GC - Java 垃圾回收器之CMS GC问题分析与解决（下）

class Metaspace : public AllStatic {

  friend class MetaspaceShared;

 public:
  enum MetadataType {
    ClassType,
    NonClassType,
    MetadataTypeCount
  };
  enum MetaspaceType {
    ZeroMetaspaceType = 0,
    StandardMetaspaceType = ZeroMetaspaceType,
    BootMetaspaceType = StandardMetaspaceType + 1,
    AnonymousMetaspaceType = BootMetaspaceType + 1,
    ReflectionMetaspaceType = AnonymousMetaspaceType + 1,
    MetaspaceTypeCount
  };

 private:

  // Align up the word size to the allocation word size
  static size_t align_word_size_up(size_t);

  // Aligned size of the metaspace.
  static size_t _compressed_class_space_size;

  static size_t compressed_class_space_size() {
    return _compressed_class_space_size;
  }

  static void set_compressed_class_space_size(size_t size) {
    _compressed_class_space_size = size;
  }

  static size_t _first_chunk_word_size;
  static size_t _first_class_chunk_word_size;

  static size_t _commit_alignment;
  static size_t _reserve_alignment;
  DEBUG_ONLY(static bool   _frozen;)

  // Virtual Space lists for both classes and other metadata
  static metaspace::VirtualSpaceList* _space_list;
  static metaspace::VirtualSpaceList* _class_space_list;

  static metaspace::ChunkManager* _chunk_manager_metadata;
  static metaspace::ChunkManager* _chunk_manager_class;

  static const MetaspaceTracer* _tracer;
}

void MetaspaceGC::compute_new_size() {
  assert(_shrink_factor <= 100, "invalid shrink factor");
  uint current_shrink_factor = _shrink_factor;
  _shrink_factor = 0;
  const size_t used_after_gc = MetaspaceUtils::committed_bytes();
  const size_t capacity_until_GC = MetaspaceGC::capacity_until_GC();

  const double minimum_free_percentage = MinMetaspaceFreeRatio / 100.0;
  const double maximum_used_percentage = 1.0 - minimum_free_percentage;

  const double min_tmp = used_after_gc / maximum_used_percentage;
  size_t minimum_desired_capacity =
    (size_t)MIN2(min_tmp, double(max_uintx));
  // Don't shrink less than the initial generation size
  minimum_desired_capacity = MAX2(minimum_desired_capacity,
                                  MetaspaceSize);

  log_trace(gc, metaspace)("MetaspaceGC::compute_new_size: ");
  log_trace(gc, metaspace)("    minimum_free_percentage: %6.2f  maximum_used_percentage: %6.2f",
                           minimum_free_percentage, maximum_used_percentage);
  log_trace(gc, metaspace)("     used_after_gc       : %6.1fKB", used_after_gc / (double) K);


  size_t shrink_bytes = 0;
  if (capacity_until_GC < minimum_desired_capacity) {
    // If we have less capacity below the metaspace HWM, then
    // increment the HWM.
    size_t expand_bytes = minimum_desired_capacity - capacity_until_GC;
    expand_bytes = align_up(expand_bytes, Metaspace::commit_alignment());
    // Don't expand unless it's significant
    if (expand_bytes >= MinMetaspaceExpansion) {
      size_t new_capacity_until_GC = 0;
      bool succeeded = MetaspaceGC::inc_capacity_until_GC(expand_bytes, &new_capacity_until_GC);
      assert(succeeded, "Should always succesfully increment HWM when at safepoint");

      Metaspace::tracer()->report_gc_threshold(capacity_until_GC,
                                               new_capacity_until_GC,
                                               MetaspaceGCThresholdUpdater::ComputeNewSize);
      log_trace(gc, metaspace)("    expanding:  minimum_desired_capacity: %6.1fKB  expand_bytes: %6.1fKB  MinMetaspaceExpansion: %6.1fKB  new metaspace HWM:  %6.1fKB",
                               minimum_desired_capacity / (double) K,
                               expand_bytes / (double) K,
                               MinMetaspaceExpansion / (double) K,
                               new_capacity_until_GC / (double) K);
    }
    return;
  }

