hotspot/src/share/vm/gc_implementation/g1/dirtyCardQueue.hpp
author tonyp
Tue, 24 Aug 2010 17:24:33 -0400
changeset 7398 e4aa6d9bda09
parent 7397 5b173b4ca846
child 13195 be27e1b6a4b9
permissions -rw-r--r--
6974966: G1: unnecessary direct-to-old allocations Summary: This change revamps the slow allocation path of G1. Improvements include the following: a) Allocations directly to old regions are now totally banned. G1 now only allows allocations out of young regions (with the only exception being humongous regions). b) The thread that allocates a new region (which is now guaranteed to be young) does not dirty all its cards. Each thread that successfully allocates out of a young region is now responsible for dirtying the cards that corresponding to the "block" that just got allocated. c) allocate_new_tlab() and mem_allocate() are now implemented differently and TLAB allocations are only done by allocate_new_tlab(). d) If a thread schedules an evacuation pause in order to satisfy an allocation request, it will perform the allocation at the end of the safepoint so that the thread that initiated the GC also gets "first pick" of any space made available by the GC. e) If a thread is unable to allocate a humongous object it will schedule an evacuation pause in case it reclaims enough regions so that the humongous allocation can be satisfied aftewards. f) The G1 policy is more careful to set the young list target length to be the survivor number +1. g) Lots of code tidy up, removal, refactoring to make future changes easier. Reviewed-by: johnc, ysr

/*
 * Copyright (c) 2001, 2010, Oracle and/or its affiliates. All rights reserved.
 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
 *
 * This code is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License version 2 only, as
 * published by the Free Software Foundation.
 *
 * This code is distributed in the hope that it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
 * version 2 for more details (a copy is included in the LICENSE file that
 * accompanied this code).
 *
 * You should have received a copy of the GNU General Public License version
 * 2 along with this work; if not, write to the Free Software Foundation,
 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
 *
 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
 * or visit www.oracle.com if you need additional information or have any
 * questions.
 *
 */

#ifndef SHARE_VM_GC_IMPLEMENTATION_G1_DIRTYCARDQUEUE_HPP
#define SHARE_VM_GC_IMPLEMENTATION_G1_DIRTYCARDQUEUE_HPP

#include "gc_implementation/g1/ptrQueue.hpp"
#include "memory/allocation.hpp"

class FreeIdSet;

// A closure class for processing card table entries.  Note that we don't
// require these closure objects to be stack-allocated.
class CardTableEntryClosure: public CHeapObj {
public:
  // Process the card whose card table entry is "card_ptr".  If returns
  // "false", terminate the iteration early.
  virtual bool do_card_ptr(jbyte* card_ptr, int worker_i = 0) = 0;
};

// A ptrQueue whose elements are "oops", pointers to object heads.
class DirtyCardQueue: public PtrQueue {
public:
  DirtyCardQueue(PtrQueueSet* qset_, bool perm = false) :
    // Dirty card queues are always active, so we create them with their
    // active field set to true.
    PtrQueue(qset_, perm, true /* active */) { }

  // Apply the closure to all elements, and reset the index to make the
  // buffer empty.  If a closure application returns "false", return
  // "false" immediately, halting the iteration.  If "consume" is true,
  // deletes processed entries from logs.
  bool apply_closure(CardTableEntryClosure* cl,
                     bool consume = true,
                     size_t worker_i = 0);

  // Apply the closure to all elements of "buf", down to "index"
  // (inclusive.)  If returns "false", then a closure application returned
  // "false", and we return immediately.  If "consume" is true, entries are
  // set to NULL as they are processed, so they will not be processed again
  // later.
  static bool apply_closure_to_buffer(CardTableEntryClosure* cl,
                                      void** buf, size_t index, size_t sz,
                                      bool consume = true,
                                      int worker_i = 0);
  void **get_buf() { return _buf;}
  void set_buf(void **buf) {_buf = buf;}
  size_t get_index() { return _index;}
  void reinitialize() { _buf = 0; _sz = 0; _index = 0;}
};



class DirtyCardQueueSet: public PtrQueueSet {
  CardTableEntryClosure* _closure;

