java - SoftReferences 与 Weakreferences/OutOfMemoryError

Question

我在处理软引用和弱引用时遇到了问题。代码有一个可以切换的标志软引用和弱引用之间的所有逻辑。虽然引用很弱，但似乎为了工作正常，使用软引用我一直得到 OutOfMemoryError。这种情况发生在 MacOSX 上的 JDK7 和 JDK6 以及 Debian 上的 IcedTea6 上。然而，带有 G1 收集器的 JDK7 是我发现使用软引用的设置，我尝试的其他所有内容(串行/并行 GC、-client/-server 等)都失败了异常。

代码有点大，但我已尝试在保留问题的同时尽可能缩小范围。
我在上面留下了大量评论，更详细地描述了如何重现问题。

/*
 *
 * Leakling.java
 *
 *
 * Issue:
 *
 *
 *   This code throws OutOfMemoryError when using soft references, whereas weak references
 *   work ok. Moreover, with JDK7 G1 garbage collector soft references work as well. Other
 *   collectors seem to fail. Code was tested with MacOSX 10.8.2 JDKs 1.7.0_10-b18 and
 *   1.6.0_37-b06-434-11M3909, with Debian 6.0 IcedTea6 1.8.13.
 *   Various command line options including -Xmx, -client/-server, -XX:+UseParallelOldGC,
 *   -XX:+UseSerialGC were tested.
 *
 *
 * Examples:
 *
 *
 * 1. Default options, weak references, this works, counters go up and down,
 *    but everything keeps going just as expected:
 *
 *   java -Xmx50m Leakling \
 *       --loop-delay=10 --min-chunk-size=1000 --max-chunk-size=100000 --use-soft-references=false
 *
 *
 * 2. Default options, soft references, this eventually throws the exception:
 *
 *   java -Xmx50m Leakling \
 *       --loop-delay=10 --min-chunk-size=1000 --max-chunk-size=100000 --use-soft-references=true
 *
 *
 * 3. G1 collector (IcedTea6 doesn't support it), weak references, this works, but it did anyway:
 *
 *   java -XX:+UseG1GC -Xmx50m Leakling \
 *       --loop-delay=10 --min-chunk-size=1000 --max-chunk-size=100000 --use-soft-references=false
 *
 *
 * 4. G1 collector, soft references, this works with JDK7.
 *    JDK6 seems to just stop after having hit memory limit (with no message whatsoever).
 *
 *   java -XX:+UseG1GC -Xmx50m Leakling \
 *       --loop-delay=10 --min-chunk-size=1000 --max-chunk-size=100000 --use-soft-references=true
 *
 *
 * jarek, 02.01.2013
 *
 *
 */

import java.lang.ref.*;
import java.util.*;

public class Leakling {
  private static final String TAG = "memory-chunk-";


  class Chunk {
    final String name;
    final int size;
    final private byte[] mem;

    Chunk(String name, int minSize, int maxSize, Random randomizer) {
      int currSize = minSize;
      if (maxSize > minSize) {
        currSize += randomizer.nextInt(maxSize - minSize + 1);
      }
      this.size = currSize;
      this.mem = new byte[currSize];
      this.name = name;
      log(this + " has been created (" + currSize + " bytes)");
    }

    @Override
    public void finalize() throws Throwable {
      log(this + " is finalizing");
    }

    @Override
    public String toString() {
      return name + " of " + getReadableMemorySize(size);
    }
  }


  class WeakChunk extends WeakReference<Chunk> {
    final String name;

    public WeakChunk(Chunk chunk, ReferenceQueue<Chunk> queue) {
      super(chunk, queue);
      this.name = chunk.name;
    }

    @Override
    public String toString() {
      return "weak reference of " + name + " is " + ((get() == null) ? "null" : "alive");
    }
  }


  class SoftChunk extends SoftReference<Chunk> {
    final String name;

    public SoftChunk(Chunk chunk, ReferenceQueue<Chunk> queue) {
      super(chunk, queue);
      this.name = chunk.name;
    }

    @Override
    public String toString() {
      return "soft reference of " + name + " is " + ((get() == null) ? "null" : "alive");
    }
  }

  // Logging as implemented here gives extra timing info (secs.milis starting from the initialization).
  private final long start = System.currentTimeMillis();
  private final Formatter formatter = new Formatter(System.err);
  private final String formatString = "%1$d.%2$03d %3$s\n";

  // I found this be better synchronized...
  synchronized void log(Object o) {
    long curr = System.currentTimeMillis();
    long diff = curr - start;
    formatter.format(formatString, (int) (diff / 1000), (int) (diff % 1000), o.toString());
  }

  private final ArrayList<Chunk> allChunks = new ArrayList<Chunk>();
  private final ReferenceQueue<Chunk> softReferences = new ReferenceQueue<Chunk>();
  private final ReferenceQueue<Chunk> weakReferences = new ReferenceQueue<Chunk>();
  private final HashSet<Reference<Chunk>> allReferences = new HashSet<Reference<Chunk>>();
  private final Random randomizer = new Random();

  private int loopDelay = 200;
  private int minChunkSize = 100;
  private int maxChunkSize = 1000;
  private int chunkCounter = 0;
  private boolean useSoftReferences = false;
  private long minMemory = 10 * 1024 * 1024;  // Default range is 10-30MB
  private long maxMemory = 3 * minMemory;
  private long usedMemory = 0;