  // No expansion, now see if we want to shrink
  // We would never want to shrink more than this
  assert(capacity_until_GC >= minimum_desired_capacity,
         SIZE_FORMAT " >= " SIZE_FORMAT,
         capacity_until_GC, minimum_desired_capacity);
  size_t max_shrink_bytes = capacity_until_GC - minimum_desired_capacity;

  // Should shrinking be considered?
  if (MaxMetaspaceFreeRatio < 100) {
    const double maximum_free_percentage = MaxMetaspaceFreeRatio / 100.0;
    const double minimum_used_percentage = 1.0 - maximum_free_percentage;
    const double max_tmp = used_after_gc / minimum_used_percentage;
    size_t maximum_desired_capacity = (size_t)MIN2(max_tmp, double(max_uintx));
    maximum_desired_capacity = MAX2(maximum_desired_capacity,
                                    MetaspaceSize);
    log_trace(gc, metaspace)("    maximum_free_percentage: %6.2f  minimum_used_percentage: %6.2f",
                             maximum_free_percentage, minimum_used_percentage);
    log_trace(gc, metaspace)("    minimum_desired_capacity: %6.1fKB  maximum_desired_capacity: %6.1fKB",
                             minimum_desired_capacity / (double) K, maximum_desired_capacity / (double) K);

    assert(minimum_desired_capacity <= maximum_desired_capacity,
           "sanity check");

    if (capacity_until_GC > maximum_desired_capacity) {
      // Capacity too large, compute shrinking size
      shrink_bytes = capacity_until_GC - maximum_desired_capacity;
      shrink_bytes = shrink_bytes / 100 * current_shrink_factor;

      shrink_bytes = align_down(shrink_bytes, Metaspace::commit_alignment());

      assert(shrink_bytes <= max_shrink_bytes,
             "invalid shrink size " SIZE_FORMAT " not <= " SIZE_FORMAT,
             shrink_bytes, max_shrink_bytes);
      if (current_shrink_factor == 0) {
        _shrink_factor = 10;
      } else {
        _shrink_factor = MIN2(current_shrink_factor * 4, (uint) 100);
      }
      log_trace(gc, metaspace)("    shrinking:  initThreshold: %.1fK  maximum_desired_capacity: %.1fK",
                               MetaspaceSize / (double) K, maximum_desired_capacity / (double) K);
      log_trace(gc, metaspace)("    shrink_bytes: %.1fK  current_shrink_factor: %d  new shrink factor: %d  MinMetaspaceExpansion: %.1fK",
                               shrink_bytes / (double) K, current_shrink_factor, _shrink_factor, MinMetaspaceExpansion / (double) K);
    }
  }

  // Don't shrink unless it's significant
  if (shrink_bytes >= MinMetaspaceExpansion &&
      ((capacity_until_GC - shrink_bytes) >= MetaspaceSize)) {
    size_t new_capacity_until_GC = MetaspaceGC::dec_capacity_until_GC(shrink_bytes);
    Metaspace::tracer()->report_gc_threshold(capacity_until_GC,
                                             new_capacity_until_GC,
                                             MetaspaceGCThresholdUpdater::ComputeNewSize);
  }
}

uint ageTable::compute_tenuring_threshold(size_t survivor_capacity) {
  //TargetSurvivorRatio默认50，意思是：在回收之后希望survivor区的占用率达到这个比例
  size_t desired_survivor_size = (size_t)((((double) survivor_capacity)*TargetSurvivorRatio)/100);
  size_t total = 0;
  uint age = 1;
  assert(sizes[0] == 0, "no objects with age zero should be recorded");
  while (age < table_size) {//table_size=16
    total += sizes[age];
    //如果加上这个年龄的所有对象的大小之后，占用量>期望的大小，就设置age为新的晋升阈值
    if (total > desired_survivor_size) break;
    age++;
  }

  uint result = age < MaxTenuringThreshold ? age : MaxTenuringThreshold;
  if (PrintTenuringDistribution || UsePerfData) {