  DirtyCardQueue _shared_dirty_card_queue;

  // Override.
  bool mut_process_buffer(void** buf);

  // Protected by the _cbl_mon.
  FreeIdSet* _free_ids;

  // The number of completed buffers processed by mutator and rs thread,
  // respectively.
  jint _processed_buffers_mut;
  jint _processed_buffers_rs_thread;

public:
  DirtyCardQueueSet(bool notify_when_complete = true);

  void initialize(Monitor* cbl_mon, Mutex* fl_lock,
                  int process_completed_threshold,
                  int max_completed_queue,
                  Mutex* lock, PtrQueueSet* fl_owner = NULL);

  // The number of parallel ids that can be claimed to allow collector or
  // mutator threads to do card-processing work.
  static size_t num_par_ids();

  static void handle_zero_index_for_thread(JavaThread* t);

  // Register "blk" as "the closure" for all queues.  Only one such closure
  // is allowed.  The "apply_closure_to_completed_buffer" method will apply
  // this closure to a completed buffer, and "iterate_closure_all_threads"
  // applies it to partially-filled buffers (the latter should only be done
  // with the world stopped).
  void set_closure(CardTableEntryClosure* closure);

  // If there is a registered closure for buffers, apply it to all entries
  // in all currently-active buffers.  This should only be applied at a
  // safepoint.  (Currently must not be called in parallel; this should
  // change in the future.)  If "consume" is true, processed entries are
  // discarded.
  void iterate_closure_all_threads(bool consume = true,
                                   size_t worker_i = 0);

  // If there exists some completed buffer, pop it, then apply the
  // registered closure to all its elements, nulling out those elements
  // processed.  If all elements are processed, returns "true".  If no
  // completed buffers exist, returns false.  If a completed buffer exists,
  // but is only partially completed before a "yield" happens, the
  // partially completed buffer (with its processed elements set to NULL)
  // is returned to the completed buffer set, and this call returns false.
  bool apply_closure_to_completed_buffer(int worker_i = 0,
                                         int stop_at = 0,
                                         bool during_pause = false);

  // If there exists some completed buffer, pop it, then apply the
  // specified closure to all its elements, nulling out those elements
  // processed.  If all elements are processed, returns "true".  If no
  // completed buffers exist, returns false.  If a completed buffer exists,
  // but is only partially completed before a "yield" happens, the
  // partially completed buffer (with its processed elements set to NULL)
  // is returned to the completed buffer set, and this call returns false.
  bool apply_closure_to_completed_buffer(CardTableEntryClosure* cl,
                                         int worker_i = 0,
                                         int stop_at = 0,
                                         bool during_pause = false);

  // Helper routine for the above.
  bool apply_closure_to_completed_buffer_helper(CardTableEntryClosure* cl,
                                                int worker_i,
                                                BufferNode* nd);

  BufferNode* get_completed_buffer(int stop_at);

  // Applies the current closure to all completed buffers,
  // non-consumptively.
  void apply_closure_to_all_completed_buffers();

  DirtyCardQueue* shared_dirty_card_queue() {
    return &_shared_dirty_card_queue;
  }

  // Deallocate any completed log buffers
  void clear();

  // If a full collection is happening, reset partial logs, and ignore
  // completed ones: the full collection will make them all irrelevant.
  void abandon_logs();

  // If any threads have partial logs, add them to the global list of logs.
  void concatenate_logs();
  void clear_n_completed_buffers() { _n_completed_buffers = 0;}

  jint processed_buffers_mut() {
    return _processed_buffers_mut;
  }
  jint processed_buffers_rs_thread() {
    return _processed_buffers_rs_thread;
  }

};

#endif // SHARE_VM_GC_IMPLEMENTATION_G1_DIRTYCARDQUEUE_HPP