[2.x] Intern analysis values while deserializing

internal/zinc-core/src/main/scala/sbt/internal/inc/AnalysisInterner.scala

@@ -0,0 +1,91 @@
+/*
+ * Zinc - The incremental compiler for Scala.
+ * Copyright Scala Center, Lightbend, and Mark Harrah
+ *
+ * Licensed under Apache License 2.0
+ * SPDX-License-Identifier: Apache-2.0
+ *
+ * See the NOTICE file distributed with this work for
+ * additional information regarding copyright ownership.
+ */
+
+package sbt.internal.inc
+
+import java.util.{ EnumSet => JEnumSet }
+
+import xsbti.UseScope
+
+/**
+ * The process-wide canonicalizer for strings and `UsedName`s: fresh
+ * (compiler-produced) and persisted (deserialized) analyses both route through
+ * it, so co-resident analyses share a single instance per distinct value.
+ *
+ * Strings are canonicalized through a weak interner: canonical instances are
+ * held only through weak references, so once every analysis referencing a
+ * string is released the canonical instance becomes eligible for GC.
+ *
+ * `UsedName`s are canonicalized without constructing a candidate first: a
+ * `UsedName` is fully determined by its (already canonical) name string and one
+ * of the eight possible `UseScope` combinations, so each combination gets a
+ * weak-valued name-keyed pool. A pool entry is removed once the canonical
+ * `UsedName` is no longer referenced by any analysis. On a pool hit no
+ * `UsedName` is constructed.
+ *
+ * Both pools make interning leak-free across the lifetime of a long-running
+ * build server. Benchmarks that need an uninterned baseline compare against a
+ * stock zinc checkout; production code always interns.
+ */
+object AnalysisInterner {
+
+  private[inc] final val DEFAULT_SCOPE = 1
+  private[inc] final val IMPLICIT_SCOPE = 2
+  private[inc] final val PAT_MAT_TARGET_SCOPE = 4
+  private final val SCOPE_COMBINATIONS = 8 // every subset of the three scopes above
+
+  private val stringPool = new WeakInterner[String]
+
+  // One weak-valued pool per UseScope combination, keyed by the canonical name.
+  private val usedNamePools: Array[WeakValuePool[String, UsedName]] =
+    Array.fill(SCOPE_COMBINATIONS)(new WeakValuePool[String, UsedName])
+
+  def internString(s: String): String = stringPool.intern(s)
+
+  /**
+   * The canonical `UsedName` for `name` used in the scope combination
+   * `scopeBits`, an or-ing of `DEFAULT_SCOPE`, `IMPLICIT_SCOPE` and
+   * `PAT_MAT_TARGET_SCOPE`. Constructs a `UsedName` only when the value is not
+   * pooled yet.
+   */
+  def usedName(name: String, scopeBits: Int): UsedName = {
+    // UsedName stores the escaped name, so the pool must be probed with it too;
+    // escaping is a no-op unless the name contains control characters.
+    val escaped = UsedName.escapeControlChars(name)
+    val pool = usedNamePools(scopeBits)
+    val existing = pool.get(escaped)
+    if (existing != null) existing
+    else {
+      val fresh = UsedName.make(escaped, scopeSets(scopeBits))
+      val prev = pool.putIfAbsent(fresh.name, fresh)
+      if (prev == null) fresh else prev
+    }
+  }
+
+  /**
+   * The eight possible scope sets, indexed by scope bits. Shared by every
+   * UsedName and treated as immutable -- they must never be mutated.
+   */
+  private[inc] val scopeSets: Array[JEnumSet[UseScope]] =
+    Array.tabulate(SCOPE_COMBINATIONS) { bits =>
+      val scopes = JEnumSet.noneOf(classOf[UseScope])
+      if ((bits & DEFAULT_SCOPE) != 0) scopes.add(UseScope.Default)
+      if ((bits & IMPLICIT_SCOPE) != 0) scopes.add(UseScope.Implicit)
+      if ((bits & PAT_MAT_TARGET_SCOPE) != 0) scopes.add(UseScope.PatMatTarget)
+      scopes
+    }
+
+  /** The inverse of `scopeSets`: also the encoding used by the persisted format. */
+  private[inc] def scopeBits(scopes: JEnumSet[UseScope]): Int =
+    (if (scopes.contains(UseScope.Default)) DEFAULT_SCOPE else 0) |
+      (if (scopes.contains(UseScope.Implicit)) IMPLICIT_SCOPE else 0) |
+      (if (scopes.contains(UseScope.PatMatTarget)) PAT_MAT_TARGET_SCOPE else 0)
+}