    //打印期望的survivor的大小以及新计算出来的阈值，和设置的最大阈值
    if (PrintTenuringDistribution) {
      gclog_or_tty->cr();
      gclog_or_tty->print_cr("Desired survivor size " SIZE_FORMAT " bytes, new threshold %u (max %u)",
        desired_survivor_size*oopSize, result, (int) MaxTenuringThreshold);
    }

    total = 0;
    age = 1;
    while (age < table_size) {
      total += sizes[age];
      if (sizes[age] > 0) {
        if (PrintTenuringDistribution) {
          gclog_or_tty->print_cr("- age %3u: " SIZE_FORMAT_W(10) " bytes, " SIZE_FORMAT_W(10) " total",
                                        age,    sizes[age]*oopSize,          total*oopSize);
        }
      }
      if (UsePerfData) {
        _perf_sizes[age]->set_value(sizes[age]*oopSize);
      }
      age++;
    }
    if (UsePerfData) {
      SharedHeap* sh = SharedHeap::heap();
      CollectorPolicy* policy = sh->collector_policy();
      GCPolicyCounters* gc_counters = policy->counters();
      gc_counters->tenuring_threshold()->set_value(result);
      gc_counters->desired_survivor_size()->set_value(
        desired_survivor_size*oopSize);
    }
  }

  return result;
}

void ConcurrentMarkSweepThread::run_service() {
  assert(this == cmst(), "just checking");

  if (BindCMSThreadToCPU && !os::bind_to_processor(CPUForCMSThread)) {
    log_warning(gc)("Couldn't bind CMS thread to processor " UINTX_FORMAT, CPUForCMSThread);
  }

  while (!should_terminate()) {
    sleepBeforeNextCycle();
    if (should_terminate()) break;
    GCIdMark gc_id_mark;
    GCCause::Cause cause = _collector->_full_gc_requested ?
      _collector->_full_gc_cause : GCCause::_cms_concurrent_mark;
    _collector->collect_in_background(cause);
  }
  verify_ok_to_terminate();
}
void ConcurrentMarkSweepThread::sleepBeforeNextCycle() {
  while (!should_terminate()) {
    if(CMSWaitDuration >= 0) {
      // Wait until the next synchronous GC, a concurrent full gc
      // request or a timeout, whichever is earlier.
      wait_on_cms_lock_for_scavenge(CMSWaitDuration);
    } else {
      // Wait until any cms_lock event or check interval not to call shouldConcurrentCollect permanently
      wait_on_cms_lock(CMSCheckInterval);
    }
    // Check if we should start a CMS collection cycle
    if (_collector->shouldConcurrentCollect()) {
      return;
    }
    // .. collection criterion not yet met, let's go back
    // and wait some more
  }
}

bool CMSCollector::shouldConcurrentCollect() {
  LogTarget(Trace, gc) log;

  if (_full_gc_requested) {
    log.print("CMSCollector: collect because of explicit  gc request (or GCLocker)");
    return true;
  }

  FreelistLocker x(this);
  // ------------------------------------------------------------------
  // Print out lots of information which affects the initiation of
  // a collection.
  if (log.is_enabled() && stats().valid()) {
    log.print("CMSCollector shouldConcurrentCollect: ");

    LogStream out(log);
    stats().print_on(&out);

    log.print("time_until_cms_gen_full %3.7f", stats().time_until_cms_gen_full());
    log.print("free=" SIZE_FORMAT, _cmsGen->free());
    log.print("contiguous_available=" SIZE_FORMAT, _cmsGen->contiguous_available());
    log.print("promotion_rate=%g", stats().promotion_rate());
    log.print("cms_allocation_rate=%g", stats().cms_allocation_rate());
    log.print("occupancy=%3.7f", _cmsGen->occupancy());
    log.print("initiatingOccupancy=%3.7f", _cmsGen->initiating_occupancy());
    log.print("cms_time_since_begin=%3.7f", stats().cms_time_since_begin());
    log.print("cms_time_since_end=%3.7f", stats().cms_time_since_end());
    log.print("metadata initialized %d", MetaspaceGC::should_concurrent_collect());
  }
  // ------------------------------------------------------------------
  if (!UseCMSInitiatingOccupancyOnly) {
    if (stats().valid()) {
      if (stats().time_until_cms_start() == 0.0) {
        return true;
      }
    } else {
  
