounters
-import com.gzzn.omms.msgexchange.infra.stub.StubInbox
-import com.gzzn.omms.msgexchange.infra.stub.StubInboxCursor
-import com.gzzn.omms.msgexchange.infra.stub.StubPipelineTx
-import com.gzzn.omms.msgexchange.infra.stub.StubProcState
-import org.junit.jupiter.api.Assertions.assertEquals
-import org.junit.jupiter.api.Assertions.assertNotNull
-import org.junit.jupiter.api.Assertions.assertNull
-import org.junit.jupiter.api.BeforeEach
-import org.junit.jupiter.api.Test
-import java.time.Clock
-import java.time.Duration
-import java.time.Instant
-import java.time.ZoneOffset
-
-/**
- * 迟到到达检测（ACM2-41 阶段 0）：**只读观测**。
- *
- * 语义：被判定为永久空洞并放行的 ID，如果后来真的出现在信箱里，就是"上游提交晚于水位推进"。
- * 阶段 0 只计数与告警，**不入队、不改变处理语义**（补入队属阶段 1，需先与库方定案）。
- */
-class LateArrivalDetectTest {
-
-    private val t0: Instant = Instant.parse("2026-09-08T03:00:00Z")
-    private val props = PipelineProps()
-
-    private lateinit var inbox: StubInbox
-    private lateinit var proc: StubProcState
-    private lateinit var cursor: StubInboxCursor
-    private lateinit var counters: PipelineCounters
-    private lateinit var poller: InboxPoller
-
-    @BeforeEach
-    fun setUp() {
-        inbox = StubInbox().apply { clear() }
-        proc = StubProcState().apply { clear() }
-        cursor = StubInboxCursor().apply { clear() }
-        counters = PipelineCounters()
-        poller = InboxPoller(inbox, proc, cursor, StubPipelineTx(), props, Clock.fixed(t0, ZoneOffset.UTC), counters)
-    }
-
-    /** 造出"1 存在、2 是空洞、3 存在"，并把空洞等到超期放行。返回迟到的那个 ID。 */
-    private fun ageOutHoleAt2(): Long {
-        inbox.simulateExternalWrite("<MSG/>")                       // 1
-        val hole = inbox.simulateExternalWrite("<MSG/>")            // 2
-        inbox.simulateExternalWrite("<MSG/>")                       // 3
-        inbox.removeRow(hole)
-        poller.pollOnce(t0)                                         // W=1，空洞在 2
-        poller.pollOnce(t0.plus(props.pipeline.maxCommitDelay))     // 空洞判永久 → 放行
-        return hole
-    }
-
-    @Test
-    fun `a hole that really appears later is detected and counted`() {
-        val hole = ageOutHoleAt2()
-        inbox.restoreRow(hole, "<MSG/>", t0.plus(props.pipeline.maxCommitDelay))
-
-        // 过了检测周期再轮询一次
-        poller.pollOnce(t0.plus(props.pipeline.maxCommitDelay).plus(props.pipeline.lateDetectPeriod))
-
-        assertEquals(1L, counters.lateArrivalDetectedCount())
-    }
-
-    @Test
-    fun `detection does not enqueue the late message - phase 0 is observation only`() {
-        val hole = ageOutHoleAt2()
-        inbox.restoreRow(hole, "<MSG/>", t0.plus(props.pipeline.maxCommitDelay))
-
-        poller.pollOnce(t0.plus(props.pipeline.maxCommitDelay).plus(props.pipeline.lateDetectPeriod))
-
-        assertEquals(1L, counters.lateArrivalDetectedCount())
-        assertNull(proc.find(hole))                                 // 仍然不会被补入队
-    }
-
-    @Test
-    fun `a hole that stays absent is not counted`() {
-        ageOutHoleAt2()
-
-        poller.pollOnce(t0.plus(props.pipeline.maxCommitDelay).plus(props.pipeline.lateDetectPeriod))
-
-        assertEquals(0L, counters.lateArrivalDetectedCount())
-    }
-
-    @Test
-    fun `detection does not run before the configured period elapses`() {
-        val hole = ageOutHoleAt2()
-        inbox.restoreRow(hole, "<MSG/>", t0)
-
-        // 只过了一个 max-commit-delay，未到检测周期
-        poller.pollOnce(t0.plus(props.pipeline.maxCommitDelay).plusSeconds(1))
-
-        assertEquals(0L, counters.lateArrivalDetectedCount())
-    }
-
-    @Test
-    fun `detection can be switched off`() {
-        props.pipeline.lateDetectPeriod = Duration.ZERO
-        val hole = ageOutHoleAt2()
-        inbox.restoreRow(hole, "<MSG/>", t0)
-
-        poller.pollOnce(t0.plus(props.pipeline.maxCommitDelay).plus(Duration.ofHours(1)))
-
-        assertEquals(0L, counters.lateArrivalDetectedCount())
-    }
-
-    @Test
-    fun `the same late id is counted once even after the hole is aged out again`() {
-        val hole = ageOutHoleAt2()
-        inbox.restoreRow(hole, "<MSG/>", t0.plus(props.pipeline.maxCommitDelay))
-        val later = t0.plus(props.pipeline.maxCommitDelay).plus(props.pipeline.lateDetectPeriod)
-        poller.pollOnce(later)
-        assertEquals(1L, counters.lateArrivalDetectedCount())
-
-        poller.pollOnce(later.plus(props.pipeline.lateDetectPeriod))
-
-        assertEquals(1L, counters.lateArrivalDetectedCount())       // 已命中的 ID 不再重复计数
-        assertNotNull(cursor.cursor)
-    }
-}
@@ -49,7 +49,6 @@ class BackfillServiceTest {
        override fun readRange(fromExclusive: Long, limit: Int): List<MailboxRow> = emptyList()
        override fun maxId(): Long? = null
        override fun minId(): Long? = null
-        override fun existingIds(msgIds: Collection<Long>): Set<Long> = emptySet()
        override fun markProcessedIfUnmarked(msgId: Long, value: String): MailboxMarkResult {
            if (fail) throw IllegalStateException("mysql-down")
            if (missing) return MailboxMarkResult.MISSING
@@ -240,7 +239,6 @@ class BackfillServiceTest {
            override fun readRange(fromExclusive: Long, limit: Int) = emptyList<MailboxRow>()
            override fun maxId(): Long? = 1L
            override fun minId(): Long? = 1L
-            override fun existingIds(msgIds: Collection<Long>): Set<Long> = emptySet()
            override fun markProcessedIfUnmarked(msgId: Long, value: String): MailboxMarkResult {
                entered.countDown()
                release.await()