internal/zinc-core/src/main/scala/sbt/internal/inc/Incremental.scala

@@ -920,9 +920,18 @@ private final class AnalysisCallback(
   }
 
   def usedName(className: String, name: String, useScopes: EnumSet[UseScope]) = {
+    // Canonicalize freshly-produced used names and their strings into the
+    // process-wide pools, so a just-compiled analysis shares them with every
+    // other resident analysis. (Api tree nodes are deduped only when an
+    // analysis is deserialized, not on this fresh-compile path.)
     usedNames
       .getOrElseUpdate(className, ConcurrentHashMap.newKeySet[UsedName].asScala)
-      .add(UsedName.make(name, useScopes))
+      .add(
+        AnalysisInterner.usedName(
+          AnalysisInterner.internString(name),
+          AnalysisInterner.scopeBits(useScopes)
+        )
+      )
     ()
   }
 

internal/zinc-core/src/main/scala/sbt/internal/inc/UsedName.scala

@@ -13,12 +13,23 @@ package sbt.internal.inc
 
 import java.{ util => ju }
 import scala.{ collection => sc }
+import scala.util.hashing.MurmurHash3
 import xsbti.compile.{ UsedName => XUsedName }
 import xsbti.UseScope
 
+/**
+ * `scopes` must never be mutated after construction: instances may share one
+ * scope set (`make` uses the set it is given, and interning aliases equal
+ * instances), and the hash below is computed once.
+ */
 case class UsedName private (name: String, scopes: ju.EnumSet[UseScope]) extends XUsedName {
   override def getName: String = name
   override def getScopes: ju.EnumSet[UseScope] = scopes
+
+  // A canonical (interned) instance is inserted into one name-set per class that
+  // uses it, and EnumSet.hashCode iterates its elements; caching makes each
+  // re-hash a field read. Fits in the object's existing alignment padding.
+  override val hashCode: Int = MurmurHash3.caseClassHash(this)
 }
 
 object UsedName {
@@ -33,7 +44,7 @@ object UsedName {
     new UsedName(escapedName, useScopes)
   }
 
-  private def escapeControlChars(name: String) = {
+  private[inc] def escapeControlChars(name: String): String = {
     if (name.indexOf('\n') > 0) // optimize for common case to regex overhead
       name.replace("\n", "\u26680A")
     else

