We introduce the Forseti system, which is a principled ap-proach for holistic memory management. It permits a sysad-min to specify the total physical memory resource that may be shared between all concurrent virtual machines on a phys-ical node. Forseti models the heap size versus application throughput for each virtual machine, and seeks to maximize the combined throughput of the set of VMs based on concepts from economic utility theory. We evaluate the Forseti system using a standard Java managed runtime, i.e. OpenJDK. Our results demonstrate that Forseti enables dramatic reductions (up to 5x) in heap footprint without compromising application execution times. Categories and Subject Descriptors D.3.4 [Programming Languages]: Processors—Me...
With the current developments in CPU implementations, it be-comes obvious that ever more parallel mu...
Heap size has a huge impact on the performance of garbage collected applications. A heap that barely...
Adopting heterogeneous execution on GPUs and FPGAs in managed runtime systems, such as Java, is a ch...
We introduce the Forseti system, which is a principled approach for holistic memory management. It ...
Multiple virtual machine (VM) workloads are increasingly com-mon, given the growth of managed enterp...
Multiple virtual machine (VM) workloads are increasingly common, given the growth of managed enterpr...
While a conventional program uses exactly as much memory as it needs, the memory use of a garbage-co...
Java applications are diverse, depending by use case, exist application that use small amount of mem...
We propose a new, principled approach to adaptive heap sizing based on control theory. We review cur...
We propose a new, principled approach to adaptive heap sizing based on control theory. We review cur...
Existing virtual memory systems usually work well with applications written in C and C++, but they d...
Abstract. Typical theorem-proving workloads on the Poly/ML runtime may execute for several hours, oc...
In this position paper, we examine how economic theory can be applied to memory management. We obser...
In conjunction with the 23rd ACM Symposium on Operating Systems Principles (SOSP 2011)International ...
Limiting the amount of memory available to a program can hamstring its performance, however in a ga...
With the current developments in CPU implementations, it be-comes obvious that ever more parallel mu...
Heap size has a huge impact on the performance of garbage collected applications. A heap that barely...
Adopting heterogeneous execution on GPUs and FPGAs in managed runtime systems, such as Java, is a ch...
We introduce the Forseti system, which is a principled approach for holistic memory management. It ...
Multiple virtual machine (VM) workloads are increasingly com-mon, given the growth of managed enterp...
Multiple virtual machine (VM) workloads are increasingly common, given the growth of managed enterpr...
While a conventional program uses exactly as much memory as it needs, the memory use of a garbage-co...
Java applications are diverse, depending by use case, exist application that use small amount of mem...
We propose a new, principled approach to adaptive heap sizing based on control theory. We review cur...
We propose a new, principled approach to adaptive heap sizing based on control theory. We review cur...
Existing virtual memory systems usually work well with applications written in C and C++, but they d...
Abstract. Typical theorem-proving workloads on the Poly/ML runtime may execute for several hours, oc...
In this position paper, we examine how economic theory can be applied to memory management. We obser...
In conjunction with the 23rd ACM Symposium on Operating Systems Principles (SOSP 2011)International ...
Limiting the amount of memory available to a program can hamstring its performance, however in a ga...
With the current developments in CPU implementations, it be-comes obvious that ever more parallel mu...
Heap size has a huge impact on the performance of garbage collected applications. A heap that barely...
Adopting heterogeneous execution on GPUs and FPGAs in managed runtime systems, such as Java, is a ch...