      if (_cmsGen->occupancy() >= _bootstrap_occupancy) {
        log.print(" CMSCollector: collect for bootstrapping statistics: occupancy = %f, boot occupancy = %f",
                  _cmsGen->occupancy(), _bootstrap_occupancy);
        return true;
      }
    }
  }

  if (_cmsGen->should_concurrent_collect()) {
    log.print("CMS old gen initiated");
    return true;
  }

  // We start a collection if we believe an incremental collection may fail;
  // this is not likely to be productive in practice because it's probably too
  // late anyway.
  CMSHeap* heap = CMSHeap::heap();
  if (heap->incremental_collection_will_fail(true /* consult_young */)) {
    log.print("CMSCollector: collect because incremental collection will fail ");
    return true;
  }

  if (MetaspaceGC::should_concurrent_collect()) {
    log.print("CMSCollector: collect for metadata allocation ");
    return true;
  }

  // CMSTriggerInterval starts a CMS cycle if enough time has passed.
  if (CMSTriggerInterval >= 0) {
    if (CMSTriggerInterval == 0) {
      // Trigger always
      return true;
    }

    // Check the CMS time since begin (we do not check the stats validity
    // as we want to be able to trigger the first CMS cycle as well)
    if (stats().cms_time_since_begin() >= (CMSTriggerInterval / ((double) MILLIUNITS))) {
      if (stats().valid()) {
        log.print("CMSCollector: collect because of trigger interval (time since last begin %3.7f secs)",
                  stats().cms_time_since_begin());
      } else {
        log.print("CMSCollector: collect because of trigger interval (first collection)");
      }
      return true;
    }
  }

  return false;
}

void CMSCollector::checkpointRootsInitialWork() {
  assert(SafepointSynchronize::is_at_safepoint(), "world should be stopped");
  assert(_collectorState == InitialMarking, "just checking");

  // Already have locks.
  assert_lock_strong(bitMapLock());
  assert(_markBitMap.isAllClear(), "was reset at end of previous cycle");

  // Setup the verification and class unloading state for this
  // CMS collection cycle.
  setup_cms_unloading_and_verification_state();

  GCTraceTime(Trace, gc, phases) ts("checkpointRootsInitialWork", _gc_timer_cm);

  // Reset all the PLAB chunk arrays if necessary.
  if (_survivor_plab_array != NULL && !CMSPLABRecordAlways) {
    reset_survivor_plab_arrays();
  }

  ResourceMark rm;
  HandleMark  hm;

  MarkRefsIntoClosure notOlder(_span, &_markBitMap);
  CMSHeap* heap = CMSHeap::heap();

  verify_work_stacks_empty();
  verify_overflow_empty();

  heap->ensure_parsability(false);  // fill TLABs, but no need to retire them
  // Update the saved marks which may affect the root scans.
  heap->save_marks();

  // weak reference processing has not started yet.
  ref_processor()->set_enqueuing_is_done(false);

  // Need to remember all newly created CLDs,
  // so that we can guarantee that the remark finds them.
  ClassLoaderDataGraph::remember_new_clds(true);

  // Whenever a CLD is found, it will be claimed before proceeding to mark
  // the klasses. The claimed marks need to be cleared before marking starts.
  ClassLoaderDataGraph::clear_claimed_marks();

  print_eden_and_survivor_chunk_arrays();

  {
    if (CMSParallelInitialMarkEnabled) {
      // The parallel version.
      WorkGang* workers = heap->workers();
      assert(workers != NULL, "Need parallel worker threads.");
      uint n_workers = workers->active_workers();

      StrongRootsScope srs(n_workers);

      CMSParInitialMarkTask tsk(this, &srs, n_workers);
      initialize_sequential_subtasks_for_young_gen_rescan(n_workers);
      // If the total workers is greater than 1, then multiple workers
      // may be used at some time and the initialization has been set
      // such that the single threaded path cannot be used.
      if (workers->total_workers() > 1) {
        workers->run_task(&tsk);
      } else {
        tsk.work(0);
      }
    } else {
      // The serial version.
      CLDToOopClosure cld_closure(&notOlder, true);
      heap->rem_set()->prepare_for_younger_refs_iterate(false); // Not parallel.

