Sun Microsystems, Inc.

Steffen Grarup

Lars Bak

Sheng Liang

Urs H&ouml;lzle

David M Ungar

Peter B Kessler

David P Stoutamire

A method and apparatus for profiling a heap. According to the method, a flexible and comprehensive general-purpose profiling interface that uniformly accommodates a wide variety of memory allocation and garbage collection methods is used. The profiling interface, among other things, employs a set of virtual machine profiling interface events that support all known types of garbage collection methods.

Method for enabling comprehensive profiling of garbage-collected memory systems

A system that associates an identifier with an instance defined within an object-oriented programming system. The system generates an identifier for the instance and associates a new near object with the instance, wherein the new near object points to a class specifying behavior for the object. The system stores the identifier in the new near object, and sets a class pointer located within a header of the instance to point to the new near object. In this way, the class pointer indirectly points to the class for the object through the new near object. The system can lock the instance to facilitate exclusive access to the instance by copying a near object associated with the instance to a method activation on the execution stack, and setting the class pointer of the instance to point to the copy of the near object on the execution stack.

Method and apparatus for facilitating compact object headers

Methods and apparatus for enabling an efficient generational scavenging garbage collection to be performed on a managed memory area are disclosed. According to one aspect of the present invention, a method for reclaiming memory space uses a managed memory area that includes a first area and a second area. The first area is arranged to store recently allocated objects, while the second area being arranged to store older objects. The method includes determining when a first section of the first area in which new objects are to be allocated is substantially filled. When it is determined that the first section is substantially filled, a garbage collection is performed on a second section of the first. After the garbage collection, the second section is set to support new object allocation such that new objects are allocated in the second section, while the first section is reset such that it is no longer arranged to support new object allocation. In one embodiment, performing the garbage collection on the second section includes copying a live object from the second section into the second area.

Method and apparatus for increasing scavenging garbage collection effectiveness

Methods and apparatus for creating a mechanism for rearranging a plurality of objects in memory are disclosed. A frequency of accesses in memory of one or more fields associated with the plurality of objects with respect to one another during execution of a computer application are determined. A mechanism for rearranging the plurality of objects in the memory in accordance with the determined frequency of accesses in memory of data referenced by the one or more fields associated with the plurality of objects with respect to one another is then generated.

Methods and apparatus for improving locality of reference through memory management

Methods and apparatus for the efficient allocation of shared memory in a multi-threaded computer system are disclosed. In accordance with one embodiment of the present invention, a computer-implemented method for allocating memory shared by multiple threads in a multi-threaded computing system includes partitioning the shared memory into a plurality of blocks, and grouping the multiple threads into at least a first group and a second group. A selected block is allocated to a selected thread which may attempt to allocate an object in the selected block. The allocation of the selected block to the selected thread is based at least partially upon whether the selected thread is a part of the first group or the second group. In one embodiment, grouping the multiple threads into the first group and the second group includes identifying a particular thread and determining whether the particular thread is a fast allocating thread. In such an embodiment, when the particular thread is fast allocating, the particular thread is grouped into the first group.

Method and apparatus for memory allocation in a multi-threaded virtual machine

The present invention relates to methods and apparatus for performing generational garbage collection within computer memory. According to one aspect of the present invention, a computer-implemented method for dynamically managing memory which includes a first memory section and a second memory section that is divided into a plurality of blocks each having an associated marker, includes performing a first garbage collection on the first memory section. The method also includes performing a second garbage collection on a selected one of the blocks in the second memory section. A third garbage collection is performed on the selected block in the second memory section. The third garbage collection includes determining whether the selected block includes a first object which references a second object which is not included in the selected block based at least in part on a status indicated by the marker associated with the selected block. The status includes an indication of whether the reference to the second object was stored after the second garbage collection was performed, and if the reference to the second object was stored after the second garbage collection was performed, a new root array is created using the selected marker.

Growing community of inventors

Palo Alto, CA, United States of America

Steffen Grarup