internal/zinc-core/src/main/scala/sbt/internal/inc/WeakPools.scala

@@ -0,0 +1,117 @@
+/*
+ * Zinc - The incremental compiler for Scala.
+ * Copyright Scala Center, Lightbend, and Mark Harrah
+ *
+ * Licensed under Apache License 2.0
+ * SPDX-License-Identifier: Apache-2.0
+ *
+ * See the NOTICE file distributed with this work for
+ * additional information regarding copyright ownership.
+ */
+
+package sbt.internal.inc
+
+import java.lang.ref.{ ReferenceQueue, WeakReference }
+import java.util.concurrent.ConcurrentHashMap
+
+import scala.annotation.tailrec
+
+/**
+ * Canonicalizing pool: `intern` returns one instance per distinct value
+ * (`equals`/`hashCode`), and holds it only through a weak reference, so a value
+ * becomes collectable as soon as the last caller drops it. Dead entries are
+ * expunged by the next pool operation.
+ */
+private[inc] final class WeakInterner[A <: AnyRef] {
+  private val stale = new ReferenceQueue[A]
+  private val pool = new ConcurrentHashMap[WeakValue[A], WeakValue[A]]
+
+  def intern(a: A): A = {
+    expunge()
+    val candidate = new WeakValue(a, stale)
+    @tailrec def publish(): A = pool.putIfAbsent(candidate, candidate) match {
+      case null => a
+      case existing =>
+        existing.get match {
+          case null => // collected since it matched: drop the dead entry and retry
+            pool.remove(existing, existing)
+            publish()
+          case canonical =>
+            candidate.clear() // never enqueue a reference that was not pooled
+            canonical
+        }
+    }
+    publish()
+  }
+
+  @tailrec private def expunge(): Unit = stale.poll() match {
+    case null => ()
+    case dead =>
+      pool.remove(dead, dead)
+      expunge()
+  }
+}
+
+/**
+ * Map that holds its values only through weak references: an entry disappears
+ * once its value is unreachable, releasing the strong reference to its key with
+ * it. Unlike an interner it is keyed by something cheaper than the value, so
+ * callers can probe the pool before constructing a candidate.
+ */
+private[inc] final class WeakValuePool[K, V <: AnyRef] {
+  private val stale = new ReferenceQueue[V]
+  private val pool = new ConcurrentHashMap[K, KeyedWeakValue[K, V]]
+
+  /** The pooled value for `key`, or `null` if there is none. */
+  def get(key: K): V = {
+    expunge()
+    pool.get(key) match {
+      case null  => null.asInstanceOf[V]
+      case entry => entry.get
+    }
+  }
+
+  /** Pools `value` under `key`, returning `null`, or the value already pooled. */
+  @tailrec def putIfAbsent(key: K, value: V): V = {
+    val candidate = new KeyedWeakValue(key, value, stale)
+    pool.putIfAbsent(key, candidate) match {
+      case null => null.asInstanceOf[V]
+      case existing =>
+        existing.get match {
+          case null => // collected since it was published: replace the dead entry
+            pool.remove(key, existing)
+            putIfAbsent(key, value)
+          case pooled =>
+            candidate.clear() // never enqueue a reference that was not pooled
+            pooled
+        }
+    }
+  }
+
+  @tailrec private def expunge(): Unit = stale.poll() match {
+    case null => ()
+    case dead =>
+      pool.remove(dead.asInstanceOf[KeyedWeakValue[K, V]].key, dead)
+      expunge()
+  }
+}
+
+/** Weak reference that hashes and compares by the value of its referent. */
+private final class WeakValue[A <: AnyRef](a: A, stale: ReferenceQueue[A])
+    extends WeakReference[A](a, stale) {
+  private val hash: Int = a.hashCode
+
+  override def hashCode(): Int = hash
+  override def equals(other: Any): Boolean = other match {
+    case that: WeakValue[?] =>
+      (this `eq` that) || {
+        val value = get
+        value != null && value == that.get
+      }
+    case _ => false
+  }
+}
+
+/** Weak reference that remembers the key its value was pooled under. */
+private final class KeyedWeakValue[K, V <: AnyRef](val key: K, v: V, stale: ReferenceQueue[V])
+    extends WeakReference[V](v, stale)