  private String getReadableMemorySize(long size) {
    if (size >= 1024 * 1024) {
      return (float) (Math.round((((float) size) / 1024f / 1024f) * 10f)) / 10f + "MB";
    }
    if (size >= 1024) {
      return (float) (Math.round((((float) size) / 1024f) * 10f)) / 10f + "kB";
    } else if (size > 0) {
      return size + "B";
    } else {
      return "0";
    }
  }

  private void allocMem() {
    Chunk chunk = new Chunk(TAG + chunkCounter++, minChunkSize, maxChunkSize, randomizer);
    allChunks.add(chunk);
    Reference ref = useSoftReferences
            ? (new SoftChunk(chunk, softReferences)) : (new WeakChunk(chunk, weakReferences));
    allReferences.add(ref);
    log(ref);
    usedMemory += chunk.size;
  }

  private void freeMem() {
    if (allChunks.size() < 1) {
      return;
    }
    int i = randomizer.nextInt(allChunks.size());
    Chunk chunk = allChunks.get(i);
    log("freeing " + chunk);
    usedMemory -= chunk.size;
    allChunks.remove(i);
  }

  private int statMem() throws Exception {
    for (Reference ref; (ref = softReferences.poll()) != null;) {
      log(ref);
      allReferences.remove(ref);
    }
    for (Reference ref; (ref = weakReferences.poll()) != null;) {
      log(ref);
      allReferences.remove(ref);
    }
    int weakRefs = 0;
    int softRefs = 0;
    for (Iterator<Reference<Chunk>> i = allReferences.iterator(); i.hasNext();) {
      Reference<Chunk> ref = i.next();
      if (ref.get() == null) {
        continue;
      }
      if (ref instanceof WeakChunk) {
        weakRefs++;
      }
      if (ref instanceof SoftChunk) {
        softRefs++;
      }
    }
    log(allChunks.size() + " chunks, "
            + softRefs + " soft refs, "
            + weakRefs + " weak refs, "
            + getReadableMemorySize(usedMemory) + " used, "
            + getReadableMemorySize(Runtime.getRuntime().freeMemory()) + " free, "
            + getReadableMemorySize(Runtime.getRuntime().totalMemory()) + " total, "
            + getReadableMemorySize(Runtime.getRuntime().maxMemory()) + " max");
    if (loopDelay > 1) {
      Thread.sleep(loopDelay);
    }
    return (int)((100 * usedMemory) / maxMemory); // Return % of maxMemory being used.
  }

  public Leakling(String[] args) throws Exception {
    for (String arg : args) {
      if (arg.startsWith("--min-memory=")) {
        minMemory = Long.parseLong(arg.substring("--min-memory=".length()));
      } else if (arg.startsWith("--max-memory=")) {
        maxMemory = Long.parseLong(arg.substring("--max-memory=".length()));
      } else if (arg.startsWith("--min-chunk-size=")) {
        minChunkSize = Integer.parseInt(arg.substring("--min-chunk-size=".length()));
      } else if (arg.startsWith("--max-chunk-size=")) {
        maxChunkSize = Integer.parseInt(arg.substring("--max-chunk-size=".length()));
      } else if (arg.startsWith("--loop-delay=")) {
        loopDelay = Integer.parseInt(arg.substring("--loop-delay=".length()));
      } else if (arg.startsWith("--use-soft-references=")) {
        useSoftReferences = Boolean.parseBoolean(arg.substring("--use-soft-references=".length()));
      } else {
        throw new Exception("Unknown command line option...");
      }
    }
  }

  public void run() throws Exception {
    log("Mem test started...");

    while(true) {
      log("going up...");
      do {// First loop allocates memory up to the given limit in a pseudo-random fashion.
          // Randomized rate of allocations/frees is about 4:1 as per the 10>=8 condition.
        if (randomizer.nextInt(10) >= 8) {
          freeMem();
        } else {
          allocMem();
        }
      } while (statMem() < 90); // Repeat until 90% of the given mem limit is hit...

      log("going down...");
      do {// Now do the reverse. Frees are four times more likely than allocations are.
        if (randomizer.nextInt(10) < 8) {
          freeMem();
        } else {
          allocMem();
        }
      } while (usedMemory > minMemory);
    }
  }

  public static void main(String[] args) throws Exception {
    (new Leakling(args)).run();
  }
}

Answer 1

首先，不要将终结器与引用混用。两者都会影响从内存中删除对象的速度，并且使用适当的引用类型可以更好地完成您可以使用终结器执行的所有操作。

其次，正如我提到的，使用引用可能会导致 gc 延迟。至少对于“常见”的 gc 算法，弱/软引用的对象在完全回收之前可能需要额外的 gc 运行。弱引用和软引用之间的本质区别在于，弱引用会被积极地 gc'ed，而软引用通常会“尽可能长地保留”。这很可能是你的原因。

当您使用弱引用对象运行时，内容会在运行过程中得到清理，从而避免 OOME。

当您使用软引用对象运行时，所有软引用对象都会保留，直到您接近限制。然后，当内存紧张时，gc 会尝试开始释放软引用的对象，但它花费的时间太长(因为它可能需要多次 gc 传递才能完全回收内存)并且您最终会遇到 OOME。

我对 G1 gc 只有粗浅的了解，所以我不知道为什么它在那种情况下“有效”。

总而言之，软引用有点不错，但由于回收延迟，它们并不总是如您所愿。另外，这是一个 great article以及一些额外的有用细节。