      StrongRootsScope srs(1);

      heap->cms_process_roots(&srs,
                             true,   // young gen as roots
                             GenCollectedHeap::ScanningOption(roots_scanning_options()),
                             should_unload_classes(),
                             &notOlder,
                             &cld_closure);
    }
  }

  // Clear mod-union table; it will be dirtied in the prologue of
  // CMS generation per each young generation collection.
  assert(_modUnionTable.isAllClear(),
       "Was cleared in most recent final checkpoint phase"
       " or no bits are set in the gc_prologue before the start of the next "
       "subsequent marking phase.");

  assert(_ct->cld_rem_set()->mod_union_is_clear(), "Must be");
  // Save the end of the used_region of the constituent generations
  // to be used to limit the extent of sweep in each generation.
  save_sweep_limits();
  verify_overflow_empty();
}
void CMSParInitialMarkTask::work(uint worker_id) {
  elapsedTimer _timer;
  ResourceMark rm;
  HandleMark   hm;

  // ---------- scan from roots --------------
  _timer.start();
  CMSHeap* heap = CMSHeap::heap();
  ParMarkRefsIntoClosure par_mri_cl(_collector->_span, &(_collector->_markBitMap));

  // ---------- young gen roots --------------
  {
    work_on_young_gen_roots(&par_mri_cl);
    _timer.stop();
    log_trace(gc, task)("Finished young gen initial mark scan work in %dth thread: %3.3f sec", worker_id, _timer.seconds());
  }

  // ---------- remaining roots --------------
  _timer.reset();
  _timer.start();

  CLDToOopClosure cld_closure(&par_mri_cl, true);

  heap->cms_process_roots(_strong_roots_scope,
                          false,     // yg was scanned above
                          GenCollectedHeap::ScanningOption(_collector->CMSCollector::roots_scanning_options()),
                          _collector->should_unload_classes(),
                          &par_mri_cl,
                          &cld_closure,
                          &_par_state_string);

  assert(_collector->should_unload_classes()
         || (_collector->CMSCollector::roots_scanning_options() & GenCollectedHeap::SO_AllCodeCache),
         "if we didn't scan the code cache, we have to be ready to drop nmethods with expired weak oops");
  _timer.stop();
  log_trace(gc, task)("Finished remaining root initial mark scan work in %dth thread: %3.3f sec", worker_id, _timer.seconds());
}

void CMSCollector::checkpointRootsFinalWork() {
  GCTraceTime(Trace, gc, phases) tm("checkpointRootsFinalWork", _gc_timer_cm);

  assert(haveFreelistLocks(), "must have free list locks");
  assert_lock_strong(bitMapLock());

  ResourceMark rm;
  HandleMark   hm;

  CMSHeap* heap = CMSHeap::heap();

  if (should_unload_classes()) {
    CodeCache::gc_prologue();
  }
  assert(haveFreelistLocks(), "must have free list locks");
  assert_lock_strong(bitMapLock());

  heap->ensure_parsability(false);  // fill TLAB's, but no need to retire them
  // Update the saved marks which may affect the root scans.
  heap->save_marks();

  print_eden_and_survivor_chunk_arrays();

  {
    if (CMSParallelRemarkEnabled) {
      GCTraceTime(Debug, gc, phases) t("Rescan (parallel)", _gc_timer_cm);
      do_remark_parallel();
    } else {
      GCTraceTime(Debug, gc, phases) t("Rescan (non-parallel)", _gc_timer_cm);
      do_remark_non_parallel();
    }
  }
  verify_work_stacks_empty();
  verify_overflow_empty();