internal/zinc-core/src/test/scala/sbt/internal/inc/AnalysisInternerSpec.scala

@@ -0,0 +1,101 @@
+/*
+ * Zinc - The incremental compiler for Scala.
+ * Copyright Scala Center, Lightbend, and Mark Harrah
+ *
+ * Licensed under Apache License 2.0
+ * SPDX-License-Identifier: Apache-2.0
+ *
+ * See the NOTICE file distributed with this work for
+ * additional information regarding copyright ownership.
+ */
+
+package sbt.internal.inc
+
+import java.lang.ref.WeakReference
+import java.util.concurrent.{ Callable, CountDownLatch, Executors, TimeUnit }
+import xsbti.UseScope
+
+class AnalysisInternerSpec extends UnitSpec {
+
+  behavior of "AnalysisInterner"
+
+  it should "canonicalize equal strings to one instance" in {
+    val s1 = new String("com.example.Foo") // force distinct heap instances
+    val s2 = new String("com.example.Foo")
+    assert(s1 `ne` s2)
+    assert(AnalysisInterner.internString(s1) `eq` AnalysisInterner.internString(s2))
+  }
+
+  it should "return one UsedName instance per (name, scope) without construction on hit" in {
+    val a = AnalysisInterner.usedName("map", 1)
+    val b = AnalysisInterner.usedName(new String("map"), 1)
+    assert(a `eq` b)
+    assert(a.name == "map")
+    assert(a.scopes.contains(UseScope.Default))
+    assert(!a.scopes.contains(UseScope.Implicit))
+  }
+
+  it should "distinguish scope combinations for the same name" in {
+    val default = AnalysisInterner.usedName("map", 1)
+    val implicitScope = AnalysisInterner.usedName("map", 2)
+    val patMat = AnalysisInterner.usedName("map", 4)
+    assert(default `ne` implicitScope)
+    assert(default `ne` patMat)
+    assert(implicitScope.scopes.contains(UseScope.Implicit))
+    assert(patMat.scopes.contains(UseScope.PatMatTarget))
+  }
+
+  it should "pool names containing control characters under their escaped form" in {
+    val a = AnalysisInterner.usedName("weird\nname", 1)
+    val b = AnalysisInterner.usedName("weird\nname", 1)
+    assert(a `eq` b)
+    assert(a.name == "weird♨0Aname") // stored escaped, exactly as UsedName.make does
+  }
+
+  it should "converge on one canonical instance under concurrent interning" in {
+    // Parallel compilation interns from many threads at once. Every thread must
+    // observe the same canonical reference, and the pools must never deadlock.
+    val threads = 16
+    val start = new CountDownLatch(1)
+    val pool = Executors.newFixedThreadPool(threads)
+    try {
+      val futures = (1 to threads).map { _ =>
+        pool.submit(new Callable[(String, UsedName)] {
+          def call(): (String, UsedName) = {
+            start.await() // release all threads together to maximize contention
+            (
+              AnalysisInterner.internString(new String("concurrent.value")),
+              AnalysisInterner.usedName(new String("concurrent.value"), 5)
+            )
+          }
+        })
+      }
+      start.countDown()
+      val results = futures.map(_.get(30, TimeUnit.SECONDS)).toList // deadlock => timeout
+      assert(results.forall(_._1 `eq` results.head._1))
+      assert(results.forall(_._2 `eq` results.head._2))
+    } finally pool.shutdownNow()
+  }
+
+  it should "release canonical instances once no analysis references them" in {
+    // The leak-free requirement: canonical instances are held only weakly, so
+    // once every analysis referencing a value is dropped it becomes GC-eligible.
+    val stringRef =
+      new WeakReference[String](AnalysisInterner.internString(new String("ephemeral.str")))
+    val usedNameRef =
+      new WeakReference[UsedName](AnalysisInterner.usedName("ephemeral.used", 1))
+    val released = (1 to 100).exists { _ =>
+      System.gc()
+      Thread.sleep(10)
+      stringRef.get() == null && usedNameRef.get() == null
+    }
+    assert(released, "weak pools must not retain values after they become unreachable")
+  }
+
+  it should "keep pooled values while an analysis still references them" in {
+    val held = AnalysisInterner.usedName("held", 1)
+    System.gc()
+    Thread.sleep(10)
+    assert(AnalysisInterner.usedName("held", 1) `eq` held)
+  }
+}