On models for object lifetime distributions

Stefanović, Darko; McKinley, Kathryn S.; Moss, J. Eliot B.

doi:10.1145/362426.362477

Cited by 4 publications

(5 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other than the weak generational hypothesis [16,25], previous work using analytical modeling and experimental classification across programs has not yielded any additional general object lifetime hypotheses [9,22]. However, many memory management techniques improve performance for a given program based on its individual characteristics.…”

Section: Related Workmentioning

confidence: 99%

Dynamic object sampling for pretenuring

Jump

Blackburn

McKinley

2004

Proceedings of the 4th International Symposium on Memory Management

Self Cite

View full text Add to dashboard Cite

Many state-of-the-art garbage collectors are generational, collecting the young nursery objects more frequently than old objects. These collectors perform well because young objects tend to die at a higher rate than old ones. However, these collectors do not examine object lifetimes with respect to any particular program or allocation site. This paper introduces low-cost object sampling to dynamically determine lifetimes. The sampler marks an object and records its allocation site every n bytes of allocation. The collector then computes per-site nursery survival rates. Sampling degrades total performance by only 3% on average for sample rates of 256 bytes in Jikes RVM, a rate at which overall lifetime accuracy compares well with sampling every object.An adaptive collector can use this information to tune itself. For example, pretenuring decreases nursery collection work by allocating new, but long-lived, objects directly into the mature space. We introduce a dynamic pretenuring mechanism that detects long-lived allocation sites and pretenures them, given sufficient samples. To react to phase changes, it occasionally backsamples. As with previous online pretenuring, consistent performance improvements on SPECjvm98 benchmarks are difficult to attain since only two combine sufficient allocation load with high nursery survival. Our pretenuring system consistently improves one of these, 213 javac, by 2% to 9% of total time by decreasing collection time by over a factor of two. Sampling and pretenuring overheads slow down all the others. This paper thus provides an efficient sampling mechanism that accurately predicts lifetimes, but leaves open optimization policies that can exploit this information.

show abstract

Section: Related Workmentioning

confidence: 99%

Dynamic object sampling for pretenuring

Jump

Blackburn

McKinley

2004

Proceedings of the 4th International Symposium on Memory Management

Self Cite

View full text Add to dashboard Cite

show abstract

“…Stefanovic et al [41] describe analytical models for object lifetimes in object-oriented programs. Appel [3] has proposed that a plausible object lifetime distribution should use the following property: the expected future lifetime of an object is proportional to its current age.…”

Section: Related Workmentioning

confidence: 99%

Exploiting prolific types for memory management and optimizations

et al. 2002

View full text Add to dashboard Cite

In this paper, we introduce the notion of prolific and non-prolific types, based on the number of instantiated objects of those types. We demonstrate that distinguishing between these types enables a new class of techniques for memory management and data locality, and facilitates the deployment of known techniques. Specifically, we first present a new type-based approach to garbage collection that has similar attributes but lower cost than generational collection. Then we describe the short type pointer technique for reducing memory requirements of objects (data) used by the program. We also discuss techniques to facilitate the recycling of prolific objects and to simplify object co-allocation decisions.We evaluate the first two techniques on a standard set of Java benchmarks (SPECjvm98 and SPECjbb2000). An implementation of the type-based collector in the Jalapeño VM shows improved pause times, elimination of unnecessary write barriers, and reduction in garbage collection time (compared to the analogous generational collector) by up to 15%. A study to evaluate the benefits of the short-type pointer technique shows a potential reduction in the heap space requirements of programs by up to 16%.

show abstract

“…Stefanović et al [23] consider mathematical models for object lifetimes and compare these models with observed behavior for 58 Smalltalk and Java programs. They find that the mathematical models do not agree entirely with observed behavior, but they generally follow a gamma distribution.…”

Section: Empirical Analysismentioning

confidence: 99%

We are all economists now

Cameron

Singer

2014

Proceedings of the 9th International Workshop on Implementation, Compilation, Optimization of Object-Oriented Languages, Progra

View full text Add to dashboard Cite

Multiple virtual machine (VM) workloads are increasingly common, given the growth of managed enterprise application systems and consolidated virtual servers. Until now, there has been no principled approach to partitioning memory resource between multiple co-located VMs. In this paper, we develop a general framework for multi-VM heap sizing, based on the principle of utility maximization from microeconomic theory. We apply utility maximization to static heap sizing, and obtain performance improvements slightly better than current best-practice static heap sizing, and comparable with HotSpot ergonomics (current best-practice dynamic heap sizing). The major advantage of our approach is its simplicity and predictable resource utilization.

show abstract

On models for object lifetime distributions

Cited by 4 publications

References 3 publications

Dynamic object sampling for pretenuring

Dynamic object sampling for pretenuring

Exploiting prolific types for memory management and optimizations

We are all economists now

Contact Info

Product

Resources

About