  {
    GCTraceTime(Trace, gc, phases) ts("refProcessingWork", _gc_timer_cm);
    refProcessingWork();
  }
  verify_work_stacks_empty();
  verify_overflow_empty();

  if (should_unload_classes()) {
    CodeCache::gc_epilogue();
  }
  JvmtiExport::gc_epilogue();
  assert(_markStack.isEmpty(), "No grey objects");
  size_t ser_ovflw = _ser_pmc_remark_ovflw + _ser_pmc_preclean_ovflw +
                     _ser_kac_ovflw        + _ser_kac_preclean_ovflw;
  if (ser_ovflw > 0) {
    log_trace(gc)("Marking stack overflow (benign) (pmc_pc=" SIZE_FORMAT ", pmc_rm=" SIZE_FORMAT ", kac=" SIZE_FORMAT ", kac_preclean=" SIZE_FORMAT ")",
                         _ser_pmc_preclean_ovflw, _ser_pmc_remark_ovflw, _ser_kac_ovflw, _ser_kac_preclean_ovflw);
    _markStack.expand();
    _ser_pmc_remark_ovflw = 0;
    _ser_pmc_preclean_ovflw = 0;
    _ser_kac_preclean_ovflw = 0;
    _ser_kac_ovflw = 0;
  }
  if (_par_pmc_remark_ovflw > 0 || _par_kac_ovflw > 0) {
     log_trace(gc)("Work queue overflow (benign) (pmc_rm=" SIZE_FORMAT ", kac=" SIZE_FORMAT ")",
                          _par_pmc_remark_ovflw, _par_kac_ovflw);
     _par_pmc_remark_ovflw = 0;
    _par_kac_ovflw = 0;
  }
   if (_markStack._hit_limit > 0) {
     log_trace(gc)(" (benign) Hit max stack size limit (" SIZE_FORMAT ")",
                          _markStack._hit_limit);
   }
   if (_markStack._failed_double > 0) {
     log_trace(gc)(" (benign) Failed stack doubling (" SIZE_FORMAT "), current capacity " SIZE_FORMAT,
                          _markStack._failed_double, _markStack.capacity());
   }
  _markStack._hit_limit = 0;
  _markStack._failed_double = 0;

  if ((VerifyAfterGC || VerifyDuringGC) &&
      CMSHeap::heap()->total_collections() >= VerifyGCStartAt) {
    verify_after_remark();
  }

  _gc_tracer_cm->report_object_count_after_gc(&_is_alive_closure);

  // Change under the freelistLocks.
  _collectorState = Sweeping;
  // Call isAllClear() under bitMapLock
  assert(_modUnionTable.isAllClear(),
      "Should be clear by end of the final marking");
  assert(_ct->cld_rem_set()->mod_union_is_clear(),
      "Should be clear by end of the final marking");
}

if (should_unload_classes()) {
    {
      GCTraceTime(Debug, gc, phases) t("Class Unloading", _gc_timer_cm);

      // Unload classes and purge the SystemDictionary.
      bool purged_class = SystemDictionary::do_unloading(_gc_timer_cm);

      // Unload nmethods.
      CodeCache::do_unloading(&_is_alive_closure, purged_class);

      // Prune dead klasses from subklass/sibling/implementor lists.
      Klass::clean_weak_klass_links(purged_class);
    }

    {
      GCTraceTime(Debug, gc, phases) t("Scrub Symbol Table", _gc_timer_cm);
      // Clean up unreferenced symbols in symbol table.
      SymbolTable::unlink();
    }

    {
      GCTraceTime(Debug, gc, phases) t("Scrub String Table", _gc_timer_cm);
      // Delete entries for dead interned strings.
      StringTable::unlink(&_is_alive_closure);
    }
  }

#include <jni.h>
#include "GCLockerTest.h"

static jbyte* sink;

JNIEXPORT void JNICALL Java_GCLockerTest_acquire(JNIEnv* env, jclass klass, jintArray arr) {
sink = (*env)->GetPrimitiveArrayCritical(env, arr, 0);
}

JNIEXPORT void JNICALL Java_GCLockerTest_release(JNIEnv* env, jclass klass, jintArray arr) {
(*env)->ReleasePrimitiveArrayCritical(env, arr, sink, 0);
}